release 2015.11.13

For providing idea for vidto.me (#7167) and extending nowvideo support (#6760)

.travis.yml

@@ -5,9 +5,8 @@ python:
   - "3.2"
   - "3.3"
   - "3.4"
-before_install:
-  - sudo apt-get update -qq
-  - sudo apt-get install -yqq rtmpdump
+  - "3.5"
+sudo: false
 script: nosetests test --verbose
 notifications:
   email:

AUTHORS

@@ -127,3 +127,22 @@ Julian Richen
 Ping O.
 Mister Hat
 Peter Ding
+jackyzy823
+George Brighton
+Remita Amine
+Aurélio A. Heckert
+Bernhard Minks
+sceext
+Zach Bruggeman
+Tjark Saul
+slangangular
+Behrouz Abbasi
+ngld
+nyuszika7h
+Shaun Walbridge
+Lee Jenkins
+Anssi Hannula
+Lukáš Lalinský
+Qijiang Fan
+Rémy Léone
+Marco Ferragina

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 **Please include the full output of youtube-dl when run with `-v`**.
 
-The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 
@@ -16,15 +16,15 @@ So please elaborate on what feature you are requesting, or what bug you want to
 
 If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
 
-For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
+For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
 **Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 
-Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
+Before reporting any issue, type `youtube-dl -U`. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
 
 ###  Is the issue already documented?
 
@@ -114,18 +114,19 @@ If you want to add support for a new site, you can follow this quick list (assum
             webpage = self._download_webpage(url, video_id)
 
             # TODO more code goes here, for example ...
-            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+            title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
 
             return {
                 'id': video_id,
                 'title': title,
                 'description': self._og_search_description(webpage),
+                'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
+7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 

README.md

@@ -9,6 +9,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 - [VIDEO SELECTION](#video-selection)
 - [FAQ](#faq)
 - [DEVELOPER INSTRUCTIONS](#developer-instructions)
+- [EMBEDDING YOUTUBE-DL](#embedding-youtube-dl)
 - [BUGS](#bugs)
 - [COPYRIGHT](#copyright)
 
@@ -34,7 +35,7 @@ You can also use pip:
 
     sudo pip install youtube-dl
 
-Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
+Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
 
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
@@ -48,109 +49,220 @@ which means you can modify it, redistribute it or use it however you like.
 # OPTIONS
     -h, --help                       Print this help text and exit
     --version                        Print program version and exit
-    -U, --update                     Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
-    -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
-    --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
+    -U, --update                     Update this program to latest version. Make
+                                     sure that you have sufficient permissions
+                                     (run with sudo if needed)
+    -i, --ignore-errors              Continue on download errors, for example to
+                                     skip unavailable videos in a playlist
+    --abort-on-error                 Abort downloading of further videos (in the
+                                     playlist or the command line) if an error
+                                     occurs
     --dump-user-agent                Display the current browser identification
     --list-extractors                List all supported extractors
-    --extractor-descriptions         Output descriptions of all supported extractors
-    --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
-                                     Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
-                                     default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
-    --ignore-config                  Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration
-                                     in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)
-    --flat-playlist                  Do not extract the videos of a playlist, only list them.
+    --extractor-descriptions         Output descriptions of all supported
+                                     extractors
+    --force-generic-extractor        Force extraction to use the generic
+                                     extractor
+    --default-search PREFIX          Use this prefix for unqualified URLs. For
+                                     example "gvsearch2:" downloads two videos
+                                     from google videos for youtube-dl "large
+                                     apple". Use the value "auto" to let
+                                     youtube-dl guess ("auto_warning" to emit a
+                                     warning when guessing). "error" just throws
+                                     an error. The default value "fixup_error"
+                                     repairs broken URLs, but emits an error if
+                                     this is not possible instead of searching.
+    --ignore-config                  Do not read configuration files. When given
+                                     in the global configuration file /etc
+                                     /youtube-dl.conf: Do not read the user
+                                     configuration in ~/.config/youtube-
+                                     dl/config (%APPDATA%/youtube-dl/config.txt
+                                     on Windows)
+    --flat-playlist                  Do not extract the videos of a playlist,
+                                     only list them.
     --no-color                       Do not emit color codes in output
 
 ## Network Options:
-    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
+    --proxy URL                      Use the specified HTTP/HTTPS proxy. Pass in
+                                     an empty string (--proxy "") for direct
+                                     connection
     --socket-timeout SECONDS         Time to wait before giving up, in seconds
-    --source-address IP              Client-side IP address to bind to (experimental)
-    -4, --force-ipv4                 Make all connections via IPv4 (experimental)
-    -6, --force-ipv6                 Make all connections via IPv6 (experimental)
-    --cn-verification-proxy URL      Use this proxy to verify the IP address for some Chinese sites. The default proxy specified by --proxy (or none, if the options is
-                                     not present) is used for the actual downloading. (experimental)
+    --source-address IP              Client-side IP address to bind to
+                                     (experimental)
+    -4, --force-ipv4                 Make all connections via IPv4
+                                     (experimental)
+    -6, --force-ipv6                 Make all connections via IPv6
+                                     (experimental)
+    --cn-verification-proxy URL      Use this proxy to verify the IP address for
+                                     some Chinese sites. The default proxy
+                                     specified by --proxy (or none, if the
+                                     options is not present) is used for the
+                                     actual downloading. (experimental)
 
 ## Video Selection:
     --playlist-start NUMBER          Playlist video to start at (default is 1)
     --playlist-end NUMBER            Playlist video to end at (default is last)
-    --playlist-items ITEM_SPEC       Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
-                                     if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
-                                     download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
-    --match-title REGEX              Download only matching titles (regex or caseless sub-string)
-    --reject-title REGEX             Skip download for matching titles (regex or caseless sub-string)
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify
+                                     indices of the videos in the playlist
+                                     separated by commas like: "--playlist-items
+                                     1,2,5,8" if you want to download videos
+                                     indexed 1, 2, 5, 8 in the playlist. You can
+                                     specify range: "--playlist-items
+                                     1-3,7,10-13", it will download the videos
+                                     at index 1, 2, 3, 7, 10, 11, 12 and 13.
+    --match-title REGEX              Download only matching titles (regex or
+                                     caseless sub-string)
+    --reject-title REGEX             Skip download for matching titles (regex or
+                                     caseless sub-string)
     --max-downloads NUMBER           Abort after downloading NUMBER files
-    --min-filesize SIZE              Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)
-    --max-filesize SIZE              Do not download any videos larger than SIZE (e.g. 50k or 44.6m)
+    --min-filesize SIZE              Do not download any videos smaller than
+                                     SIZE (e.g. 50k or 44.6m)
+    --max-filesize SIZE              Do not download any videos larger than SIZE
+                                     (e.g. 50k or 44.6m)
     --date DATE                      Download only videos uploaded in this date
-    --datebefore DATE                Download only videos uploaded on or before this date (i.e. inclusive)
-    --dateafter DATE                 Download only videos uploaded on or after this date (i.e. inclusive)
-    --min-views COUNT                Do not download any videos with less than COUNT views
-    --max-views COUNT                Do not download any videos with more than COUNT views
-    --match-filter FILTER            Generic video filter (experimental). Specify any key (see help for -o for a list of available keys) to match if the key is present,
-                                     !key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against
-                                     a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the
-                                     operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike
-                                     functionality is not available at the given service), but who also have a description, use  --match-filter "like_count > 100 &
+    --datebefore DATE                Download only videos uploaded on or before
+                                     this date (i.e. inclusive)
+    --dateafter DATE                 Download only videos uploaded on or after
+                                     this date (i.e. inclusive)
+    --min-views COUNT                Do not download any videos with less than
+                                     COUNT views
+    --max-views COUNT                Do not download any videos with more than
+                                     COUNT views
+    --match-filter FILTER            Generic video filter (experimental).
+                                     Specify any key (see help for -o for a list
+                                     of available keys) to match if the key is
+                                     present, !key to check if the key is not
+                                     present,key > NUMBER (like "comment_count >
+                                     12", also works with >=, <, <=, !=, =) to
+                                     compare against a number, and & to require
+                                     multiple matches. Values which are not
+                                     known are excluded unless you put a
+                                     question mark (?) after the operator.For
+                                     example, to only match videos that have
+                                     been liked more than 100 times and disliked
+                                     less than 50 times (or the dislike
+                                     functionality is not available at the given
+                                     service), but who also have a description,
+                                     use --match-filter "like_count > 100 &
                                      dislike_count <? 50 & description" .
-    --no-playlist                    Download only the video, if the URL refers to a video and a playlist.
-    --yes-playlist                   Download the playlist, if the URL refers to a video and a playlist.
-    --age-limit YEARS                Download only videos suitable for the given age
-    --download-archive FILE          Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.
-    --include-ads                    Download advertisements as well (experimental)
+    --no-playlist                    Download only the video, if the URL refers
+                                     to a video and a playlist.
+    --yes-playlist                   Download the playlist, if the URL refers to
+                                     a video and a playlist.
+    --age-limit YEARS                Download only videos suitable for the given
+                                     age
+    --download-archive FILE          Download only videos not listed in the
+                                     archive file. Record the IDs of all
+                                     downloaded videos in it.
+    --include-ads                    Download advertisements as well
+                                     (experimental)
 
 ## Download Options:
-    -r, --rate-limit LIMIT           Maximum download rate in bytes per second (e.g. 50K or 4.2M)
-    -R, --retries RETRIES            Number of retries (default is 10), or "infinite".
-    --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K) (default is 1024)
-    --no-resize-buffer               Do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
+    -r, --rate-limit LIMIT           Maximum download rate in bytes per second
+                                     (e.g. 50K or 4.2M)
+    -R, --retries RETRIES            Number of retries (default is 10), or
+                                     "infinite".
+    --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
+                                     (default is 1024)
+    --no-resize-buffer               Do not automatically adjust the buffer
+                                     size. By default, the buffer size is
+                                     automatically resized from an initial value
+                                     of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
-    --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
-    --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
-    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,wget
-    --external-downloader-args ARGS  Give these arguments to the external downloader
+    --xattr-set-filesize             Set file xattribute ytdl.filesize with
+                                     expected filesize (experimental)
+    --hls-prefer-native              Use the native HLS downloader instead of
+                                     ffmpeg (experimental)
+    --external-downloader COMMAND    Use the specified external downloader.
+                                     Currently supports
+                                     aria2c,axel,curl,httpie,wget
+    --external-downloader-args ARGS  Give these arguments to the external
+                                     downloader
 
 ## Filesystem Options:
-    -a, --batch-file FILE            File containing URLs to download ('-' for stdin)
+    -a, --batch-file FILE            File containing URLs to download ('-' for
+                                     stdin)
     --id                             Use only video ID in file name
-    -o, --output TEMPLATE            Output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
-                                     nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for
-                                     the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like YouTube's itags: "137"),
-                                     %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id,
-                                     %(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
-                                     %(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format.
-                                     %(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout.
-                                     Can also be used to download to a different directory, for example with -o '/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
-    --autonumber-size NUMBER         Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
-    --restrict-filenames             Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames
-    -A, --auto-number                [deprecated; use  -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000
-    -t, --title                      [deprecated] Use title in file name (default)
+    -o, --output TEMPLATE            Output filename template. Use %(title)s to
+                                     get the title, %(uploader)s for the
+                                     uploader name, %(uploader_id)s for the
+                                     uploader nickname if different,
+                                     %(autonumber)s to get an automatically
+                                     incremented number, %(ext)s for the
+                                     filename extension, %(format)s for the
+                                     format description (like "22 - 1280x720" or
+                                     "HD"), %(format_id)s for the unique id of
+                                     the format (like YouTube's itags: "137"),
+                                     %(upload_date)s for the upload date
+                                     (YYYYMMDD), %(extractor)s for the provider
+                                     (youtube, metacafe, etc), %(id)s for the
+                                     video id, %(playlist_title)s,
+                                     %(playlist_id)s, or %(playlist)s (=title if
+                                     present, ID otherwise) for the playlist the
+                                     video is in, %(playlist_index)s for the
+                                     position in the playlist. %(height)s and
+                                     %(width)s for the width and height of the
+                                     video format. %(resolution)s for a textual
+                                     description of the resolution of the video
+                                     format. %% for a literal percent. Use - to
+                                     output to stdout. Can also be used to
+                                     download to a different directory, for
+                                     example with -o '/my/downloads/%(uploader)s
+                                     /%(title)s-%(id)s.%(ext)s' .
+    --autonumber-size NUMBER         Specify the number of digits in
+                                     %(autonumber)s when it is present in output
+                                     filename template or --auto-number option
+                                     is given
+    --restrict-filenames             Restrict filenames to only ASCII
+                                     characters, and avoid "&" and spaces in
+                                     filenames
+    -A, --auto-number                [deprecated; use -o
+                                     "%(autonumber)s-%(title)s.%(ext)s" ] Number
+                                     downloaded files starting from 00000
+    -t, --title                      [deprecated] Use title in file name
+                                     (default)
     -l, --literal                    [deprecated] Alias of --title
     -w, --no-overwrites              Do not overwrite files
-    -c, --continue                   Force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
-    --no-continue                    Do not resume partially downloaded files (restart from beginning)
-    --no-part                        Do not use .part files - write directly into output file
-    --no-mtime                       Do not use the Last-modified header to set the file modification time
-    --write-description              Write video description to a .description file
+    -c, --continue                   Force resume of partially downloaded files.
+                                     By default, youtube-dl will resume
+                                     downloads if possible.
+    --no-continue                    Do not resume partially downloaded files
+                                     (restart from beginning)
+    --no-part                        Do not use .part files - write directly
+                                     into output file
+    --no-mtime                       Do not use the Last-modified header to set
+                                     the file modification time
+    --write-description              Write video description to a .description
+                                     file
     --write-info-json                Write video metadata to a .info.json file
-    --write-annotations              Write video annotations to a .annotations.xml file
-    --load-info FILE                 JSON file containing the video information (created with the "--write-info-json" option)
-    --cookies FILE                   File to read cookies from and dump cookie jar in
-    --cache-dir DIR                  Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
-                                     or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
-                                     change.
+    --write-annotations              Write video annotations to a
+                                     .annotations.xml file
+    --load-info FILE                 JSON file containing the video information
+                                     (created with the "--write-info-json"
+                                     option)
+    --cookies FILE                   File to read cookies from and dump cookie
+                                     jar in
+    --cache-dir DIR                  Location in the filesystem where youtube-dl
+                                     can store some downloaded information
+                                     permanently. By default $XDG_CACHE_HOME
+                                     /youtube-dl or ~/.cache/youtube-dl . At the
+                                     moment, only YouTube player files (for
+                                     videos with obfuscated signatures) are
+                                     cached, but that may change.
     --no-cache-dir                   Disable filesystem caching
     --rm-cache-dir                   Delete all filesystem cache files
 
 ## Thumbnail images:
     --write-thumbnail                Write thumbnail image to disk
     --write-all-thumbnails           Write all thumbnail image formats to disk
-    --list-thumbnails                Simulate and list all available thumbnail formats
+    --list-thumbnails                Simulate and list all available thumbnail
+                                     formats
 
 ## Verbosity / Simulation Options:
     -q, --quiet                      Activate quiet mode
     --no-warnings                    Ignore warnings
-    -s, --simulate                   Do not download the video and do not write anything to disk
+    -s, --simulate                   Do not download the video and do not write
+                                     anything to disk
     --skip-download                  Do not download the video
     -g, --get-url                    Simulate, quiet but print URL
     -e, --get-title                  Simulate, quiet but print title
@@ -160,85 +272,170 @@ which means you can modify it, redistribute it or use it however you like.
     --get-duration                   Simulate, quiet but print video length
     --get-filename                   Simulate, quiet but print output filename
     --get-format                     Simulate, quiet but print output format
-    -j, --dump-json                  Simulate, quiet but print JSON information. See --output for a description of available keys.
-    -J, --dump-single-json           Simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
-                                     information in a single line.
-    --print-json                     Be quiet and print the video information as JSON (video is still being downloaded).
+    -j, --dump-json                  Simulate, quiet but print JSON information.
+                                     See --output for a description of available
+                                     keys.
+    -J, --dump-single-json           Simulate, quiet but print JSON information
+                                     for each command-line argument. If the URL
+                                     refers to a playlist, dump the whole
+                                     playlist information in a single line.
+    --print-json                     Be quiet and print the video information as
+                                     JSON (video is still being downloaded).
     --newline                        Output progress bar as new lines
     --no-progress                    Do not print progress bar
     --console-title                  Display progress in console titlebar
     -v, --verbose                    Print various debugging information
-    --dump-pages                     Print downloaded pages encoded using base64 to debug problems (very verbose)
-    --write-pages                    Write downloaded intermediary pages to files in the current directory to debug problems
+    --dump-pages                     Print downloaded pages encoded using base64
+                                     to debug problems (very verbose)
+    --write-pages                    Write downloaded intermediary pages to
+                                     files in the current directory to debug
+                                     problems
     --print-traffic                  Display sent and read HTTP traffic
     -C, --call-home                  Contact the youtube-dl server for debugging
-    --no-call-home                   Do NOT contact the youtube-dl server for debugging
+    --no-call-home                   Do NOT contact the youtube-dl server for
+                                     debugging
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
     --no-check-certificate           Suppress HTTPS certificate validation
-    --prefer-insecure                Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
+    --prefer-insecure                Use an unencrypted connection to retrieve
+                                     information about the video. (Currently
+                                     supported only for YouTube)
     --user-agent UA                  Specify a custom user agent
-    --referer URL                    Specify a custom referer, use if the video access is restricted to one domain
-    --add-header FIELD:VALUE         Specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
-    --bidi-workaround                Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
-    --sleep-interval SECONDS         Number of seconds to sleep before each download.
+    --referer URL                    Specify a custom referer, use if the video
+                                     access is restricted to one domain
+    --add-header FIELD:VALUE         Specify a custom HTTP header and its value,
+                                     separated by a colon ':'. You can use this
+                                     option multiple times
+    --bidi-workaround                Work around terminals that lack
+                                     bidirectional text support. Requires bidiv
+                                     or fribidi executable in PATH
+    --sleep-interval SECONDS         Number of seconds to sleep before each
+                                     download.
 
 ## Video Format Options:
-    -f, --format FORMAT              Video format code, see the "FORMAT SELECTION" for all the info
+    -f, --format FORMAT              Video format code, see the "FORMAT
+                                     SELECTION" for all the info
     --all-formats                    Download all available video formats
-    --prefer-free-formats            Prefer free video formats unless a specific one is requested
+    --prefer-free-formats            Prefer free video formats unless a specific
+                                     one is requested
     -F, --list-formats               List all available formats
-    --youtube-skip-dash-manifest     Do not download the DASH manifest on YouTube videos
-    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
-                                     merge is required
+    --youtube-skip-dash-manifest     Do not download the DASH manifests and
+                                     related data on YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g.
+                                     bestvideo+bestaudio), output to given
+                                     container format. One of mkv, mp4, ogg,
+                                     webm, flv. Ignored if no merge is required
 
 ## Subtitle Options:
     --write-sub                      Write subtitle file
-    --write-auto-sub                 Write automatic subtitle file (YouTube only)
-    --all-subs                       Download all the available subtitles of the video
+    --write-auto-sub                 Write automatic subtitle file (YouTube
+                                     only)
+    --all-subs                       Download all the available subtitles of the
+                                     video
     --list-subs                      List all available subtitles for the video
-    --sub-format FORMAT              Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"
-    --sub-lang LANGS                 Languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
+    --sub-format FORMAT              Subtitle format, accepts formats
+                                     preference, for example: "srt" or
+                                     "ass/srt/best"
+    --sub-lang LANGS                 Languages of the subtitles to download
+                                     (optional) separated by commas, use IETF
+                                     language tags like 'en,pt'
 
 ## Authentication Options:
     -u, --username USERNAME          Login with this account ID
-    -p, --password PASSWORD          Account password. If this option is left out, youtube-dl will ask interactively.
+    -p, --password PASSWORD          Account password. If this option is left
+                                     out, youtube-dl will ask interactively.
     -2, --twofactor TWOFACTOR        Two-factor auth code
     -n, --netrc                      Use .netrc authentication data
-    --video-password PASSWORD        Video password (vimeo, smotri)
+    --video-password PASSWORD        Video password (vimeo, smotri, youku)
 
 ## Post-processing Options:
-    -x, --extract-audio              Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
-    --audio-format FORMAT            Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
-    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
-                                     5)
-    --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
-    -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
-    --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
-    --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
+    -x, --extract-audio              Convert video files to audio-only files
+                                     (requires ffmpeg or avconv and ffprobe or
+                                     avprobe)
+    --audio-format FORMAT            Specify audio format: "best", "aac",
+                                     "vorbis", "mp3", "m4a", "opus", or "wav";
+                                     "best" by default
+    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert
+                                     a value between 0 (better) and 9 (worse)
+                                     for VBR or a specific bitrate like 128K
+                                     (default 5)
+    --recode-video FORMAT            Encode the video to another format if
+                                     necessary (currently supported:
+                                     mp4|flv|ogg|webm|mkv|avi)
+    --postprocessor-args ARGS        Give these arguments to the postprocessor
+    -k, --keep-video                 Keep the video file on disk after the post-
+                                     processing; the video is erased by default
+    --no-post-overwrites             Do not overwrite post-processed files; the
+                                     post-processed files are overwritten by
+                                     default
+    --embed-subs                     Embed subtitles in the video (only for mkv
+                                     and mp4 videos)
     --embed-thumbnail                Embed thumbnail in the audio as cover art
     --add-metadata                   Write metadata to the video file
-    --metadata-from-title FORMAT     Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
-                                     parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
-                                     %(title)s" matches a title like "Coldplay - Paradise"
-    --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
-    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default;
-                                     fix file if we can, warn otherwise)
-    --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
-    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.
-    --exec CMD                       Execute a command on the file after downloading, similar to find's -exec syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm
-                                     {}'
-    --convert-subtitles FORMAT       Convert the subtitles to other format (currently supported: srt|ass|vtt)
+    --metadata-from-title FORMAT     Parse additional metadata like song title /
+                                     artist from the video title. The format
+                                     syntax is the same as --output, the parsed
+                                     parameters replace existing values.
+                                     Additional templates: %(album)s,
+                                     %(artist)s. Example: --metadata-from-title
+                                     "%(artist)s - %(title)s" matches a title
+                                     like "Coldplay - Paradise"
+    --xattrs                         Write metadata to the video file's xattrs
+                                     (using dublin core and xdg standards)
+    --fixup POLICY                   Automatically correct known faults of the
+                                     file. One of never (do nothing), warn (only
+                                     emit a warning), detect_or_warn (the
+                                     default; fix file if we can, warn
+                                     otherwise)
+    --prefer-avconv                  Prefer avconv over ffmpeg for running the
+                                     postprocessors (default)
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
+                                     postprocessors
+    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
+                                     either the path to the binary or its
+                                     containing directory.
+    --exec CMD                       Execute a command on the file after
+                                     downloading, similar to find's -exec
+                                     syntax. Example: --exec 'adb push {}
+                                     /sdcard/Music/ && rm {}'
+    --convert-subtitles FORMAT       Convert the subtitles to other format
+                                     (currently supported: srt|ass|vtt)
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
+You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime and use a proxy:
+```
+--extract-audio
+--no-mtime
+--proxy 127.0.0.1:3128
+```
+
+You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
+
+### Authentication with `.netrc` file ###
+
+You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
+```
+touch $HOME/.netrc
+chmod a-rwx,u+rw $HOME/.netrc
+```
+After that you can add credentials for extractor in the following format, where *extractor* is the name of extractor in lowercase:
+```
+machine <extractor> login <login> password <password>
+```
+For example:
+```
+machine youtube login myaccount@gmail.com password my_youtube_password
+machine twitch login my_twitch_account_name password my_twitch_password
+```
+To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration).
+
+On Windows you may also need to setup the `%HOME%` environment variable manually.
 
 # OUTPUT TEMPLATE
 
-The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
+The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
 
  - `id`: The sequence will be replaced by the video identifier.
  - `url`: The sequence will be replaced by the video URL.
@@ -248,8 +445,10 @@ The `-o` option allows users to indicate a template for the output file names. T
  - `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
  - `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
  - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- - `playlist`: The name or the id of the playlist that contains the video.
- - `playlist_index`: The index of the video in the playlist, a five-digit number.
+ - `playlist`: The sequence will be replaced by the name or the id of the playlist that contains the video.
+ - `playlist_index`: The sequence will be replaced by the index of the video in the playlist padded with leading zeros according to the total length of the playlist.
+ - `format_id`: The sequence will be replaced by the format code specified by `--format`.
+ - `duration`: The sequence will be replaced by the length of the video in seconds.
 
 The current default template is `%(title)s-%(id)s.%(ext)s`.
 
@@ -264,18 +463,18 @@ youtube-dl_test_video_.mp4          # A simple file name
 
 # FORMAT SELECTION
 
-By default youtube-dl tries to download the best quality, but sometimes you may want to download other format.
+By default youtube-dl tries to download the best quality, but sometimes you may want to download in a different format.
 The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
 
-If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).  This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so  `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`.
+If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).  This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so  `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
 
-Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
+Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
 
-If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
+If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
 
 # VIDEO SELECTION
 
-Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
+Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`. They accept dates in two formats:
 
  - Absolute dates: Dates in the format `YYYYMMDD`.
  - Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?`
@@ -289,7 +488,7 @@ $ youtube-dl --dateafter now-6months
 # Download only the videos uploaded on January 1, 1970
 $ youtube-dl --date 19700101
 
-$ # will only download the videos uploaded in the 200x decade
+$ # Download only the videos uploaded in the 200x decade
 $ youtube-dl --dateafter 20000101 --datebefore 20091231
 ```
 
@@ -301,7 +500,7 @@ If you've followed [our manual installation instructions](http://rg3.github.io/y
 
 If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
 
-If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distributions serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
+If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
 
 As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
 
@@ -327,7 +526,7 @@ If you have installed youtube-dl with a package manager, pip, setup.py or a tarb
 
 By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`.
 
-### Can you please put the -b option back?
+### Can you please put the `-b` option back?
 
 Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the `-b` option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you're interested in. In that case, simply request it with the `-f` option and youtube-dl will try to download it.
 
@@ -339,13 +538,13 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
 
 Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
 
-### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser.
+### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
 
 It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies.  Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
 
 It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
 
-Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well.
+Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using `-g`, your own downloader must support these as well.
 
 If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn.
 
@@ -359,7 +558,7 @@ YouTube requires an additional signature since September 2012 which is not suppo
 
 ### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
 
-That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
+That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
 
 For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
 
@@ -379,7 +578,7 @@ In February 2015, the new YouTube player contained a character sequence in a str
 
 ### HTTP Error 429: Too Many Requests or 402: Payment Required
 
-These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--network-address` options](#network-options) to select another IP address.
+These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
 
 ### SyntaxError: Non-ASCII character ###
 
@@ -417,6 +616,12 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
     youtube-dl -- -wNyEUrxzFU
     youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
 
+### How do I pass cookies to youtube-dl?
+
+Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
+
+Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly.
+
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
 As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
@@ -505,18 +710,19 @@ If you want to add support for a new site, you can follow this quick list (assum
             webpage = self._download_webpage(url, video_id)
 
             # TODO more code goes here, for example ...
-            title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+            title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
 
             return {
                 'id': video_id,
                 'title': title,
                 'description': self._og_search_description(webpage),
+                'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
-6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
-7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
+7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
@@ -544,7 +750,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L117-L265). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
@@ -589,7 +795,7 @@ Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/i
 
 **Please include the full output of youtube-dl when run with `-v`**.
 
-The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
+The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
 Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
 
@@ -605,15 +811,15 @@ So please elaborate on what feature you are requesting, or what bug you want to
 
 If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
 
-For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
+For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
 
-If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
+If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
 **Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
 
 ###  Are you using the latest version?
 
-Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
+Before reporting any issue, type `youtube-dl -U`. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
 
 ###  Is the issue already documented?
 

devscripts/bash-completion.py

@@ -5,7 +5,7 @@ import os
 from os.path import dirname as dirn
 import sys
 
-sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
+sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
 import youtube_dl
 
 BASH_COMPLETION_FILE = "youtube-dl.bash-completion"

devscripts/fish-completion.py

@@ -6,7 +6,7 @@ import os
 from os.path import dirname as dirn
 import sys
 
-sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
+sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
 import youtube_dl
 from youtube_dl.utils import shell_quote
 

devscripts/gh-pages/update-sites.py

@@ -6,7 +6,7 @@ import os
 import textwrap
 
 # We must be able to import youtube_dl
-sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
 
 import youtube_dl
 

devscripts/make_supportedsites.py

@@ -9,7 +9,7 @@ import sys
 
 # Import youtube_dl
 ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
-sys.path.append(ROOT_DIR)
+sys.path.insert(0, ROOT_DIR)
 import youtube_dl
 
 

devscripts/prepare_manpage.py

@@ -8,6 +8,35 @@ import re
 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 README_FILE = os.path.join(ROOT_DIR, 'README.md')
 
+
+def filter_options(readme):
+    ret = ''
+    in_options = False
+    for line in readme.split('\n'):
+        if line.startswith('# '):
+            if line[2:].startswith('OPTIONS'):
+                in_options = True
+            else:
+                in_options = False
+
+        if in_options:
+            if line.lstrip().startswith('-'):
+                option, description = re.split(r'\s{2,}', line.lstrip())
+                split_option = option.split(' ')
+
+                if not split_option[-1].startswith('-'):  # metavar
+                    option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
+
+                # Pandoc's definition_lists. See http://pandoc.org/README.html
+                # for more information.
+                ret += '\n%s\n:   %s\n' % (option, description)
+            else:
+                ret += line.lstrip() + '\n'
+        else:
+            ret += line + '\n'
+
+    return ret
+
 with io.open(README_FILE, encoding='utf-8') as f:
     readme = f.read()
 
@@ -26,6 +55,8 @@ readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
 readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
 readme = PREFIX + readme
 
+readme = filter_options(readme)
+
 if sys.version_info < (3, 0):
     print(readme.encode('utf-8'))
 else:

devscripts/zsh-completion.py

@@ -5,7 +5,7 @@ import os
 from os.path import dirname as dirn
 import sys
 
-sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
+sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
 import youtube_dl
 
 ZSH_COMPLETION_FILE = "youtube-dl.zsh"

docs/supportedsites.md

@@ -17,6 +17,7 @@
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVVideo**
  - **AdultSwim**
  - **Aftenposten**
  - **Aftonbladet**
@@ -27,7 +28,8 @@
  - **anitube.se**
  - **AnySex**
  - **Aparat**
- - **AppleDaily**
+ - **AppleConnect**
+ - **AppleDaily**: 臺灣蘋果日報
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -44,12 +46,14 @@
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
- - **BaiduVideo**
+ - **BaiduVideo**: 百度视频
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
  - **Bandcamp:album**
+ - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
+ - **bbc.co.uk:article**: BBC articles
  - **BeatportPro**
  - **Beeg**
  - **BehindKink**
@@ -78,16 +82,18 @@
  - **CBSSports**
  - **CeskaTelevize**
  - **channel9**: Channel 9
+ - **Chaturbate**
  - **Chilloutzone**
  - **chirbit**
  - **chirbit:profile**
  - **Cinchcast**
  - **Cinemassacre**
- - **clipfish**
+ - **Clipfish**
  - **cliphunter**
  - **Clipsyndicate**
  - **Cloudy**
  - **Clubic**
+ - **Clyp**
  - **cmt.com**
  - **CNET**
  - **CNN**
@@ -98,28 +104,30 @@
  - **ComCarCoff**
  - **ComedyCentral**
  - **ComedyCentralShows**: The Daily Show / The Colbert Report
- - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
+ - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
  - **Cracked**
  - **Criterion**
  - **CrooksAndLiars**
  - **Crunchyroll**
  - **crunchyroll:playlist**
  - **CSpan**: C-SPAN
- - **CtsNews**
+ - **CtsNews**: 華視新聞
  - **culturebox.francetvinfo.fr**
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
+ - **DailymotionCloud**
  - **daum.net**
  - **DBTV**
+ - **DCN**
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
+ - **democracynow**
  - **DHM**: Filmarchiv - Deutsches Historisches Museum
  - **Discovery**
- - **divxstage**: DivxStage
  - **Dotsub**
- - **DouyuTV**
+ - **DouyuTV**: 斗鱼
  - **dramafever**
  - **dramafever:series**
  - **DRBonanza**
@@ -145,6 +153,8 @@
  - **EroProfile**
  - **Escapist**
  - **ESPN** (Currently broken)
+ - **EsriVideo**
+ - **Europa**
  - **EveryonesMixtape**
  - **exfm**: ex.fm
  - **ExpoTV**
@@ -152,15 +162,15 @@
  - **facebook**
  - **faz.net**
  - **fc2**
+ - **Fczenit**
  - **fernsehkritik.tv**
- - **fernsehkritik.tv:postecke**
  - **Firstpost**
  - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
  - **Foxgay**
- - **FoxNews**
+ - **FoxNews**: Fox News and Fox Business Video
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
@@ -186,10 +196,10 @@
  - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
+ - **GloboArticle**
  - **GodTube**
  - **GoldenMoustache**
  - **Golem**
- - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net
  - **Goshgay**
  - **Groupon**
  - **Hark**
@@ -203,7 +213,6 @@
  - **hitbox**
  - **hitbox:live**
  - **HornBunny**
- - **HostingBulk**
  - **HotNewHipHop**
  - **Howcast**
  - **HowStuffWorks**
@@ -214,13 +223,17 @@
  - **imdb**: Internet Movie Database trailers
  - **imdb:list**: Internet Movie Database lists
  - **Imgur**
+ - **ImgurAlbum**
  - **Ina**
+ - **Indavideo**
+ - **IndavideoEmbed**
  - **InfoQ**
  - **Instagram**
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
  - **IPrima**
- - **iqiyi**
+ - **iqiyi**: 爱奇艺
+ - **Ir90Tv**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **Izlesene**
@@ -241,14 +254,24 @@
  - **kontrtube**: KontrTube.ru - Труба зовёт
  - **KrasView**: Красвью
  - **Ku6**
+ - **kuwo:album**: 酷我音乐 - 专辑
+ - **kuwo:category**: 酷我音乐 - 分类
+ - **kuwo:chart**: 酷我音乐 - 排行榜
+ - **kuwo:mv**: 酷我音乐 - MV
+ - **kuwo:singer**: 酷我音乐 - 歌手
+ - **kuwo:song**: 酷我音乐
  - **la7.tv**
  - **Laola1Tv**
- - **Letv**
+ - **Lecture2Go**
+ - **Letv**: 乐视网
  - **LetvPlaylist**
  - **LetvTv**
  - **Libsyn**
  - **life:embed**
  - **lifenews**: LIFE | NEWS
+ - **limelight**
+ - **limelight:channel**
+ - **limelight:channel_list**
  - **LiveLeak**
  - **livestream**
  - **livestream:original**
@@ -260,16 +283,15 @@
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
  - **Malemotion**
- - **MDR**
+ - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
- - **MegaVideoz**
  - **metacafe**
  - **Metacritic**
  - **Mgoon**
  - **Minhateca**
  - **MinistryGrid**
  - **miomio.tv**
- - **mitele.es**
+ - **MiTele**: mitele.es
  - **mixcloud**
  - **MLB**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
@@ -281,22 +303,25 @@
  - **Motherless**
  - **Motorsport**: motorsport.com
  - **MovieClips**
+ - **MovieFap**
  - **Moviezine**
  - **movshare**: MovShare
  - **MPORA**
+ - **MSNBC**
  - **MTV**
+ - **mtv.de**
  - **mtviggy.com**
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
  - **MusicPlayOn**
- - **MusicVault**
  - **muzu.tv**
+ - **Mwave**
  - **MySpace**
  - **MySpace:album**
  - **MySpass**
+ - **Myvi**
  - **myvideo**
  - **MyVidster**
- - **N-JOY**
  - **n-tv.de**
  - **NationalGeographic**
  - **Naver**
@@ -305,15 +330,24 @@
  - **NBCNews**
  - **NBCSports**
  - **NBCSportsVPlayer**
- - **ndr**: NDR.de - Mediathek
+ - **ndr**: NDR.de - Norddeutscher Rundfunk
+ - **ndr:embed**
+ - **ndr:embed:base**
  - **NDTV**
  - **NerdCubedFeed**
  - **Nerdist**
+ - **netease:album**: 网易云音乐 - 专辑
+ - **netease:djradio**: 网易云音乐 - 电台
+ - **netease:mv**: 网易云音乐 - MV
+ - **netease:playlist**: 网易云音乐 - 歌单
+ - **netease:program**: 网易云音乐 - 电台节目
+ - **netease:singer**: 网易云音乐 - 歌手
+ - **netease:song**: 网易云音乐
  - **Netzkino**
  - **Newgrounds**
  - **Newstube**
- - **NextMedia**
- - **NextMediaActionNews**
+ - **NextMedia**: 蘋果日報
+ - **NextMediaActionNews**: 蘋果日報 - 動新聞
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
@@ -321,21 +355,25 @@
  - **nhl.com:videocenter**: NHL videocenter category
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
+ - **njoy**: N-JOY
+ - **njoy:embed**
  - **Noco**
  - **Normalboots**
  - **NosVideo**
  - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
  - **novamov**: NovaMov
- - **Nowness**
+ - **nowness**
+ - **nowness:playlist**
+ - **nowness:series**
  - **NowTV**
  - **nowvideo**: NowVideo
- - **npo.nl**
+ - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
  - **NRKPlaylist**
- - **NRKTV**
+ - **NRKTV**: NRK TV and NRK Radio
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
@@ -344,9 +382,9 @@
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
- - **OpenFilm**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
@@ -354,15 +392,20 @@
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **PBS**
+ - **Periscope**: Periscope
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
+ - **Pinkbike**
  - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
  - **played.to**
+ - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
  - **Playwire**
+ - **pluralsight**
+ - **pluralsight:course**
  - **plus.google**: Google Plus
  - **pluzz.francetv.fr**
  - **podomatic**
@@ -377,10 +420,12 @@
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
  - **Pyvideo**
- - **qqmusic**
- - **qqmusic:album**
- - **qqmusic:singer**
- - **qqmusic:toplist**
+ - **qqmusic**: QQ音乐
+ - **qqmusic:album**: QQ音乐 - 专辑
+ - **qqmusic:playlist**: QQ音乐 - 歌单
+ - **qqmusic:singer**: QQ音乐 - 歌手
+ - **qqmusic:toplist**: QQ音乐 - 排行榜
+ - **Quickscope**: Quick Scope
  - **QuickVid**
  - **R7**
  - **radio.de**
@@ -389,6 +434,7 @@
  - **RadioJavan**
  - **Rai**
  - **RBMARadio**
+ - **RDS**: RDS.ca
  - **RedTube**
  - **Restudy**
  - **ReverbNation**
@@ -404,6 +450,7 @@
  - **rtve.es:alacarta**: RTVE a la carta
  - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
+ - **RTVNH**
  - **RUHD**
  - **rutube**: Rutube videos
  - **rutube:channel**: Rutube channels
@@ -427,7 +474,8 @@
  - **ServingSys**
  - **Sexu**
  - **SexyKarma**: Sexy Karma and Watch Indian Porn
- - **Shared**
+ - **Shahid**
+ - **Shared**: shared.sx and vivo.sx
  - **ShareSix**
  - **Sina**
  - **Slideshare**
@@ -436,6 +484,8 @@
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
+ - **SnagFilms**
+ - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
  - **soompi**
@@ -462,11 +512,13 @@
  - **SportBox**
  - **SportBoxEmbed**
  - **SportDeutschland**
+ - **Sportschau**
  - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
  - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
+ - **Stitcher**
  - **streamcloud.eu**
  - **StreamCZ**
  - **StreetVoice**
@@ -487,9 +539,9 @@
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
- - **tegenlicht.vpro.nl**
  - **TeleBruxelles**
- - **telecinco.es**
+ - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
+ - **Telegraaf**
  - **TeleMB**
  - **TeleTask**
  - **TenPlay**
@@ -497,7 +549,9 @@
  - **TF1**
  - **TheOnion**
  - **ThePlatform**
+ - **ThePlatformFeed**
  - **TheSixtyOne**
+ - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
  - **THVideoPlaylist**
@@ -538,10 +592,12 @@
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
+ - **twitter**
+ - **twitter:card**
  - **Ubu**
  - **udemy**
  - **udemy:course**
- - **UDNEmbed**
+ - **UDNEmbed**: 聯合影音
  - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
@@ -560,10 +616,8 @@
  - **Viddler**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
- - **VideoBam**
  - **VideoDetective**
  - **videofy.me**
- - **videolectures.net**
  - **VideoMega**
  - **VideoPremium**
  - **VideoTt**: video.tt - Your True Tube
@@ -573,6 +627,7 @@
  - **vier**
  - **vier:videos**
  - **Viewster**
+ - **Viidea**
  - **viki**
  - **viki:channel**
  - **vimeo**
@@ -586,11 +641,13 @@
  - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
- - **vk.com**
- - **vk.com:user-videos**: vk.com:All of a user's videos
+ - **vk**: VK
+ - **vk:uservideos**: VK - User's Videos
+ - **vlive**
  - **Vodlocker**
  - **VoiceRepublic**
  - **Vporn**
+ - **vpro**: npo.nl and ntr.nl
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
@@ -603,32 +660,37 @@
  - **wdr:mobile**
  - **WDRMaus**: Sendung mit der Maus
  - **WebOfStories**
+ - **WebOfStoriesPlaylist**
  - **Weibo**
  - **Wimp**
  - **Wistia**
+ - **WNL**
  - **WorldStarHipHop**
  - **wrzuta.pl**
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
+ - **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me
  - **XHamster**
+ - **XHamsterEmbed**
  - **XMinus**
  - **XNXX**
  - **Xstream**
  - **XTube**
  - **XTubeUser**: XTube user profile
- - **Xuite**
+ - **Xuite**: 隨意窩Xuite影音
  - **XVideos**
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
- - **Yam**
+ - **Yam**: 蕃薯藤yam天空部落
  - **yandexmusic:album**: Яндекс.Музыка - Альбом
  - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
  - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
+ - **yinyuetai:video**: 音悦Tai
  - **Ynet**
  - **YouJizz**
- - **Youku**
+ - **youku**: 优酷
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com

setup.py

@@ -28,7 +28,7 @@ py2exe_options = {
     "compressed": 1,
     "optimize": 2,
     "dist_dir": '.',
-    "dll_excludes": ['w9xpopen.exe'],
+    "dll_excludes": ['w9xpopen.exe', 'crypt32.dll'],
 }
 
 py2exe_console = [{

test/helper.py

@@ -89,66 +89,81 @@ def gettestcases(include_onlymatching=False):
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
 
-def expect_info_dict(self, got_dict, expected_dict):
+def expect_value(self, got, expected, field):
+    if isinstance(expected, compat_str) and expected.startswith('re:'):
+        match_str = expected[len('re:'):]
+        match_rex = re.compile(match_str)
+
+        self.assertTrue(
+            isinstance(got, compat_str),
+            'Expected a %s object, but got %s for field %s' % (
+                compat_str.__name__, type(got).__name__, field))
+        self.assertTrue(
+            match_rex.match(got),
+            'field %s (value: %r) should match %r' % (field, got, match_str))
+    elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
+        start_str = expected[len('startswith:'):]
+        self.assertTrue(
+            isinstance(got, compat_str),
+            'Expected a %s object, but got %s for field %s' % (
+                compat_str.__name__, type(got).__name__, field))
+        self.assertTrue(
+            got.startswith(start_str),
+            'field %s (value: %r) should start with %r' % (field, got, start_str))
+    elif isinstance(expected, compat_str) and expected.startswith('contains:'):
+        contains_str = expected[len('contains:'):]
+        self.assertTrue(
+            isinstance(got, compat_str),
+            'Expected a %s object, but got %s for field %s' % (
+                compat_str.__name__, type(got).__name__, field))
+        self.assertTrue(
+            contains_str in got,
+            'field %s (value: %r) should contain %r' % (field, got, contains_str))
+    elif isinstance(expected, type):
+        self.assertTrue(
+            isinstance(got, expected),
+            'Expected type %r for field %s, but got value %r of type %r' % (expected, field, got, type(got)))
+    elif isinstance(expected, dict) and isinstance(got, dict):
+        expect_dict(self, got, expected)
+    elif isinstance(expected, list) and isinstance(got, list):
+        self.assertEqual(
+            len(expected), len(got),
+            'Expect a list of length %d, but got a list of length %d for field %s' % (
+                len(expected), len(got), field))
+        for index, (item_got, item_expected) in enumerate(zip(got, expected)):
+            type_got = type(item_got)
+            type_expected = type(item_expected)
+            self.assertEqual(
+                type_expected, type_got,
+                'Type mismatch for list item at index %d for field %s, expected %r, got %r' % (
+                    index, field, type_expected, type_got))
+            expect_value(self, item_got, item_expected, field)
+    else:
+        if isinstance(expected, compat_str) and expected.startswith('md5:'):
+            got = 'md5:' + md5(got)
+        elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
+            self.assertTrue(
+                isinstance(got, (list, dict)),
+                'Expected field %s to be a list or a dict, but it is of type %s' % (
+                    field, type(got).__name__))
+            expected_num = int(expected.partition(':')[2])
+            assertGreaterEqual(
+                self, len(got), expected_num,
+                'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got)))
+            return
+        self.assertEqual(
+            expected, got,
+            'Invalid value for field %s, expected %r, got %r' % (field, expected, got))
+
+
+def expect_dict(self, got_dict, expected_dict):
     for info_field, expected in expected_dict.items():
-        if isinstance(expected, compat_str) and expected.startswith('re:'):
-            got = got_dict.get(info_field)
-            match_str = expected[len('re:'):]
-            match_rex = re.compile(match_str)
+        got = got_dict.get(info_field)
+        expect_value(self, got, expected, info_field)
 
-            self.assertTrue(
-                isinstance(got, compat_str),
-                'Expected a %s object, but got %s for field %s' % (
-                    compat_str.__name__, type(got).__name__, info_field))
-            self.assertTrue(
-                match_rex.match(got),
-                'field %s (value: %r) should match %r' % (info_field, got, match_str))
-        elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
-            got = got_dict.get(info_field)
-            start_str = expected[len('startswith:'):]
-            self.assertTrue(
-                isinstance(got, compat_str),
-                'Expected a %s object, but got %s for field %s' % (
-                    compat_str.__name__, type(got).__name__, info_field))
-            self.assertTrue(
-                got.startswith(start_str),
-                'field %s (value: %r) should start with %r' % (info_field, got, start_str))
-        elif isinstance(expected, compat_str) and expected.startswith('contains:'):
-            got = got_dict.get(info_field)
-            contains_str = expected[len('contains:'):]
-            self.assertTrue(
-                isinstance(got, compat_str),
-                'Expected a %s object, but got %s for field %s' % (
-                    compat_str.__name__, type(got).__name__, info_field))
-            self.assertTrue(
-                contains_str in got,
-                'field %s (value: %r) should contain %r' % (info_field, got, contains_str))
-        elif isinstance(expected, type):
-            got = got_dict.get(info_field)
-            self.assertTrue(isinstance(got, expected),
-                            'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
-        else:
-            if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                got = 'md5:' + md5(got_dict.get(info_field))
-            elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
-                got = got_dict.get(info_field)
-                self.assertTrue(
-                    isinstance(got, list),
-                    'Expected field %s to be a list, but it is of type %s' % (
-                        info_field, type(got).__name__))
-                expected_num = int(expected.partition(':')[2])
-                assertGreaterEqual(
-                    self, len(got), expected_num,
-                    'Expected %d items in field %s, but only got %d' % (
-                        expected_num, info_field, len(got)
-                    )
-                )
-                continue
-            else:
-                got = got_dict.get(info_field)
-            self.assertEqual(expected, got,
-                             'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
+def expect_info_dict(self, got_dict, expected_dict):
+    expect_dict(self, got_dict, expected_dict)
     # Check for the presence of mandatory fields
     if got_dict.get('_type') not in ('playlist', 'multi_video'):
         for key in ('id', 'url', 'title', 'ext'):
@@ -160,7 +175,7 @@ def expect_info_dict(self, got_dict, expected_dict):
     # Are checkable fields missing from the test case definition?
     test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
                           for key, value in got_dict.items()
-                          if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
+                          if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location', 'age_limit'))
     missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
     if missing_keys:
         def _repr(v):

test/test_InfoExtractor.py

@@ -35,10 +35,18 @@ class TestInfoExtractor(unittest.TestCase):
             <meta name="og:title" content='Foo'/>
             <meta content="Some video's description " name="og:description"/>
             <meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
+            <meta content='application/x-shockwave-flash' property='og:video:type'>
+            <meta content='Foo' property=og:foobar>
+            <meta name="og:test1" content='foo > < bar'/>
+            <meta name="og:test2" content="foo >//< bar"/>
             '''
         self.assertEqual(ie._og_search_title(html), 'Foo')
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
         self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
+        self.assertEqual(ie._og_search_video_url(html, default=None), None)
+        self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
+        self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
+        self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
 
     def test_html_search_meta(self):
         ie = self.ie

test/test_YoutubeDL.py

@@ -15,7 +15,7 @@ from youtube_dl import YoutubeDL
 from youtube_dl.compat import compat_str
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
-from youtube_dl.utils import match_filter_func
+from youtube_dl.utils import ExtractorError, match_filter_func
 
 TEST_URL = 'http://localhost/sample.mp4'
 
@@ -105,6 +105,7 @@ class TestFormatSelection(unittest.TestCase):
     def test_format_selection(self):
         formats = [
             {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
             {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
             {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
             {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
@@ -136,6 +137,11 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], '35')
 
+        ydl = YDL({'format': 'example-with-dashes'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'example-with-dashes')
+
     def test_format_selection_audio(self):
         formats = [
             {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
@@ -229,21 +235,70 @@ class TestFormatSelection(unittest.TestCase):
             '141', '172', '140', '171', '139',
         ]
 
-        for f1id, f2id in zip(order, order[1:]):
-            f1 = YoutubeIE._formats[f1id].copy()
-            f1['format_id'] = f1id
-            f1['url'] = 'url:' + f1id
-            f2 = YoutubeIE._formats[f2id].copy()
-            f2['format_id'] = f2id
-            f2['url'] = 'url:' + f2id
+        def format_info(f_id):
+            info = YoutubeIE._formats[f_id].copy()
+            info['format_id'] = f_id
+            info['url'] = 'url:' + f_id
+            return info
+        formats_order = [format_info(f_id) for f_id in order]
 
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': 'bestvideo+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], '137+141')
+        self.assertEqual(downloaded['ext'], 'mp4')
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], '38')
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': 'bestvideo/best,bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['137', '141'])
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['137+141', '248+141'])
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['136+141', '247+141'])
+
+        info_dict = _make_result(list(formats_order), extractor='youtube')
+        ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
+        yie = YoutubeIE(ydl)
+        yie._sort_formats(info_dict['formats'])
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['248+141'])
+
+        for f1, f2 in zip(formats_order, formats_order[1:]):
             info_dict = _make_result([f1, f2], extractor='youtube')
             ydl = YDL({'format': 'best/bestvideo'})
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
             ydl.process_ie_result(info_dict)
             downloaded = ydl.downloaded_info_dicts[0]
-            self.assertEqual(downloaded['format_id'], f1id)
+            self.assertEqual(downloaded['format_id'], f1['format_id'])
 
             info_dict = _make_result([f2, f1], extractor='youtube')
             ydl = YDL({'format': 'best/bestvideo'})
@@ -251,7 +306,18 @@ class TestFormatSelection(unittest.TestCase):
             yie._sort_formats(info_dict['formats'])
             ydl.process_ie_result(info_dict)
             downloaded = ydl.downloaded_info_dicts[0]
-            self.assertEqual(downloaded['format_id'], f1id)
+            self.assertEqual(downloaded['format_id'], f1['format_id'])
+
+    def test_invalid_format_specs(self):
+        def assert_syntax_error(format_spec):
+            ydl = YDL({'format': format_spec})
+            info_dict = _make_result([{'format_id': 'foo', 'url': TEST_URL}])
+            self.assertRaises(SyntaxError, ydl.process_ie_result, info_dict)
+
+        assert_syntax_error('bestvideo,,best')
+        assert_syntax_error('+bestaudio')
+        assert_syntax_error('bestvideo+')
+        assert_syntax_error('/')
 
     def test_format_filtering(self):
         formats = [
@@ -308,6 +374,18 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'G')
 
+        ydl = YDL({'format': 'all[width>=400][width<=600]'})
+        ydl.process_ie_result(info_dict)
+        downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
+        self.assertEqual(downloaded_ids, ['B', 'C', 'D'])
+
+        ydl = YDL({'format': 'best[height<40]'})
+        try:
+            ydl.process_ie_result(info_dict)
+        except ExtractorError:
+            pass
+        self.assertEqual(ydl.downloaded_info_dicts, [])
+
 
 class TestYoutubeDL(unittest.TestCase):
     def test_subtitles(self):

test/test_compat.py

@@ -13,7 +13,12 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from youtube_dl.utils import get_filesystem_encoding
 from youtube_dl.compat import (
     compat_getenv,
+    compat_etree_fromstring,
     compat_expanduser,
+    compat_shlex_split,
+    compat_str,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,
 )
 
 
@@ -42,5 +47,46 @@ class TestCompat(unittest.TestCase):
             dir(youtube_dl.compat))) - set(['unicode_literals'])
         self.assertEqual(all_names, sorted(present_names))
 
+    def test_compat_urllib_parse_unquote(self):
+        self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
+        self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def')
+        self.assertEqual(compat_urllib_parse_unquote(''), '')
+        self.assertEqual(compat_urllib_parse_unquote('%'), '%')
+        self.assertEqual(compat_urllib_parse_unquote('%%'), '%%')
+        self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%')
+        self.assertEqual(compat_urllib_parse_unquote('%2F'), '/')
+        self.assertEqual(compat_urllib_parse_unquote('%2f'), '/')
+        self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波')
+        self.assertEqual(
+            compat_urllib_parse_unquote('''<meta property="og:description" content="%E2%96%81%E2%96%82%E2%96%83%E2%96%84%25%E2%96%85%E2%96%86%E2%96%87%E2%96%88" />
+%<a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B3%D9%88%D9%86%D8%A7%D9%85%D9%8A">%a'''),
+            '''<meta property="og:description" content="▁▂▃▄%▅▆▇█" />
+%<a href="https://ar.wikipedia.org/wiki/تسونامي">%a''')
+        self.assertEqual(
+            compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%87%80    %E2%86%B6%I%Break%25Things%'''),
+            '''(^◣_◢^)っ︻デ═一    ⇀    ⇀    ⇀    ⇀    ⇀    ↶%I%Break%Things%''')
+
+    def test_compat_urllib_parse_unquote_plus(self):
+        self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
+        self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
+
+    def test_compat_shlex_split(self):
+        self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
+
+    def test_compat_etree_fromstring(self):
+        xml = '''
+            <root foo="bar" spam="中文">
+                <normal>foo</normal>
+                <chinese>中文</chinese>
+                <foo><bar>spam</bar></foo>
+            </root>
+        '''
+        doc = compat_etree_fromstring(xml.encode('utf-8'))
+        self.assertTrue(isinstance(doc.attrib['foo'], compat_str))
+        self.assertTrue(isinstance(doc.attrib['spam'], compat_str))
+        self.assertTrue(isinstance(doc.find('normal').text, compat_str))
+        self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
+        self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -102,7 +102,7 @@ def generator(test_case):
 
         params = get_params(test_case.get('params', {}))
         if is_playlist and 'playlist' not in test_case:
-            params.setdefault('extract_flat', True)
+            params.setdefault('extract_flat', 'in_playlist')
             params.setdefault('skip_download', True)
 
         ydl = YoutubeDL(params, auto_init=False)
@@ -136,7 +136,9 @@ def generator(test_case):
                     # We're not using .download here sine that is just a shim
                     # for outside error handling, and returns the exit code
                     # instead of the result dict.
-                    res_dict = ydl.extract_info(test_case['url'])
+                    res_dict = ydl.extract_info(
+                        test_case['url'],
+                        force_generic_extractor=params.get('force_generic_extractor', False))
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
                     if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):

test/test_jsinterp.py

@@ -19,6 +19,9 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function x3(){return 42;}')
         self.assertEqual(jsi.call_function('x3'), 42)
 
+        jsi = JSInterpreter('var x5 = function(){return 42;}')
+        self.assertEqual(jsi.call_function('x5'), 42)
+
     def test_calc(self):
         jsi = JSInterpreter('function x4(a){return 2*a+1;}')
         self.assertEqual(jsi.call_function('x4', 3), 7)

test/test_subtitles.py

@@ -25,8 +25,10 @@ from youtube_dl.extractor import (
     RaiIE,
     VikiIE,
     ThePlatformIE,
+    ThePlatformFeedIE,
     RTVEALaCartaIE,
     FunnyOrDieIE,
+    DemocracynowIE,
 )
 
 
@@ -307,6 +309,18 @@ class TestThePlatformSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
 
 
+class TestThePlatformFeedSubtitles(BaseTestSubtitles):
+    url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
+    IE = ThePlatformFeedIE
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), '48649a22e82b2da21c9a67a395eedade')
+
+
 class TestRtveSubtitles(BaseTestSubtitles):
     url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/'
     IE = RTVEALaCartaIE
@@ -333,5 +347,25 @@ class TestFunnyOrDieSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
 
 
+class TestDemocracynowSubtitles(BaseTestSubtitles):
+    url = 'http://www.democracynow.org/shows/2015/7/3'
+    IE = DemocracynowIE
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+
+    def test_subtitles_in_page(self):
+        self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -57,11 +57,19 @@ from youtube_dl.utils import (
     urlencode_postdata,
     version_tuple,
     xpath_with_ns,
+    xpath_element,
     xpath_text,
+    xpath_attr,
     render_table,
     match_str,
     parse_dfxp_time_expr,
     dfxp2srt,
+    cli_option,
+    cli_valueless_option,
+    cli_bool_option,
+)
+from youtube_dl.compat import (
+    compat_etree_fromstring,
 )
 
 
@@ -228,6 +236,7 @@ class TestUtil(unittest.TestCase):
             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
             '20150202')
         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
+        self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -235,12 +244,21 @@ class TestUtil(unittest.TestCase):
             <node x="a"/>
             <node x="a" y="c" />
             <node x="b" y="d" />
+            <node x="" />
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
 
+        self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
 
     def test_xpath_with_ns(self):
         testxml = '''<root xmlns:media="http://example.com/">
@@ -249,23 +267,56 @@ class TestUtil(unittest.TestCase):
                 <url>http://server.com/download.mp3</url>
             </media:song>
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
         self.assertTrue(find('media:song') is not None)
         self.assertEqual(find('media:song/media:author').text, 'The Author')
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
+    def test_xpath_element(self):
+        doc = xml.etree.ElementTree.Element('root')
+        div = xml.etree.ElementTree.SubElement(doc, 'div')
+        p = xml.etree.ElementTree.SubElement(div, 'p')
+        p.text = 'Foo'
+        self.assertEqual(xpath_element(doc, 'div/p'), p)
+        self.assertEqual(xpath_element(doc, ['div/p']), p)
+        self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
+        self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
+        self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
+        self.assertTrue(xpath_element(doc, 'div/bar') is None)
+        self.assertTrue(xpath_element(doc, ['div/bar']) is None)
+        self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
+        self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
+        self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
+        self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
+
     def test_xpath_text(self):
         testxml = '''<root>
             <div>
                 <p>Foo</p>
             </div>
         </root>'''
-        doc = xml.etree.ElementTree.fromstring(testxml)
+        doc = compat_etree_fromstring(testxml)
         self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+        self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
         self.assertTrue(xpath_text(doc, 'div/bar') is None)
         self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
 
+    def test_xpath_attr(self):
+        testxml = '''<root>
+            <div>
+                <p x="a">Foo</p>
+            </div>
+        </root>'''
+        doc = compat_etree_fromstring(testxml)
+        self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
+        self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
+        self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
+        self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
+        self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
+        self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
+        self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
+
     def test_smuggle_url(self):
         data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
@@ -324,6 +375,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('02:03:04'), 7384)
         self.assertEqual(parse_duration('01:02:03:04'), 93784)
         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
+        self.assertEqual(parse_duration('87 Min.'), 5220)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -384,6 +436,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
+        self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
+        self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
 
     def test_strip_jsonp(self):
         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@@ -454,6 +508,9 @@ class TestUtil(unittest.TestCase):
             "playlist":[{"controls":{"all":null}}]
         }''')
 
+        inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
+        self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
+
         inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
         json_code = js_to_json(inp)
         self.assertEqual(json.loads(json_code), json.loads(inp))
@@ -636,6 +693,51 @@ The first line
 '''
         self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
 
+    def test_cli_option(self):
+        self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
+        self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
+        self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
+
+    def test_cli_valueless_option(self):
+        self.assertEqual(cli_valueless_option(
+            {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
+        self.assertEqual(cli_valueless_option(
+            {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
+        self.assertEqual(cli_valueless_option(
+            {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
+        self.assertEqual(cli_valueless_option(
+            {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
+        self.assertEqual(cli_valueless_option(
+            {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
+        self.assertEqual(cli_valueless_option(
+            {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
+
+    def test_cli_bool_option(self):
+        self.assertEqual(
+            cli_bool_option(
+                {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
+            ['--no-check-certificate', 'true'])
+        self.assertEqual(
+            cli_bool_option(
+                {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
+            ['--no-check-certificate=true'])
+        self.assertEqual(
+            cli_bool_option(
+                {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
+            ['--check-certificate', 'false'])
+        self.assertEqual(
+            cli_bool_option(
+                {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
+            ['--check-certificate=false'])
+        self.assertEqual(
+            cli_bool_option(
+                {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
+            ['--check-certificate', 'true'])
+        self.assertEqual(
+            cli_bool_option(
+                {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
+            ['--check-certificate=true'])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -33,7 +33,7 @@ params = get_params({
 
 
 TEST_ID = 'gr51aVj-mLg'
-ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
+ANNOTATIONS_FILE = TEST_ID + '.annotations.xml'
 EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
 
 

test/test_youtube_lists.py

@@ -57,5 +57,14 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertEqual(len(entries), 100)
 
+    def test_youtube_flat_playlist_titles(self):
+        dl = FakeYDL()
+        dl.params['extract_flat'] = True
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
+        self.assertIsPlaylist(result)
+        for entry in result['entries']:
+            self.assertTrue(entry.get('title'))
+
 if __name__ == '__main__':
     unittest.main()

tox.ini

@@ -1,5 +1,5 @@
 [tox]
-envlist = py26,py27,py33,py34
+envlist = py26,py27,py33,py34,py35
 [testenv]
 deps =
    nose

youtube_dl/YoutubeDL.py

@@ -21,24 +21,25 @@ import subprocess
 import socket
 import sys
 import time
+import tokenize
 import traceback
 
 if os.name == 'nt':
     import ctypes
 
 from .compat import (
-    compat_basestring,
     compat_cookiejar,
     compat_expanduser,
     compat_get_terminal_size,
     compat_http_client,
     compat_kwargs,
     compat_str,
+    compat_tokenize_tokenize,
     compat_urllib_error,
     compat_urllib_request,
+    compat_urllib_request_DataHandler,
 )
 from .utils import (
-    escape_url,
     ContentTooShortError,
     date_from_str,
     DateRange,
@@ -49,7 +50,6 @@ from .utils import (
     ExtractorError,
     format_bytes,
     formatSeconds,
-    HEADRequest,
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
@@ -70,6 +70,7 @@ from .utils import (
     version_tuple,
     write_json_file,
     write_string,
+    YoutubeDLCookieProcessor,
     YoutubeDLHandler,
     prepend_extension,
     replace_extension,
@@ -139,6 +140,7 @@ class YoutubeDL(object):
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
+    force_generic_extractor: Force downloader to use the generic extractor
     nooverwrites:      Prevent overwriting files.
     playliststart:     Playlist item to start at.
     playlistend:       Playlist item to end at.
@@ -261,6 +263,8 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
+    postprocessor_args: A list of additional command-line arguments for the
+                        postprocessor.
     """
 
     params = None
@@ -282,7 +286,11 @@ class YoutubeDL(object):
         self._num_downloads = 0
         self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
         self._err_file = sys.stderr
-        self.params = params
+        self.params = {
+            # Default parameters
+            'nocheckcertificate': False,
+        }
+        self.params.update(params)
         self.cache = Cache(self)
 
         if params.get('bidi_workaround', False):
@@ -564,7 +572,7 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
+            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787
@@ -572,7 +580,7 @@ class YoutubeDL(object):
             # to workaround encoding issues with subprocess on python2 @ Windows
             if sys.version_info < (3, 0) and sys.platform == 'win32':
                 filename = encodeFilename(filename, True).decode(preferredencoding())
-            return filename
+            return sanitize_path(filename)
         except ValueError as err:
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
@@ -626,13 +634,16 @@ class YoutubeDL(object):
             info_dict.setdefault(key, value)
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
-                     process=True):
+                     process=True, force_generic_extractor=False):
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
         '''
 
+        if not ie_key and force_generic_extractor:
+            ie_key = 'Generic'
+
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
         else:
@@ -847,8 +858,8 @@ class YoutubeDL(object):
         else:
             raise Exception('Invalid result type: %s' % result_type)
 
-    def _apply_format_filter(self, format_spec, available_formats):
-        " Returns a tuple of the remaining format_spec and filtered formats "
+    def _build_format_filter(self, filter_spec):
+        " Returns a function to filter the formats according to the filter_spec "
 
         OPERATORS = {
             '<': operator.lt,
@@ -858,13 +869,13 @@ class YoutubeDL(object):
             '=': operator.eq,
             '!=': operator.ne,
         }
-        operator_rex = re.compile(r'''(?x)\s*\[
+        operator_rex = re.compile(r'''(?x)\s*
             (?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)
             \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
             (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
-            \]$
+            $
             ''' % '|'.join(map(re.escape, OPERATORS.keys())))
-        m = operator_rex.search(format_spec)
+        m = operator_rex.search(filter_spec)
         if m:
             try:
                 comparison_value = int(m.group('value'))
@@ -875,7 +886,7 @@ class YoutubeDL(object):
                 if comparison_value is None:
                     raise ValueError(
                         'Invalid value %r in format specification %r' % (
-                            m.group('value'), format_spec))
+                            m.group('value'), filter_spec))
             op = OPERATORS[m.group('op')]
 
         if not m:
@@ -883,85 +894,283 @@ class YoutubeDL(object):
                 '=': operator.eq,
                 '!=': operator.ne,
             }
-            str_operator_rex = re.compile(r'''(?x)\s*\[
+            str_operator_rex = re.compile(r'''(?x)
                 \s*(?P<key>ext|acodec|vcodec|container|protocol)
                 \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
                 \s*(?P<value>[a-zA-Z0-9_-]+)
-                \s*\]$
+                \s*$
                 ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
-            m = str_operator_rex.search(format_spec)
+            m = str_operator_rex.search(filter_spec)
             if m:
                 comparison_value = m.group('value')
                 op = STR_OPERATORS[m.group('op')]
 
         if not m:
-            raise ValueError('Invalid format specification %r' % format_spec)
+            raise ValueError('Invalid filter specification %r' % filter_spec)
 
         def _filter(f):
             actual_value = f.get(m.group('key'))
             if actual_value is None:
                 return m.group('none_inclusive')
             return op(actual_value, comparison_value)
-        new_formats = [f for f in available_formats if _filter(f)]
+        return _filter
 
-        new_format_spec = format_spec[:-len(m.group(0))]
-        if not new_format_spec:
-            new_format_spec = 'best'
+    def build_format_selector(self, format_spec):
+        def syntax_error(note, start):
+            message = (
+                'Invalid format specification: '
+                '{0}\n\t{1}\n\t{2}^'.format(note, format_spec, ' ' * start[1]))
+            return SyntaxError(message)
 
-        return (new_format_spec, new_formats)
+        PICKFIRST = 'PICKFIRST'
+        MERGE = 'MERGE'
+        SINGLE = 'SINGLE'
+        GROUP = 'GROUP'
+        FormatSelector = collections.namedtuple('FormatSelector', ['type', 'selector', 'filters'])
 
-    def select_format(self, format_spec, available_formats):
-        while format_spec.endswith(']'):
-            format_spec, available_formats = self._apply_format_filter(
-                format_spec, available_formats)
-        if not available_formats:
-            return None
+        def _parse_filter(tokens):
+            filter_parts = []
+            for type, string, start, _, _ in tokens:
+                if type == tokenize.OP and string == ']':
+                    return ''.join(filter_parts)
+                else:
+                    filter_parts.append(string)
 
-        if format_spec in ['best', 'worst', None]:
-            format_idx = 0 if format_spec == 'worst' else -1
-            audiovideo_formats = [
-                f for f in available_formats
-                if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
-            if audiovideo_formats:
-                return audiovideo_formats[format_idx]
-            # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format
-            elif (all(f.get('acodec') != 'none' for f in available_formats) or
-                  all(f.get('vcodec') != 'none' for f in available_formats)):
-                return available_formats[format_idx]
-        elif format_spec == 'bestaudio':
-            audio_formats = [
-                f for f in available_formats
-                if f.get('vcodec') == 'none']
-            if audio_formats:
-                return audio_formats[-1]
-        elif format_spec == 'worstaudio':
-            audio_formats = [
-                f for f in available_formats
-                if f.get('vcodec') == 'none']
-            if audio_formats:
-                return audio_formats[0]
-        elif format_spec == 'bestvideo':
-            video_formats = [
-                f for f in available_formats
-                if f.get('acodec') == 'none']
-            if video_formats:
-                return video_formats[-1]
-        elif format_spec == 'worstvideo':
-            video_formats = [
-                f for f in available_formats
-                if f.get('acodec') == 'none']
-            if video_formats:
-                return video_formats[0]
-        else:
-            extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
-            if format_spec in extensions:
-                filter_f = lambda f: f['ext'] == format_spec
-            else:
-                filter_f = lambda f: f['format_id'] == format_spec
-            matches = list(filter(filter_f, available_formats))
-            if matches:
-                return matches[-1]
-        return None
+        def _remove_unused_ops(tokens):
+            # Remove operators that we don't use and join them with the sourrounding strings
+            # for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
+            ALLOWED_OPS = ('/', '+', ',', '(', ')')
+            last_string, last_start, last_end, last_line = None, None, None, None
+            for type, string, start, end, line in tokens:
+                if type == tokenize.OP and string == '[':
+                    if last_string:
+                        yield tokenize.NAME, last_string, last_start, last_end, last_line
+                        last_string = None
+                    yield type, string, start, end, line
+                    # everything inside brackets will be handled by _parse_filter
+                    for type, string, start, end, line in tokens:
+                        yield type, string, start, end, line
+                        if type == tokenize.OP and string == ']':
+                            break
+                elif type == tokenize.OP and string in ALLOWED_OPS:
+                    if last_string:
+                        yield tokenize.NAME, last_string, last_start, last_end, last_line
+                        last_string = None
+                    yield type, string, start, end, line
+                elif type in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]:
+                    if not last_string:
+                        last_string = string
+                        last_start = start
+                        last_end = end
+                    else:
+                        last_string += string
+            if last_string:
+                yield tokenize.NAME, last_string, last_start, last_end, last_line
+
+        def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, inside_group=False):
+            selectors = []
+            current_selector = None
+            for type, string, start, _, _ in tokens:
+                # ENCODING is only defined in python 3.x
+                if type == getattr(tokenize, 'ENCODING', None):
+                    continue
+                elif type in [tokenize.NAME, tokenize.NUMBER]:
+                    current_selector = FormatSelector(SINGLE, string, [])
+                elif type == tokenize.OP:
+                    if string == ')':
+                        if not inside_group:
+                            # ')' will be handled by the parentheses group
+                            tokens.restore_last_token()
+                        break
+                    elif inside_merge and string in ['/', ',']:
+                        tokens.restore_last_token()
+                        break
+                    elif inside_choice and string == ',':
+                        tokens.restore_last_token()
+                        break
+                    elif string == ',':
+                        if not current_selector:
+                            raise syntax_error('"," must follow a format selector', start)
+                        selectors.append(current_selector)
+                        current_selector = None
+                    elif string == '/':
+                        if not current_selector:
+                            raise syntax_error('"/" must follow a format selector', start)
+                        first_choice = current_selector
+                        second_choice = _parse_format_selection(tokens, inside_choice=True)
+                        current_selector = FormatSelector(PICKFIRST, (first_choice, second_choice), [])
+                    elif string == '[':
+                        if not current_selector:
+                            current_selector = FormatSelector(SINGLE, 'best', [])
+                        format_filter = _parse_filter(tokens)
+                        current_selector.filters.append(format_filter)
+                    elif string == '(':
+                        if current_selector:
+                            raise syntax_error('Unexpected "("', start)
+                        group = _parse_format_selection(tokens, inside_group=True)
+                        current_selector = FormatSelector(GROUP, group, [])
+                    elif string == '+':
+                        video_selector = current_selector
+                        audio_selector = _parse_format_selection(tokens, inside_merge=True)
+                        if not video_selector or not audio_selector:
+                            raise syntax_error('"+" must be between two format selectors', start)
+                        current_selector = FormatSelector(MERGE, (video_selector, audio_selector), [])
+                    else:
+                        raise syntax_error('Operator not recognized: "{0}"'.format(string), start)
+                elif type == tokenize.ENDMARKER:
+                    break
+            if current_selector:
+                selectors.append(current_selector)
+            return selectors
+
+        def _build_selector_function(selector):
+            if isinstance(selector, list):
+                fs = [_build_selector_function(s) for s in selector]
+
+                def selector_function(formats):
+                    for f in fs:
+                        for format in f(formats):
+                            yield format
+                return selector_function
+            elif selector.type == GROUP:
+                selector_function = _build_selector_function(selector.selector)
+            elif selector.type == PICKFIRST:
+                fs = [_build_selector_function(s) for s in selector.selector]
+
+                def selector_function(formats):
+                    for f in fs:
+                        picked_formats = list(f(formats))
+                        if picked_formats:
+                            return picked_formats
+                    return []
+            elif selector.type == SINGLE:
+                format_spec = selector.selector
+
+                def selector_function(formats):
+                    formats = list(formats)
+                    if not formats:
+                        return
+                    if format_spec == 'all':
+                        for f in formats:
+                            yield f
+                    elif format_spec in ['best', 'worst', None]:
+                        format_idx = 0 if format_spec == 'worst' else -1
+                        audiovideo_formats = [
+                            f for f in formats
+                            if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
+                        if audiovideo_formats:
+                            yield audiovideo_formats[format_idx]
+                        # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format
+                        elif (all(f.get('acodec') != 'none' for f in formats) or
+                              all(f.get('vcodec') != 'none' for f in formats)):
+                            yield formats[format_idx]
+                    elif format_spec == 'bestaudio':
+                        audio_formats = [
+                            f for f in formats
+                            if f.get('vcodec') == 'none']
+                        if audio_formats:
+                            yield audio_formats[-1]
+                    elif format_spec == 'worstaudio':
+                        audio_formats = [
+                            f for f in formats
+                            if f.get('vcodec') == 'none']
+                        if audio_formats:
+                            yield audio_formats[0]
+                    elif format_spec == 'bestvideo':
+                        video_formats = [
+                            f for f in formats
+                            if f.get('acodec') == 'none']
+                        if video_formats:
+                            yield video_formats[-1]
+                    elif format_spec == 'worstvideo':
+                        video_formats = [
+                            f for f in formats
+                            if f.get('acodec') == 'none']
+                        if video_formats:
+                            yield video_formats[0]
+                    else:
+                        extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
+                        if format_spec in extensions:
+                            filter_f = lambda f: f['ext'] == format_spec
+                        else:
+                            filter_f = lambda f: f['format_id'] == format_spec
+                        matches = list(filter(filter_f, formats))
+                        if matches:
+                            yield matches[-1]
+            elif selector.type == MERGE:
+                def _merge(formats_info):
+                    format_1, format_2 = [f['format_id'] for f in formats_info]
+                    # The first format must contain the video and the
+                    # second the audio
+                    if formats_info[0].get('vcodec') == 'none':
+                        self.report_error('The first format must '
+                                          'contain the video, try using '
+                                          '"-f %s+%s"' % (format_2, format_1))
+                        return
+                    output_ext = (
+                        formats_info[0]['ext']
+                        if self.params.get('merge_output_format') is None
+                        else self.params['merge_output_format'])
+                    return {
+                        'requested_formats': formats_info,
+                        'format': '%s+%s' % (formats_info[0].get('format'),
+                                             formats_info[1].get('format')),
+                        'format_id': '%s+%s' % (formats_info[0].get('format_id'),
+                                                formats_info[1].get('format_id')),
+                        'width': formats_info[0].get('width'),
+                        'height': formats_info[0].get('height'),
+                        'resolution': formats_info[0].get('resolution'),
+                        'fps': formats_info[0].get('fps'),
+                        'vcodec': formats_info[0].get('vcodec'),
+                        'vbr': formats_info[0].get('vbr'),
+                        'stretched_ratio': formats_info[0].get('stretched_ratio'),
+                        'acodec': formats_info[1].get('acodec'),
+                        'abr': formats_info[1].get('abr'),
+                        'ext': output_ext,
+                    }
+                video_selector, audio_selector = map(_build_selector_function, selector.selector)
+
+                def selector_function(formats):
+                    formats = list(formats)
+                    for pair in itertools.product(video_selector(formats), audio_selector(formats)):
+                        yield _merge(pair)
+
+            filters = [self._build_format_filter(f) for f in selector.filters]
+
+            def final_selector(formats):
+                for _filter in filters:
+                    formats = list(filter(_filter, formats))
+                return selector_function(formats)
+            return final_selector
+
+        stream = io.BytesIO(format_spec.encode('utf-8'))
+        try:
+            tokens = list(_remove_unused_ops(compat_tokenize_tokenize(stream.readline)))
+        except tokenize.TokenError:
+            raise syntax_error('Missing closing/opening brackets or parenthesis', (0, len(format_spec)))
+
+        class TokenIterator(object):
+            def __init__(self, tokens):
+                self.tokens = tokens
+                self.counter = 0
+
+            def __iter__(self):
+                return self
+
+            def __next__(self):
+                if self.counter >= len(self.tokens):
+                    raise StopIteration()
+                value = self.tokens[self.counter]
+                self.counter += 1
+                return value
+
+            next = __next__
+
+            def restore_last_token(self):
+                self.counter -= 1
+
+        parsed_selector = _parse_format_selection(iter(TokenIterator(tokens)))
+        return _build_selector_function(parsed_selector)
 
     def _calc_headers(self, info_dict):
         res = std_headers.copy()
@@ -1004,7 +1213,7 @@ class YoutubeDL(object):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
-                if 'width' in t and 'height' in t:
+                if t.get('width') and t.get('height'):
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i
@@ -1024,21 +1233,22 @@ class YoutubeDL(object):
             except (ValueError, OverflowError, OSError):
                 pass
 
+        subtitles = info_dict.get('subtitles')
+        if subtitles:
+            for _, subtitle in subtitles.items():
+                for subtitle_format in subtitle:
+                    if 'ext' not in subtitle_format:
+                        subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
+
         if self.params.get('listsubtitles', False):
             if 'automatic_captions' in info_dict:
                 self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions')
-            self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles')
+            self.list_subtitles(info_dict['id'], subtitles, 'subtitles')
             return
         info_dict['requested_subtitles'] = self.process_subtitles(
-            info_dict['id'], info_dict.get('subtitles'),
+            info_dict['id'], subtitles,
             info_dict.get('automatic_captions'))
 
-        # This extractors handle format selection themselves
-        if info_dict['extractor'] in ['Youku']:
-            if download:
-                self.process_info(info_dict)
-            return info_dict
-
         # We now pick which formats have to be downloaded
         if info_dict.get('formats') is None:
             # There's only one format available
@@ -1104,62 +1314,15 @@ class YoutubeDL(object):
         if req_format is None:
             req_format_list = []
             if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
-                    info_dict['extractor'] in ['youtube', 'ted']):
+                    info_dict['extractor'] in ['youtube', 'ted'] and
+                    not info_dict.get('is_live')):
                 merger = FFmpegMergerPP(self)
                 if merger.available and merger.can_merge():
                     req_format_list.append('bestvideo+bestaudio')
             req_format_list.append('best')
             req_format = '/'.join(req_format_list)
-        formats_to_download = []
-        if req_format == 'all':
-            formats_to_download = formats
-        else:
-            for rfstr in req_format.split(','):
-                # We can accept formats requested in the format: 34/5/best, we pick
-                # the first that is available, starting from left
-                req_formats = rfstr.split('/')
-                for rf in req_formats:
-                    if re.match(r'.+?\+.+?', rf) is not None:
-                        # Two formats have been requested like '137+139'
-                        format_1, format_2 = rf.split('+')
-                        formats_info = (self.select_format(format_1, formats),
-                                        self.select_format(format_2, formats))
-                        if all(formats_info):
-                            # The first format must contain the video and the
-                            # second the audio
-                            if formats_info[0].get('vcodec') == 'none':
-                                self.report_error('The first format must '
-                                                  'contain the video, try using '
-                                                  '"-f %s+%s"' % (format_2, format_1))
-                                return
-                            output_ext = (
-                                formats_info[0]['ext']
-                                if self.params.get('merge_output_format') is None
-                                else self.params['merge_output_format'])
-                            selected_format = {
-                                'requested_formats': formats_info,
-                                'format': '%s+%s' % (formats_info[0].get('format'),
-                                                     formats_info[1].get('format')),
-                                'format_id': '%s+%s' % (formats_info[0].get('format_id'),
-                                                        formats_info[1].get('format_id')),
-                                'width': formats_info[0].get('width'),
-                                'height': formats_info[0].get('height'),
-                                'resolution': formats_info[0].get('resolution'),
-                                'fps': formats_info[0].get('fps'),
-                                'vcodec': formats_info[0].get('vcodec'),
-                                'vbr': formats_info[0].get('vbr'),
-                                'stretched_ratio': formats_info[0].get('stretched_ratio'),
-                                'acodec': formats_info[1].get('acodec'),
-                                'abr': formats_info[1].get('abr'),
-                                'ext': output_ext,
-                            }
-                        else:
-                            selected_format = None
-                    else:
-                        selected_format = self.select_format(rf, formats)
-                    if selected_format is not None:
-                        formats_to_download.append(selected_format)
-                        break
+        format_selector = self.build_format_selector(req_format)
+        formats_to_download = list(format_selector(formats))
         if not formats_to_download:
             raise ExtractorError('requested format not available',
                                  expected=True)
@@ -1499,7 +1662,8 @@ class YoutubeDL(object):
         for url in url_list:
             try:
                 # It also downloads the videos
-                res = self.extract_info(url)
+                res = self.extract_info(
+                    url, force_generic_extractor=self.params.get('force_generic_extractor', False))
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
@@ -1706,27 +1870,6 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
-
-        # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
-        # always respected by websites, some tend to give out URLs with non percent-encoded
-        # non-ASCII characters (see telemb.py, ard.py [#3412])
-        # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
-        # To work around aforementioned issue we will replace request's original URL with
-        # percent-encoded one
-        req_is_string = isinstance(req, compat_basestring)
-        url = req if req_is_string else req.get_full_url()
-        url_escaped = escape_url(url)
-
-        # Substitute URL if any change after escaping
-        if url != url_escaped:
-            if req_is_string:
-                req = url_escaped
-            else:
-                req_type = HEADRequest if req.get_method() == 'HEAD' else compat_urllib_request.Request
-                req = req_type(
-                    url_escaped, data=req.data, headers=req.headers,
-                    origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
-
         return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):
@@ -1809,8 +1952,7 @@ class YoutubeDL(object):
             if os.access(opts_cookiefile, os.R_OK):
                 self.cookiejar.load()
 
-        cookie_processor = compat_urllib_request.HTTPCookieProcessor(
-            self.cookiejar)
+        cookie_processor = YoutubeDLCookieProcessor(self.cookiejar)
         if opts_proxy is not None:
             if opts_proxy == '':
                 proxies = {}
@@ -1826,8 +1968,9 @@ class YoutubeDL(object):
         debuglevel = 1 if self.params.get('debug_printtraffic') else 0
         https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
         ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
+        data_handler = compat_urllib_request_DataHandler()
         opener = compat_urllib_request.build_opener(
-            proxy_handler, https_handler, cookie_processor, ydlh)
+            proxy_handler, https_handler, cookie_processor, ydlh, data_handler)
 
         # Delete the default user-agent header, which would otherwise apply in
         # cases where our custom HTTP handler doesn't come into play
@@ -1879,7 +2022,7 @@ class YoutubeDL(object):
                                (info_dict['extractor'], info_dict['id'], thumb_display_id))
                 try:
                     uf = self.urlopen(t['url'])
-                    with open(thumb_filename, 'wb') as thumbf:
+                    with open(encodeFilename(thumb_filename), 'wb') as thumbf:
                         shutil.copyfileobj(uf, thumbf)
                     self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
                                    (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))

youtube_dl/__init__.py

@@ -9,7 +9,6 @@ import codecs
 import io
 import os
 import random
-import shlex
 import sys
 
 
@@ -20,6 +19,7 @@ from .compat import (
     compat_expanduser,
     compat_getpass,
     compat_print,
+    compat_shlex_split,
     workaround_optparse_bug9161,
 )
 from .utils import (
@@ -169,7 +169,7 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
             parser.error('invalid video recode format specified')
     if opts.convertsubtitles is not None:
         if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
@@ -262,7 +262,10 @@ def _real_main(argv=None):
             parser.error('setting filesize xattr requested but python-xattr is not available')
     external_downloader_args = None
     if opts.external_downloader_args:
-        external_downloader_args = shlex.split(opts.external_downloader_args)
+        external_downloader_args = compat_shlex_split(opts.external_downloader_args)
+    postprocessor_args = None
+    if opts.postprocessor_args:
+        postprocessor_args = compat_shlex_split(opts.postprocessor_args)
     match_filter = (
         None if opts.match_filter is None
         else match_filter_func(opts.match_filter))
@@ -293,6 +296,7 @@ def _real_main(argv=None):
         'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
+        'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts_retries,
@@ -366,6 +370,7 @@ def _real_main(argv=None):
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
         'external_downloader_args': external_downloader_args,
+        'postprocessor_args': postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
     }
 

youtube_dl/__main__.py

@@ -11,7 +11,7 @@ if __package__ is None and not hasattr(sys, "frozen"):
     # direct call of __main__.py
     import os.path
     path = os.path.realpath(os.path.abspath(__file__))
-    sys.path.append(os.path.dirname(os.path.dirname(path)))
+    sys.path.insert(0, os.path.dirname(os.path.dirname(path)))
 
 import youtube_dl
 

youtube_dl/compat.py

@@ -1,14 +1,20 @@
 from __future__ import unicode_literals
 
+import binascii
 import collections
+import email
 import getpass
+import io
 import optparse
 import os
 import re
+import shlex
 import shutil
 import socket
 import subprocess
 import sys
+import itertools
+import xml.etree.ElementTree
 
 
 try:
@@ -36,11 +42,21 @@ try:
 except ImportError:  # Python 2
     import urlparse as compat_urlparse
 
+try:
+    import urllib.response as compat_urllib_response
+except ImportError:  # Python 2
+    import urllib as compat_urllib_response
+
 try:
     import http.cookiejar as compat_cookiejar
 except ImportError:  # Python 2
     import cookielib as compat_cookiejar
 
+try:
+    import http.cookies as compat_cookies
+except ImportError:  # Python 2
+    import Cookie as compat_cookies
+
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
@@ -74,47 +90,113 @@ except ImportError:
     import BaseHTTPServer as compat_http_server
 
 try:
+    compat_str = unicode  # Python 2
+except NameError:
+    compat_str = str
+
+try:
+    from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
-except ImportError:
-    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
-        if string == '':
+    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
+except ImportError:  # Python 2
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile('([\x00-\x7f]+)'))
+
+    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
+    # implementations from cpython 3.4.3's stdlib. Python 2's version
+    # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
+
+    def compat_urllib_parse_unquote_to_bytes(string):
+        """unquote_to_bytes('abc%20def') -> b'abc def'."""
+        # Note: strings are encoded as UTF-8. This is only an issue if it contains
+        # unescaped non-ASCII characters, which URIs should not.
+        if not string:
+            # Is it a string-like object?
+            string.split
+            return b''
+        if isinstance(string, compat_str):
+            string = string.encode('utf-8')
+        bits = string.split(b'%')
+        if len(bits) == 1:
             return string
-        res = string.split('%')
-        if len(res) == 1:
+        res = [bits[0]]
+        append = res.append
+        for item in bits[1:]:
+            try:
+                append(compat_urllib_parse._hextochr[item[:2]])
+                append(item[2:])
+            except KeyError:
+                append(b'%')
+                append(item)
+        return b''.join(res)
+
+    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+        """Replace %xx escapes by their single-character equivalent. The optional
+        encoding and errors parameters specify how to decode percent-encoded
+        sequences into Unicode characters, as accepted by the bytes.decode()
+        method.
+        By default, percent-encoded sequences are decoded with UTF-8, and invalid
+        sequences are replaced by a placeholder character.
+
+        unquote('abc%20def') -> 'abc def'.
+        """
+        if '%' not in string:
+            string.split
             return string
         if encoding is None:
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
-        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
-        pct_sequence = b''
-        string = res[0]
-        for item in res[1:]:
-            try:
-                if not item:
-                    raise ValueError
-                pct_sequence += item[:2].decode('hex')
-                rest = item[2:]
-                if not rest:
-                    # This segment was just a single percent-encoded character.
-                    # May be part of a sequence of code units, so delay decoding.
-                    # (Stored in pct_sequence).
-                    continue
-            except ValueError:
-                rest = '%' + item
-            # Encountered non-percent-encoded characters. Flush the current
-            # pct_sequence.
-            string += pct_sequence.decode(encoding, errors) + rest
-            pct_sequence = b''
-        if pct_sequence:
-            # Flush the final pct_sequence
-            string += pct_sequence.decode(encoding, errors)
-        return string
+        bits = _asciire.split(string)
+        res = [bits[0]]
+        append = res.append
+        for i in range(1, len(bits), 2):
+            append(compat_urllib_parse_unquote_to_bytes(bits[i]).decode(encoding, errors))
+            append(bits[i + 1])
+        return ''.join(res)
+
+    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
+        """Like unquote(), but also replace plus signs by spaces, as required for
+        unquoting HTML form values.
+
+        unquote_plus('%7e/abc+def') -> '~/abc def'
+        """
+        string = string.replace('+', ' ')
+        return compat_urllib_parse_unquote(string, encoding, errors)
 
 try:
-    compat_str = unicode  # Python 2
-except NameError:
-    compat_str = str
+    from urllib.request import DataHandler as compat_urllib_request_DataHandler
+except ImportError:  # Python < 3.4
+    # Ported from CPython 98774:1733b3bd46db, Lib/urllib/request.py
+    class compat_urllib_request_DataHandler(compat_urllib_request.BaseHandler):
+        def data_open(self, req):
+            # data URLs as specified in RFC 2397.
+            #
+            # ignores POSTed data
+            #
+            # syntax:
+            # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
+            # mediatype := [ type "/" subtype ] *( ";" parameter )
+            # data      := *urlchar
+            # parameter := attribute "=" value
+            url = req.get_full_url()
+
+            scheme, data = url.split(":", 1)
+            mediatype, data = data.split(",", 1)
+
+            # even base64 encoded data URLs might be quoted so unquote in any case:
+            data = compat_urllib_parse_unquote_to_bytes(data)
+            if mediatype.endswith(";base64"):
+                data = binascii.a2b_base64(data)
+                mediatype = mediatype[:-7]
+
+            if not mediatype:
+                mediatype = "text/plain;charset=US-ASCII"
+
+            headers = email.message_from_string(
+                "Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
+
+            return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
 try:
     compat_basestring = basestring  # Python 2
@@ -131,6 +213,43 @@ try:
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
+if sys.version_info[0] >= 3:
+    compat_etree_fromstring = xml.etree.ElementTree.fromstring
+else:
+    # python 2.x tries to encode unicode strings with ascii (see the
+    # XMLParser._fixtext method)
+    etree = xml.etree.ElementTree
+
+    try:
+        _etree_iter = etree.Element.iter
+    except AttributeError:  # Python <=2.6
+        def _etree_iter(root):
+            for el in root.findall('*'):
+                yield el
+                for sub in _etree_iter(el):
+                    yield sub
+
+    # on 2.6 XML doesn't have a parser argument, function copied from CPython
+    # 2.7 source
+    def _XML(text, parser=None):
+        if not parser:
+            parser = etree.XMLParser(target=etree.TreeBuilder())
+        parser.feed(text)
+        return parser.close()
+
+    def _element_factory(*args, **kwargs):
+        el = etree.Element(*args, **kwargs)
+        for k, v in el.items():
+            if isinstance(v, bytes):
+                el.set(k, v.decode('utf-8'))
+        return el
+
+    def compat_etree_fromstring(text):
+        doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory)))
+        for el in _etree_iter(doc):
+            if el.text is not None and isinstance(el.text, bytes):
+                el.text = el.text.decode('utf-8')
+        return doc
 
 try:
     from urllib.parse import parse_qs as compat_parse_qs
@@ -189,6 +308,17 @@ except ImportError:  # Python < 3.3
             return "'" + s.replace("'", "'\"'\"'") + "'"
 
 
+if sys.version_info >= (2, 7, 3):
+    compat_shlex_split = shlex.split
+else:
+    # Working around shlex issue with unicode strings on some python 2
+    # versions (see http://bugs.python.org/issue1548891)
+    def compat_shlex_split(s, comments=False, posix=True):
+        if isinstance(s, compat_str):
+            s = s.encode('utf-8')
+        return shlex.split(s, comments, posix)
+
+
 def compat_ord(c):
     if type(c) is int:
         return c
@@ -366,34 +496,56 @@ if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
 else:
     _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
 
-    def compat_get_terminal_size():
-        columns = compat_getenv('COLUMNS', None)
+    def compat_get_terminal_size(fallback=(80, 24)):
+        columns = compat_getenv('COLUMNS')
         if columns:
             columns = int(columns)
         else:
             columns = None
-        lines = compat_getenv('LINES', None)
+        lines = compat_getenv('LINES')
         if lines:
             lines = int(lines)
         else:
             lines = None
 
-        try:
-            sp = subprocess.Popen(
-                ['stty', 'size'],
-                stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-            out, err = sp.communicate()
-            lines, columns = map(int, out.split())
-        except Exception:
-            pass
+        if columns is None or lines is None or columns <= 0 or lines <= 0:
+            try:
+                sp = subprocess.Popen(
+                    ['stty', 'size'],
+                    stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+                out, err = sp.communicate()
+                _lines, _columns = map(int, out.split())
+            except Exception:
+                _columns, _lines = _terminal_size(*fallback)
+
+            if columns is None or columns <= 0:
+                columns = _columns
+            if lines is None or lines <= 0:
+                lines = _lines
         return _terminal_size(columns, lines)
 
+try:
+    itertools.count(start=0, step=1)
+    compat_itertools_count = itertools.count
+except TypeError:  # Python 2.6
+    def compat_itertools_count(start=0, step=1):
+        n = start
+        while True:
+            yield n
+            n += step
+
+if sys.version_info >= (3, 0):
+    from tokenize import tokenize as compat_tokenize_tokenize
+else:
+    from tokenize import generate_tokens as compat_tokenize_tokenize
 
 __all__ = [
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',
     'compat_cookiejar',
+    'compat_cookies',
+    'compat_etree_fromstring',
     'compat_expanduser',
     'compat_get_terminal_size',
     'compat_getenv',
@@ -401,18 +553,25 @@ __all__ = [
     'compat_html_entities',
     'compat_http_client',
     'compat_http_server',
+    'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',
     'compat_print',
+    'compat_shlex_split',
     'compat_socket_create_connection',
     'compat_str',
     'compat_subprocess_get_DEVNULL',
+    'compat_tokenize_tokenize',
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
+    'compat_urllib_parse_unquote_plus',
+    'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',
+    'compat_urllib_request_DataHandler',
+    'compat_urllib_response',
     'compat_urlparse',
     'compat_urlretrieve',
     'compat_xml_parse_error',

youtube_dl/downloader/__init__.py

@@ -8,6 +8,7 @@ from .hls import NativeHlsFD
 from .http import HttpFD
 from .rtsp import RtspFD
 from .rtmp import RtmpFD
+from .dash import DashSegmentsFD
 
 from ..utils import (
     determine_protocol,
@@ -20,6 +21,7 @@ PROTOCOL_MAP = {
     'mms': RtspFD,
     'rtsp': RtspFD,
     'f4m': F4mFD,
+    'http_dash_segments': DashSegmentsFD,
 }
 
 

youtube_dl/downloader/common.py

@@ -325,7 +325,7 @@ class FileDownloader(object):
         )
 
         # Check file already present
-        if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
+        if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
             self.report_file_already_downloaded(filename)
             self._hook_progress({
                 'filename': filename,

youtube_dl/downloader/dash.py

@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import FileDownloader
+from ..compat import compat_urllib_request
+
+
+class DashSegmentsFD(FileDownloader):
+    """
+    Download segments in a DASH manifest
+    """
+    def real_download(self, filename, info_dict):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+        base_url = info_dict['url']
+        segment_urls = info_dict['segment_urls']
+
+        is_test = self.params.get('test', False)
+        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
+        byte_counter = 0
+
+        def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
+            self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
+            req = compat_urllib_request.Request(target_url)
+            if remaining_bytes is not None:
+                req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
+
+            data = self.ydl.urlopen(req).read()
+
+            if remaining_bytes is not None:
+                data = data[:remaining_bytes]
+
+            outf.write(data)
+            return len(data)
+
+        def combine_url(base_url, target_url):
+            if re.match(r'^https?://', target_url):
+                return target_url
+            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
+
+        with open(tmpfilename, 'wb') as outf:
+            append_url_to_file(
+                outf, combine_url(base_url, info_dict['initialization_url']),
+                'initialization segment')
+            for i, segment_url in enumerate(segment_urls):
+                segment_len = append_url_to_file(
+                    outf, combine_url(base_url, segment_url),
+                    'segment %d / %d' % (i + 1, len(segment_urls)),
+                    remaining_bytes)
+                byte_counter += segment_len
+                if remaining_bytes is not None:
+                    remaining_bytes -= segment_len
+                    if remaining_bytes <= 0:
+                        break
+
+        self.try_rename(tmpfilename, filename)
+
+        self._hook_progress({
+            'downloaded_bytes': byte_counter,
+            'total_bytes': byte_counter,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True

youtube_dl/downloader/external.py

@@ -5,6 +5,10 @@ import subprocess
 
 from .common import FileDownloader
 from ..utils import (
+    cli_option,
+    cli_valueless_option,
+    cli_bool_option,
+    cli_configuration_args,
     encodeFilename,
     encodeArgument,
 )
@@ -45,18 +49,17 @@ class ExternalFD(FileDownloader):
     def supports(cls, info_dict):
         return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
 
-    def _source_address(self, command_option):
-        source_address = self.params.get('source_address')
-        if source_address is None:
-            return []
-        return [command_option, source_address]
+    def _option(self, command_option, param):
+        return cli_option(self.params, command_option, param)
+
+    def _bool_option(self, command_option, param, true_value='true', false_value='false', separator=None):
+        return cli_bool_option(self.params, command_option, param, true_value, false_value, separator)
+
+    def _valueless_option(self, command_option, param, expected_value=True):
+        return cli_valueless_option(self.params, command_option, param, expected_value)
 
     def _configuration_args(self, default=[]):
-        ex_args = self.params.get('external_downloader_args')
-        if ex_args is None:
-            return default
-        assert isinstance(ex_args, list)
-        return ex_args
+        return cli_configuration_args(self.params, 'external_downloader_args', default)
 
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
@@ -77,7 +80,19 @@ class CurlFD(ExternalFD):
         cmd = [self.exe, '--location', '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._source_address('--interface')
+        cmd += self._option('--interface', 'source_address')
+        cmd += self._option('--proxy', 'proxy')
+        cmd += self._valueless_option('--insecure', 'nocheckcertificate')
+        cmd += self._configuration_args()
+        cmd += ['--', info_dict['url']]
+        return cmd
+
+
+class AxelFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = [self.exe, '-o', tmpfilename]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['-H', '%s: %s' % (key, val)]
         cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
         return cmd
@@ -88,7 +103,9 @@ class WgetFD(ExternalFD):
         cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._source_address('--bind-address')
+        cmd += self._option('--bind-address', 'source_address')
+        cmd += self._option('--proxy', 'proxy')
+        cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
         cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
         return cmd
@@ -105,10 +122,20 @@ class Aria2cFD(ExternalFD):
         cmd += ['--out', os.path.basename(tmpfilename)]
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
-        cmd += self._source_address('--interface')
+        cmd += self._option('--interface', 'source_address')
+        cmd += self._option('--all-proxy', 'proxy')
+        cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
         cmd += ['--', info_dict['url']]
         return cmd
 
+
+class HttpieFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['%s:%s' % (key, val)]
+        return cmd
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()
@@ -123,5 +150,6 @@ def list_external_downloaders():
 def get_external_downloader(external_downloader):
     """ Given the name of the executable, see whether we support the given
         downloader . """
-    bn = os.path.basename(external_downloader)
+    # Drop .exe extension on Windows
+    bn = os.path.splitext(os.path.basename(external_downloader))[0]
     return _BY_NAME[bn]

youtube_dl/downloader/f4m.py

@@ -5,19 +5,19 @@ import io
 import itertools
 import os
 import time
-import xml.etree.ElementTree as etree
 
-from .common import FileDownloader
-from .http import HttpFD
+from .fragment import FragmentFD
 from ..compat import (
+    compat_etree_fromstring,
     compat_urlparse,
     compat_urllib_error,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
-    struct_pack,
-    struct_unpack,
     encodeFilename,
     sanitize_open,
+    struct_pack,
+    struct_unpack,
     xpath_text,
 )
 
@@ -226,16 +226,13 @@ def _add_ns(prop):
     return '{http://ns.adobe.com/f4m/1.0}%s' % prop
 
 
-class HttpQuietDownloader(HttpFD):
-    def to_screen(self, *args, **kargs):
-        pass
-
-
-class F4mFD(FileDownloader):
+class F4mFD(FragmentFD):
     """
     A downloader for f4m manifests or AdobeHDS.
     """
 
+    FD_NAME = 'f4m'
+
     def _get_unencrypted_media(self, doc):
         media = doc.findall(_add_ns('media'))
         if not media:
@@ -288,10 +285,12 @@ class F4mFD(FileDownloader):
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
         requested_bitrate = info_dict.get('tbr')
-        self.to_screen('[download] Downloading f4m manifest')
-        manifest = self.ydl.urlopen(man_url).read()
+        self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
+        urlh = self.ydl.urlopen(man_url)
+        man_url = urlh.geturl()
+        manifest = urlh.read()
 
-        doc = etree.fromstring(manifest)
+        doc = compat_etree_fromstring(manifest)
         formats = [(int(f.attrib.get('bitrate', -1)), f)
                    for f in self._get_unencrypted_media(doc)]
         if requested_bitrate is None:
@@ -320,94 +319,53 @@ class F4mFD(FileDownloader):
         # For some akamai manifests we'll need to add a query to the fragment url
         akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
 
-        self.report_destination(filename)
-        http_dl = HttpQuietDownloader(
-            self.ydl,
-            {
-                'continuedl': True,
-                'quiet': True,
-                'noprogress': True,
-                'ratelimit': self.params.get('ratelimit', None),
-                'test': self.params.get('test', False),
-            }
-        )
-        tmpfilename = self.temp_name(filename)
-        (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
+        ctx = {
+            'filename': filename,
+            'total_frags': total_frags,
+        }
+
+        self._prepare_frag_download(ctx)
+
+        dest_stream = ctx['dest_stream']
 
         write_flv_header(dest_stream)
         if not live:
             write_metadata_tag(dest_stream, metadata)
 
-        # This dict stores the download progress, it's updated by the progress
-        # hook
-        state = {
-            'status': 'downloading',
-            'downloaded_bytes': 0,
-            'frag_index': 0,
-            'frag_count': total_frags,
-            'filename': filename,
-            'tmpfilename': tmpfilename,
-        }
-        start = time.time()
+        base_url_parsed = compat_urllib_parse_urlparse(base_url)
 
-        def frag_progress_hook(s):
-            if s['status'] not in ('downloading', 'finished'):
-                return
-
-            frag_total_bytes = s.get('total_bytes', 0)
-            if s['status'] == 'finished':
-                state['downloaded_bytes'] += frag_total_bytes
-                state['frag_index'] += 1
-
-            estimated_size = (
-                (state['downloaded_bytes'] + frag_total_bytes) /
-                (state['frag_index'] + 1) * total_frags)
-            time_now = time.time()
-            state['total_bytes_estimate'] = estimated_size
-            state['elapsed'] = time_now - start
-
-            if s['status'] == 'finished':
-                progress = self.calc_percent(state['frag_index'], total_frags)
-            else:
-                frag_downloaded_bytes = s['downloaded_bytes']
-                frag_progress = self.calc_percent(frag_downloaded_bytes,
-                                                  frag_total_bytes)
-                progress = self.calc_percent(state['frag_index'], total_frags)
-                progress += frag_progress / float(total_frags)
-
-                state['eta'] = self.calc_eta(
-                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
-                state['speed'] = s.get('speed')
-            self._hook_progress(state)
-
-        http_dl.add_progress_hook(frag_progress_hook)
+        self._start_frag_download(ctx)
 
         frags_filenames = []
         while fragments_list:
             seg_i, frag_i = fragments_list.pop(0)
             name = 'Seg%d-Frag%d' % (seg_i, frag_i)
-            url = base_url + name
+            query = []
+            if base_url_parsed.query:
+                query.append(base_url_parsed.query)
             if akamai_pv:
-                url += '?' + akamai_pv.strip(';')
+                query.append(akamai_pv.strip(';'))
             if info_dict.get('extra_param_to_segment_url'):
-                url += info_dict.get('extra_param_to_segment_url')
-            frag_filename = '%s-%s' % (tmpfilename, name)
+                query.append(info_dict['extra_param_to_segment_url'])
+            url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
+            frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
             try:
-                success = http_dl.download(frag_filename, {'url': url})
+                success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
                 if not success:
                     return False
-                with open(frag_filename, 'rb') as down:
-                    down_data = down.read()
-                    reader = FlvReader(down_data)
-                    while True:
-                        _, box_type, box_data = reader.read_box_info()
-                        if box_type == b'mdat':
-                            dest_stream.write(box_data)
-                            break
+                (down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
+                down_data = down.read()
+                down.close()
+                reader = FlvReader(down_data)
+                while True:
+                    _, box_type, box_data = reader.read_box_info()
+                    if box_type == b'mdat':
+                        dest_stream.write(box_data)
+                        break
                 if live:
-                    os.remove(frag_filename)
+                    os.remove(encodeFilename(frag_sanitized))
                 else:
-                    frags_filenames.append(frag_filename)
+                    frags_filenames.append(frag_sanitized)
             except (compat_urllib_error.HTTPError, ) as err:
                 if live and (err.code == 404 or err.code == 410):
                     # We didn't keep up with the live window. Continue
@@ -425,20 +383,9 @@ class F4mFD(FileDownloader):
                     msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1))
                     self.report_warning(msg)
 
-        dest_stream.close()
+        self._finish_frag_download(ctx)
 
-        elapsed = time.time() - start
-        self.try_rename(tmpfilename, filename)
         for frag_file in frags_filenames:
-            os.remove(frag_file)
-
-        fsize = os.path.getsize(encodeFilename(filename))
-        self._hook_progress({
-            'downloaded_bytes': fsize,
-            'total_bytes': fsize,
-            'filename': filename,
-            'status': 'finished',
-            'elapsed': elapsed,
-        })
+            os.remove(encodeFilename(frag_file))
 
         return True

youtube_dl/downloader/fragment.py

@@ -0,0 +1,111 @@
+from __future__ import division, unicode_literals
+
+import os
+import time
+
+from .common import FileDownloader
+from .http import HttpFD
+from ..utils import (
+    encodeFilename,
+    sanitize_open,
+)
+
+
+class HttpQuietDownloader(HttpFD):
+    def to_screen(self, *args, **kargs):
+        pass
+
+
+class FragmentFD(FileDownloader):
+    """
+    A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests).
+    """
+
+    def _prepare_and_start_frag_download(self, ctx):
+        self._prepare_frag_download(ctx)
+        self._start_frag_download(ctx)
+
+    def _prepare_frag_download(self, ctx):
+        self.to_screen('[%s] Total fragments: %d' % (self.FD_NAME, ctx['total_frags']))
+        self.report_destination(ctx['filename'])
+        dl = HttpQuietDownloader(
+            self.ydl,
+            {
+                'continuedl': True,
+                'quiet': True,
+                'noprogress': True,
+                'ratelimit': self.params.get('ratelimit', None),
+                'retries': self.params.get('retries', 0),
+                'test': self.params.get('test', False),
+            }
+        )
+        tmpfilename = self.temp_name(ctx['filename'])
+        dest_stream, tmpfilename = sanitize_open(tmpfilename, 'wb')
+        ctx.update({
+            'dl': dl,
+            'dest_stream': dest_stream,
+            'tmpfilename': tmpfilename,
+        })
+
+    def _start_frag_download(self, ctx):
+        total_frags = ctx['total_frags']
+        # This dict stores the download progress, it's updated by the progress
+        # hook
+        state = {
+            'status': 'downloading',
+            'downloaded_bytes': 0,
+            'frag_index': 0,
+            'frag_count': total_frags,
+            'filename': ctx['filename'],
+            'tmpfilename': ctx['tmpfilename'],
+        }
+        start = time.time()
+        ctx['started'] = start
+
+        def frag_progress_hook(s):
+            if s['status'] not in ('downloading', 'finished'):
+                return
+
+            frag_total_bytes = s.get('total_bytes', 0)
+            if s['status'] == 'finished':
+                state['downloaded_bytes'] += frag_total_bytes
+                state['frag_index'] += 1
+
+            estimated_size = (
+                (state['downloaded_bytes'] + frag_total_bytes) /
+                (state['frag_index'] + 1) * total_frags)
+            time_now = time.time()
+            state['total_bytes_estimate'] = estimated_size
+            state['elapsed'] = time_now - start
+
+            if s['status'] == 'finished':
+                progress = self.calc_percent(state['frag_index'], total_frags)
+            else:
+                frag_downloaded_bytes = s['downloaded_bytes']
+                frag_progress = self.calc_percent(frag_downloaded_bytes,
+                                                  frag_total_bytes)
+                progress = self.calc_percent(state['frag_index'], total_frags)
+                progress += frag_progress / float(total_frags)
+
+                state['eta'] = self.calc_eta(
+                    start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
+                state['speed'] = s.get('speed')
+            self._hook_progress(state)
+
+        ctx['dl'].add_progress_hook(frag_progress_hook)
+
+        return start
+
+    def _finish_frag_download(self, ctx):
+        ctx['dest_stream'].close()
+        elapsed = time.time() - ctx['started']
+        self.try_rename(ctx['tmpfilename'], ctx['filename'])
+        fsize = os.path.getsize(encodeFilename(ctx['filename']))
+
+        self._hook_progress({
+            'downloaded_bytes': fsize,
+            'total_bytes': fsize,
+            'filename': ctx['filename'],
+            'status': 'finished',
+            'elapsed': elapsed,
+        })

youtube_dl/downloader/hls.py

@@ -4,15 +4,15 @@ import os
 import re
 import subprocess
 
-from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from .common import FileDownloader
-from ..compat import (
-    compat_urlparse,
-    compat_urllib_request,
-)
+from .fragment import FragmentFD
+
+from ..compat import compat_urlparse
+from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..utils import (
     encodeArgument,
     encodeFilename,
+    sanitize_open,
 )
 
 
@@ -28,10 +28,21 @@ class HlsFD(FileDownloader):
             return False
         ffpp.check_version()
 
-        args = [
-            encodeArgument(opt)
-            for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
-        args.append(encodeFilename(tmpfilename, True))
+        args = [ffpp.executable, '-y']
+
+        if info_dict['http_headers'] and re.match(r'^https?://', url):
+            # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
+            # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
+            args += [
+                '-headers',
+                ''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())]
+
+        args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']
+
+        args = [encodeArgument(opt) for opt in args]
+        args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
+
+        self._debug_cmd(args)
 
         retval = subprocess.call(args)
         if retval == 0:
@@ -51,54 +62,51 @@ class HlsFD(FileDownloader):
             return False
 
 
-class NativeHlsFD(FileDownloader):
+class NativeHlsFD(FragmentFD):
     """ A more limited implementation that does not require ffmpeg """
 
-    def real_download(self, filename, info_dict):
-        url = info_dict['url']
-        self.report_destination(filename)
-        tmpfilename = self.temp_name(filename)
+    FD_NAME = 'hlsnative'
 
-        self.to_screen(
-            '[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id'])
-        data = self.ydl.urlopen(url).read()
-        s = data.decode('utf-8', 'ignore')
-        segment_urls = []
+    def real_download(self, filename, info_dict):
+        man_url = info_dict['url']
+        self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
+        manifest = self.ydl.urlopen(man_url).read()
+
+        s = manifest.decode('utf-8', 'ignore')
+        fragment_urls = []
         for line in s.splitlines():
             line = line.strip()
             if line and not line.startswith('#'):
                 segment_url = (
                     line
                     if re.match(r'^https?://', line)
-                    else compat_urlparse.urljoin(url, line))
-                segment_urls.append(segment_url)
-
-        is_test = self.params.get('test', False)
-        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
-        byte_counter = 0
-        with open(tmpfilename, 'wb') as outf:
-            for i, segurl in enumerate(segment_urls):
-                self.to_screen(
-                    '[hlsnative] %s: Downloading segment %d / %d' %
-                    (info_dict['id'], i + 1, len(segment_urls)))
-                seg_req = compat_urllib_request.Request(segurl)
-                if remaining_bytes is not None:
-                    seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
-
-                segment = self.ydl.urlopen(seg_req).read()
-                if remaining_bytes is not None:
-                    segment = segment[:remaining_bytes]
-                    remaining_bytes -= len(segment)
-                outf.write(segment)
-                byte_counter += len(segment)
-                if remaining_bytes is not None and remaining_bytes <= 0:
+                    else compat_urlparse.urljoin(man_url, line))
+                fragment_urls.append(segment_url)
+                # We only download the first fragment during the test
+                if self.params.get('test', False):
                     break
 
-        self._hook_progress({
-            'downloaded_bytes': byte_counter,
-            'total_bytes': byte_counter,
+        ctx = {
             'filename': filename,
-            'status': 'finished',
-        })
-        self.try_rename(tmpfilename, filename)
+            'total_frags': len(fragment_urls),
+        }
+
+        self._prepare_and_start_frag_download(ctx)
+
+        frags_filenames = []
+        for i, frag_url in enumerate(fragment_urls):
+            frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+            if not success:
+                return False
+            down, frag_sanitized = sanitize_open(frag_filename, 'rb')
+            ctx['dest_stream'].write(down.read())
+            down.close()
+            frags_filenames.append(frag_sanitized)
+
+        self._finish_frag_download(ctx)
+
+        for frag_file in frags_filenames:
+            os.remove(encodeFilename(frag_file))
+
         return True

youtube_dl/downloader/http.py

@@ -4,6 +4,7 @@ import errno
 import os
 import socket
 import time
+import re
 
 from .common import FileDownloader
 from ..compat import (
@@ -57,6 +58,24 @@ class HttpFD(FileDownloader):
             # Establish connection
             try:
                 data = self.ydl.urlopen(request)
+                # When trying to resume, Content-Range HTTP header of response has to be checked
+                # to match the value of requested Range HTTP header. This is due to a webservers
+                # that don't support resuming and serve a whole file with no Content-Range
+                # set in response despite of requested Range (see
+                # https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
+                if resume_len > 0:
+                    content_range = data.headers.get('Content-Range')
+                    if content_range:
+                        content_range_m = re.search(r'bytes (\d+)-', content_range)
+                        # Content-Range is present and matches requested Range, resume is possible
+                        if content_range_m and resume_len == int(content_range_m.group(1)):
+                            break
+                    # Content-Range is either not present or invalid. Assuming remote webserver is
+                    # trying to send the whole file, resume is not possible, so wiping the local file
+                    # and performing entire redownload
+                    self.report_unable_to_resume()
+                    resume_len = 0
+                    open_mode = 'wb'
                 break
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:

youtube_dl/downloader/rtmp.py

@@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
         protocol = info_dict.get('rtmp_protocol', None)
         real_time = info_dict.get('rtmp_real_time', False)
         no_resume = info_dict.get('no_resume', False)
-        continue_dl = info_dict.get('continuedl', True)
+        continue_dl = self.params.get('continuedl', True)
 
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)

youtube_dl/extractor/__init__.py

@@ -4,7 +4,10 @@ from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
-from .adobetv import AdobeTVIE
+from .adobetv import (
+    AdobeTVIE,
+    AdobeTVVideoIE,
+)
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
@@ -16,9 +19,14 @@ from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aparat import AparatIE
+from .appleconnect import AppleConnectIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
-from .ard import ARDIE, ARDMediathekIE
+from .ard import (
+    ARDIE,
+    ARDMediathekIE,
+    SportschauIE,
+)
 from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
@@ -35,7 +43,11 @@ from .azubu import AzubuIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
-from .bbccouk import BBCCoUkIE
+from .bbc import (
+    BBCCoUkIE,
+    BBCCoUkArticleIE,
+    BBCIE,
+)
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .beatportpro import BeatportProIE
@@ -65,6 +77,7 @@ from .cbssports import CBSSportsIE
 from .ccc import CCCIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
+from .chaturbate import ChaturbateIE
 from .chilloutzone import ChilloutzoneIE
 from .chirbit import (
     ChirbitIE,
@@ -77,6 +90,7 @@ from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cloudy import CloudyIE
 from .clubic import ClubicIE
+from .clyp import ClypIE
 from .cmt import CMTIE
 from .cnet import CNETIE
 from .cnn import (
@@ -103,11 +117,14 @@ from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
+    DailymotionCloudIE,
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
+from .dcn import DCNIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
+from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .dotsub import DotsubIE
@@ -125,7 +142,6 @@ from .dump import DumpIE
 from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
-from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
 from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
@@ -140,12 +156,13 @@ from .ellentv import (
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
 from .espn import ESPNIE
+from .esri import EsriVideoIE
+from .europa import EuropaIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
@@ -153,14 +170,12 @@ from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
 from .fc2 import FC2IE
+from .fczenit import FczenitIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
-from .fktv import (
-    FKTVIE,
-    FKTVPosteckeIE,
-)
+from .fktv import FKTVIE
 from .flickr import FlickrIE
 from .folketinget import FolketingetIE
 from .footyroom import FootyRoomIE
@@ -197,13 +212,15 @@ from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
 from .giga import GigaIE
 from .glide import GlideIE
-from .globo import GloboIE
+from .globo import (
+    GloboIE,
+    GloboArticleIE,
+)
 from .godtube import GodTubeIE
 from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
-from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
 from .groupon import GrouponIE
 from .hark import HarkIE
@@ -216,7 +233,6 @@ from .historicfilms import HistoricFilmsIE
 from .history import HistoryIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
-from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
@@ -228,13 +244,21 @@ from .imdb import (
     ImdbIE,
     ImdbListIE
 )
-from .imgur import ImgurIE
+from .imgur import (
+    ImgurIE,
+    ImgurAlbumIE,
+)
 from .ina import InaIE
+from .indavideo import (
+    IndavideoIE,
+    IndavideoEmbedIE,
+)
 from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .iqiyi import IqiyiIE
+from .ir90tv import Ir90TvIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -257,8 +281,17 @@ from .keek import KeekIE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
+from .kuwo import (
+    KuwoIE,
+    KuwoAlbumIE,
+    KuwoChartIE,
+    KuwoSingerIE,
+    KuwoCategoryIE,
+    KuwoMvIE,
+)
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
+from .lecture2go import Lecture2GoIE
 from .letv import (
     LetvIE,
     LetvTvIE,
@@ -269,6 +302,11 @@ from .lifenews import (
     LifeNewsIE,
     LifeEmbedIE,
 )
+from .limelight import (
+    LimelightMediaIE,
+    LimelightChannelIE,
+    LimelightChannelListIE,
+)
 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,
@@ -286,7 +324,6 @@ from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
-from .megavideoz import MegaVideozIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
@@ -313,13 +350,15 @@ from .mtv import (
     MTVIE,
     MTVServicesEmbeddedIE,
     MTVIggyIE,
+    MTVDEIE,
 )
 from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
-from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
+from .mwave import MwaveIE
 from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
+from .myvi import MyviIE
 from .myvideo import MyVideoIE
 from .myvidster import MyVidsterIE
 from .nationalgeographic import NationalGeographicIE
@@ -330,15 +369,28 @@ from .nbc import (
     NBCNewsIE,
     NBCSportsIE,
     NBCSportsVPlayerIE,
+    MSNBCIE,
 )
 from .ndr import (
     NDRIE,
     NJoyIE,
+    NDREmbedBaseIE,
+    NDREmbedIE,
+    NJoyEmbedIE,
 )
 from .ndtv import NDTVIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
 from .nerdist import NerdistIE
+from .neteasemusic import (
+    NetEaseMusicIE,
+    NetEaseMusicAlbumIE,
+    NetEaseMusicSingerIE,
+    NetEaseMusicListIE,
+    NetEaseMusicMvIE,
+    NetEaseMusicProgramIE,
+    NetEaseMusicDjRadioIE,
+)
 from .newgrounds import NewgroundsIE
 from .newstube import NewstubeIE
 from .nextmedia import (
@@ -360,7 +412,11 @@ from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .nova import NovaIE
 from .novamov import NovaMovIE
-from .nowness import NownessIE
+from .nowness import (
+    NownessIE,
+    NownessPlaylistIE,
+    NownessSeriesIE,
+)
 from .nowtv import NowTVIE
 from .nowvideo import NowVideoIE
 from .npo import (
@@ -368,7 +424,8 @@ from .npo import (
     NPOLiveIE,
     NPORadioIE,
     NPORadioFragmentIE,
-    TegenlichtVproIE,
+    VPROIE,
+    WNLIE
 )
 from .nrk import (
     NRKIE,
@@ -384,11 +441,11 @@ from .nytimes import (
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .onionstudios import OnionStudiosIE
 from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
 )
-from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,
     ORFOE1IE,
@@ -398,15 +455,25 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .periscope import (
+    PeriscopeIE,
+    QuickscopeIE,
+)
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pinkbike import PinkbikeIE
 from .planetaplay import PlanetaPlayIE
 from .pladform import PladformIE
 from .played import PlayedIE
 from .playfm import PlayFMIE
+from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
+from .pluralsight import (
+    PluralsightIE,
+    PluralsightCourseIE,
+)
 from .podomatic import PodomaticIE
 from .porn91 import Porn91IE
 from .pornhd import PornHdIE
@@ -427,6 +494,7 @@ from .qqmusic import (
     QQMusicSingerIE,
     QQMusicAlbumIE,
     QQMusicToplistIE,
+    QQMusicPlaylistIE,
 )
 from .quickvid import QuickVidIE
 from .r7 import R7IE
@@ -436,6 +504,7 @@ from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
+from .rds import RDSIE
 from .redtube import RedTubeIE
 from .restudy import RestudyIE
 from .reverbnation import ReverbNationIE
@@ -450,6 +519,7 @@ from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
+from .rtvnh import RTVNHIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -476,6 +546,7 @@ from .senateisvp import SenateISVPIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
+from .shahid import ShahidIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE
@@ -487,6 +558,10 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snagfilms import (
+    SnagFilmsIE,
+    SnagFilmsEmbedIE,
+)
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .soompi import (
@@ -516,6 +591,7 @@ from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
+from .stitcher import StitcherIE
 from .sport5 import Sport5IE
 from .sportbox import (
     SportBoxIE,
@@ -551,6 +627,7 @@ from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
+from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
@@ -558,8 +635,12 @@ from .testurl import TestURLIE
 from .testtube import TestTubeIE
 from .tf1 import TF1IE
 from .theonion import TheOnionIE
-from .theplatform import ThePlatformIE
+from .theplatform import (
+    ThePlatformIE,
+    ThePlatformFeedIE,
+)
 from .thesixtyone import TheSixtyOneIE
+from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
@@ -567,7 +648,11 @@ from .tmz import (
     TMZIE,
     TMZArticleIE,
 )
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -611,6 +696,7 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
+from .twitter import TwitterCardIE, TwitterIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -636,9 +722,7 @@ from .vgtv import (
 from .vh1 import VH1IE
 from .vice import ViceIE
 from .viddler import ViddlerIE
-from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
-from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
 from .videopremium import VideoPremiumIE
@@ -648,6 +732,7 @@ from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
 from .viewster import ViewsterIE
+from .viidea import ViideaIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -671,6 +756,7 @@ from .vk import (
     VKIE,
     VKUserVideosIE,
 )
+from .vlive import VLiveIE
 from .vodlocker import VodlockerIE
 from .voicerepublic import VoiceRepublicIE
 from .vporn import VpornIE
@@ -687,7 +773,10 @@ from .wdr import (
     WDRMobileIE,
     WDRMausIE,
 )
-from .webofstories import WebOfStoriesIE
+from .webofstories import (
+    WebOfStoriesIE,
+    WebOfStoriesPlaylistIE,
+)
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
@@ -696,7 +785,11 @@ from .wrzuta import WrzutaIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
-from .xhamster import XHamsterIE
+from .xfileshare import XFileShareIE
+from .xhamster import (
+    XHamsterIE,
+    XHamsterEmbedIE,
+)
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xstream import XstreamIE
@@ -715,6 +808,7 @@ from .yandexmusic import (
     YandexMusicPlaylistIE,
 )
 from .yesjapan import YesJapanIE
+from .yinyuetai import YinYueTaiIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE

youtube_dl/extractor/abc.py

@@ -1,16 +1,20 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    js_to_json,
+    int_or_none,
+)
 
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
         'md5': 'cb3dd03b18455a661071ee1e28344d9f',
         'info_dict': {
@@ -19,23 +23,62 @@ class ABCIE(InfoExtractor):
             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
         },
-    }
+    }, {
+        'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
+        'md5': 'db2a5369238b51f9811ad815b69dc086',
+        'info_dict': {
+            'id': 'NvqvPeNZsHU',
+            'ext': 'mp4',
+            'upload_date': '20150816',
+            'uploader': 'ABC News (Australia)',
+            'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
+            'uploader_id': 'NewsOnABC',
+            'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
+        },
+        'add_ie': ['Youtube'],
+    }, {
+        'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
+        'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
+        'info_dict': {
+            'id': '6880080',
+            'ext': 'mp3',
+            'title': 'NAB lifts interest rates, following Westpac and CBA',
+            'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
+        },
+    }, {
+        'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        urls_info_json = self._search_regex(
-            r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls',
-            flags=re.DOTALL)
-        urls_info = json.loads(urls_info_json.replace('\'', '"'))
+        mobj = re.search(
+            r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
+            webpage)
+        if mobj is None:
+            raise ExtractorError('Unable to extract video urls')
+
+        urls_info = self._parse_json(
+            mobj.group('json_data'), video_id, transform_source=js_to_json)
+
+        if not isinstance(urls_info, list):
+            urls_info = [urls_info]
+
+        if mobj.group('type') == 'YouTube':
+            return self.playlist_result([
+                self.url_result(url_info['url']) for url_info in urls_info])
+
         formats = [{
             'url': url_info['url'],
-            'width': int(url_info['width']),
-            'height': int(url_info['height']),
-            'tbr': int(url_info['bitrate']),
-            'filesize': int(url_info['filesize']),
+            'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
+            'width': int_or_none(url_info.get('width')),
+            'height': int_or_none(url_info.get('height')),
+            'tbr': int_or_none(url_info.get('bitrate')),
+            'filesize': int_or_none(url_info.get('filesize')),
         } for url_info in urls_info]
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/academicearth.py

@@ -15,7 +15,7 @@ class AcademicEarthCourseIE(InfoExtractor):
             'title': 'Laws of Nature',
             'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
         },
-        'playlist_count': 4,
+        'playlist_count': 3,
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/adobetv.py

@@ -5,6 +5,8 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     str_to_int,
+    float_or_none,
+    ISO639Utils,
 )
 
 
@@ -69,3 +71,61 @@ class AdobeTVIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class AdobeTVVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+
+    _TEST = {
+        # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
+        'url': 'https://video.tv.adobe.com/v/2456/',
+        'md5': '43662b577c018ad707a63766462b1e87',
+        'info_dict': {
+            'id': '2456',
+            'ext': 'mp4',
+            'title': 'New experience with Acrobat DC',
+            'description': 'New experience with Acrobat DC',
+            'duration': 248.667,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_params = self._parse_json(self._search_regex(
+            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
+            video_id)
+
+        formats = [{
+            'url': source['src'],
+            'width': source.get('width'),
+            'height': source.get('height'),
+            'tbr': source.get('bitrate'),
+        } for source in player_params['sources']]
+
+        # For both metadata and downloaded files the duration varies among
+        # formats. I just pick the max one
+        duration = max(filter(None, [
+            float_or_none(source.get('duration'), scale=1000)
+            for source in player_params['sources']]))
+
+        subtitles = {}
+        for translation in player_params.get('translations', []):
+            lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
+            if lang_id not in subtitles:
+                subtitles[lang_id] = []
+            subtitles[lang_id].append({
+                'url': translation['vttPath'],
+                'ext': 'vtt',
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': player_params['title'],
+            'description': self._og_search_description(webpage),
+            'duration': duration,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/adultswim.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     float_or_none,
     xpath_text,
@@ -40,7 +41,8 @@ class AdultSwimIE(InfoExtractor):
             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
             'title': 'Rick and Morty - Pilot',
             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
-        }
+        },
+        'skip': 'This video is only available for registered users',
     }, {
         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
         'playlist': [
@@ -123,7 +125,6 @@ class AdultSwimIE(InfoExtractor):
         else:
             collections = bootstrapped_data['show']['collections']
             collection, video_info = self.find_collection_containing_video(collections, episode_path)
-
             # Video wasn't found in the collections, let's try `slugged_video`.
             if video_info is None:
                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
@@ -133,7 +134,15 @@ class AdultSwimIE(InfoExtractor):
 
             show = bootstrapped_data['show']
             show_title = show['title']
-            segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
+            stream = video_info.get('stream')
+            clips = [stream] if stream else video_info.get('clips')
+            if not clips:
+                raise ExtractorError(
+                    'This video is only available via cable service provider subscription that'
+                    ' is not currently supported. You may want to use --cookies.'
+                    if video_info.get('auth') is True else 'Unable to find stream or clips',
+                    expected=True)
+            segment_ids = [clip['videoPlaybackID'] for clip in clips]
 
         episode_id = video_info['id']
         episode_title = video_info['title']
@@ -142,7 +151,7 @@ class AdultSwimIE(InfoExtractor):
 
         entries = []
         for part_num, segment_id in enumerate(segment_ids):
-            segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
+            segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
 
             segment_title = '%s - %s' % (show_title, episode_title)
             if len(segment_ids) > 1:
@@ -156,19 +165,32 @@ class AdultSwimIE(InfoExtractor):
                 xpath_text(idoc, './/trt', 'segment duration').strip())
 
             formats = []
-            file_els = idoc.findall('.//files/file')
+            file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
 
+            unique_urls = []
+            unique_file_els = []
             for file_el in file_els:
+                media_url = file_el.text
+                if not media_url or determine_ext(media_url) == 'f4m':
+                    continue
+                if file_el.text not in unique_urls:
+                    unique_urls.append(file_el.text)
+                    unique_file_els.append(file_el)
+
+            for file_el in unique_file_els:
                 bitrate = file_el.attrib.get('bitrate')
                 ftype = file_el.attrib.get('type')
-
-                formats.append({
-                    'format_id': '%s_%s' % (bitrate, ftype),
-                    'url': file_el.text.strip(),
-                    # The bitrate may not be a number (for example: 'iphone')
-                    'tbr': int(bitrate) if bitrate.isdigit() else None,
-                    'quality': 1 if ftype == 'hd' else -1
-                })
+                media_url = file_el.text
+                if determine_ext(media_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        media_url, segment_title, 'mp4', preference=0, m3u8_id='hls'))
+                else:
+                    formats.append({
+                        'format_id': '%s_%s' % (bitrate, ftype),
+                        'url': file_el.text.strip(),
+                        # The bitrate may not be a number (for example: 'iphone')
+                        'tbr': int(bitrate) if bitrate.isdigit() else None,
+                    })
 
             self._sort_formats(formats)
 

youtube_dl/extractor/airmozilla.py

@@ -20,14 +20,14 @@ class AirMozillaIE(InfoExtractor):
             'id': '6x4q2w',
             'ext': 'mp4',
             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
-            'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
+            'thumbnail': 're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
             'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
             'timestamp': 1422487800,
             'upload_date': '20150128',
             'location': 'SFO Commons',
             'duration': 3780,
             'view_count': int,
-            'categories': ['Main'],
+            'categories': ['Main', 'Privacy'],
         }
     }
 

youtube_dl/extractor/aljazeera.py

@@ -16,6 +16,7 @@ class AlJazeeraIE(InfoExtractor):
             'uploader': 'Al Jazeera English',
         },
         'add_ie': ['Brightcove'],
+        'skip': 'Not accessible from Travis CI server',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/anitube.py

@@ -26,8 +26,8 @@ class AnitubeIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        key = self._html_search_regex(
-            r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
+        key = self._search_regex(
+            r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
 
         config_xml = self._download_xml(
             'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)

youtube_dl/extractor/appleconnect.py

@@ -0,0 +1,50 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    str_to_int,
+    ExtractorError
+)
+
+
+class AppleConnectIE(InfoExtractor):
+    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
+    _TEST = {
+        'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+        'md5': '10d0f2799111df4cb1c924520ca78f98',
+        'info_dict': {
+            'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
+            'ext': 'm4v',
+            'title': 'Energy',
+            'uploader': 'Drake',
+            'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
+            'upload_date': '20150710',
+            'timestamp': 1436545535,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        try:
+            video_json = self._html_search_regex(
+                r'class="auc-video-data">(\{.*?\})', webpage, 'json')
+        except ExtractorError:
+            raise ExtractorError('This post doesn\'t contain a video', expected=True)
+
+        video_data = self._parse_json(video_json, video_id)
+        timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
+        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count'))
+
+        return {
+            'id': video_id,
+            'url': video_data['sslSrc'],
+            'title': video_data['title'],
+            'description': video_data['description'],
+            'uploader': video_data['artistName'],
+            'thumbnail': video_data['artworkUrl'],
+            'timestamp': timestamp,
+            'like_count': like_count,
+        }

youtube_dl/extractor/appletrailers.py

@@ -13,53 +13,53 @@ from ..utils import (
 class AppleTrailersIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
     _TESTS = [{
-        "url": "http://trailers.apple.com/trailers/wb/manofsteel/",
+        'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
         'info_dict': {
             'id': 'manofsteel',
         },
-        "playlist": [
+        'playlist': [
             {
-                "md5": "d97a8e575432dbcb81b7c3acb741f8a8",
-                "info_dict": {
-                    "id": "manofsteel-trailer4",
-                    "ext": "mov",
-                    "duration": 111,
-                    "title": "Trailer 4",
-                    "upload_date": "20130523",
-                    "uploader_id": "wb",
+                'md5': 'd97a8e575432dbcb81b7c3acb741f8a8',
+                'info_dict': {
+                    'id': 'manofsteel-trailer4',
+                    'ext': 'mov',
+                    'duration': 111,
+                    'title': 'Trailer 4',
+                    'upload_date': '20130523',
+                    'uploader_id': 'wb',
                 },
             },
             {
-                "md5": "b8017b7131b721fb4e8d6f49e1df908c",
-                "info_dict": {
-                    "id": "manofsteel-trailer3",
-                    "ext": "mov",
-                    "duration": 182,
-                    "title": "Trailer 3",
-                    "upload_date": "20130417",
-                    "uploader_id": "wb",
+                'md5': 'b8017b7131b721fb4e8d6f49e1df908c',
+                'info_dict': {
+                    'id': 'manofsteel-trailer3',
+                    'ext': 'mov',
+                    'duration': 182,
+                    'title': 'Trailer 3',
+                    'upload_date': '20130417',
+                    'uploader_id': 'wb',
                 },
             },
             {
-                "md5": "d0f1e1150989b9924679b441f3404d48",
-                "info_dict": {
-                    "id": "manofsteel-trailer",
-                    "ext": "mov",
-                    "duration": 148,
-                    "title": "Trailer",
-                    "upload_date": "20121212",
-                    "uploader_id": "wb",
+                'md5': 'd0f1e1150989b9924679b441f3404d48',
+                'info_dict': {
+                    'id': 'manofsteel-trailer',
+                    'ext': 'mov',
+                    'duration': 148,
+                    'title': 'Trailer',
+                    'upload_date': '20121212',
+                    'uploader_id': 'wb',
                 },
             },
             {
-                "md5": "5fe08795b943eb2e757fa95cb6def1cb",
-                "info_dict": {
-                    "id": "manofsteel-teaser",
-                    "ext": "mov",
-                    "duration": 93,
-                    "title": "Teaser",
-                    "upload_date": "20120721",
-                    "uploader_id": "wb",
+                'md5': '5fe08795b943eb2e757fa95cb6def1cb',
+                'info_dict': {
+                    'id': 'manofsteel-teaser',
+                    'ext': 'mov',
+                    'duration': 93,
+                    'title': 'Teaser',
+                    'upload_date': '20120721',
+                    'uploader_id': 'wb',
                 },
             },
         ]

youtube_dl/extractor/ard.py

@@ -8,13 +8,14 @@ from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
+    get_element_by_attribute,
     qualities,
     int_or_none,
     parse_duration,
     unified_strdate,
     xpath_text,
-    parse_xml,
 )
+from ..compat import compat_etree_fromstring
 
 
 class ARDMediathekIE(InfoExtractor):
@@ -22,19 +23,125 @@ class ARDMediathekIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
+        'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
+        'info_dict': {
+            'id': '29582122',
+            'ext': 'mp4',
+            'title': 'Ich liebe das Leben trotzdem',
+            'description': 'md5:45e4c225c72b27993314b31a84a5261c',
+            'duration': 4557,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
+        'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
+        'info_dict': {
+            'id': '29522730',
+            'ext': 'mp4',
+            'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
+            'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
+            'duration': 5252,
+        },
+    }, {
+        # audio
+        'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
+        'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
+        'info_dict': {
+            'id': '28488308',
+            'ext': 'mp3',
+            'title': 'Tod eines Fußballers',
+            'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
+            'duration': 3240,
+        },
+    }, {
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
         'only_matching': True,
-    }, {
-        'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
-        'info_dict': {
-            'id': '22490580',
-            'ext': 'mp4',
-            'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)',
-            'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.',
-        },
-        'skip': 'Blocked outside of Germany',
     }]
 
+    def _extract_media_info(self, media_info_url, webpage, video_id):
+        media_info = self._download_json(
+            media_info_url, video_id, 'Downloading media JSON')
+
+        formats = self._extract_formats(media_info, video_id)
+
+        if not formats:
+            if '"fsk"' in webpage:
+                raise ExtractorError(
+                    'This video is only available after 20:00', expected=True)
+            elif media_info.get('_geoblocked'):
+                raise ExtractorError('This video is not available due to geo restriction', expected=True)
+
+        self._sort_formats(formats)
+
+        duration = int_or_none(media_info.get('_duration'))
+        thumbnail = media_info.get('_previewImage')
+
+        subtitles = {}
+        subtitle_url = media_info.get('_subtitleUrl')
+        if subtitle_url:
+            subtitles['de'] = [{
+                'ext': 'srt',
+                'url': subtitle_url,
+            }]
+
+        return {
+            'id': video_id,
+            'duration': duration,
+            'thumbnail': thumbnail,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _extract_formats(self, media_info, video_id):
+        type_ = media_info.get('_type')
+        media_array = media_info.get('_mediaArray', [])
+        formats = []
+        for num, media in enumerate(media_array):
+            for stream in media.get('_mediaStreamArray', []):
+                stream_urls = stream.get('_stream')
+                if not stream_urls:
+                    continue
+                if not isinstance(stream_urls, list):
+                    stream_urls = [stream_urls]
+                quality = stream.get('_quality')
+                server = stream.get('_server')
+                for stream_url in stream_urls:
+                    ext = determine_ext(stream_url)
+                    if ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
+                            video_id, preference=-1, f4m_id='hds'))
+                    elif ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls'))
+                    else:
+                        if server and server.startswith('rtmp'):
+                            f = {
+                                'url': server,
+                                'play_path': stream_url,
+                                'format_id': 'a%s-rtmp-%s' % (num, quality),
+                            }
+                        elif stream_url.startswith('http'):
+                            f = {
+                                'url': stream_url,
+                                'format_id': 'a%s-%s-%s' % (num, ext, quality)
+                            }
+                        else:
+                            continue
+                        m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
+                        if m:
+                            f.update({
+                                'width': int(m.group('width')),
+                                'height': int(m.group('height')),
+                            })
+                        if type_ == 'audio':
+                            f['vcodec'] = 'none'
+                        formats.append(f)
+        return formats
+
     def _real_extract(self, url):
         # determine video id from url
         m = re.match(self._VALID_URL, url)
@@ -54,7 +161,7 @@ class ARDMediathekIE(InfoExtractor):
             raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
 
         if re.search(r'[\?&]rss($|[=&])', url):
-            doc = parse_xml(webpage)
+            doc = compat_etree_fromstring(webpage.encode('utf-8'))
             if doc.tag == 'rss':
                 return GenericIE()._extract_rss(url, video_id, doc)
 
@@ -92,46 +199,22 @@ class ARDMediathekIE(InfoExtractor):
                     'format_id': fid,
                     'url': furl,
                 })
+            self._sort_formats(formats)
+            info = {
+                'formats': formats,
+            }
         else:  # request JSON file
-            media_info = self._download_json(
-                'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
-            # The second element of the _mediaArray contains the standard http urls
-            streams = media_info['_mediaArray'][1]['_mediaStreamArray']
-            if not streams:
-                if '"fsk"' in webpage:
-                    raise ExtractorError('This video is only available after 20:00')
+            info = self._extract_media_info(
+                'http://www.ardmediathek.de/play/media/%s' % video_id, webpage, video_id)
 
-            formats = []
-            for s in streams:
-                if type(s['_stream']) == list:
-                    for index, url in enumerate(s['_stream'][::-1]):
-                        quality = s['_quality'] + index
-                        formats.append({
-                            'quality': quality,
-                            'url': url,
-                            'format_id': '%s-%s' % (determine_ext(url), quality)
-                        })
-                    continue
-
-                format = {
-                    'quality': s['_quality'],
-                    'url': s['_stream'],
-                }
-
-                format['format_id'] = '%s-%s' % (
-                    determine_ext(format['url']), format['quality'])
-
-                formats.append(format)
-
-        self._sort_formats(formats)
-
-        return {
+        info.update({
             'id': video_id,
             'title': title,
             'description': description,
-            'formats': formats,
             'thumbnail': thumbnail,
-        }
+        })
+
+        return info
 
 
 class ARDIE(InfoExtractor):
@@ -189,3 +272,41 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
+
+
+class SportschauIE(ARDMediathekIE):
+    IE_NAME = 'Sportschau'
+    _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html'
+    _TESTS = [{
+        'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html',
+        'info_dict': {
+            'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
+            'ext': 'mp4',
+            'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        base_url = mobj.group('baseurl')
+
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_attribute('class', 'headline', webpage)
+        description = self._html_search_meta('description', webpage, 'description')
+
+        info = self._extract_media_info(
+            base_url + '-mc_defaultQuality-h.json', webpage, video_id)
+
+        info.update({
+            'title': title,
+            'description': description,
+        })
+
+        return info

youtube_dl/extractor/arte.py

@@ -4,6 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
     find_xpath_attr,
     unified_strdate,
@@ -77,7 +81,13 @@ class ArteTVPlus7IE(InfoExtractor):
     def _extract_from_webpage(self, webpage, video_id, lang):
         json_url = self._html_search_regex(
             [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
-            webpage, 'json vp url')
+            webpage, 'json vp url', default=None)
+        if not json_url:
+            iframe_url = self._html_search_regex(
+                r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
+                webpage, 'iframe url', group='url')
+            json_url = compat_parse_qs(
+                compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):

youtube_dl/extractor/baidu.py

@@ -8,6 +8,7 @@ from ..compat import compat_urlparse
 
 
 class BaiduVideoIE(InfoExtractor):
+    IE_DESC = '百度视频'
     _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
     _TESTS = [{
         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',

youtube_dl/extractor/bandcamp.py

@@ -10,6 +10,8 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
+    int_or_none,
 )
 
 
@@ -52,11 +54,11 @@ class BandcampIE(InfoExtractor):
                     ext, abr_str = format_id.split('-', 1)
                     formats.append({
                         'format_id': format_id,
-                        'url': format_url,
+                        'url': self._proto_relative_url(format_url, 'http:'),
                         'ext': ext,
                         'vcodec': 'none',
                         'acodec': ext,
-                        'abr': int(abr_str),
+                        'abr': int_or_none(abr_str),
                     })
 
                 self._sort_formats(formats)
@@ -65,7 +67,7 @@ class BandcampIE(InfoExtractor):
                     'id': compat_str(data['id']),
                     'title': data['title'],
                     'formats': formats,
-                    'duration': float(data['duration']),
+                    'duration': float_or_none(data.get('duration')),
                 }
             else:
                 raise ExtractorError('No free songs found')
@@ -93,8 +95,8 @@ class BandcampIE(InfoExtractor):
         final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
         # If we could correctly generate the .rand field the url would be
         # in the "download_url" key
-        final_url = self._search_regex(
-            r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
+        final_url = self._proto_relative_url(self._search_regex(
+            r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
 
         return {
             'id': video_id,

youtube_dl/extractor/bbc.py

@@ -0,0 +1,937 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    remove_end,
+    unescapeHTML,
+)
+from ..compat import (
+    compat_etree_fromstring,
+    compat_HTTPError,
+)
+
+
+class BBCCoUkIE(InfoExtractor):
+    IE_NAME = 'bbc.co.uk'
+    IE_DESC = 'BBC iPlayer'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
+
+    _MEDIASELECTOR_URLS = [
+        # Provides HQ HLS streams with even better quality that pc mediaset but fails
+        # with geolocation in some cases when it's even not geo restricted at all (e.g.
+        # http://www.bbc.co.uk/programmes/b06bp7lf)
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
+    ]
+
+    _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
+    _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
+
+    _NAMESPACES = (
+        _MEDIASELECTION_NS,
+        _EMP_PLAYLIST_NS,
+    )
+
+    _TESTS = [
+        {
+            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
+            'info_dict': {
+                'id': 'b039d07m',
+                'ext': 'flv',
+                'title': 'Kaleidoscope, Leonard Cohen',
+                'description': 'The Canadian poet and songwriter reflects on his musical career.',
+                'duration': 1740,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Man in Black: Series 3: The Printed Name',
+                'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
+                'duration': 1800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Voice UK: Series 3: Blind Auditions 5',
+                'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
+                'duration': 5100,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
+            'info_dict': {
+                'id': 'b03k3pb7',
+                'ext': 'flv',
+                'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
+                'description': '2. Invasion',
+                'duration': 3600,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+        }, {
+            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
+            'info_dict': {
+                'id': 'b04v209v',
+                'ext': 'flv',
+                'title': 'Pete Tong, The Essential New Tune Special',
+                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
+                'duration': 10800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+            'note': 'Audio',
+            'info_dict': {
+                'id': 'p02frcch',
+                'ext': 'flv',
+                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
+                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
+                'duration': 3507,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
+            'note': 'Video',
+            'info_dict': {
+                'id': 'p025c103',
+                'ext': 'flv',
+                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
+                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
+                'duration': 226,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
+            'info_dict': {
+                'id': 'p02n76xf',
+                'ext': 'flv',
+                'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
+                'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
+            'info_dict': {
+                'id': 'b05zmgw1',
+                'ext': 'flv',
+                'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.',
+                'title': 'Royal Academy Summer Exhibition',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
+        }, {
+            # iptv-all mediaset fails with geolocation however there is no geo restriction
+            # for this programme at all
+            'url': 'http://www.bbc.co.uk/programmes/b06bp7lf',
+            'info_dict': {
+                'id': 'b06bp7kf',
+                'ext': 'flv',
+                'title': "Annie Mac's Friday Night, B.Traits sits in for Annie",
+                'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.',
+                'duration': 10800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
+            'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
+            'only_matching': True,
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
+            'only_matching': True,
+        }
+    ]
+
+    class MediaSelectionError(Exception):
+        def __init__(self, id):
+            self.id = id
+
+    def _extract_asx_playlist(self, connection, programme_id):
+        asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
+        return [ref.get('href') for ref in asx.findall('./Entry/ref')]
+
+    def _extract_connection(self, connection, programme_id):
+        formats = []
+        kind = connection.get('kind')
+        protocol = connection.get('protocol')
+        supplier = connection.get('supplier')
+        if protocol == 'http':
+            href = connection.get('href')
+            transfer_format = connection.get('transferFormat')
+            # ASX playlist
+            if supplier == 'asx':
+                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
+                    formats.append({
+                        'url': ref,
+                        'format_id': 'ref%s_%s' % (i, supplier),
+                    })
+            # Skip DASH until supported
+            elif transfer_format == 'dash':
+                pass
+            elif transfer_format == 'hls':
+                m3u8_formats = self._extract_m3u8_formats(
+                    href, programme_id, ext='mp4', entry_protocol='m3u8_native',
+                    m3u8_id=supplier, fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+            # Direct link
+            else:
+                formats.append({
+                    'url': href,
+                    'format_id': supplier or kind or protocol,
+                })
+        elif protocol == 'rtmp':
+            application = connection.get('application', 'ondemand')
+            auth_string = connection.get('authString')
+            identifier = connection.get('identifier')
+            server = connection.get('server')
+            formats.append({
+                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                'play_path': identifier,
+                'app': '%s?%s' % (application, auth_string),
+                'page_url': 'http://www.bbc.co.uk',
+                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
+                'rtmp_live': False,
+                'ext': 'flv',
+                'format_id': supplier,
+            })
+        return formats
+
+    def _extract_items(self, playlist):
+        return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
+
+    def _findall_ns(self, element, xpath):
+        elements = []
+        for ns in self._NAMESPACES:
+            elements.extend(element.findall(xpath % ns))
+        return elements
+
+    def _extract_medias(self, media_selection):
+        error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
+        if error is None:
+            media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
+        if error is not None:
+            raise BBCCoUkIE.MediaSelectionError(error.get('id'))
+        return self._findall_ns(media_selection, './{%s}media')
+
+    def _extract_connections(self, media):
+        return self._findall_ns(media, './{%s}connection')
+
+    def _extract_video(self, media, programme_id):
+        formats = []
+        vbr = int_or_none(media.get('bitrate'))
+        vcodec = media.get('encoding')
+        service = media.get('service')
+        width = int_or_none(media.get('width'))
+        height = int_or_none(media.get('height'))
+        file_size = int_or_none(media.get('media_file_size'))
+        for connection in self._extract_connections(media):
+            conn_formats = self._extract_connection(connection, programme_id)
+            for format in conn_formats:
+                format.update({
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                    'vcodec': vcodec,
+                    'filesize': file_size,
+                })
+                if service:
+                    format['format_id'] = '%s_%s' % (service, format['format_id'])
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_audio(self, media, programme_id):
+        formats = []
+        abr = int_or_none(media.get('bitrate'))
+        acodec = media.get('encoding')
+        service = media.get('service')
+        for connection in self._extract_connections(media):
+            conn_formats = self._extract_connection(connection, programme_id)
+            for format in conn_formats:
+                format.update({
+                    'format_id': '%s_%s' % (service, format['format_id']),
+                    'abr': abr,
+                    'acodec': acodec,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _get_subtitles(self, media, programme_id):
+        subtitles = {}
+        for connection in self._extract_connections(media):
+            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+            lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
+            subtitles[lang] = [
+                {
+                    'url': connection.get('href'),
+                    'ext': 'ttml',
+                },
+            ]
+        return subtitles
+
+    def _raise_extractor_error(self, media_selection_error):
+        raise ExtractorError(
+            '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
+            expected=True)
+
+    def _download_media_selector(self, programme_id):
+        last_exception = None
+        for mediaselector_url in self._MEDIASELECTOR_URLS:
+            try:
+                return self._download_media_selector_url(
+                    mediaselector_url % programme_id, programme_id)
+            except BBCCoUkIE.MediaSelectionError as e:
+                if e.id in ('notukerror', 'geolocation'):
+                    last_exception = e
+                    continue
+                self._raise_extractor_error(e)
+        self._raise_extractor_error(last_exception)
+
+    def _download_media_selector_url(self, url, programme_id=None):
+        try:
+            media_selection = self._download_xml(
+                url, programme_id, 'Downloading media selection XML')
+        except ExtractorError as ee:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
+                media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
+            else:
+                raise
+        return self._process_media_selector(media_selection, programme_id)
+
+    def _process_media_selector(self, media_selection, programme_id):
+        formats = []
+        subtitles = None
+
+        for media in self._extract_medias(media_selection):
+            kind = media.get('kind')
+            if kind == 'audio':
+                formats.extend(self._extract_audio(media, programme_id))
+            elif kind == 'video':
+                formats.extend(self._extract_video(media, programme_id))
+            elif kind == 'captions':
+                subtitles = self.extract_subtitles(media, programme_id)
+        return formats, subtitles
+
+    def _download_playlist(self, playlist_id):
+        try:
+            playlist = self._download_json(
+                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
+                playlist_id, 'Downloading playlist JSON')
+
+            version = playlist.get('defaultAvailableVersion')
+            if version:
+                smp_config = version['smpConfig']
+                title = smp_config['title']
+                description = smp_config['summary']
+                for item in smp_config['items']:
+                    kind = item['kind']
+                    if kind != 'programme' and kind != 'radioProgramme':
+                        continue
+                    programme_id = item.get('vpid')
+                    duration = int_or_none(item.get('duration'))
+                    formats, subtitles = self._download_media_selector(programme_id)
+                return programme_id, title, description, duration, formats, subtitles
+        except ExtractorError as ee:
+            if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
+                raise
+
+        # fallback to legacy playlist
+        return self._process_legacy_playlist(playlist_id)
+
+    def _process_legacy_playlist_url(self, url, display_id):
+        playlist = self._download_legacy_playlist_url(url, display_id)
+        return self._extract_from_legacy_playlist(playlist, display_id)
+
+    def _process_legacy_playlist(self, playlist_id):
+        return self._process_legacy_playlist_url(
+            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
+
+    def _download_legacy_playlist_url(self, url, playlist_id=None):
+        return self._download_xml(
+            url, playlist_id, 'Downloading legacy playlist XML')
+
+    def _extract_from_legacy_playlist(self, playlist, playlist_id):
+        no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
+        if no_items is not None:
+            reason = no_items.get('reason')
+            if reason == 'preAvailability':
+                msg = 'Episode %s is not yet available' % playlist_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % playlist_id
+            elif reason == 'noMedia':
+                msg = 'Episode %s is not currently available' % playlist_id
+            else:
+                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
+            raise ExtractorError(msg, expected=True)
+
+        for item in self._extract_items(playlist):
+            kind = item.get('kind')
+            if kind != 'programme' and kind != 'radioProgramme':
+                continue
+            title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
+            description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
+            description = description_el.text if description_el is not None else None
+
+            def get_programme_id(item):
+                def get_from_attributes(item):
+                    for p in('identifier', 'group'):
+                        value = item.get(p)
+                        if value and re.match(r'^[pb][\da-z]{7}$', value):
+                            return value
+                get_from_attributes(item)
+                mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
+                if mediator is not None:
+                    return get_from_attributes(mediator)
+
+            programme_id = get_programme_id(item)
+            duration = int_or_none(item.get('duration'))
+
+            if programme_id:
+                formats, subtitles = self._download_media_selector(programme_id)
+            else:
+                formats, subtitles = self._process_media_selector(item, playlist_id)
+                programme_id = playlist_id
+
+        return programme_id, title, description, duration, formats, subtitles
+
+    def _real_extract(self, url):
+        group_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+
+        programme_id = None
+
+        tviplayer = self._search_regex(
+            r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
+            webpage, 'player', default=None)
+
+        if tviplayer:
+            player = self._parse_json(tviplayer, group_id).get('player', {})
+            duration = int_or_none(player.get('duration'))
+            programme_id = player.get('vpid')
+
+        if not programme_id:
+            programme_id = self._search_regex(
+                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+
+        if programme_id:
+            formats, subtitles = self._download_media_selector(programme_id)
+            title = self._og_search_title(webpage)
+            description = self._search_regex(
+                r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
+                webpage, 'description', fatal=False)
+        else:
+            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': programme_id,
+            'title': title,
+            'description': description,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class BBCIE(BBCCoUkIE):
+    IE_NAME = 'bbc'
+    IE_DESC = 'BBC'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
+
+    _MEDIASELECTOR_URLS = [
+        # Provides HQ HLS streams but fails with geolocation in some cases when it's
+        # even not geo restricted at all
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
+        # Provides more formats, namely direct mp4 links, but fails on some videos with
+        # notukerror for non UK (?) users (e.g.
+        # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
+        'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
+        # Provides fewer formats, but works everywhere for everybody (hopefully)
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
+    ]
+
+    _TESTS = [{
+        # article with multiple videos embedded with data-playable containing vpids
+        'url': 'http://www.bbc.com/news/world-europe-32668511',
+        'info_dict': {
+            'id': 'world-europe-32668511',
+            'title': 'Russia stages massive WW2 parade despite Western boycott',
+            'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
+        },
+        'playlist_count': 2,
+    }, {
+        # article with multiple videos embedded with data-playable (more videos)
+        'url': 'http://www.bbc.com/news/business-28299555',
+        'info_dict': {
+            'id': 'business-28299555',
+            'title': 'Farnborough Airshow: Video highlights',
+            'description': 'BBC reports and video highlights at the Farnborough Airshow.',
+        },
+        'playlist_count': 9,
+        'skip': 'Save time',
+    }, {
+        # article with multiple videos embedded with `new SMP()`
+        # broken
+        'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
+        'info_dict': {
+            'id': '3662a707-0af9-3149-963f-47bea720b460',
+            'title': 'BBC Blogs - Adam Curtis - BUGGER',
+        },
+        'playlist_count': 18,
+    }, {
+        # single video embedded with data-playable containing vpid
+        'url': 'http://www.bbc.com/news/world-europe-32041533',
+        'info_dict': {
+            'id': 'p02mprgb',
+            'ext': 'mp4',
+            'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+            'description': 'md5:2868290467291b37feda7863f7a83f54',
+            'duration': 47,
+            'timestamp': 1427219242,
+            'upload_date': '20150324',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # article with single video embedded with data-playable containing XML playlist
+        # with direct video links as progressiveDownloadUrl (for now these are extracted)
+        # and playlist with f4m and m3u8 as streamingUrl
+        'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
+        'info_dict': {
+            'id': '150615_telabyad_kentin_cogu',
+            'ext': 'mp4',
+            'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
+            'timestamp': 1434397334,
+            'upload_date': '20150615',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # single video embedded with data-playable containing XML playlists (regional section)
+        'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
+        'info_dict': {
+            'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
+            'ext': 'mp4',
+            'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
+            'timestamp': 1434713142,
+            'upload_date': '20150619',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # single video from video playlist embedded with vxp-playlist-data JSON
+        'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
+        'info_dict': {
+            'id': 'p02w6qjc',
+            'ext': 'mp4',
+            'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
+            'duration': 56,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # single video story with digitalData
+        'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
+        'info_dict': {
+            'id': 'p02q6gc4',
+            'ext': 'flv',
+            'title': 'Sri Lanka’s spicy secret',
+            'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
+            'timestamp': 1437674293,
+            'upload_date': '20150723',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # single video story without digitalData
+        'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
+        'info_dict': {
+            'id': 'p018zqqg',
+            'ext': 'mp4',
+            'title': 'Hyundai Santa Fe Sport: Rock star',
+            'description': 'md5:b042a26142c4154a6e472933cf20793d',
+            'timestamp': 1415867444,
+            'upload_date': '20141113',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # single video with playlist.sxml URL in playlist param
+        'url': 'http://www.bbc.com/sport/0/football/33653409',
+        'info_dict': {
+            'id': 'p02xycnp',
+            'ext': 'mp4',
+            'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
+            'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
+            'duration': 140,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # article with multiple videos embedded with playlist.sxml in playlist param
+        'url': 'http://www.bbc.com/sport/0/football/34475836',
+        'info_dict': {
+            'id': '34475836',
+            'title': 'What Liverpool can expect from Klopp',
+        },
+        'playlist_count': 3,
+    }, {
+        # single video with playlist URL from weather section
+        'url': 'http://www.bbc.com/weather/features/33601775',
+        'only_matching': True,
+    }, {
+        # custom redirection to www.bbc.com
+        'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
+
+    def _extract_from_media_meta(self, media_meta, video_id):
+        # Direct links to media in media metadata (e.g.
+        # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
+        # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
+        source_files = media_meta.get('sourceFiles')
+        if source_files:
+            return [{
+                'url': f['url'],
+                'format_id': format_id,
+                'ext': f.get('encoding'),
+                'tbr': float_or_none(f.get('bitrate'), 1000),
+                'filesize': int_or_none(f.get('filesize')),
+            } for format_id, f in source_files.items() if f.get('url')], []
+
+        programme_id = media_meta.get('externalId')
+        if programme_id:
+            return self._download_media_selector(programme_id)
+
+        # Process playlist.sxml as legacy playlist
+        href = media_meta.get('href')
+        if href:
+            playlist = self._download_legacy_playlist_url(href)
+            _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id)
+            return formats, subtitles
+
+        return [], []
+
+    def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
+        programme_id, title, description, duration, formats, subtitles = \
+            self._process_legacy_playlist_url(url, playlist_id)
+        self._sort_formats(formats)
+        return {
+            'id': programme_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        timestamp = None
+        playlist_title = None
+        playlist_description = None
+
+        ld = self._parse_json(
+            self._search_regex(
+                r'(?s)<script type="application/ld\+json">(.+?)</script>',
+                webpage, 'ld json', default='{}'),
+            playlist_id, fatal=False)
+        if ld:
+            timestamp = parse_iso8601(ld.get('datePublished'))
+            playlist_title = ld.get('headline')
+            playlist_description = ld.get('articleBody')
+
+        if not timestamp:
+            timestamp = parse_iso8601(self._search_regex(
+                [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
+                 r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
+                 r'"datePublished":\s*"([^"]+)'],
+                webpage, 'date', default=None))
+
+        entries = []
+
+        # article with multiple videos embedded with playlist.sxml (e.g.
+        # http://www.bbc.com/sport/0/football/34475836)
+        playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
+        if playlists:
+            entries = [
+                self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
+                for playlist_url in playlists]
+
+        # news article with multiple videos embedded with data-playable
+        data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
+        if data_playables:
+            for _, data_playable_json in data_playables:
+                data_playable = self._parse_json(
+                    unescapeHTML(data_playable_json), playlist_id, fatal=False)
+                if not data_playable:
+                    continue
+                settings = data_playable.get('settings', {})
+                if settings:
+                    # data-playable with video vpid in settings.playlistObject.items (e.g.
+                    # http://www.bbc.com/news/world-us-canada-34473351)
+                    playlist_object = settings.get('playlistObject', {})
+                    if playlist_object:
+                        items = playlist_object.get('items')
+                        if items and isinstance(items, list):
+                            title = playlist_object['title']
+                            description = playlist_object.get('summary')
+                            duration = int_or_none(items[0].get('duration'))
+                            programme_id = items[0].get('vpid')
+                            formats, subtitles = self._download_media_selector(programme_id)
+                            self._sort_formats(formats)
+                            entries.append({
+                                'id': programme_id,
+                                'title': title,
+                                'description': description,
+                                'timestamp': timestamp,
+                                'duration': duration,
+                                'formats': formats,
+                                'subtitles': subtitles,
+                            })
+                    else:
+                        # data-playable without vpid but with a playlist.sxml URLs
+                        # in otherSettings.playlist (e.g.
+                        # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
+                        playlist = data_playable.get('otherSettings', {}).get('playlist', {})
+                        if playlist:
+                            entries.append(self._extract_from_playlist_sxml(
+                                playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
+
+        if entries:
+            playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News')
+            playlist_description = playlist_description or self._og_search_description(webpage, default=None)
+            return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
+
+        # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
+        programme_id = self._search_regex(
+            [r'data-video-player-vpid="([\da-z]{8})"',
+             r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+            webpage, 'vpid', default=None)
+
+        if programme_id:
+            formats, subtitles = self._download_media_selector(programme_id)
+            self._sort_formats(formats)
+            # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
+            digital_data = self._parse_json(
+                self._search_regex(
+                    r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
+                programme_id, fatal=False)
+            page_info = digital_data.get('page', {}).get('pageInfo', {})
+            title = page_info.get('pageName') or self._og_search_title(webpage)
+            description = page_info.get('description') or self._og_search_description(webpage)
+            timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
+            return {
+                'id': programme_id,
+                'title': title,
+                'description': description,
+                'timestamp': timestamp,
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+        playlist_title = self._html_search_regex(
+            r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
+        playlist_description = self._og_search_description(webpage, default=None)
+
+        def extract_all(pattern):
+            return list(filter(None, map(
+                lambda s: self._parse_json(s, playlist_id, fatal=False),
+                re.findall(pattern, webpage))))
+
+        # Multiple video article (e.g.
+        # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
+        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+        entries = []
+        for match in extract_all(r'new\s+SMP\(({.+?})\)'):
+            embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
+            if embed_url and re.match(EMBED_URL, embed_url):
+                entries.append(embed_url)
+        entries.extend(re.findall(
+            r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
+        if entries:
+            return self.playlist_result(
+                [self.url_result(entry, 'BBCCoUk') for entry in entries],
+                playlist_id, playlist_title, playlist_description)
+
+        # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
+        medias = extract_all(r"data-media-meta='({[^']+})'")
+
+        if not medias:
+            # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
+            media_asset = self._search_regex(
+                r'mediaAssetPage\.init\(\s*({.+?}), "/',
+                webpage, 'media asset', default=None)
+            if media_asset:
+                media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
+                medias = []
+                for video in media_asset_page.get('videos', {}).values():
+                    medias.extend(video.values())
+
+        if not medias:
+            # Multiple video playlist with single `now playing` entry (e.g.
+            # http://www.bbc.com/news/video_and_audio/must_see/33767813)
+            vxp_playlist = self._parse_json(
+                self._search_regex(
+                    r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
+                    webpage, 'playlist data'),
+                playlist_id)
+            playlist_medias = []
+            for item in vxp_playlist:
+                media = item.get('media')
+                if not media:
+                    continue
+                playlist_medias.append(media)
+                # Download single video if found media with asset id matching the video id from URL
+                if item.get('advert', {}).get('assetId') == playlist_id:
+                    medias = [media]
+                    break
+            # Fallback to the whole playlist
+            if not medias:
+                medias = playlist_medias
+
+        entries = []
+        for num, media_meta in enumerate(medias, start=1):
+            formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
+            if not formats:
+                continue
+            self._sort_formats(formats)
+
+            video_id = media_meta.get('externalId')
+            if not video_id:
+                video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
+
+            title = media_meta.get('caption')
+            if not title:
+                title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
+
+            duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
+
+            images = []
+            for image in media_meta.get('images', {}).values():
+                images.extend(image.values())
+            if 'image' in media_meta:
+                images.append(media_meta['image'])
+
+            thumbnails = [{
+                'url': image.get('href'),
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            } for image in images]
+
+            entries.append({
+                'id': video_id,
+                'title': title,
+                'thumbnails': thumbnails,
+                'duration': duration,
+                'timestamp': timestamp,
+                'formats': formats,
+                'subtitles': subtitles,
+            })
+
+        return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
+
+
+class BBCCoUkArticleIE(InfoExtractor):
+    _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    IE_NAME = 'bbc.co.uk:article'
+    IE_DESC = 'BBC articles'
+
+    _TEST = {
+        'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
+        'info_dict': {
+            'id': '3jNQLTMrPlYGTBn0WV6M2MS',
+            'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
+            'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
+        },
+        'playlist_count': 4,
+        'add_ie': ['BBCCoUk'],
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage).strip()
+
+        entries = [self.url_result(programme_url) for programme_url in re.findall(
+            r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
+
+        return self.playlist_result(entries, playlist_id, title, description)

youtube_dl/extractor/bbccouk.py

@@ -1,380 +0,0 @@
-from __future__ import unicode_literals
-
-import xml.etree.ElementTree
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-)
-from ..compat import compat_HTTPError
-
-
-class BBCCoUkIE(InfoExtractor):
-    IE_NAME = 'bbc.co.uk'
-    IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
-
-    _TESTS = [
-        {
-            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
-            'info_dict': {
-                'id': 'b039d07m',
-                'ext': 'flv',
-                'title': 'Kaleidoscope, Leonard Cohen',
-                'description': 'The Canadian poet and songwriter reflects on his musical career.',
-                'duration': 1740,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        },
-        {
-            'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
-            'info_dict': {
-                'id': 'b00yng1d',
-                'ext': 'flv',
-                'title': 'The Man in Black: Series 3: The Printed Name',
-                'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
-                'duration': 1800,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
-            'skip': 'Episode is no longer available on BBC iPlayer Radio',
-        },
-        {
-            'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
-            'info_dict': {
-                'id': 'b00yng1d',
-                'ext': 'flv',
-                'title': 'The Voice UK: Series 3: Blind Auditions 5',
-                'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
-                'duration': 5100,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
-            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
-        },
-        {
-            'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
-            'info_dict': {
-                'id': 'b03k3pb7',
-                'ext': 'flv',
-                'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
-                'description': '2. Invasion',
-                'duration': 3600,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
-            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
-        }, {
-            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
-            'info_dict': {
-                'id': 'b04v209v',
-                'ext': 'flv',
-                'title': 'Pete Tong, The Essential New Tune Special',
-                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
-                'duration': 10800,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        }, {
-            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
-            'note': 'Audio',
-            'info_dict': {
-                'id': 'p02frcch',
-                'ext': 'flv',
-                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
-                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
-                'duration': 3507,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        }, {
-            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
-            'note': 'Video',
-            'info_dict': {
-                'id': 'p025c103',
-                'ext': 'flv',
-                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
-                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
-                'duration': 226,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            }
-        }, {
-            'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
-            'info_dict': {
-                'id': 'p02n76xf',
-                'ext': 'flv',
-                'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
-                'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
-                'duration': 3540,
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
-            'skip': 'geolocation',
-        }, {
-            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
-            'only_matching': True,
-        }, {
-            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
-            'only_matching': True,
-        }, {
-            'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
-            'only_matching': True,
-        }
-    ]
-
-    def _extract_asx_playlist(self, connection, programme_id):
-        asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
-        return [ref.get('href') for ref in asx.findall('./Entry/ref')]
-
-    def _extract_connection(self, connection, programme_id):
-        formats = []
-        protocol = connection.get('protocol')
-        supplier = connection.get('supplier')
-        if protocol == 'http':
-            href = connection.get('href')
-            # ASX playlist
-            if supplier == 'asx':
-                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
-                    formats.append({
-                        'url': ref,
-                        'format_id': 'ref%s_%s' % (i, supplier),
-                    })
-            # Direct link
-            else:
-                formats.append({
-                    'url': href,
-                    'format_id': supplier,
-                })
-        elif protocol == 'rtmp':
-            application = connection.get('application', 'ondemand')
-            auth_string = connection.get('authString')
-            identifier = connection.get('identifier')
-            server = connection.get('server')
-            formats.append({
-                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
-                'play_path': identifier,
-                'app': '%s?%s' % (application, auth_string),
-                'page_url': 'http://www.bbc.co.uk',
-                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
-                'rtmp_live': False,
-                'ext': 'flv',
-                'format_id': supplier,
-            })
-        return formats
-
-    def _extract_items(self, playlist):
-        return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
-
-    def _extract_medias(self, media_selection):
-        error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
-        if error is not None:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
-        return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
-
-    def _extract_connections(self, media):
-        return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
-
-    def _extract_video(self, media, programme_id):
-        formats = []
-        vbr = int(media.get('bitrate'))
-        vcodec = media.get('encoding')
-        service = media.get('service')
-        width = int(media.get('width'))
-        height = int(media.get('height'))
-        file_size = int(media.get('media_file_size'))
-        for connection in self._extract_connections(media):
-            conn_formats = self._extract_connection(connection, programme_id)
-            for format in conn_formats:
-                format.update({
-                    'format_id': '%s_%s' % (service, format['format_id']),
-                    'width': width,
-                    'height': height,
-                    'vbr': vbr,
-                    'vcodec': vcodec,
-                    'filesize': file_size,
-                })
-            formats.extend(conn_formats)
-        return formats
-
-    def _extract_audio(self, media, programme_id):
-        formats = []
-        abr = int(media.get('bitrate'))
-        acodec = media.get('encoding')
-        service = media.get('service')
-        for connection in self._extract_connections(media):
-            conn_formats = self._extract_connection(connection, programme_id)
-            for format in conn_formats:
-                format.update({
-                    'format_id': '%s_%s' % (service, format['format_id']),
-                    'abr': abr,
-                    'acodec': acodec,
-                })
-            formats.extend(conn_formats)
-        return formats
-
-    def _get_subtitles(self, media, programme_id):
-        subtitles = {}
-        for connection in self._extract_connections(media):
-            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
-            lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
-            ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
-            srt = ''
-
-            def _extract_text(p):
-                if p.text is not None:
-                    stripped_text = p.text.strip()
-                    if stripped_text:
-                        return stripped_text
-                return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span'))
-            for pos, p in enumerate(ps):
-                srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p))
-            subtitles[lang] = [
-                {
-                    'url': connection.get('href'),
-                    'ext': 'ttml',
-                },
-                {
-                    'data': srt,
-                    'ext': 'srt',
-                },
-            ]
-        return subtitles
-
-    def _download_media_selector(self, programme_id):
-        try:
-            media_selection = self._download_xml(
-                'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
-                programme_id, 'Downloading media selection XML')
-        except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
-                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
-            else:
-                raise
-
-        formats = []
-        subtitles = None
-
-        for media in self._extract_medias(media_selection):
-            kind = media.get('kind')
-            if kind == 'audio':
-                formats.extend(self._extract_audio(media, programme_id))
-            elif kind == 'video':
-                formats.extend(self._extract_video(media, programme_id))
-            elif kind == 'captions':
-                subtitles = self.extract_subtitles(media, programme_id)
-
-        return formats, subtitles
-
-    def _download_playlist(self, playlist_id):
-        try:
-            playlist = self._download_json(
-                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
-                playlist_id, 'Downloading playlist JSON')
-
-            version = playlist.get('defaultAvailableVersion')
-            if version:
-                smp_config = version['smpConfig']
-                title = smp_config['title']
-                description = smp_config['summary']
-                for item in smp_config['items']:
-                    kind = item['kind']
-                    if kind != 'programme' and kind != 'radioProgramme':
-                        continue
-                    programme_id = item.get('vpid')
-                    duration = int(item.get('duration'))
-                    formats, subtitles = self._download_media_selector(programme_id)
-                return programme_id, title, description, duration, formats, subtitles
-        except ExtractorError as ee:
-            if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
-                raise
-
-        # fallback to legacy playlist
-        playlist = self._download_xml(
-            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
-            playlist_id, 'Downloading legacy playlist XML')
-
-        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
-        if no_items is not None:
-            reason = no_items.get('reason')
-            if reason == 'preAvailability':
-                msg = 'Episode %s is not yet available' % playlist_id
-            elif reason == 'postAvailability':
-                msg = 'Episode %s is no longer available' % playlist_id
-            elif reason == 'noMedia':
-                msg = 'Episode %s is not currently available' % playlist_id
-            else:
-                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
-            raise ExtractorError(msg, expected=True)
-
-        for item in self._extract_items(playlist):
-            kind = item.get('kind')
-            if kind != 'programme' and kind != 'radioProgramme':
-                continue
-            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
-            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
-            programme_id = item.get('identifier')
-            duration = int(item.get('duration'))
-            formats, subtitles = self._download_media_selector(programme_id)
-
-        return programme_id, title, description, duration, formats, subtitles
-
-    def _real_extract(self, url):
-        group_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, group_id, 'Downloading video page')
-
-        programme_id = None
-
-        tviplayer = self._search_regex(
-            r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
-            webpage, 'player', default=None)
-
-        if tviplayer:
-            player = self._parse_json(tviplayer, group_id).get('player', {})
-            duration = int_or_none(player.get('duration'))
-            programme_id = player.get('vpid')
-
-        if not programme_id:
-            programme_id = self._search_regex(
-                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
-
-        if programme_id:
-            formats, subtitles = self._download_media_selector(programme_id)
-            title = self._og_search_title(webpage)
-            description = self._search_regex(
-                r'<p class="medium-description">([^<]+)</p>',
-                webpage, 'description', fatal=False)
-        else:
-            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
-
-        self._sort_formats(formats)
-
-        return {
-            'id': programme_id,
-            'title': title,
-            'description': description,
-            'thumbnail': self._og_search_thumbnail(webpage, default=None),
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-        }

youtube_dl/extractor/beeg.py

@@ -1,65 +1,69 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class BeegIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',
-        'md5': '1bff67111adb785c51d1b42959ec10e5',
+        'md5': '46c384def73b33dbc581262e5ee67cef',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',
             'title': 'Sultry Striptease',
-            'description': 'md5:6db3c6177972822aaba18652ff59c773',
-            'categories': list,  # NSFW
-            'thumbnail': 're:https?://.*\.jpg$',
+            'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
+            'timestamp': 1391813355,
+            'upload_date': '20140207',
+            'duration': 383,
+            'tags': list,
             'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-
-        quality_arr = self._search_regex(
-            r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
-
-        formats = [{
-            'url': fmt[1],
-            'format_id': fmt[0],
-            'height': int(fmt[0][:-1]),
-        } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
+        video = self._download_json(
+            'http://beeg.com/api/v1/video/%s' % video_id, video_id)
 
+        formats = []
+        for format_id, video_url in video.items():
+            if not video_url:
+                continue
+            height = self._search_regex(
+                r'^(\d+)[pP]$', format_id, 'height', default=None)
+            if not height:
+                continue
+            formats.append({
+                'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
+                'format_id': format_id,
+                'height': int(height),
+            })
         self._sort_formats(formats)
 
-        title = self._html_search_regex(
-            r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
+        title = video['title']
+        video_id = video.get('id') or video_id
+        display_id = video.get('code')
+        description = video.get('desc')
 
-        description = self._html_search_regex(
-            r'<meta name="description" content="([^"]*)"',
-            webpage, 'description', fatal=False)
-        thumbnail = self._html_search_regex(
-            r'\'previewer.url\'\s*:\s*"([^"]*)"',
-            webpage, 'thumbnail', fatal=False)
+        timestamp = parse_iso8601(video.get('date'), ' ')
+        duration = int_or_none(video.get('duration'))
 
-        categories_str = self._html_search_regex(
-            r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
-        categories = (
-            None if categories_str is None
-            else categories_str.split(','))
+        tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
-            'categories': categories,
+            'timestamp': timestamp,
+            'duration': duration,
+            'tags': tags,
             'formats': formats,
             'age_limit': 18,
         }

youtube_dl/extractor/bet.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     xpath_text,
     xpath_with_ns,
@@ -57,7 +57,7 @@ class BetIE(InfoExtractor):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
 
-        media_url = compat_urllib_parse.unquote(self._search_regex(
+        media_url = compat_urllib_parse_unquote(self._search_regex(
             [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
             webpage, 'media URL'))
 

youtube_dl/extractor/bild.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    fix_xml_ampersands,
+    unescapeHTML,
 )
 
 
@@ -17,26 +17,24 @@ class BildIE(InfoExtractor):
         'info_dict': {
             'id': '38184146',
             'ext': 'mp4',
-            'title': 'BILD hat sie getestet',
+            'title': 'Das können die  neuen iPads',
+            'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 196,
-            'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
-        doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
-
-        duration = int_or_none(doc.attrib.get('duration'), scale=1000)
+        video_data = self._download_json(
+            url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
 
         return {
             'id': video_id,
-            'title': doc.attrib['ueberschrift'],
-            'description': doc.attrib.get('text'),
-            'url': doc.attrib['src'],
-            'thumbnail': doc.attrib.get('img'),
-            'duration': duration,
+            'title': unescapeHTML(video_data['title']).strip(),
+            'description': unescapeHTML(video_data.get('description')),
+            'url': video_data['clipList'][0]['srces'][0]['src'],
+            'thumbnail': video_data.get('poster'),
+            'duration': int_or_none(video_data.get('durationSec')),
         }

youtube_dl/extractor/bilibili.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 import itertools
 import json
-import xml.etree.ElementTree as ET
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_etree_fromstring,
+)
 from ..utils import (
     int_or_none,
     unified_strdate,
@@ -41,8 +43,15 @@ class BiliBiliIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None):
-            raise ExtractorError('The video does not exist or was deleted', expected=True)
+        if '(此视频不存在或被删除)' in webpage:
+            raise ExtractorError(
+                'The video does not exist or was deleted', expected=True)
+
+        if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
+            raise ExtractorError(
+                'The video is not available in your region due to copyright reasons',
+                expected=True)
+
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 
@@ -81,7 +90,7 @@ class BiliBiliIE(InfoExtractor):
         except ValueError:
             pass
 
-        lq_doc = ET.fromstring(lq_page)
+        lq_doc = compat_etree_fromstring(lq_page)
         lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(

youtube_dl/extractor/bliptv.py

@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 
 from ..compat import (
-    compat_str,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -14,6 +13,8 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     unescapeHTML,
+    xpath_text,
+    xpath_with_ns,
 )
 
 
@@ -23,10 +24,10 @@ class BlipTVIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-            'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+            'md5': '80baf1ec5c3d2019037c1c707d676b9f',
             'info_dict': {
                 'id': '5779306',
-                'ext': 'mov',
+                'ext': 'm4v',
                 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
                 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
                 'timestamp': 1323138843,
@@ -100,6 +101,20 @@ class BlipTVIE(InfoExtractor):
                 'vcodec': 'none',
             }
         },
+        {
+            # missing duration
+            'url': 'http://blip.tv/rss/flash/6700880',
+            'info_dict': {
+                'id': '6684191',
+                'ext': 'm4v',
+                'title': 'Cowboy Bebop: Gateway Shuffle Review',
+                'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8',
+                'timestamp': 1386639757,
+                'upload_date': '20131210',
+                'uploader': 'sfdebris',
+                'uploader_id': '706520',
+            }
+        }
     ]
 
     @staticmethod
@@ -128,35 +143,34 @@ class BlipTVIE(InfoExtractor):
 
         rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
 
-        def blip(s):
-            return '{http://blip.tv/dtd/blip/1.0}%s' % s
-
-        def media(s):
-            return '{http://search.yahoo.com/mrss/}%s' % s
-
-        def itunes(s):
-            return '{http://www.itunes.com/dtds/podcast-1.0.dtd}%s' % s
+        def _x(p):
+            return xpath_with_ns(p, {
+                'blip': 'http://blip.tv/dtd/blip/1.0',
+                'media': 'http://search.yahoo.com/mrss/',
+                'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
+            })
 
         item = rss.find('channel/item')
 
-        video_id = item.find(blip('item_id')).text
-        title = item.find('./title').text
-        description = clean_html(compat_str(item.find(blip('puredescription')).text))
-        timestamp = parse_iso8601(item.find(blip('datestamp')).text)
-        uploader = item.find(blip('user')).text
-        uploader_id = item.find(blip('userid')).text
-        duration = int(item.find(blip('runtime')).text)
-        media_thumbnail = item.find(media('thumbnail'))
-        thumbnail = media_thumbnail.get('url') if media_thumbnail is not None else item.find(itunes('image')).text
-        categories = [category.text for category in item.findall('category')]
+        video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id
+        title = xpath_text(item, 'title', 'title', fatal=True)
+        description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description'))
+        timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp'))
+        uploader = xpath_text(item, _x('blip:user'), 'uploader')
+        uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id')
+        duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration'))
+        media_thumbnail = item.find(_x('media:thumbnail'))
+        thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None
+                     else xpath_text(item, 'image', 'thumbnail'))
+        categories = [category.text for category in item.findall('category') if category is not None]
 
         formats = []
         subtitles_urls = {}
 
-        media_group = item.find(media('group'))
-        for media_content in media_group.findall(media('content')):
+        media_group = item.find(_x('media:group'))
+        for media_content in media_group.findall(_x('media:content')):
             url = media_content.get('url')
-            role = media_content.get(blip('role'))
+            role = media_content.get(_x('blip:role'))
             msg = self._download_webpage(
                 url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
                 video_id, 'Resolving URL for %s' % role)
@@ -175,8 +189,8 @@ class BlipTVIE(InfoExtractor):
                     'url': real_url,
                     'format_id': role,
                     'format_note': media_type,
-                    'vcodec': media_content.get(blip('vcodec')) or 'none',
-                    'acodec': media_content.get(blip('acodec')),
+                    'vcodec': media_content.get(_x('blip:vcodec')) or 'none',
+                    'acodec': media_content.get(_x('blip:acodec')),
                     'filesize': media_content.get('filesize'),
                     'width': int_or_none(media_content.get('width')),
                     'height': int_or_none(media_content.get('height')),

youtube_dl/extractor/breakcom.py

@@ -18,6 +18,7 @@ class BreakIE(InfoExtractor):
             'id': '2468056',
             'ext': 'mp4',
             'title': 'When Girls Act Like D-Bags',
+            'age_limit': 13,
         }
     }, {
         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',

youtube_dl/extractor/brightcove.py

@@ -3,16 +3,17 @@ from __future__ import unicode_literals
 
 import re
 import json
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_etree_fromstring,
     compat_parse_qs,
     compat_str,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 )
 from ..utils import (
     determine_ext,
@@ -118,8 +119,8 @@ class BrightcoveIE(InfoExtractor):
         object_str = fix_xml_ampersands(object_str)
 
         try:
-            object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
-        except xml.etree.ElementTree.ParseError:
+            object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
+        except compat_xml_parse_error:
             return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')

youtube_dl/extractor/canalc2.py

@@ -4,38 +4,53 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import parse_duration
 
 
 class Canalc2IE(InfoExtractor):
     IE_NAME = 'canalc2.tv'
-    _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+        'url': 'http://www.canalc2.tv/video/12163',
         'md5': '060158428b650f896c542dfbb3d6487f',
         'info_dict': {
             'id': '12163',
-            'ext': 'mp4',
-            'title': 'Terrasses du Numérique'
+            'ext': 'flv',
+            'title': 'Terrasses du Numérique',
+            'duration': 122,
+        },
+        'params': {
+            'skip_download': True,  # Requires rtmpdump
         }
     }
 
     def _real_extract(self, url):
-        video_id = re.match(self._VALID_URL, url).group('id')
-        # We need to set the voir field for getting the file name
-        url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        file_name = self._search_regex(
-            r"so\.addVariable\('file','(.*?)'\);",
-            webpage, 'file name')
-        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
+        video_url = self._search_regex(
+            r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
+            webpage, 'video_url', group='file')
+        formats = [{'url': video_url}]
+        if video_url.startswith('rtmp://'):
+            rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
+            formats[0].update({
+                'url': rtmp.group('url'),
+                'ext': 'flv',
+                'app': rtmp.group('app'),
+                'play_path': rtmp.group('play_path'),
+                'page_url': url,
+            })
 
         title = self._html_search_regex(
-            r'class="evenement8">(.*?)</a>', webpage, 'title')
+            r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
+        duration = parse_duration(self._search_regex(
+            r'id=["\']video_duree["\'][^>]*>([^<]+)',
+            webpage, 'duration', fatal=False))
 
         return {
             'id': video_id,
-            'ext': 'mp4',
-            'url': video_url,
             'title': title,
+            'duration': duration,
+            'formats': formats,
         }

youtube_dl/extractor/canalplus.py

@@ -78,7 +78,8 @@ class CanalplusIE(InfoExtractor):
         if video_id is None:
             webpage = self._download_webpage(url, display_id)
             video_id = self._search_regex(
-                r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
+                [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
+                webpage, 'video id', group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         doc = self._download_xml(info_url, video_id, 'Downloading video XML')
@@ -106,15 +107,11 @@ class CanalplusIE(InfoExtractor):
                 continue
             format_id = fmt.tag
             if format_id == 'HLS':
-                hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
-                for fmt in hls_formats:
-                    fmt['preference'] = preference(format_id)
-                formats.extend(hls_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', preference=preference(format_id)))
             elif format_id == 'HDS':
-                hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
-                for fmt in hds_formats:
-                    fmt['preference'] = preference(format_id)
-                formats.extend(hds_formats)
+                formats.extend(self._extract_f4m_formats(
+                    format_url + '?hdcore=2.11.3', video_id, preference=preference(format_id)))
             else:
                 formats.append({
                     'url': format_url,

youtube_dl/extractor/cbsnews.py

@@ -67,9 +67,12 @@ class CBSNewsIE(InfoExtractor):
                 'format_id': format_id,
             }
             if uri.startswith('rtmp'):
+                play_path = re.sub(
+                    r'{slistFilePath}', '',
+                    uri.split('<break>')[-1].split('{break}')[-1])
                 fmt.update({
                     'app': 'ondemand?auth=cbs',
-                    'play_path': 'mp4:' + uri.split('<break>')[-1],
+                    'play_path': 'mp4:' + play_path,
                     'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
                     'page_url': 'http://www.cbsnews.com',
                     'ext': 'flv',

youtube_dl/extractor/ceskatelevize.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_request,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -16,55 +17,81 @@ from ..utils import (
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
-
-    _TESTS = [
-        {
-            'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
-            'info_dict': {
-                'id': '214411058091220',
-                'ext': 'mp4',
-                'title': 'Hyde Park Civilizace',
-                'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře',
-                'thumbnail': 're:^https?://.*\.jpg',
-                'duration': 3350,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
+    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
+    _TESTS = [{
+        'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
+        'info_dict': {
+            'id': '61924494876951776',
+            'ext': 'mp4',
+            'title': 'Hyde Park Civilizace',
+            'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 3350,
         },
-        {
-            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
-            'info_dict': {
-                'id': '14716',
-                'ext': 'mp4',
-                'title': 'První republika: Zpěvačka z Dupárny Bobina',
-                'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
-                'thumbnail': 're:^https?://.*\.jpg',
-                'duration': 88.4,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
         },
-    ]
+    }, {
+        'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
+        'info_dict': {
+            'id': '61924494876844374',
+            'ext': 'mp4',
+            'title': 'První republika: Zpěvačka z Dupárny Bobina',
+            'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 88.4,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # video with 18+ caution trailer
+        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
+        'info_dict': {
+            'id': '215562210900007-bogotart',
+            'title': 'Queer: Bogotart',
+            'description': 'Alternativní průvodce současným queer světem',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '61924494876844842',
+                'ext': 'mp4',
+                'title': 'Queer: Bogotart (Varování 18+)',
+                'duration': 10.2,
+            },
+        }, {
+            'info_dict': {
+                'id': '61924494877068022',
+                'ext': 'mp4',
+                'title': 'Queer: Bogotart (Queer)',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 1558.3,
+            },
+        }],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
 
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        playlist_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, playlist_id)
 
         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
-        typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
-        episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
+        typ = self._html_search_regex(
+            r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
+        episode_id = self._html_search_regex(
+            r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
 
         data = {
             'playlist[0][type]': typ,
@@ -82,42 +109,52 @@ class CeskaTelevizeIE(InfoExtractor):
         req.add_header('X-Requested-With', 'XMLHttpRequest')
         req.add_header('Referer', url)
 
-        playlistpage = self._download_json(req, video_id)
+        playlistpage = self._download_json(req, playlist_id)
 
         playlist_url = playlistpage['url']
         if playlist_url == 'error_region':
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
-        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
+        req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
         req.add_header('Referer', url)
 
-        playlist = self._download_json(req, video_id)
+        playlist_title = self._og_search_title(webpage)
+        playlist_description = self._og_search_description(webpage)
 
-        item = playlist['playlist'][0]
-        formats = []
-        for format_id, stream_url in item['streamUrls'].items():
-            formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
-        self._sort_formats(formats)
+        playlist = self._download_json(req, playlist_id)['playlist']
+        playlist_len = len(playlist)
 
-        title = self._og_search_title(webpage)
-        description = self._og_search_description(webpage)
-        duration = float_or_none(item.get('duration'))
-        thumbnail = item.get('previewImageUrl')
+        entries = []
+        for item in playlist:
+            formats = []
+            for format_id, stream_url in item['streamUrls'].items():
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
+            self._sort_formats(formats)
 
-        subtitles = {}
-        subs = item.get('subtitles')
-        if subs:
-            subtitles = self.extract_subtitles(episode_id, subs)
+            item_id = item.get('id') or item['assetId']
+            title = item['title']
 
-        return {
-            'id': episode_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-        }
+            duration = float_or_none(item.get('duration'))
+            thumbnail = item.get('previewImageUrl')
+
+            subtitles = {}
+            if item.get('type') == 'VOD':
+                subs = item.get('subtitles')
+                if subs:
+                    subtitles = self.extract_subtitles(episode_id, subs)
+
+            entries.append({
+                'id': item_id,
+                'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
+                'description': playlist_description if playlist_len == 1 else None,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'formats': formats,
+                'subtitles': subtitles,
+            })
+
+        return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
     def _get_subtitles(self, episode_id, subs):
         original_subtitles = self._download_webpage(

youtube_dl/extractor/channel9.py

@@ -3,7 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    parse_filesize,
+    qualities,
+)
 
 
 class Channel9IE(InfoExtractor):
@@ -28,7 +32,7 @@ class Channel9IE(InfoExtractor):
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
-                'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                'thumbnail': 're:http://.*\.jpg',
                 'session_code': 'KOS002',
                 'session_day': 'Day 1',
                 'session_room': 'Arena 1A',
@@ -44,31 +48,29 @@ class Channel9IE(InfoExtractor):
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,
-                'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                'thumbnail': 're:http://.*\.jpg',
                 'authors': ['Mike Wilmot'],
             },
+        },
+        {
+            # low quality mp4 is best
+            'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+            'info_dict': {
+                'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+                'ext': 'mp4',
+                'title': 'Ranges for the Standard Library',
+                'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
+                'duration': 5646,
+                'thumbnail': 're:http://.*\.jpg',
+            },
+            'params': {
+                'skip_download': True,
+            },
         }
     ]
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
-    # Sorted by quality
-    _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
-
-    def _restore_bytes(self, formatted_size):
-        if not formatted_size:
-            return 0
-        m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
-        if not m:
-            return 0
-        units = m.group('units')
-        try:
-            exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
-        except ValueError:
-            return 0
-        size = float(m.group('size'))
-        return int(size * (1024 ** exponent))
-
     def _formats_from_html(self, html):
         FORMAT_REGEX = r'''
             (?x)
@@ -78,16 +80,20 @@ class Channel9IE(InfoExtractor):
             <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
             </div>)?                                                # File size part may be missing
         '''
-        # Extract known formats
+        quality = qualities((
+            'MP3', 'MP4',
+            'Low Quality WMV', 'Low Quality MP4',
+            'Mid Quality WMV', 'Mid Quality MP4',
+            'High Quality WMV', 'High Quality MP4'))
         formats = [{
             'url': x.group('url'),
             'format_id': x.group('quality'),
             'format_note': x.group('note'),
             'format': '%s (%s)' % (x.group('quality'), x.group('note')),
-            'filesize': self._restore_bytes(x.group('filesize')),  # File size is approximate
-            'preference': self._known_formats.index(x.group('quality')),
+            'filesize_approx': parse_filesize(x.group('filesize')),
+            'quality': quality(x.group('quality')),
             'vcodec': 'none' if x.group('note') == 'Audio only' else None,
-        } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
+        } for x in list(re.finditer(FORMAT_REGEX, html))]
 
         self._sort_formats(formats)
 
@@ -158,7 +164,7 @@ class Channel9IE(InfoExtractor):
 
     def _extract_session_day(self, html):
         m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
-        return m.group('day') if m is not None else None
+        return m.group('day').strip() if m is not None else None
 
     def _extract_session_room(self, html):
         m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
@@ -224,12 +230,12 @@ class Channel9IE(InfoExtractor):
         if contents is None:
             return contents
 
-        authors = self._extract_authors(html)
+        if len(contents) > 1:
+            raise ExtractorError('Got more than one entry')
+        result = contents[0]
+        result['authors'] = self._extract_authors(html)
 
-        for content in contents:
-            content['authors'] = authors
-
-        return contents
+        return result
 
     def _extract_session(self, html, content_path):
         contents = self._extract_content(html, content_path)

youtube_dl/extractor/chaturbate.py

@@ -0,0 +1,50 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class ChaturbateIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.chaturbate.com/siswet19/',
+        'info_dict': {
+            'id': 'siswet19',
+            'ext': 'mp4',
+            'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'age_limit': 18,
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://en.chaturbate.com/siswet19/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        m3u8_url = self._search_regex(
+            r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
+            'playlist', default=None, group='url')
+
+        if not m3u8_url:
+            error = self._search_regex(
+                r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
+                webpage, 'error', group='error')
+            raise ExtractorError(error, expected=True)
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+
+        return {
+            'id': video_id,
+            'title': self._live_title(video_id),
+            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
+            'age_limit': self._rta_search(webpage),
+            'is_live': True,
+            'formats': formats,
+        }

youtube_dl/extractor/cinemassacre.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import ExtractorError
 from .bliptv import BlipTVIE
+from .screenwavemedia import ScreenwaveMediaIE
 
 
 class CinemassacreIE(InfoExtractor):
@@ -83,10 +84,10 @@ class CinemassacreIE(InfoExtractor):
 
         playerdata_url = self._search_regex(
             [
-                r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
-                r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+                ScreenwaveMediaIE.EMBED_PATTERN,
+                r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
             ],
-            webpage, 'player data URL', default=None)
+            webpage, 'player data URL', default=None, group='url')
         if not playerdata_url:
             playerdata_url = BlipTVIE._extract_url(webpage)
         if not playerdata_url:

youtube_dl/extractor/clipfish.py

@@ -1,53 +1,68 @@
 from __future__ import unicode_literals
 
 import re
-import time
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
-    parse_duration,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+    remove_end,
 )
 
 
 class ClipfishIE(InfoExtractor):
-    IE_NAME = 'clipfish'
-
-    _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
-        'md5': '2521cd644e862936cf2e698206e47385',
+        'md5': '79bc922f3e8a9097b3d68a93780fd475',
         'info_dict': {
             'id': '3966754',
             'ext': 'mp4',
             'title': 'FIFA 14 - E3 2013 Trailer',
+            'timestamp': 1370938118,
+            'upload_date': '20130611',
             'duration': 82,
-        },
-        'skip': 'Blocked in the US'
+        }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
 
-        info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
-                    (video_id, int(time.time())))
-        doc = self._download_xml(
-            info_url, video_id, note='Downloading info page')
-        title = doc.find('title').text
-        video_url = doc.find('filename').text
-        if video_url is None:
-            xml_bytes = xml.etree.ElementTree.tostring(doc)
-            raise ExtractorError('Cannot find video URL in document %r' %
-                                 xml_bytes)
-        thumbnail = doc.find('imageurl').text
-        duration = parse_duration(doc.find('duration').text)
+        webpage = self._download_webpage(url, video_id)
+
+        video_info = self._parse_json(
+            js_to_json(self._html_search_regex(
+                '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
+            video_id)
+
+        formats = []
+        for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.append({
+                    'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+                    'ext': 'mp4',
+                    'format_id': 'hls',
+                })
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': ext,
+                })
+        self._sort_formats(formats)
+
+        title = remove_end(self._og_search_title(webpage), ' - Video')
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(video_info.get('length'))
+        timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
 
         return {
             'id': video_id,
             'title': title,
-            'url': video_url,
+            'formats': formats,
             'thumbnail': thumbnail,
             'duration': duration,
+            'timestamp': timestamp,
         }

youtube_dl/extractor/clipsyndicate.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
@@ -10,9 +8,9 @@ from ..utils import (
 
 
 class ClipsyndicateIE(InfoExtractor):
-    _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+    _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
         'md5': '4d7d549451bad625e0ff3d7bd56d776c',
         'info_dict': {
@@ -22,11 +20,13 @@ class ClipsyndicateIE(InfoExtractor):
             'duration': 612,
             'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         js_player = self._download_webpage(
             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
             video_id, 'Downlaoding player')

youtube_dl/extractor/clubic.py

@@ -12,9 +12,9 @@ from ..utils import (
 
 
 class ClubicIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
         'md5': '1592b694ba586036efac1776b0b43cd3',
         'info_dict': {
@@ -24,7 +24,10 @@ class ClubicIE(InfoExtractor):
             'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
             'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'http://www.clubic.com/video/video-clubic-week-2-0-apple-iphone-6s-et-plus-mais-surtout-le-pencil-469792.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/clyp.py

@@ -0,0 +1,57 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    parse_iso8601,
+)
+
+
+class ClypIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
+    _TEST = {
+        'url': 'https://clyp.it/ojz2wfah',
+        'md5': '1d4961036c41247ecfdcc439c0cddcbb',
+        'info_dict': {
+            'id': 'ojz2wfah',
+            'ext': 'mp3',
+            'title': 'Krisson80 - bits wip wip',
+            'description': '#Krisson80BitsWipWip #chiptune\n#wip',
+            'duration': 263.21,
+            'timestamp': 1443515251,
+            'upload_date': '20150929',
+        },
+    }
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        metadata = self._download_json(
+            'https://api.clyp.it/%s' % audio_id, audio_id)
+
+        formats = []
+        for secure in ('', 'Secure'):
+            for ext in ('Ogg', 'Mp3'):
+                format_id = '%s%s' % (secure, ext)
+                format_url = metadata.get('%sUrl' % format_id)
+                if format_url:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': format_id,
+                        'vcodec': 'none',
+                    })
+        self._sort_formats(formats)
+
+        title = metadata['Title']
+        description = metadata.get('Description')
+        duration = float_or_none(metadata.get('Duration'))
+        timestamp = parse_iso8601(metadata.get('DateCreated'))
+
+        return {
+            'id': audio_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/cmt.py

@@ -4,7 +4,7 @@ from .mtv import MTVIE
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
+    _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{
@@ -16,4 +16,7 @@ class CMTIE(MTVIE):
             'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
             'description': 'Blame It All On My Roots',
         },
+    }, {
+        'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
+        'only_matching': True,
     }]

youtube_dl/extractor/comcarcoff.py

@@ -36,7 +36,7 @@ class ComCarCoffIE(InfoExtractor):
             webpage, 'full data json'))
 
         video_id = full_data['activeVideo']['video']
-        video_data = full_data['videos'][video_id]
+        video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
         thumbnails = [{
             'url': video_data['images']['thumb'],
         }, {

youtube_dl/extractor/comedycentral.py

@@ -151,12 +151,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         if mobj.group('shortname'):
-            if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = 'http://thedailyshow.cc.com/full-episodes/'
-            else:
-                url = 'http://thecolbertreport.cc.com/full-episodes/'
-            mobj = re.match(self._VALID_URL, url, re.VERBOSE)
-            assert mobj is not None
+            return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes')
 
         if mobj.group('clip'):
             if mobj.group('videotitle'):

youtube_dl/extractor/common.py

@@ -10,30 +10,39 @@ import re
 import socket
 import sys
 import time
-import xml.etree.ElementTree
 
 from ..compat import (
     compat_cookiejar,
-    compat_HTTPError,
+    compat_cookies,
+    compat_getpass,
     compat_http_client,
     compat_urllib_error,
+    compat_urllib_parse,
     compat_urllib_parse_urlparse,
+    compat_urllib_request,
     compat_urlparse,
     compat_str,
+    compat_etree_fromstring,
 )
 from ..utils import (
+    NO_DEFAULT,
     age_restricted,
     bug_reports_message,
     clean_html,
     compiled_regex_type,
+    determine_ext,
     ExtractorError,
+    fix_xml_ampersands,
     float_or_none,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
     unescapeHTML,
+    unified_strdate,
+    url_basename,
+    xpath_text,
+    xpath_with_ns,
 )
-_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
@@ -63,7 +72,7 @@ class InfoExtractor(object):
 
                     Potential fields:
                     * url        Mandatory. The URL of the video file
-                    * ext        Will be calculated from url if missing
+                    * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
                                  Calculated from the format_id, width, height.
@@ -143,6 +152,7 @@ class InfoExtractor(object):
     description:    Full video description.
     uploader:       Full name of the video uploader.
     creator:        The main artist who created the video.
+    release_date:   The date (YYYYMMDD) when the video was released.
     timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
@@ -153,13 +163,15 @@ class InfoExtractor(object):
                     lower to higher preference, each element is a dictionary
                     with the "ext" entry and one of:
                         * "data": The subtitles file contents
-                        * "url": A url pointing to the subtitles file
+                        * "url": A URL pointing to the subtitles file
+                    "ext" will be calculated from URL if missing
     automatic_captions: Like 'subtitles', used by the YoutubeIE for
                     automatically generated captions
     duration:       Length of the video in seconds, as an integer.
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video
+    repost_count:   Number of reposts of the video
     average_rating: Average rating give by users, the scale used depends on the webpage
     comment_count:  Number of comments on the video
     comments:       A list of comments, each with one or more of the following
@@ -174,13 +186,18 @@ class InfoExtractor(object):
                                      Set to "root" to indicate that this is a
                                      comment to the original video.
     age_limit:      Age restriction for the video, as an integer (years)
-    webpage_url:    The url to the video webpage, if given to youtube-dl it
+    webpage_url:    The URL to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
                     by YoutubeDL if it's missing)
     categories:     A list of categories that the video falls in, for example
                     ["Sports", "Berlin"]
+    tags:           A list of tags assigned to the video, e.g. ["sweden", "pop music"]
     is_live:        True, False, or None (=unknown). Whether this video is a
                     live stream that goes on instead of a fixed-length video.
+    start_time:     Time in seconds where the reproduction should start, as
+                    specified in the URL.
+    end_time:       Time in seconds where the reproduction should end, as
+                    specified in the URL.
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -191,8 +208,8 @@ class InfoExtractor(object):
     There must be a key "entries", which is a list, an iterable, or a PagedList
     object, each element of which is a valid dictionary by this specification.
 
-    Additionally, playlists can have "title" and "id" attributes with the same
-    semantics as videos (see above).
+    Additionally, playlists can have "title", "description" and "id" attributes
+    with the same semantics as videos (see above).
 
 
     _type "multi_video" indicates that there are multiple videos that
@@ -293,11 +310,11 @@ class InfoExtractor(object):
     @classmethod
     def ie_key(cls):
         """A string for getting the InfoExtractor with get_info_extractor"""
-        return cls.__name__[:-2]
+        return compat_str(cls.__name__[:-2])
 
     @property
     def IE_NAME(self):
-        return type(self).__name__[:-2]
+        return compat_str(type(self).__name__[:-2])
 
     def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the response handle """
@@ -444,7 +461,7 @@ class InfoExtractor(object):
             return xml_string
         if transform_source:
             xml_string = transform_source(xml_string)
-        return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
+        return compat_etree_fromstring(xml_string.encode('utf-8'))
 
     def _download_json(self, url_or_request, video_id,
                        note='Downloading JSON metadata',
@@ -496,10 +513,22 @@ class InfoExtractor(object):
         """Report attempt to log in."""
         self.to_screen('Logging in')
 
+    @staticmethod
+    def raise_login_required(msg='This video is only available for registered users'):
+        raise ExtractorError(
+            '%s. Use --username and --password or --netrc to provide account credentials.' % msg,
+            expected=True)
+
+    @staticmethod
+    def raise_geo_restricted(msg='This video is not available from your location due to geo restriction'):
+        raise ExtractorError(
+            '%s. You might want to use --proxy to workaround.' % msg,
+            expected=True)
+
     # Methods for following #608
     @staticmethod
     def url_result(url, ie=None, video_id=None, video_title=None):
-        """Returns a url that points to a page that should be processed"""
+        """Returns a URL that points to a page that should be processed"""
         # TODO: ie should be the class used for getting the info
         video_info = {'_type': 'url',
                       'url': url,
@@ -523,7 +552,7 @@ class InfoExtractor(object):
             video_info['description'] = playlist_description
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -549,7 +578,7 @@ class InfoExtractor(object):
                 return next(g for g in mobj.groups() if g is not None)
             else:
                 return mobj.group(group)
-        elif default is not _NO_DEFAULT:
+        elif default is not NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
@@ -557,7 +586,7 @@ class InfoExtractor(object):
             self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
@@ -597,7 +626,7 @@ class InfoExtractor(object):
 
         return (username, password)
 
-    def _get_tfa_info(self):
+    def _get_tfa_info(self, note='two-factor verification code'):
         """
         Get the two-factor authentication info
         TODO - asking the user will be required for sms/phone verify
@@ -611,19 +640,26 @@ class InfoExtractor(object):
         if downloader_params.get('twofactor', None) is not None:
             return downloader_params['twofactor']
 
-        return None
+        return compat_getpass('Type %s and press [Return]: ' % note)
 
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
-        property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
+        content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
+        property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
+                       % {'prop': re.escape(prop)})
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
             template % (property_re, content_re),
             template % (content_re, property_re),
         ]
 
+    @staticmethod
+    def _meta_regex(prop):
+        return r'''(?isx)<meta
+                    (?=[^>]+(?:itemprop|name|property|id|http-equiv)=(["\']?)%s\1)
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
+
     def _og_search_property(self, prop, html, name=None, **kargs):
         if name is None:
             name = 'OpenGraph %s' % prop
@@ -633,7 +669,7 @@ class InfoExtractor(object):
         return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)
+        return self._og_search_property('image', html, 'thumbnail URL', fatal=False, **kargs)
 
     def _og_search_description(self, html, **kargs):
         return self._og_search_property('description', html, fatal=False, **kargs)
@@ -654,9 +690,7 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?isx)<meta
-                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
+            self._meta_regex(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -705,6 +739,28 @@ class InfoExtractor(object):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
+    @staticmethod
+    def _hidden_inputs(html):
+        html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
+        hidden_inputs = {}
+        for input in re.findall(r'(?i)<input([^>]+)>', html):
+            if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
+                continue
+            name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
+            if not name:
+                continue
+            value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
+            if not value:
+                continue
+            hidden_inputs[name.group('value')] = value.group('value')
+        return hidden_inputs
+
+    def _form_hidden_inputs(self, form_id, html):
+        form = self._search_regex(
+            r'(?is)<form[^>]+?id=(["\'])%s\1[^>]*>(?P<form>.+?)</form>' % form_id,
+            html, '%s form' % form_id, group='form')
+        return self._hidden_inputs(form)
+
     def _sort_formats(self, formats, field_preference=None):
         if not formats:
             raise ExtractorError('No video formats found')
@@ -785,7 +841,7 @@ class InfoExtractor(object):
             self._request_webpage(url, video_id, 'Checking %s URL' % item)
             return True
         except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError):
+            if isinstance(e.cause, compat_urllib_error.URLError):
                 self.to_screen(
                     '%s: %s URL is invalid, skipping' % (video_id, item))
                 return False
@@ -815,10 +871,19 @@ class InfoExtractor(object):
         self.to_screen(msg)
         time.sleep(timeout)
 
-    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
+    def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None,
+                             transform_source=lambda s: fix_xml_ampersands(s).strip(),
+                             fatal=True):
         manifest = self._download_xml(
             manifest_url, video_id, 'Downloading f4m manifest',
-            'Unable to download f4m manifest')
+            'Unable to download f4m manifest',
+            # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
+            # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244)
+            transform_source=transform_source,
+            fatal=fatal)
+
+        if manifest is False:
+            return manifest
 
         formats = []
         manifest_version = '1.0'
@@ -828,8 +893,22 @@ class InfoExtractor(object):
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
             if manifest_version == '2.0':
-                manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' +
-                                (media_el.attrib.get('href') or media_el.attrib.get('url')))
+                media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
+                if not media_url:
+                    continue
+                manifest_url = (
+                    media_url if media_url.startswith('http://') or media_url.startswith('https://')
+                    else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
+                # If media_url is itself a f4m manifest do the recursive extraction
+                # since bitrates in parent manifest (this one) and media_url manifest
+                # may differ leading to inability to resolve the format by requested
+                # bitrate in f4m downloader
+                if determine_ext(manifest_url) == 'f4m':
+                    f4m_formats = self._extract_f4m_formats(
+                        manifest_url, video_id, preference, f4m_id, fatal=fatal)
+                    if f4m_formats:
+                        formats.extend(f4m_formats)
+                    continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
                 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
@@ -846,7 +925,8 @@ class InfoExtractor(object):
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None,
-                              m3u8_id=None, note=None, errnote=None):
+                              m3u8_id=None, note=None, errnote=None,
+                              fatal=True):
 
         formats = [{
             'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
@@ -863,10 +943,15 @@ class InfoExtractor(object):
             if re.match(r'^https?://', u)
             else compat_urlparse.urljoin(m3u8_url, u))
 
-        m3u8_doc = self._download_webpage(
+        res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
-            errnote=errnote or 'Failed to download m3u8 information')
+            errnote=errnote or 'Failed to download m3u8 information',
+            fatal=fatal)
+        if res is False:
+            return res
+        m3u8_doc, urlh = res
+        m3u8_url = urlh.geturl()
         last_info = None
         last_media = None
         kv_rex = re.compile(
@@ -927,69 +1012,237 @@ class InfoExtractor(object):
         self._sort_formats(formats)
         return formats
 
-    # TODO: improve extraction
-    def _extract_smil_formats(self, smil_url, video_id, fatal=True):
-        smil = self._download_xml(
-            smil_url, video_id, 'Downloading SMIL file',
-            'Unable to download SMIL file', fatal=fatal)
+    @staticmethod
+    def _xpath_ns(path, namespace=None):
+        if not namespace:
+            return path
+        out = []
+        for c in path.split('/'):
+            if not c or c == '.':
+                out.append(c)
+            else:
+                out.append('{%s}%s' % (namespace, c))
+        return '/'.join(out)
+
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None):
+        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+
         if smil is False:
             assert not fatal
             return []
 
-        base = smil.find('./head/meta').get('base')
+        namespace = self._parse_smil_namespace(smil)
+
+        return self._parse_smil_formats(
+            smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params)
+
+    def _extract_smil_info(self, smil_url, video_id, fatal=True, f4m_params=None):
+        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+        if smil is False:
+            return {}
+        return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
+
+    def _download_smil(self, smil_url, video_id, fatal=True):
+        return self._download_xml(
+            smil_url, video_id, 'Downloading SMIL file',
+            'Unable to download SMIL file', fatal=fatal)
+
+    def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
+        namespace = self._parse_smil_namespace(smil)
+
+        formats = self._parse_smil_formats(
+            smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params)
+        subtitles = self._parse_smil_subtitles(smil, namespace=namespace)
+
+        video_id = os.path.splitext(url_basename(smil_url))[0]
+        title = None
+        description = None
+        upload_date = None
+        for meta in smil.findall(self._xpath_ns('./head/meta', namespace)):
+            name = meta.attrib.get('name')
+            content = meta.attrib.get('content')
+            if not name or not content:
+                continue
+            if not title and name == 'title':
+                title = content
+            elif not description and name in ('description', 'abstract'):
+                description = content
+            elif not upload_date and name == 'date':
+                upload_date = unified_strdate(content)
+
+        thumbnails = [{
+            'id': image.get('type'),
+            'url': image.get('src'),
+            'width': int_or_none(image.get('width')),
+            'height': int_or_none(image.get('height')),
+        } for image in smil.findall(self._xpath_ns('.//image', namespace)) if image.get('src')]
+
+        return {
+            'id': video_id,
+            'title': title or video_id,
+            'description': description,
+            'upload_date': upload_date,
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _parse_smil_namespace(self, smil):
+        return self._search_regex(
+            r'(?i)^{([^}]+)?}smil$', smil.tag, 'namespace', default=None)
+
+    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
+        base = smil_url
+        for meta in smil.findall(self._xpath_ns('./head/meta', namespace)):
+            b = meta.get('base') or meta.get('httpBase')
+            if b:
+                base = b
+                break
 
         formats = []
         rtmp_count = 0
-        if smil.findall('./body/seq/video'):
-            video = smil.findall('./body/seq/video')[0]
-            fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
-            formats.extend(fmts)
-        else:
-            for video in smil.findall('./body/switch/video'):
-                fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count)
-                formats.extend(fmts)
+        http_count = 0
+
+        videos = smil.findall(self._xpath_ns('.//video', namespace))
+        for video in videos:
+            src = video.get('src')
+            if not src:
+                continue
+
+            bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
+            filesize = int_or_none(video.get('size') or video.get('fileSize'))
+            width = int_or_none(video.get('width'))
+            height = int_or_none(video.get('height'))
+            proto = video.get('proto')
+            ext = video.get('ext')
+            src_ext = determine_ext(src)
+            streamer = video.get('streamer') or base
+
+            if proto == 'rtmp' or streamer.startswith('rtmp'):
+                rtmp_count += 1
+                formats.append({
+                    'url': streamer,
+                    'play_path': src,
+                    'ext': 'flv',
+                    'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
+                    'tbr': bitrate,
+                    'filesize': filesize,
+                    'width': width,
+                    'height': height,
+                })
+                if transform_rtmp_url:
+                    streamer, src = transform_rtmp_url(streamer, src)
+                    formats[-1].update({
+                        'url': streamer,
+                        'play_path': src,
+                    })
+                continue
+
+            src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src)
+
+            if proto == 'm3u8' or src_ext == 'm3u8':
+                m3u8_formats = self._extract_m3u8_formats(
+                    src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+                continue
+
+            if src_ext == 'f4m':
+                f4m_url = src_url
+                if not f4m_params:
+                    f4m_params = {
+                        'hdcore': '3.2.0',
+                        'plugin': 'flowplayer-3.2.0.1',
+                    }
+                f4m_url += '&' if '?' in f4m_url else '?'
+                f4m_url += compat_urllib_parse.urlencode(f4m_params)
+                f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
+                continue
+
+            if src_url.startswith('http') and self._is_valid_url(src, video_id):
+                http_count += 1
+                formats.append({
+                    'url': src_url,
+                    'ext': ext or src_ext or 'flv',
+                    'format_id': 'http-%d' % (bitrate or http_count),
+                    'tbr': bitrate,
+                    'filesize': filesize,
+                    'width': width,
+                    'height': height,
+                })
+                continue
 
         self._sort_formats(formats)
 
         return formats
 
-    def _parse_smil_video(self, video, video_id, base, rtmp_count):
-        src = video.get('src')
-        if not src:
-            return ([], rtmp_count)
-        bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
-        width = int_or_none(video.get('width'))
-        height = int_or_none(video.get('height'))
-        proto = video.get('proto')
-        if not proto:
-            if base:
-                if base.startswith('rtmp'):
-                    proto = 'rtmp'
-                elif base.startswith('http'):
-                    proto = 'http'
-        ext = video.get('ext')
-        if proto == 'm3u8':
-            return (self._extract_m3u8_formats(src, video_id, ext), rtmp_count)
-        elif proto == 'rtmp':
-            rtmp_count += 1
-            streamer = video.get('streamer') or base
-            return ([{
-                'url': streamer,
-                'play_path': src,
-                'ext': 'flv',
-                'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
-                'tbr': bitrate,
-                'width': width,
-                'height': height,
-            }], rtmp_count)
-        elif proto.startswith('http'):
-            return ([{
-                'url': base + src,
-                'ext': ext or 'flv',
-                'tbr': bitrate,
-                'width': width,
-                'height': height,
-            }], rtmp_count)
+    def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
+        subtitles = {}
+        for num, textstream in enumerate(smil.findall(self._xpath_ns('.//textstream', namespace))):
+            src = textstream.get('src')
+            if not src:
+                continue
+            ext = textstream.get('ext') or determine_ext(src)
+            if not ext:
+                type_ = textstream.get('type')
+                SUBTITLES_TYPES = {
+                    'text/vtt': 'vtt',
+                    'text/srt': 'srt',
+                    'application/smptett+xml': 'tt',
+                }
+                if type_ in SUBTITLES_TYPES:
+                    ext = SUBTITLES_TYPES[type_]
+            lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
+            subtitles.setdefault(lang, []).append({
+                'url': src,
+                'ext': ext,
+            })
+        return subtitles
+
+    def _extract_xspf_playlist(self, playlist_url, playlist_id, fatal=True):
+        xspf = self._download_xml(
+            playlist_url, playlist_id, 'Downloading xpsf playlist',
+            'Unable to download xspf manifest', fatal=fatal)
+        if xspf is False:
+            return []
+        return self._parse_xspf(xspf, playlist_id)
+
+    def _parse_xspf(self, playlist, playlist_id):
+        NS_MAP = {
+            'xspf': 'http://xspf.org/ns/0/',
+            's1': 'http://static.streamone.nl/player/ns/0',
+        }
+
+        entries = []
+        for track in playlist.findall(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP)):
+            title = xpath_text(
+                track, xpath_with_ns('./xspf:title', NS_MAP), 'title', default=playlist_id)
+            description = xpath_text(
+                track, xpath_with_ns('./xspf:annotation', NS_MAP), 'description')
+            thumbnail = xpath_text(
+                track, xpath_with_ns('./xspf:image', NS_MAP), 'thumbnail')
+            duration = float_or_none(
+                xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'), 1000)
+
+            formats = [{
+                'url': location.text,
+                'format_id': location.get(xpath_with_ns('s1:label', NS_MAP)),
+                'width': int_or_none(location.get(xpath_with_ns('s1:width', NS_MAP))),
+                'height': int_or_none(location.get(xpath_with_ns('s1:height', NS_MAP))),
+            } for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP))]
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': playlist_id,
+                'title': title,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'formats': formats,
+            })
+        return entries
 
     def _live_title(self, name):
         """ Generate the title for a live video """
@@ -1025,6 +1278,12 @@ class InfoExtractor(object):
             None, '/', True, False, expire_time, '', None, None, None)
         self._downloader.cookiejar.set_cookie(cookie)
 
+    def _get_cookies(self, url):
+        """ Return a compat_cookies.SimpleCookie with the cookies for the url """
+        req = compat_urllib_request.Request(url)
+        self._downloader.cookiejar.add_cookie_header(req)
+        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+
     def get_testcases(self, include_onlymatching=False):
         t = getattr(self, '_TEST', None)
         if t:
@@ -1063,6 +1322,23 @@ class InfoExtractor(object):
     def _get_subtitles(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
+    @staticmethod
+    def _merge_subtitle_items(subtitle_list1, subtitle_list2):
+        """ Merge subtitle items for one language. Items with duplicated URLs
+        will be dropped. """
+        list1_urls = set([item['url'] for item in subtitle_list1])
+        ret = list(subtitle_list1)
+        ret.extend([item for item in subtitle_list2 if item['url'] not in list1_urls])
+        return ret
+
+    @classmethod
+    def _merge_subtitles(cls, subtitle_dict1, subtitle_dict2):
+        """ Merge two subtitle dictionaries, language by language. """
+        ret = dict(subtitle_dict1)
+        for lang in subtitle_dict2:
+            ret[lang] = cls._merge_subtitle_items(subtitle_dict1.get(lang, []), subtitle_dict2[lang])
+        return ret
+
     def extract_automatic_captions(self, *args, **kwargs):
         if (self._downloader.params.get('writeautomaticsub', False) or
                 self._downloader.params.get('listsubtitles')):
@@ -1076,7 +1352,7 @@ class InfoExtractor(object):
 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.
-    They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
+    They accept URLs in the format _SEARCH_KEY(|all|[0-9]):{query}
     Instances should define _SEARCH_KEY and _MAX_RESULTS.
     """
 

youtube_dl/extractor/condenast.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..compat import (
@@ -12,6 +11,7 @@ from ..compat import (
 )
 from ..utils import (
     orderedSet,
+    remove_end,
 )
 
 
@@ -24,21 +24,33 @@ class CondeNastIE(InfoExtractor):
     # The keys are the supported sites and the values are the name to be shown
     # to the user and in the extractor description.
     _SITES = {
-        'wired': 'WIRED',
-        'gq': 'GQ',
-        'vogue': 'Vogue',
-        'glamour': 'Glamour',
-        'wmagazine': 'W Magazine',
-        'vanityfair': 'Vanity Fair',
+        'allure': 'Allure',
+        'architecturaldigest': 'Architectural Digest',
+        'arstechnica': 'Ars Technica',
+        'bonappetit': 'Bon Appétit',
+        'brides': 'Brides',
         'cnevids': 'Condé Nast',
+        'cntraveler': 'Condé Nast Traveler',
+        'details': 'Details',
+        'epicurious': 'Epicurious',
+        'glamour': 'Glamour',
+        'golfdigest': 'Golf Digest',
+        'gq': 'GQ',
+        'newyorker': 'The New Yorker',
+        'self': 'SELF',
+        'teenvogue': 'Teen Vogue',
+        'vanityfair': 'Vanity Fair',
+        'vogue': 'Vogue',
+        'wired': 'WIRED',
+        'wmagazine': 'W Magazine',
     }
 
-    _VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
+    _VALID_URL = r'http://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
-    EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed)/.+?' % '|'.join(_SITES.keys())
+    EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed(?:js)?)/.+?' % '|'.join(_SITES.keys())
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
         'md5': '1921f713ed48aabd715691f774c451f7',
         'info_dict': {
@@ -47,7 +59,16 @@ class CondeNastIE(InfoExtractor):
             'title': '3D Printed Speakers Lit With LED',
             'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
         }
-    }
+    }, {
+        # JS embed
+        'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js',
+        'md5': 'f1a6f9cafb7083bab74a710f65d08999',
+        'info_dict': {
+            'id': '55f9cf8b61646d1acf00000c',
+            'ext': 'mp4',
+            'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
+        }
+    }]
 
     def _extract_series(self, url, webpage):
         title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
@@ -86,8 +107,8 @@ class CondeNastIE(InfoExtractor):
         info_url = base_info_url + data
         info_page = self._download_webpage(info_url, video_id,
                                            'Downloading video info')
-        video_info = self._search_regex(r'var video = ({.+?});', info_page, 'video info')
-        video_info = json.loads(video_info)
+        video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info')
+        video_info = self._parse_json(video_info, video_id)
 
         formats = [{
             'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
@@ -111,6 +132,13 @@ class CondeNastIE(InfoExtractor):
         url_type = mobj.group('type')
         item_id = mobj.group('id')
 
+        # Convert JS embed to regular embed
+        if url_type == 'embedjs':
+            parsed_url = compat_urlparse.urlparse(url)
+            url = compat_urlparse.urlunparse(parsed_url._replace(
+                path=remove_end(parsed_url.path, '.js').replace('/embedjs/', '/embed/')))
+            url_type = 'embed'
+
         self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site])
         webpage = self._download_webpage(url, item_id)
 

youtube_dl/extractor/criterion.py

@@ -27,9 +27,7 @@ class CriterionIE(InfoExtractor):
         final_url = self._search_regex(
             r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
         title = self._og_search_title(webpage)
-        description = self._html_search_regex(
-            r'<meta name="description" content="(.+?)" />',
-            webpage, 'video description')
+        description = self._html_search_meta('description', webpage)
         thumbnail = self._search_regex(
             r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
             webpage, 'thumbnail url')

youtube_dl/extractor/crunchyroll.py

@@ -5,57 +5,35 @@ import re
 import json
 import base64
 import zlib
-import xml.etree.ElementTree
 
 from hashlib import sha1
 from math import pow, sqrt, floor
 from .common import InfoExtractor
 from ..compat import (
+    compat_etree_fromstring,
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
+    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
     bytes_to_intlist,
     intlist_to_bytes,
+    int_or_none,
+    lowercase_escape,
+    remove_end,
     unified_strdate,
     urlencode_postdata,
+    xpath_text,
 )
 from ..aes import (
     aes_cbc_decrypt,
 )
 
 
-class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+class CrunchyrollBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'crunchyroll'
-    _TESTS = [{
-        'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        'info_dict': {
-            'id': '645513',
-            'ext': 'flv',
-            'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
-            'description': 'md5:2d17137920c64f2f49981a7797d275ef',
-            'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
-            'uploader': 'Yomiuri Telecasting Corporation (YTV)',
-            'upload_date': '20131013',
-            'url': 're:(?!.*&amp)',
-        },
-        'params': {
-            # rtmp
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
-        'only_matching': True,
-    }]
-
-    _FORMAT_IDS = {
-        '360': ('60', '106'),
-        '480': ('61', '106'),
-        '720': ('62', '106'),
-        '1080': ('80', '108'),
-    }
 
     def _login(self):
         (username, password) = self._get_login_info()
@@ -75,6 +53,83 @@ class CrunchyrollIE(InfoExtractor):
     def _real_initialize(self):
         self._login()
 
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
+        request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
+                   else compat_urllib_request.Request(url_or_request))
+        # Accept-Language must be set explicitly to accept any language to avoid issues
+        # similar to https://github.com/rg3/youtube-dl/issues/6797.
+        # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
+        # should be imposed or not (from what I can see it just takes the first language
+        # ignoring the priority and requires it to correspond the IP). By the way this causes
+        # Crunchyroll to not work in georestriction cases in some browsers that don't place
+        # the locale lang first in header. However allowing any language seems to workaround the issue.
+        request.add_header('Accept-Language', '*')
+        return super(CrunchyrollBaseIE, self)._download_webpage(
+            request, video_id, note, errnote, fatal, tries, timeout, encoding)
+
+    @staticmethod
+    def _add_skip_wall(url):
+        parsed_url = compat_urlparse.urlparse(url)
+        qs = compat_urlparse.parse_qs(parsed_url.query)
+        # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
+        # > This content may be inappropriate for some people.
+        # > Are you sure you want to continue?
+        # since it's not disabled by default in crunchyroll account's settings.
+        # See https://github.com/rg3/youtube-dl/issues/7202.
+        qs['skip_wall'] = ['1']
+        return compat_urlparse.urlunparse(
+            parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
+
+
+class CrunchyrollIE(CrunchyrollBaseIE):
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
+        'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
+        'info_dict': {
+            'id': '645513',
+            'ext': 'flv',
+            'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
+            'description': 'md5:2d17137920c64f2f49981a7797d275ef',
+            'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
+            'uploader': 'Yomiuri Telecasting Corporation (YTV)',
+            'upload_date': '20131013',
+            'url': 're:(?!.*&amp)',
+        },
+        'params': {
+            # rtmp
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
+        'info_dict': {
+            'id': '589804',
+            'ext': 'flv',
+            'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
+            'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Danny Choo Network',
+            'upload_date': '20120213',
+        },
+        'params': {
+            # rtmp
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
+        'only_matching': True,
+    }, {
+        # geo-restricted (US), 18+ maturity wall, non-premium available
+        'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
+        'only_matching': True,
+    }]
+
+    _FORMAT_IDS = {
+        '360': ('60', '106'),
+        '480': ('61', '106'),
+        '720': ('62', '106'),
+        '1080': ('80', '108'),
+    }
+
     def _decrypt_subtitles(self, data, iv, id):
         data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
         iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
@@ -180,7 +235,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         return output
 
     def _extract_subtitles(self, subtitle):
-        sub_root = xml.etree.ElementTree.fromstring(subtitle)
+        sub_root = compat_etree_fromstring(subtitle)
         return [{
             'ext': 'srt',
             'data': self._convert_subtitles_to_srt(sub_root),
@@ -191,7 +246,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
     def _get_subtitles(self, video_id, webpage):
         subtitles = {}
-        for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
+        for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
             sub_page = self._download_webpage(
                 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
                 video_id, note='Downloading subtitles for ' + sub_name)
@@ -217,8 +272,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         else:
             webpage_url = 'http://www.' + mobj.group('url')
 
-        webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
-        note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='')
+        webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
+        note_m = self._html_search_regex(
+            r'<div class="showmedia-trailer-notice">(.+?)</div>',
+            webpage, 'trailer-notice', default='')
         if note_m:
             raise ExtractorError(note_m)
 
@@ -228,17 +285,28 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             if msg.get('type') == 'error':
                 raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
 
-        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
+        if 'To view this, please log in to verify you are 18 or older.' in webpage:
+            self.raise_login_required()
+
+        video_title = self._html_search_regex(
+            r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
+            webpage, 'video_title')
         video_title = re.sub(r' {2,}', ' ', video_title)
-        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
-        if not video_description:
-            video_description = None
-        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
+        video_description = self._html_search_regex(
+            r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
+            webpage, 'description', default=None)
+        if video_description:
+            video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
+        video_upload_date = self._html_search_regex(
+            [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
+            webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
         if video_upload_date:
             video_upload_date = unified_strdate(video_upload_date)
-        video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
+        video_uploader = self._html_search_regex(
+            r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
+            'video_uploader', fatal=False)
 
-        playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
+        playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
         playerdata_req = compat_urllib_request.Request(playerdata_url)
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
@@ -251,23 +319,44 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
-            streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
-            # urlencode doesn't work!
-            streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
+            streamdata_req = compat_urllib_request.Request(
+                'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
+                % (stream_id, stream_format, stream_quality),
+                compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
-            video_url = streamdata.find('./host').text
-            video_play_path = streamdata.find('./file').text
-            formats.append({
+            stream_info = streamdata.find('./{default}preload/stream_info')
+            video_url = stream_info.find('./host').text
+            video_play_path = stream_info.find('./file').text
+            metadata = stream_info.find('./metadata')
+            format_info = {
+                'format': video_format,
+                'format_id': video_format,
+                'height': int_or_none(xpath_text(metadata, './height')),
+                'width': int_or_none(xpath_text(metadata, './width')),
+            }
+
+            if '.fplive.net/' in video_url:
+                video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
+                parsed_video_url = compat_urlparse.urlparse(video_url)
+                direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
+                    netloc='v.lvlt.crcdn.net',
+                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
+                if self._is_valid_url(direct_video_url, video_id, video_format):
+                    format_info.update({
+                        'url': direct_video_url,
+                    })
+                    formats.append(format_info)
+                    continue
+
+            format_info.update({
                 'url': video_url,
                 'play_path': video_play_path,
                 'ext': 'flv',
-                'format': video_format,
-                'format_id': video_format,
             })
+            formats.append(format_info)
 
         subtitles = self.extract_subtitles(video_id, webpage)
 
@@ -283,9 +372,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         }
 
 
-class CrunchyrollShowPlaylistIE(InfoExtractor):
+class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
     IE_NAME = "crunchyroll:playlist"
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
 
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@@ -294,12 +383,25 @@ class CrunchyrollShowPlaylistIE(InfoExtractor):
             'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
         },
         'playlist_count': 13,
+    }, {
+        # geo-restricted (US), 18+ maturity wall, non-premium available
+        'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
+        'info_dict': {
+            'id': 'cosplay-complex-ova',
+            'title': 'Cosplay Complex OVA'
+        },
+        'playlist_count': 3,
+        'skip': 'Georestricted',
+    }, {
+        # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
+        'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, show_id)
+        webpage = self._download_webpage(self._add_skip_wall(url), show_id)
         title = self._html_search_regex(
             r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
             webpage, 'title')

youtube_dl/extractor/ctsnews.py

@@ -6,6 +6,7 @@ from ..utils import parse_iso8601, ExtractorError
 
 
 class CtsNewsIE(InfoExtractor):
+    IE_DESC = '華視新聞'
     # https connection failed (Connection reset)
     _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{

youtube_dl/extractor/dailymotion.py

@@ -13,8 +13,9 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    determine_ext,
     int_or_none,
-    orderedSet,
+    parse_iso8601,
     str_to_int,
     unescapeHTML,
 )
@@ -28,10 +29,16 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
         request.add_header('Cookie', 'family_filter=off; ff=off')
         return request
 
+    def _download_webpage_handle_no_ff(self, url, *args, **kwargs):
+        request = self._build_request(url)
+        return self._download_webpage_handle(request, *args, **kwargs)
+
+    def _download_webpage_no_ff(self, url, *args, **kwargs):
+        request = self._build_request(url)
+        return self._download_webpage(request, *args, **kwargs)
+
 
 class DailymotionIE(DailymotionBaseInfoExtractor):
-    """Information Extractor for Dailymotion"""
-
     _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
     IE_NAME = 'dailymotion'
 
@@ -50,9 +57,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'info_dict': {
                 'id': 'x2iuewm',
                 'ext': 'mp4',
-                'uploader': 'IGN',
                 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
+                'description': 'Several come bundled with the Steam Controller.',
+                'thumbnail': 're:^https?:.*\.(?:jpg|png)$',
+                'duration': 74,
+                'timestamp': 1425657362,
                 'upload_date': '20150306',
+                'uploader': 'IGN',
+                'uploader_id': 'xijv66',
+                'age_limit': 0,
+                'view_count': int,
+                'comment_count': int,
             }
         },
         # Vevo video
@@ -81,46 +96,128 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'uploader': 'HotWaves1012',
                 'age_limit': 18,
             }
+        },
+        # geo-restricted, player v5
+        {
+            'url': 'http://www.dailymotion.com/video/xhza0o',
+            'only_matching': True,
         }
     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        url = 'https://www.dailymotion.com/video/%s' % video_id
 
-        # Retrieve video webpage to extract further information
-        request = self._build_request(url)
-        webpage = self._download_webpage(request, video_id)
-
-        # Extract URL, uploader and title from webpage
-        self.report_extraction(video_id)
-
-        # It may just embed a vevo video:
-        m_vevo = re.search(
-            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
-            webpage)
-        if m_vevo is not None:
-            vevo_id = m_vevo.group('id')
-            self.to_screen('Vevo video detected: %s' % vevo_id)
-            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+        webpage = self._download_webpage_no_ff(
+            'https://www.dailymotion.com/video/%s' % video_id, video_id)
 
         age_limit = self._rta_search(webpage)
 
-        video_upload_date = None
-        mobj = re.search(r'<meta property="video:release_date" content="([0-9]{4})-([0-9]{2})-([0-9]{2}).+?"/>', webpage)
-        if mobj is not None:
-            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
+        description = self._og_search_description(webpage) or self._html_search_meta(
+            'description', webpage, 'description')
 
-        embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id
-        embed_request = self._build_request(embed_url)
-        embed_page = self._download_webpage(
-            embed_request, video_id, 'Downloading embed page')
-        info = self._search_regex(r'var info = ({.*?}),$', embed_page,
-                                  'video info', flags=re.MULTILINE)
-        info = json.loads(info)
-        if info.get('error') is not None:
-            msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
-            raise ExtractorError(msg, expected=True)
+        view_count = str_to_int(self._search_regex(
+            [r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"',
+             r'video_views_count[^>]+>\s+([\d\.,]+)'],
+            webpage, 'view count', fatal=False))
+        comment_count = int_or_none(self._search_regex(
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
+            webpage, 'comment count', fatal=False))
+
+        player_v5 = self._search_regex(
+            [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'],
+            webpage, 'player v5', default=None)
+        if player_v5:
+            player = self._parse_json(player_v5, video_id)
+            metadata = player['metadata']
+
+            self._check_error(metadata)
+
+            formats = []
+            for quality, media_list in metadata['qualities'].items():
+                for media in media_list:
+                    media_url = media.get('url')
+                    if not media_url:
+                        continue
+                    type_ = media.get('type')
+                    if type_ == 'application/vnd.lumberjack.manifest':
+                        continue
+                    ext = determine_ext(media_url)
+                    if type_ == 'application/x-mpegURL' or ext == 'm3u8':
+                        m3u8_formats = self._extract_m3u8_formats(
+                            media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+                        if m3u8_formats:
+                            formats.extend(m3u8_formats)
+                    elif type_ == 'application/f4m' or ext == 'f4m':
+                        f4m_formats = self._extract_f4m_formats(
+                            media_url, video_id, preference=-1, f4m_id='hds', fatal=False)
+                        if f4m_formats:
+                            formats.extend(f4m_formats)
+                    else:
+                        f = {
+                            'url': media_url,
+                            'format_id': quality,
+                        }
+                        m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
+                        if m:
+                            f.update({
+                                'width': int(m.group('width')),
+                                'height': int(m.group('height')),
+                            })
+                        formats.append(f)
+            self._sort_formats(formats)
+
+            title = metadata['title']
+            duration = int_or_none(metadata.get('duration'))
+            timestamp = int_or_none(metadata.get('created_time'))
+            thumbnail = metadata.get('poster_url')
+            uploader = metadata.get('owner', {}).get('screenname')
+            uploader_id = metadata.get('owner', {}).get('id')
+
+            subtitles = {}
+            for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items():
+                subtitles[subtitle_lang] = [{
+                    'ext': determine_ext(subtitle_url),
+                    'url': subtitle_url,
+                } for subtitle_url in subtitle.get('urls', [])]
+
+            return {
+                'id': video_id,
+                'title': title,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'timestamp': timestamp,
+                'uploader': uploader,
+                'uploader_id': uploader_id,
+                'age_limit': age_limit,
+                'view_count': view_count,
+                'comment_count': comment_count,
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+        # vevo embed
+        vevo_id = self._search_regex(
+            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
+            webpage, 'vevo embed', default=None)
+        if vevo_id:
+            return self.url_result('vevo:%s' % vevo_id, 'Vevo')
+
+        # fallback old player
+        embed_page = self._download_webpage_no_ff(
+            'https://www.dailymotion.com/embed/video/%s' % video_id,
+            video_id, 'Downloading embed page')
+
+        timestamp = parse_iso8601(self._html_search_meta(
+            'video:release_date', webpage, 'upload date'))
+
+        info = self._parse_json(
+            self._search_regex(
+                r'var info = ({.*?}),$', embed_page,
+                'video info', flags=re.MULTILINE),
+            video_id)
+
+        self._check_error(info)
 
         formats = []
         for (key, format_id) in self._FORMATS:
@@ -138,16 +235,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                     'width': width,
                     'height': height,
                 })
-        if not formats:
-            raise ExtractorError('Unable to extract video URL')
+        self._sort_formats(formats)
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)
 
-        view_count = str_to_int(self._search_regex(
-            r'video_views_count[^>]+>\s+([\d\.,]+)',
-            webpage, 'view count', fatal=False))
-
         title = self._og_search_title(webpage, default=None)
         if title is None:
             title = self._html_search_regex(
@@ -158,14 +250,21 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'id': video_id,
             'formats': formats,
             'uploader': info['owner.screenname'],
-            'upload_date': video_upload_date,
+            'timestamp': timestamp,
             'title': title,
+            'description': description,
             'subtitles': video_subtitles,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,
+            'duration': info['duration']
         }
 
+    def _check_error(self, info):
+        if info.get('error') is not None:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
+
     def _get_subtitles(self, video_id, webpage):
         try:
             sub_list = self._download_webpage(
@@ -197,18 +296,26 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
     }]
 
     def _extract_entries(self, id):
-        video_ids = []
+        video_ids = set()
+        processed_urls = set()
         for pagenum in itertools.count(1):
-            request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
-            webpage = self._download_webpage(request,
-                                             id, 'Downloading page %s' % pagenum)
+            page_url = self._PAGE_TEMPLATE % (id, pagenum)
+            webpage, urlh = self._download_webpage_handle_no_ff(
+                page_url, id, 'Downloading page %s' % pagenum)
+            if urlh.geturl() in processed_urls:
+                self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
+                    page_url, urlh.geturl()), id)
+                break
 
-            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
+            processed_urls.add(urlh.geturl())
+
+            for video_id in re.findall(r'data-xid="(.+?)"', webpage):
+                if video_id not in video_ids:
+                    yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+                    video_ids.add(video_id)
 
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
-        return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
-                for video_id in orderedSet(video_ids)]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -225,7 +332,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:(?:old/)?user/)?(?P<user>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',
@@ -234,6 +341,17 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': 'Rémi Gaillard',
         },
         'playlist_mincount': 100,
+    }, {
+        'url': 'http://www.dailymotion.com/user/UnderProject',
+        'info_dict': {
+            'id': 'UnderProject',
+            'title': 'UnderProject',
+        },
+        'playlist_mincount': 1800,
+        'expected_warnings': [
+            'Stopped at duplicated page',
+        ],
+        'skip': 'Takes too long time',
     }]
 
     def _real_extract(self, url):
@@ -251,3 +369,52 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': full_user,
             'entries': self._extract_entries(user),
         }
+
+
+class DailymotionCloudIE(DailymotionBaseInfoExtractor):
+    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
+    _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
+
+    _TESTS = [{
+        # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
+        # Tested at FranceTvInfo_2
+        'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
+        'only_matching': True,
+    }, {
+        # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
+        'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_dmcloud_url(self, webpage):
+        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+        if mobj:
+            return mobj.group(1)
+
+        mobj = re.search(
+            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+            webpage)
+        if mobj:
+            return mobj.group(1)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage_no_ff(url, video_id)
+
+        title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
+
+        video_info = self._parse_json(self._search_regex(
+            r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
+
+        # TODO: parse ios_url, which is in fact a manifest
+        video_url = video_info['mp4_url']
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': video_info.get('thumbnail_url'),
+        }

youtube_dl/extractor/dcn.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DCNIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887',
+        'info_dict':
+        {
+            'id': '17375',
+            'ext': 'mp4',
+            'title': 'رحلة العمر : الحلقة 1',
+            'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 2041,
+            'timestamp': 1227504126,
+            'upload_date': '20081124',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        request = compat_urllib_request.Request(
+            'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
+            headers={'Origin': 'http://www.dcndigital.ae'})
+
+        video = self._download_json(request, video_id)
+        title = video.get('title_en') or video['title_ar']
+
+        webpage = self._download_webpage(
+            'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
+            compat_urllib_parse.urlencode({
+                'id': video['id'],
+                'user_id': video['user_id'],
+                'signature': video['signature'],
+                'countries': 'Q0M=',
+                'filter': 'DENY',
+            }), video_id)
+
+        m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url')
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+
+        rtsp_url = self._search_regex(
+            r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False)
+        if rtsp_url:
+            formats.append({
+                'url': rtsp_url,
+                'format_id': 'rtsp',
+            })
+
+        self._sort_formats(formats)
+
+        img = video.get('img')
+        thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
+        duration = int_or_none(video.get('duration'))
+        description = video.get('description_en') or video.get('description_ar')
+        timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/democracynow.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import os.path
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    url_basename,
+    remove_start,
+)
+
+
+class DemocracynowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
+    IE_NAME = 'democracynow'
+    _TESTS = [{
+        'url': 'http://www.democracynow.org/shows/2015/7/3',
+        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'info_dict': {
+            'id': '2015-0703-001',
+            'ext': 'mp4',
+            'title': 'July 03, 2015 - Democracy Now!',
+            'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
+        },
+    }, {
+        'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
+        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'info_dict': {
+            'id': '2015-0703-001',
+            'ext': 'mp4',
+            'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
+            'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        description = self._og_search_description(webpage)
+
+        json_data = self._parse_json(self._search_regex(
+            r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
+            display_id)
+        video_id = None
+        formats = []
+
+        default_lang = 'en'
+
+        subtitles = {}
+
+        def add_subtitle_item(lang, info_dict):
+            if lang not in subtitles:
+                subtitles[lang] = []
+            subtitles[lang].append(info_dict)
+
+        # chapter_file are not subtitles
+        if 'caption_file' in json_data:
+            add_subtitle_item(default_lang, {
+                'url': compat_urlparse.urljoin(url, json_data['caption_file']),
+            })
+
+        for subtitle_item in json_data.get('captions', []):
+            lang = subtitle_item.get('language', '').lower() or default_lang
+            add_subtitle_item(lang, {
+                'url': compat_urlparse.urljoin(url, subtitle_item['url']),
+            })
+
+        for key in ('file', 'audio', 'video'):
+            media_url = json_data.get(key, '')
+            if not media_url:
+                continue
+            media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
+            video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
+            formats.append({
+                'url': media_url,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id or display_id,
+            'title': json_data['title'],
+            'description': description,
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/dfb.py

@@ -3,42 +3,47 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import unified_strdate
 
 
 class DFBIE(InfoExtractor):
     IE_NAME = 'tv.dfb.de'
-    _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://tv\.dfb\.de/video/(?P<display_id>[^/]+)/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/',
+        'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/',
         # The md5 is different each time
         'info_dict': {
-            'id': '9070',
+            'id': '11633',
+            'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland',
             'ext': 'flv',
-            'title': 'Highlights des Empfangs in Berlin',
-            'upload_date': '20140716',
+            'title': 'U 19-EM: Stimmen zum Spiel gegen Russland',
+            'upload_date': '20150714',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
         player_info = self._download_xml(
             'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
-            video_id)
+            display_id)
         video_info = player_info.find('video')
 
-        f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id)
+        f4m_info = self._download_xml(
+            self._proto_relative_url(video_info.find('url').text.strip()), display_id)
         token_el = f4m_info.find('token')
         manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
+        formats = self._extract_f4m_formats(manifest_url, display_id)
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': video_info.find('title').text,
-            'url': manifest_url,
-            'ext': 'flv',
             'thumbnail': self._og_search_thumbnail(webpage),
-            'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]),
+            'upload_date': unified_strdate(video_info.find('time_date').text),
+            'formats': formats,
         }

youtube_dl/extractor/dhm.py

@@ -1,10 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    xpath_text,
-    parse_duration,
-)
+from ..utils import parse_duration
 
 
 class DHMIE(InfoExtractor):
@@ -34,24 +31,14 @@ class DHMIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        playlist_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, playlist_id)
 
         playlist_url = self._search_regex(
             r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
 
-        playlist = self._download_xml(playlist_url, video_id)
-
-        track = playlist.find(
-            './{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
-
-        video_url = xpath_text(
-            track, './{http://xspf.org/ns/0/}location',
-            'video url', fatal=True)
-        thumbnail = xpath_text(
-            track, './{http://xspf.org/ns/0/}image',
-            'thumbnail')
+        entries = self._extract_xspf_playlist(playlist_url, playlist_id)
 
         title = self._search_regex(
             [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
@@ -63,11 +50,10 @@ class DHMIE(InfoExtractor):
             r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
             webpage, 'duration', default=None))
 
-        return {
-            'id': video_id,
-            'url': video_url,
+        entries[0].update({
             'title': title,
             'description': description,
             'duration': duration,
-            'thumbnail': thumbnail,
-        }
+        })
+
+        return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/divxstage.py

@@ -1,27 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class DivxStageIE(NovaMovIE):
-    IE_NAME = 'divxstage'
-    IE_DESC = 'DivxStage'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'}
-
-    _HOST = 'www.divxstage.eu'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _TITLE_REGEX = r'<div class="video_det">\s*<strong>([^<]+)</strong>'
-    _DESCRIPTION_REGEX = r'<div class="video_det">\s*<strong>[^<]+</strong>\s*<p>([^<]+)</p>'
-
-    _TEST = {
-        'url': 'http://www.divxstage.eu/video/57f238e2e5e01',
-        'md5': '63969f6eb26533a1968c4d325be63e72',
-        'info_dict': {
-            'id': '57f238e2e5e01',
-            'ext': 'flv',
-            'title': 'youtubedl test video',
-            'description': 'This is a test video for youtubedl.',
-        }
-    }

youtube_dl/extractor/douyutv.py

@@ -9,6 +9,7 @@ from ..compat import (compat_str, compat_basestring)
 
 
 class DouyuTVIE(InfoExtractor):
+    IE_DESC = '斗鱼'
     _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'http://www.douyutv.com/iseven',

youtube_dl/extractor/dramafever.py

@@ -6,6 +6,8 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
+    compat_urllib_parse,
+    compat_urllib_request,
     compat_urlparse,
 )
 from ..utils import (
@@ -17,7 +19,54 @@ from ..utils import (
 )
 
 
-class DramaFeverIE(InfoExtractor):
+class DramaFeverBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
+    _NETRC_MACHINE = 'dramafever'
+
+    _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
+
+    _consumer_secret = None
+
+    def _get_consumer_secret(self):
+        mainjs = self._download_webpage(
+            'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
+            None, 'Downloading main.js', fatal=False)
+        if not mainjs:
+            return self._CONSUMER_SECRET
+        return self._search_regex(
+            r"var\s+cs\s*=\s*'([^']+)'", mainjs,
+            'consumer secret', default=self._CONSUMER_SECRET)
+
+    def _real_initialize(self):
+        self._login()
+        self._consumer_secret = self._get_consumer_secret()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'username': username,
+            'password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        if all(logout_pattern not in response
+               for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
+            error = self._html_search_regex(
+                r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
+                response, 'error message', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+
+class DramaFeverIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever'
     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
     _TEST = {
@@ -85,6 +134,23 @@ class DramaFeverIE(InfoExtractor):
                 'url': href,
             }]
 
+        series_id, episode_number = video_id.split('.')
+        episode_info = self._download_json(
+            # We only need a single episode info, so restricting page size to one episode
+            # and dealing with page number as with episode number
+            r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
+            % (self._consumer_secret, series_id, episode_number),
+            video_id, 'Downloading episode info JSON', fatal=False)
+        if episode_info:
+            value = episode_info.get('value')
+            if value:
+                subfile = value[0].get('subfile') or value[0].get('new_subfile')
+                if subfile and subfile != 'http://www.dramafever.com/st/':
+                    subtitles.setdefault('English', []).append({
+                        'ext': 'srt',
+                        'url': subfile,
+                    })
+
         return {
             'id': video_id,
             'title': title,
@@ -97,7 +163,7 @@ class DramaFeverIE(InfoExtractor):
         }
 
 
-class DramaFeverSeriesIE(InfoExtractor):
+class DramaFeverSeriesIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever:series'
     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
     _TESTS = [{
@@ -118,27 +184,14 @@ class DramaFeverSeriesIE(InfoExtractor):
         'playlist_count': 20,
     }]
 
-    _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 
-    def _get_consumer_secret(self, video_id):
-        mainjs = self._download_webpage(
-            'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
-            video_id, 'Downloading main.js', fatal=False)
-        if not mainjs:
-            return self._CONSUMER_SECRET
-        return self._search_regex(
-            r"var\s+cs\s*=\s*'([^']+)'", mainjs,
-            'consumer secret', default=self._CONSUMER_SECRET)
-
     def _real_extract(self, url):
         series_id = self._match_id(url)
 
-        consumer_secret = self._get_consumer_secret(series_id)
-
         series = self._download_json(
             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
-            % (consumer_secret, series_id),
+            % (self._consumer_secret, series_id),
             series_id, 'Downloading series JSON')['series'][series_id]
 
         title = clean_html(series['name'])
@@ -148,11 +201,14 @@ class DramaFeverSeriesIE(InfoExtractor):
         for page_num in itertools.count(1):
             episodes = self._download_json(
                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
-                % (consumer_secret, series_id, self._PAGE_SIZE, page_num),
+                % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
                 series_id, 'Downloading episodes JSON page #%d' % page_num)
             for episode in episodes.get('value', []):
+                episode_url = episode.get('episode_url')
+                if not episode_url:
+                    continue
                 entries.append(self.url_result(
-                    compat_urlparse.urljoin(url, episode['episode_url']),
+                    compat_urlparse.urljoin(url, episode_url),
                     'DramaFever', episode.get('guid')))
             if page_num == episodes['num_pages']:
                 break

youtube_dl/extractor/drbonanza.py

@@ -15,7 +15,6 @@ class DRBonanzaIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
-        'md5': 'fe330252ddea607635cf2eb2c99a0af3',
         'info_dict': {
             'id': '65517',
             'ext': 'mp4',
@@ -26,6 +25,9 @@ class DRBonanzaIE(InfoExtractor):
             'upload_date': '20110120',
             'duration': 3664,
         },
+        'params': {
+            'skip_download': True,  # requires rtmp
+        },
     }, {
         'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
         'md5': '6dfe039417e76795fb783c52da3de11d',
@@ -93,6 +95,11 @@ class DRBonanzaIE(InfoExtractor):
                         'format_id': file['Type'].replace('Video', ''),
                         'preference': preferencemap.get(file['Type'], -10),
                     })
+                    if format['url'].startswith('rtmp'):
+                        rtmp_url = format['url']
+                        format['rtmp_live'] = True  # --resume does not work
+                        if '/bonanza/' in rtmp_url:
+                            format['play_path'] = rtmp_url.split('/bonanza/')[1]
                     formats.append(format)
                 elif file['Type'] == "Thumb":
                     thumbnail = file['Location']
@@ -111,9 +118,6 @@ class DRBonanzaIE(InfoExtractor):
         description = '%s\n%s\n%s\n' % (
             info['Description'], info['Actors'], info['Colophon'])
 
-        for f in formats:
-            f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
-            f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
         self._sort_formats(formats)
 
         display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id

youtube_dl/extractor/drtuber.py

@@ -36,25 +36,24 @@ class DrTuberIE(InfoExtractor):
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            [r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
+            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        like_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        dislike_count = str_to_int(self._html_search_regex(
-            r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
-            webpage, 'like count', fatal=False))
-        comment_count = str_to_int(self._html_search_regex(
-            r'<span class="comments_count">([\d,\.]+)</span>',
-            webpage, 'comment count', fatal=False))
+        def extract_count(id_, name):
+            return str_to_int(self._html_search_regex(
+                r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+                webpage, '%s count' % name, fatal=False))
+
+        like_count = extract_count('rate_likes', 'like')
+        dislike_count = extract_count('rate_dislikes', 'dislike')
+        comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(
-            r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
         categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
 
         return {

youtube_dl/extractor/dumpert.py

@@ -9,8 +9,8 @@ from ..utils import qualities
 
 
 class DumpertIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
+    _TESTS = [{
         'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
         'info_dict': {
@@ -20,11 +20,15 @@ class DumpertIE(InfoExtractor):
             'description': 'Niet schrikken hoor',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        url = 'https://www.dumpert.nl/mediabase/' + video_id
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'nsfw=1; cpc=10')
         webpage = self._download_webpage(req, video_id)

youtube_dl/extractor/eagleplatform.py

@@ -21,7 +21,7 @@ class EaglePlatformIE(InfoExtractor):
     _TESTS = [{
         # http://lenta.ru/news/2015/03/06/navalny/
         'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
-        'md5': '0b7994faa2bd5c0f69a3db6db28d078d',
+        'md5': '70f5187fb620f2c1d503b3b22fd4efe3',
         'info_dict': {
             'id': '227304',
             'ext': 'mp4',
@@ -36,7 +36,7 @@ class EaglePlatformIE(InfoExtractor):
         # http://muz-tv.ru/play/7129/
         # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
         'url': 'eagleplatform:media.clipyou.ru:12820',
-        'md5': '6c2ebeab03b739597ce8d86339d5a905',
+        'md5': '90b26344ba442c8e44aa4cf8f301164a',
         'info_dict': {
             'id': '12820',
             'ext': 'mp4',
@@ -48,7 +48,8 @@ class EaglePlatformIE(InfoExtractor):
         'skip': 'Georestricted',
     }]
 
-    def _handle_error(self, response):
+    @staticmethod
+    def _handle_error(response):
         status = int_or_none(response.get('status', 200))
         if status != 200:
             raise ExtractorError(' '.join(response['errors']), expected=True)
@@ -58,6 +59,9 @@ class EaglePlatformIE(InfoExtractor):
         self._handle_error(response)
         return response
 
+    def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
+        return self._download_json(url_or_request, video_id, note)['data'][0]
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
@@ -69,7 +73,7 @@ class EaglePlatformIE(InfoExtractor):
 
         title = media['title']
         description = media.get('description')
-        thumbnail = media.get('snapshot')
+        thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
         duration = int_or_none(media.get('duration'))
         view_count = int_or_none(media.get('views'))
 
@@ -78,13 +82,20 @@ class EaglePlatformIE(InfoExtractor):
         if age_restriction:
             age_limit = 0 if age_restriction == 'allow_all' else 18
 
-        m3u8_data = self._download_json(
-            media['sources']['secure_m3u8']['auto'],
-            video_id, 'Downloading m3u8 JSON')
+        secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
 
+        m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
         formats = self._extract_m3u8_formats(
-            m3u8_data['data'][0], video_id,
-            'mp4', entry_protocol='m3u8_native')
+            m3u8_url, video_id,
+            'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+
+        mp4_url = self._get_video_url(
+            # Secure mp4 URL is constructed according to Player.prototype.mp4 from
+            # http://lentaru.media.eagleplatform.com/player/player.js
+            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8),
+            video_id, 'Downloading mp4 JSON')
+        formats.append({'url': mp4_url, 'format_id': 'mp4'})
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/ehow.py

@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
-from ..compat import (
-    compat_urllib_parse,
-)
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 
 
 class EHowIE(InfoExtractor):
@@ -26,7 +24,7 @@ class EHowIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
-        final_url = compat_urllib_parse.unquote(video_url)
+        final_url = compat_urllib_parse_unquote(video_url)
         uploader = self._html_search_meta('uploader', webpage)
         title = self._og_search_title(webpage).replace(' | eHow', '')
 

youtube_dl/extractor/eitb.py

@@ -1,39 +1,92 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from .brightcove import BrightcoveIE
-from ..utils import ExtractorError
+from ..compat import compat_urllib_request
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class EitbIE(InfoExtractor):
     IE_NAME = 'eitb.tv'
-    _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'
 
     _TEST = {
-        'add_ie': ['Brightcove'],
-        'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
+        'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
         'md5': 'edf4436247185adee3ea18ce64c47998',
         'info_dict': {
-            'id': '2743577154001',
+            'id': '4090227752001',
             'ext': 'mp4',
             'title': '60 minutos (Lasa y Zabala, 30 años)',
-            # All videos from eitb has this description in the brightcove info
-            'description': '.',
-            'uploader': 'Euskal Telebista',
+            'description': 'Programa de reportajes de actualidad.',
+            'duration': 3996.76,
+            'timestamp': 1381789200,
+            'upload_date': '20131014',
+            'tags': list,
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        chapter_id = mobj.group('chapter_id')
-        webpage = self._download_webpage(url, chapter_id)
-        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
-        if bc_url is None:
-            raise ExtractorError('Could not extract the Brightcove url')
-        # The BrightcoveExperience object doesn't contain the video id, we set
-        # it manually
-        bc_url += '&%40videoPlayer={0}'.format(chapter_id)
-        return self.url_result(bc_url, BrightcoveIE.ie_key())
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id,
+            video_id, 'Downloading video JSON')
+
+        media = video['web_media'][0]
+
+        formats = []
+        for rendition in media['RENDITIONS']:
+            video_url = rendition.get('PMD_URL')
+            if not video_url:
+                continue
+            tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
+            format_id = 'http'
+            if tbr:
+                format_id += '-%d' % int(tbr)
+            formats.append({
+                'url': rendition['PMD_URL'],
+                'format_id': format_id,
+                'width': int_or_none(rendition.get('FRAME_WIDTH')),
+                'height': int_or_none(rendition.get('FRAME_HEIGHT')),
+                'tbr': tbr,
+            })
+
+        hls_url = media.get('HLS_SURL')
+        if hls_url:
+            request = compat_urllib_request.Request(
+                'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
+                headers={'Referer': url})
+            token_data = self._download_json(
+                request, video_id, 'Downloading auth token', fatal=False)
+            if token_data:
+                token = token_data.get('token')
+                if token:
+                    m3u8_formats = self._extract_m3u8_formats(
+                        '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)
+                    if m3u8_formats:
+                        formats.extend(m3u8_formats)
+
+        hds_url = media.get('HDS_SURL')
+        if hds_url:
+            f4m_formats = self._extract_f4m_formats(
+                '%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'),
+                video_id, f4m_id='hds', fatal=False)
+            if f4m_formats:
+                formats.extend(f4m_formats)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
+            'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
+            'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
+            'duration': float_or_none(media.get('LENGTH'), 1000),
+            'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
+            'tags': media.get('TAGS'),
+            'formats': formats,
+        }

youtube_dl/extractor/empflix.py

@@ -1,31 +0,0 @@
-from __future__ import unicode_literals
-
-from .tnaflix import TNAFlixIE
-
-
-class EMPFlixIE(TNAFlixIE):
-    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
-
-    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
-    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TESTS = [
-        {
-            'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-            'md5': 'b1bc15b6412d33902d6e5952035fcabc',
-            'info_dict': {
-                'id': '33051',
-                'display_id': 'Amateur-Finger-Fuck',
-                'ext': 'mp4',
-                'title': 'Amateur Finger Fuck',
-                'description': 'Amateur solo finger fucking.',
-                'thumbnail': 're:https?://.*\.jpg$',
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
-            'only_matching': True,
-        }
-    ]

youtube_dl/extractor/engadget.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class EngadgetIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://www.engadget.com/
-        (?:video/5min/(?P<id>\d+)|
+        (?:video(?:/5min)?/(?P<id>\d+)|
             [\d/]+/.*?)
         '''
 

youtube_dl/extractor/eroprofile.py

@@ -71,8 +71,7 @@ class EroProfileIE(InfoExtractor):
 
         m = re.search(r'You must be logged in to view this video\.', webpage)
         if m:
-            raise ExtractorError(
-                'This video requires login. Please specify a username and password and try again.', expected=True)
+            self.raise_login_required('This video requires login')
 
         video_id = self._search_regex(
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],

youtube_dl/extractor/esri.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    int_or_none,
+    parse_filesize,
+    unified_strdate,
+)
+
+
+class EsriVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.esri\.com/watch/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://video.esri.com/watch/1124/arcgis-online-_dash_-developing-applications',
+        'md5': 'd4aaf1408b221f1b38227a9bbaeb95bc',
+        'info_dict': {
+            'id': '1124',
+            'ext': 'mp4',
+            'title': 'ArcGIS Online - Developing Applications',
+            'description': 'Jeremy Bartley demonstrates how to develop applications with ArcGIS Online.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 185,
+            'upload_date': '20120419',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = []
+        for width, height, content in re.findall(
+                r'(?s)<li><strong>(\d+)x(\d+):</strong>(.+?)</li>', webpage):
+            for video_url, ext, filesize in re.findall(
+                    r'<a[^>]+href="([^"]+)">([^<]+)&nbsp;\(([^<]+)\)</a>', content):
+                formats.append({
+                    'url': compat_urlparse.urljoin(url, video_url),
+                    'ext': ext.lower(),
+                    'format_id': '%s-%s' % (ext.lower(), height),
+                    'width': int(width),
+                    'height': int(height),
+                    'filesize_approx': parse_filesize(filesize),
+                })
+        self._sort_formats(formats)
+
+        title = self._html_search_meta('title', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description', fatal=False)
+
+        thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail', fatal=False)
+        if thumbnail:
+            thumbnail = re.sub(r'_[st]\.jpg$', '_x.jpg', thumbnail)
+
+        duration = int_or_none(self._search_regex(
+            [r'var\s+videoSeconds\s*=\s*(\d+)', r"'duration'\s*:\s*(\d+)"],
+            webpage, 'duration', fatal=False))
+
+        upload_date = unified_strdate(self._html_search_meta(
+            'last-modified', webpage, 'upload date', fatal=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'upload_date': upload_date,
+            'formats': formats
+        }

youtube_dl/extractor/europa.py

@@ -0,0 +1,93 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    int_or_none,
+    orderedSet,
+    parse_duration,
+    qualities,
+    unified_strdate,
+    xpath_text
+)
+
+
+class EuropaIE(InfoExtractor):
+    _VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P<id>[A-Za-z0-9-]+)'
+    _TESTS = [{
+        'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758',
+        'md5': '574f080699ddd1e19a675b0ddf010371',
+        'info_dict': {
+            'id': 'I107758',
+            'ext': 'mp4',
+            'title': 'TRADE - Wikileaks on TTIP',
+            'description': 'NEW  LIVE EC Midday press briefing of 11/08/2015',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20150811',
+            'duration': 34,
+            'view_count': int,
+            'formats': 'mincount:3',
+        }
+    }, {
+        'url': 'http://ec.europa.eu/avservices/video/player.cfm?sitelang=en&ref=I107786',
+        'only_matching': True,
+    }, {
+        'url': 'http://ec.europa.eu/avservices/audio/audioDetails.cfm?ref=I-109295&sitelang=en',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        playlist = self._download_xml(
+            'http://ec.europa.eu/avservices/video/player/playlist.cfm?ID=%s' % video_id, video_id)
+
+        def get_item(type_, preference):
+            items = {}
+            for item in playlist.findall('./info/%s/item' % type_):
+                lang, label = xpath_text(item, 'lg', default=None), xpath_text(item, 'label', default=None)
+                if lang and label:
+                    items[lang] = label.strip()
+            for p in preference:
+                if items.get(p):
+                    return items[p]
+
+        query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        preferred_lang = query.get('sitelang', ('en', ))[0]
+
+        preferred_langs = orderedSet((preferred_lang, 'en', 'int'))
+
+        title = get_item('title', preferred_langs) or video_id
+        description = get_item('description', preferred_langs)
+        thumbnmail = xpath_text(playlist, './info/thumburl', 'thumbnail')
+        upload_date = unified_strdate(xpath_text(playlist, './info/date', 'upload date'))
+        duration = parse_duration(xpath_text(playlist, './info/duration', 'duration'))
+        view_count = int_or_none(xpath_text(playlist, './info/views', 'views'))
+
+        language_preference = qualities(preferred_langs[::-1])
+
+        formats = []
+        for file_ in playlist.findall('./files/file'):
+            video_url = xpath_text(file_, './url')
+            if not video_url:
+                continue
+            lang = xpath_text(file_, './lg')
+            formats.append({
+                'url': video_url,
+                'format_id': lang,
+                'format_note': xpath_text(file_, './lglabel'),
+                'language_preference': language_preference(lang)
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnmail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats
+        }

youtube_dl/extractor/expotv.py

@@ -33,20 +33,27 @@ class ExpoTVIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         player_key = self._search_regex(
             r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
-        config_url = 'http://client.expotv.com/video/config/%s/%s' % (
-            video_id, player_key)
         config = self._download_json(
-            config_url, video_id,
-            note='Downloading video configuration')
+            'http://client.expotv.com/video/config/%s/%s' % (video_id, player_key),
+            video_id, 'Downloading video configuration')
 
-        formats = [{
-            'url': fcfg['file'],
-            'height': int_or_none(fcfg.get('height')),
-            'format_note': fcfg.get('label'),
-            'ext': self._search_regex(
-                r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'],
-                'file extension', default=None),
-        } for fcfg in config['sources']]
+        formats = []
+        for fcfg in config['sources']:
+            media_url = fcfg.get('file')
+            if not media_url:
+                continue
+            if fcfg.get('type') == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    media_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': media_url,
+                    'height': int_or_none(fcfg.get('height')),
+                    'format_id': fcfg.get('label'),
+                    'ext': self._search_regex(
+                        r'filename=.*\.([a-z0-9_A-Z]+)&', media_url,
+                        'file extension', default=None) or fcfg.get('type'),
+                })
         self._sort_formats(formats)
 
         title = self._og_search_title(webpage)

youtube_dl/extractor/extremetube.py

@@ -3,23 +3,20 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_urllib_request,
-)
+from ..compat import compat_urllib_request
 from ..utils import (
-    qualities,
+    int_or_none,
     str_to_int,
 )
 
 
 class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
         'info_dict': {
-            'id': '652431',
+            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
@@ -29,12 +26,16 @@ class ExtremeTubeIE(InfoExtractor):
     }, {
         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
         'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/652431',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -49,20 +50,36 @@ class ExtremeTubeIE(InfoExtractor):
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
-        flash_vars = compat_parse_qs(self._search_regex(
-            r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
+        flash_vars = self._parse_json(
+            self._search_regex(
+                r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
+            video_id)
 
         formats = []
-        quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
-        for k, vals in flash_vars.items():
-            m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
-            if m is not None:
-                formats.append({
-                    'format_id': m.group('quality'),
-                    'quality': quality(m.group('quality')),
-                    'url': vals[0],
+        for quality_key, video_url in flash_vars.items():
+            height = int_or_none(self._search_regex(
+                r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
+            if not height:
+                continue
+            f = {
+                'url': video_url,
+            }
+            mobj = re.search(
+                r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
+            if mobj:
+                height = int(mobj.group('height'))
+                bitrate = int(mobj.group('bitrate'))
+                f.update({
+                    'format_id': '%dp-%dk' % (height, bitrate),
+                    'height': height,
+                    'tbr': bitrate,
                 })
-
+            else:
+                f.update({
+                    'format_id': '%dp' % height,
+                    'height': height,
+                })
+            formats.append(f)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/facebook.py

@@ -9,14 +9,15 @@ from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
-    compat_urllib_parse,
+    compat_urllib_parse_unquote,
     compat_urllib_request,
 )
 from ..utils import (
     ExtractorError,
-    int_or_none,
     limit_length,
     urlencode_postdata,
+    get_element_by_id,
+    clean_html,
 )
 
 
@@ -42,6 +43,7 @@ class FacebookIE(InfoExtractor):
             'id': '637842556329505',
             'ext': 'mp4',
             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
+            'uploader': 'Tennis on Facebook',
         }
     }, {
         'note': 'Video without discernible title',
@@ -50,6 +52,7 @@ class FacebookIE(InfoExtractor):
             'id': '274175099429670',
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',
+            'uploader': 'Asif Nawab Butt',
         },
         'expected_warnings': [
             'title'
@@ -136,18 +139,22 @@ class FacebookIE(InfoExtractor):
             else:
                 raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
-        params_raw = compat_urllib_parse.unquote(data['params'])
+        params_raw = compat_urllib_parse_unquote(data['params'])
         params = json.loads(params_raw)
-        video_data = params['video_data'][0]
 
         formats = []
-        for quality in ['sd', 'hd']:
-            src = video_data.get('%s_src' % quality)
-            if src is not None:
-                formats.append({
-                    'format_id': quality,
-                    'url': src,
-                })
+        for format_id, f in params['video_data'].items():
+            if not f or not isinstance(f, list):
+                continue
+            for quality in ('sd', 'hd'):
+                for src_type in ('src', 'src_no_ratelimit'):
+                    src = f[0].get('%s_%s' % (quality, src_type))
+                    if src:
+                        formats.append({
+                            'format_id': '%s_%s_%s' % (format_id, quality, src_type),
+                            'url': src,
+                            'preference': -10 if format_id == 'progressive' else 0,
+                        })
         if not formats:
             raise ExtractorError('Cannot find video formats')
 
@@ -161,11 +168,11 @@ class FacebookIE(InfoExtractor):
             video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id
+        uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
 
         return {
             'id': video_id,
             'title': video_title,
             'formats': formats,
-            'duration': int_or_none(video_data.get('video_duration')),
-            'thumbnail': video_data.get('thumbnail_src'),
+            'uploader': uploader,
         }