release 2017.01.02

Update Readme: Set HOME properly in install command

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.11.14*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.11.14**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.02**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.11.14
+[debug] youtube-dl version 2017.01.02
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}
@@ -50,6 +50,8 @@ $ youtube-dl -v <your command line>
 - Single video: https://youtu.be/BaW_jenozKc
 - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
 
+Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
+
 ---
 
 ### Description of your *issue*, suggested solution and other information

.github/ISSUE_TEMPLATE_tmpl.md

@@ -50,6 +50,8 @@ $ youtube-dl -v <your command line>
 - Single video: https://youtu.be/BaW_jenozKc
 - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
 
+Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
+
 ---
 
 ### Description of your *issue*, suggested solution and other information

.gitignore

@@ -31,6 +31,9 @@ updates_key.pem
 *.mp3
 *.3gp
 *.wav
+*.ape
+*.mkv
+*.swf
 *.part
 *.swp
 test/testdata

AUTHORS

@@ -190,3 +190,4 @@ John Hawkinson
 Rich Leeper
 Zhong Jianxin
 Thor77
+Mattias Wadman

CONTRIBUTING.md

@@ -58,7 +58,7 @@ We are then presented with a very complicated request when the original problem
 
 Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
 
-In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, White house podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
 
 ###  Is anyone going to need the feature?
 
@@ -92,9 +92,9 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
+If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
 
-After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
+After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
 2. Check out the source code with:
@@ -199,7 +199,7 @@ Assume at this point `meta`'s layout is:
 }
 ```
 
-Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
+Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional meta field you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
 
 ```python
 description = meta.get('summary')  # correct

ChangeLog

@@ -1,4 +1,183 @@
-version 2016.11.14
+version 2017.01.02
+
+Extractors
+* [cctv] Improve extraction (#879, #6753, #8541)
++ [nrktv:episodes] Add support for episodes (#11571)
++ [arkena] Add support for video.arkena.com (#11568)
+
+
+version 2016.12.31
+
+Core
++ Introduce --config-location option for custom configuration files (#6745,
+  #10648)
+
+Extractors
++ [twitch] Add support for player.twitch.tv (#11535, #11537)
++ [videa] Add support for videa.hu (#8181, #11133)
+* [vk] Fix postlive videos extraction
+* [vk] Extract from playerParams (#11555)
+- [freevideo] Remove extractor (#11515)
++ [showroomlive] Add support for showroom-live.com (#11458)
+* [xhamster] Fix duration extraction (#11549)
+* [rtve:live] Fix extraction (#11529)
+* [brightcove:legacy] Improve embeds detection (#11523)
++ [twitch] Add support for rechat messages (#11524)
+* [acast] Fix audio and timestamp extraction (#11521)
+
+
+version 2016.12.22
+
+Core
+* [extractor/common] Improve detection of video-only formats in m3u8
+  manifests (#11507)
+
+Extractors
++ [theplatform] Pass geo verification headers to SMIL request (#10146)
++ [viu] Pass geo verification headers to auth request
+* [rtl2] Extract more formats and metadata
+* [vbox7] Skip malformed JSON-LD (#11501)
+* [uplynk] Force downloading using native HLS downloader (#11496)
++ [laola1] Add support for another extraction scenario (#11460)
+
+
+version 2016.12.20
+
+Core
+* [extractor/common] Improve fragment URL construction for DASH media
+* [extractor/common] Fix codec information extraction for mixed audio/video
+  DASH media (#11490)
+
+Extractors
+* [vbox7] Fix extraction (#11494)
++ [uktvplay] Add support for uktvplay.uktv.co.uk (#11027)
++ [piksel] Add support for player.piksel.com (#11246)
++ [vimeo] Add support for DASH formats
+* [vimeo] Fix extraction for HLS formats (#11490)
+* [kaltura] Fix wrong widget ID in some cases (#11480)
++ [nrktv:direkte] Add support for live streams (#11488)
+* [pbs] Fix extraction for geo restricted videos (#7095)
+* [brightcove:new] Skip widevine classic videos
++ [viu] Add support for viu.com (#10607, #11329)
+
+
+version 2016.12.18
+
+Core
++ [extractor/common] Recognize DASH formats in html5 media entries
+
+Extractors
++ [ccma] Add support for ccma.cat (#11359)
+* [laola1tv] Improve extraction
++ [laola1tv] Add support embed URLs (#11460)
+* [nbc] Fix extraction for MSNBC videos (#11466)
+* [twitch] Adapt to new videos pages URL schema (#11469)
++ [meipai] Add support for meipai.com (#10718)
+* [jwplatform] Improve subtitles and duration extraction
++ [ondemandkorea] Add support for ondemandkorea.com (#10772)
++ [vvvvid] Add support for vvvvid.it (#5915)
+
+
+version 2016.12.15
+
+Core
++ [utils] Add convenience urljoin
+
+Extractors
++ [openload] Recognize oload.tv URLs (#10408)
++ [facebook] Recognize .onion URLs (#11443)
+* [vlive] Fix extraction (#11375, #11383)
++ [canvas] Extract DASH formats
++ [melonvod] Add support for vod.melon.com (#11419)
+
+
+version 2016.12.12
+
+Core
++ [utils] Add common user agents map
++ [common] Recognize HLS manifests that contain video only formats (#11394)
+
+Extractors
++ [dplay] Use Safari user agent for HLS (#11418)
++ [facebook] Detect login required error message
+* [facebook] Improve video selection (#11390)
++ [canalplus] Add another video id pattern (#11399)
+* [mixcloud] Relax URL regular expression (#11406)
+* [ctvnews] Relax URL regular expression (#11394)
++ [rte] Capture and output error message (#7746, #10498)
++ [prosiebensat1] Add support for DASH formats
+* [srgssr] Improve extraction for geo restricted videos (#11089)
+* [rts] Improve extraction for geo restricted videos (#4989)
+
+
+version 2016.12.09
+
+Core
+* [socks] Fix error reporting (#11355)
+
+Extractors
+* [openload] Fix extraction (#10408)
+* [pandoratv] Fix extraction (#11023)
++ [telebruxelles] Add support for emission URLs
+* [telebruxelles] Extract all formats
++ [bloomberg] Add another video id regular expression (#11371)
+* [fusion] Update ooyala id regular expression (#11364)
++ [1tv] Add support for playlists (#11335)
+* [1tv] Improve extraction (#11335)
++ [aenetworks] Extract more formats (#11321)
++ [thisoldhouse] Recognize /tv-episode/ URLs (#11271)
+
+
+version 2016.12.01
+
+Extractors
+* [soundcloud] Update client id (#11327)
+* [ruutu] Detect DRM protected videos
++ [liveleak] Add support for youtube embeds (#10688)
+* [spike] Fix full episodes support (#11312)
+* [comedycentral] Fix full episodes support
+* [normalboots] Rewrite in terms of JWPlatform (#11184)
+* [teamfourstar] Rewrite in terms of JWPlatform (#11184)
+- [screenwavemedia] Remove extractor (#11184)
+
+
+version 2016.11.27
+
+Extractors
++ [webcaster] Add support for webcaster.pro
++ [azubu] Add support for azubu.uol.com.br (#11305)
+* [viki] Prefer hls formats
+* [viki] Fix rtmp formats extraction (#11255)
+* [puls4] Relax URL regular expression (#11267)
+* [vevo] Improve artist extraction (#10911)
+* [mitele] Relax URL regular expression and extract more metadata (#11244)
++ [cbslocal] Recognize New York site (#11285)
++ [youtube:playlist] Pass disable_polymer in URL query (#11193)
+
+
+version 2016.11.22
+
+Extractors
+* [hellporno] Fix video extension extraction (#11247)
++ [hellporno] Add support for hellporno.net (#11247)
++ [amcnetworks] Recognize more BBC America URLs (#11263)
+* [funnyordie] Improve extraction (#11208)
+* [extractor/generic] Improve limelight embeds support
+- [crunchyroll] Remove ScaledBorderAndShadow from ASS subtitles (#8207, #9028)
+* [bandcamp] Fix free downloads extraction and extract all formats (#11067)
+* [twitter:card] Relax URL regular expression (#11225)
++ [tvanouvelles] Add support for tvanouvelles.ca (#10616)
+
+
+version 2016.11.18
+
+Extractors
+* [youtube:live] Relax URL regular expression (#11164)
+* [openload] Fix extraction (#10408, #11122)
+* [vlive] Prefer locale over language for subtitles id (#11203)
+
+
+version 2016.11.14.1
 
 Core
 + [downoader/fragment,f4m,hls] Respect HTTP headers from info dict

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 

README.md

@@ -29,7 +29,7 @@ Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.ex
 
 You can also use pip:
 
-    sudo pip install --upgrade youtube-dl
+    sudo -H pip install --upgrade youtube-dl
     
 This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
 
@@ -44,11 +44,7 @@ Or with [MacPorts](https://www.macports.org/):
 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 the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
-**youtube-dl** is a command-line program to download videos from
-YouTube.com and a few more sites. It requires the Python interpreter, version
-2.6, 2.7, or 3.2+, and it is not platform specific. It should work on
-your Unix box, on Windows or on Mac OS X. It is released to the public domain,
-which means you can modify it, redistribute it or use it however you like.
+**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
 
     youtube-dl [OPTIONS] URL [URL...]
 
@@ -84,6 +80,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      configuration in ~/.config/youtube-
                                      dl/config (%APPDATA%/youtube-dl/config.txt
                                      on Windows)
+    --config-location PATH           Location of the configuration file; either
+                                     the path to the config or its containing
+                                     directory.
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
     --mark-watched                   Mark videos watched (YouTube only)
@@ -187,7 +186,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with
-                                     expected filesize (experimental)
+                                     expected file size (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of
                                      ffmpeg
     --hls-prefer-ffmpeg              Use ffmpeg instead of the native HLS
@@ -354,7 +353,7 @@ which means you can modify it, redistribute it or use it however you like.
     -u, --username USERNAME          Login with this account ID
     -p, --password PASSWORD          Account password. If this option is left
                                      out, youtube-dl will ask interactively.
-    -2, --twofactor TWOFACTOR        Two-factor auth code
+    -2, --twofactor TWOFACTOR        Two-factor authentication code
     -n, --netrc                      Use .netrc authentication data
     --video-password PASSWORD        Video password (vimeo, smotri, youku)
 
@@ -638,7 +637,7 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
  - `acodec`: Name of the audio codec in use
  - `vcodec`: Name of the video codec in use
  - `container`: Name of the container format
- - `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native`
+ - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `m3u8`, or `m3u8_native`)
  - `format_id`: A short description of the format
 
 Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.
@@ -664,7 +663,7 @@ $ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best'
 # Download best format available but not better that 480p
 $ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]'
 
-# Download best video only format but no bigger that 50 MB
+# Download best video only format but no bigger than 50 MB
 $ youtube-dl -f 'best[filesize<50M]'
 
 # Download best format available via direct link over HTTP/HTTPS protocol
@@ -744,7 +743,7 @@ Most people asking this question are not aware that youtube-dl now defaults to d
 
 ### I get HTTP error 402 when trying to download a video. What's this?
 
-Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
+Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a web browser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
 
 ### Do I need any other programs?
 
@@ -756,7 +755,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
 
 Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [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 web browser.
 
 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 and/or HTTP headers. 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. You can also get necessary cookies and HTTP headers from JSON output obtained with `--dump-json`.
 
@@ -930,9 +929,9 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
+If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
 
-After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
+After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
 2. Check out the source code with:
@@ -1037,7 +1036,7 @@ Assume at this point `meta`'s layout is:
 }
 ```
 
-Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
+Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional meta field you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
 
 ```python
 description = meta.get('summary')  # correct
@@ -1149,7 +1148,7 @@ 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 options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L128-L278). 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 options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L129-L279). 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:
 
@@ -1252,7 +1251,7 @@ We are then presented with a very complicated request when the original problem
 
 Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
 
-In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, White house podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
 
 ###  Is anyone going to need the feature?
 

devscripts/bash-completion.py

@@ -25,5 +25,6 @@ def build_completion(opt_parser):
         filled_template = template.replace("{{flags}}", " ".join(opts_flag))
         f.write(filled_template)
 
+
 parser = youtube_dl.parseOpts()[0]
 build_completion(parser)

devscripts/buildserver.py

@@ -424,8 +424,6 @@ class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler):
                     self.send_header('Content-Length', len(msg))
                     self.end_headers()
                     self.wfile.write(msg)
-                except HTTPError as e:
-                    self.send_response(e.code, str(e))
             else:
                 self.send_response(500, 'Unknown build method "%s"' % action)
         else:

devscripts/create-github-release.py

@@ -2,11 +2,13 @@
 from __future__ import unicode_literals
 
 import base64
+import io
 import json
 import mimetypes
 import netrc
 import optparse
 import os
+import re
 import sys
 
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -90,16 +92,23 @@ class GitHubReleaser(object):
 
 
 def main():
-    parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH')
+    parser = optparse.OptionParser(usage='%prog CHANGELOG VERSION BUILDPATH')
     options, args = parser.parse_args()
-    if len(args) != 2:
+    if len(args) != 3:
         parser.error('Expected a version and a build directory')
 
-    version, build_path = args
+    changelog_file, version, build_path = args
+
+    with io.open(changelog_file, encoding='utf-8') as inf:
+        changelog = inf.read()
+
+    mobj = re.search(r'(?s)version %s\n{2}(.+?)\n{3}' % version, changelog)
+    body = mobj.group(1) if mobj else ''
 
     releaser = GitHubReleaser()
 
-    new_release = releaser.create_release(version, name='youtube-dl %s' % version)
+    new_release = releaser.create_release(
+        version, name='youtube-dl %s' % version, body=body)
     release_id = new_release['id']
 
     for asset in os.listdir(build_path):

devscripts/fish-completion.py

@@ -44,5 +44,6 @@ def build_completion(opt_parser):
     with open(FISH_COMPLETION_FILE, 'w') as f:
         f.write(filled_template)
 
+
 parser = youtube_dl.parseOpts()[0]
 build_completion(parser)

devscripts/generate_aes_testdata.py

@@ -23,6 +23,7 @@ def openssl_encode(algo, key, iv):
     out, _ = prog.communicate(secret_msg)
     return out
 
+
 iv = key = [0x20, 0x15] + 14 * [0]
 
 r = openssl_encode('aes-128-cbc', key, iv)

devscripts/gh-pages/update-sites.py

@@ -32,5 +32,6 @@ def main():
     with open('supportedsites.html', 'w', encoding='utf-8') as sitesf:
         sitesf.write(template)
 
+
 if __name__ == '__main__':
     main()

devscripts/make_contributing.py

@@ -28,5 +28,6 @@ def main():
     with io.open(outfile, 'w', encoding='utf-8') as outf:
         outf.write(out)
 
+
 if __name__ == '__main__':
     main()

devscripts/make_lazy_extractors.py

@@ -59,6 +59,7 @@ def build_lazy_ie(ie, name):
         s += make_valid_template.format(valid_url=ie._make_valid_url())
     return s
 
+
 # find the correct sorting and add the required base classes so that sublcasses
 # can be correctly created
 classes = _ALL_CLASSES[:-1]

devscripts/make_supportedsites.py

@@ -41,5 +41,6 @@ def main():
     with io.open(outfile, 'w', encoding='utf-8') as outf:
         outf.write(out)
 
+
 if __name__ == '__main__':
     main()

devscripts/prepare_manpage.py

@@ -74,5 +74,6 @@ def filter_options(readme):
 
     return ret
 
+
 if __name__ == '__main__':
     main()

devscripts/release.sh

@@ -110,7 +110,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 
 ROOT=$(pwd)
-python devscripts/create-github-release.py $version "$ROOT/build/$version"
+python devscripts/create-github-release.py ChangeLog $version "$ROOT/build/$version"
 
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
 

devscripts/zsh-completion.py

@@ -44,5 +44,6 @@ def build_completion(opt_parser):
     with open(ZSH_COMPLETION_FILE, "w") as f:
         f.write(template)
 
+
 parser = youtube_dl.parseOpts()[0]
 build_completion(parser)

docs/supportedsites.md

@@ -131,7 +131,8 @@
  - **cbsnews**: CBS News
  - **cbsnews:livevideo**: CBS News Live Videos
  - **CBSSports**
- - **CCTV**
+ - **CCMA**
+ - **CCTV**: 央视网
  - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
@@ -158,6 +159,7 @@
  - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
+ - **ComedyCentralFullEpisodes**
  - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **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
@@ -261,7 +263,6 @@
  - **francetvinfo.fr**
  - **Freesound**
  - **freespeech.org**
- - **FreeVideo**
  - **Funimation**
  - **FunnyOrDie**
  - **Fusion**
@@ -363,7 +364,8 @@
  - **kuwo:singer**: 酷我音乐 - 歌手
  - **kuwo:song**: 酷我音乐
  - **la7.it**
- - **Laola1Tv**
+ - **laola1tv**
+ - **laola1tv:embed**
  - **LCI**
  - **Lcp**
  - **LcpPlay**
@@ -401,6 +403,8 @@
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
+ - **Meipai**: 美拍
+ - **MelonVOD**
  - **META**
  - **metacafe**
  - **Metacritic**
@@ -512,6 +516,8 @@
  - **NRKPlaylist**
  - **NRKSkole**: NRK Skole
  - **NRKTV**: NRK TV and NRK Radio
+ - **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
+ - **NRKTVEpisodes**
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
@@ -522,6 +528,7 @@
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnDemandKorea**
  - **onet.tv**
  - **onet.tv:channel**
  - **OnionStudios**
@@ -545,6 +552,7 @@
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **phoenix.de**
  - **Photobucket**
+ - **Piksel**
  - **Pinkbike**
  - **Pladform**
  - **play.fm**
@@ -643,7 +651,6 @@
  - **Screencast**
  - **ScreencastOMatic**
  - **ScreenJunkies**
- - **ScreenwaveMedia**
  - **Seeker**
  - **SenateISVP**
  - **SendtoNews**
@@ -652,6 +659,7 @@
  - **Shahid**
  - **Shared**: shared.sx
  - **ShareSix**
+ - **ShowRoomLive**
  - **Sina**
  - **SixPlay**
  - **skynewsarabia:article**
@@ -715,7 +723,7 @@
  - **teachertube:user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
  - **Teamcoco**
- - **TeamFour**
+ - **TeamFourStar**
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
@@ -771,6 +779,8 @@
  - **TV2Article**
  - **TV3**
  - **TV4**: tv4.se and tv4play.se
+ - **TVANouvelles**
+ - **TVANouvellesArticle**
  - **TVC**
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
@@ -782,10 +792,13 @@
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**
- - **twitch:past_broadcasts**
  - **twitch:profile**
  - **twitch:stream**
  - **twitch:video**
+ - **twitch:videos:all**
+ - **twitch:videos:highlights**
+ - **twitch:videos:past-broadcasts**
+ - **twitch:videos:uploads**
  - **twitch:vod**
  - **twitter**
  - **twitter:amplify**
@@ -793,6 +806,7 @@
  - **udemy**
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
+ - **UKTVPlay**
  - **Unistra**
  - **uol.com.br**
  - **uplynk**
@@ -821,6 +835,7 @@
  - **ViceShow**
  - **Vidbit**
  - **Viddler**
+ - **Videa**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
  - **VideoDetective**
@@ -857,6 +872,9 @@
  - **Vimple**: Vimple - one-click video hosting
  - **Vine**
  - **vine:user**
+ - **Viu**
+ - **viu:ott**
+ - **viu:playlist**
  - **Vivo**: vivo.sx
  - **vk**: VK
  - **vk:uservideos**: VK - User's Videos
@@ -871,6 +889,7 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
+ - **VVVVID**
  - **VyboryMos**
  - **Vzaar**
  - **Walla**
@@ -880,6 +899,8 @@
  - **WatchIndianPorn**: Watch Indian Porn
  - **WDR**
  - **wdr:mobile**
+ - **Webcaster**
+ - **WebcasterFeed**
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
  - **WeiqiTV**: WQTV

test/test_InfoExtractor.py

@@ -84,5 +84,6 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
         self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -51,5 +51,6 @@ class TestAES(unittest.TestCase):
         decrypted = (aes_decrypt_text(encrypted, password, 32))
         self.assertEqual(decrypted, self.secret_msg)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -60,6 +60,7 @@ def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
+
 defs = gettestcases()
 
 
@@ -217,6 +218,7 @@ def generator(test_case):
 
     return test_template
 
+
 # And add them to TestDownload
 for n, test_case in enumerate(defs):
     test_method = generator(test_case)

test/test_execution.py

@@ -39,5 +39,6 @@ class TestExecution(unittest.TestCase):
         _, stderr = p.communicate()
         self.assertFalse(stderr)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_http.py

@@ -169,5 +169,6 @@ class TestProxy(unittest.TestCase):
         # b'xn--fiq228c' is '中文'.encode('idna')
         self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_iqiyi_sdk_interpreter.py

@@ -43,5 +43,6 @@ class TestIqiyiSDKInterpreter(unittest.TestCase):
         ie._login()
         self.assertTrue('unable to log in:' in logger.messages[0])
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_jsinterp.py

@@ -104,6 +104,14 @@ class TestJSInterpreter(unittest.TestCase):
         }''')
         self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
 
+    def test_call(self):
+        jsi = JSInterpreter('''
+        function x() { return 2; }
+        function y(a) { return x() + a; }
+        function z() { return y(3); }
+        ''')
+        self.assertEqual(jsi.call_function('z'), 5)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -70,6 +70,7 @@ from youtube_dl.utils import (
     lowercase_escape,
     url_basename,
     base_url,
+    urljoin,
     urlencode_postdata,
     urshift,
     update_url_query,
@@ -445,6 +446,23 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
         self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
 
+    def test_urljoin(self):
+        self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+        self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+        self.assertEqual(urljoin('http://foo.de/', None), None)
+        self.assertEqual(urljoin('http://foo.de/', ''), None)
+        self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
+        self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
+
     def test_parse_age_limit(self):
         self.assertEqual(parse_age_limit(None), None)
         self.assertEqual(parse_age_limit(False), None)
@@ -1075,5 +1093,6 @@ The first line
         self.assertEqual(get_element_by_class('foo', html), 'nice')
         self.assertEqual(get_element_by_class('no-such-class', html), None)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_verbose_output.py

@@ -66,5 +66,6 @@ class TestVerboseOutput(unittest.TestCase):
         self.assertTrue(b'-p' in serr)
         self.assertTrue(b'secret' not in serr)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -24,6 +24,7 @@ class YoutubeDL(youtube_dl.YoutubeDL):
         super(YoutubeDL, self).__init__(*args, **kwargs)
         self.to_stderr = self.to_screen
 
+
 params = get_params({
     'writeannotations': True,
     'skip_download': True,
@@ -74,5 +75,6 @@ class TestAnnotations(unittest.TestCase):
     def tearDown(self):
         try_rm(ANNOTATIONS_FILE)
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -66,5 +66,6 @@ class TestYoutubeLists(unittest.TestCase):
         for entry in result['entries']:
             self.assertTrue(entry.get('title'))
 
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -114,6 +114,7 @@ def make_tfunc(url, stype, sig_input, expected_sig):
     test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
     setattr(TestSignature, test_func.__name__, test_func)
 
+
 for test_spec in _TESTS:
     make_tfunc(*test_spec)
 

youtube_dl/__init__.py

@@ -95,8 +95,7 @@ def _real_main(argv=None):
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
         except IOError:
             sys.exit('ERROR: batch file could not be read')
-    all_urls = batch_urls + args
-    all_urls = [url.strip() for url in all_urls]
+    all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
@@ -406,7 +405,7 @@ def _real_main(argv=None):
         'postprocessor_args': postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
         'geo_verification_proxy': opts.geo_verification_proxy,
-
+        'config_location': opts.config_location,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -450,4 +449,5 @@ def main(argv=None):
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
 
+
 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

youtube_dl/aes.py

@@ -174,6 +174,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
 
     return plaintext
 
+
 RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
 SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
         0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
@@ -328,4 +329,5 @@ def inc(data):
             break
     return data
 
+
 __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

youtube_dl/compat.py

@@ -2491,6 +2491,7 @@ class _TreeBuilder(etree.TreeBuilder):
     def doctype(self, name, pubid, system):
         pass
 
+
 if sys.version_info[0] >= 3:
     def compat_etree_fromstring(text):
         return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
@@ -2787,6 +2788,7 @@ def workaround_optparse_bug9161():
             return real_add_option(self, *bargs, **bkwargs)
         optparse.OptionGroup.add_option = _compat_add_option
 
+
 if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
     compat_get_terminal_size = shutil.get_terminal_size
 else:

youtube_dl/downloader/external.py

@@ -293,6 +293,7 @@ class FFmpegFD(ExternalFD):
 class AVconvFD(FFmpegFD):
     pass
 
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()

youtube_dl/downloader/hls.py

@@ -65,6 +65,9 @@ class HlsFD(FragmentFD):
         s = manifest.decode('utf-8', 'ignore')
 
         if not self.can_download(s, info_dict):
+            if info_dict.get('extra_param_to_segment_url'):
+                self.report_error('pycrypto not found. Please install it.')
+                return False
             self.report_warning(
                 'hlsnative has detected features it does not support, '
                 'extraction will be delegated to ffmpeg')

youtube_dl/extractor/acast.py

@@ -8,6 +8,7 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     int_or_none,
+    parse_iso8601,
     OnDemandPagedList,
 )
 
@@ -15,18 +16,33 @@ from ..utils import (
 class ACastIE(InfoExtractor):
     IE_NAME = 'acast'
     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
-    _TEST = {
+    _TESTS = [{
+        # test with one bling
         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
         'md5': 'ada3de5a1e3a2a381327d749854788bb',
         'info_dict': {
             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
             'ext': 'mp3',
             'title': '"Where Are You?": Taipei 101, Taiwan',
-            'timestamp': 1196172000000,
+            'timestamp': 1196172000,
+            'upload_date': '20071127',
             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
             'duration': 211,
         }
-    }
+    }, {
+        # test with multiple blings
+        'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
+        'md5': '55c0097badd7095f494c99a172f86501',
+        'info_dict': {
+            'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
+            'ext': 'mp3',
+            'title': '2. Raggarmordet - Röster ur det förflutna',
+            'timestamp': 1477346700,
+            'upload_date': '20161024',
+            'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
+            'duration': 2797,
+        }
+    }]
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
@@ -35,11 +51,11 @@ class ACastIE(InfoExtractor):
         return {
             'id': compat_str(cast_data['id']),
             'display_id': display_id,
-            'url': cast_data['blings'][0]['audio'],
+            'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
             'title': cast_data['name'],
             'description': cast_data.get('description'),
             'thumbnail': cast_data.get('image'),
-            'timestamp': int_or_none(cast_data.get('publishingDate')),
+            'timestamp': parse_iso8601(cast_data.get('publishingDate')),
             'duration': int_or_none(cast_data.get('duration')),
         }
 

youtube_dl/extractor/aenetworks.py

@@ -26,7 +26,7 @@ class AENetworksIE(AENetworksBaseIE):
     _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
-        'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
+        'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
         'info_dict': {
             'id': '22253814',
             'ext': 'mp4',
@@ -99,7 +99,7 @@ class AENetworksIE(AENetworksBaseIE):
 
         query = {
             'mbr': 'true',
-            'assetTypes': 'medium_video_s3'
+            'assetTypes': 'high_video_s3'
         }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(
@@ -155,7 +155,7 @@ class HistoryTopicIE(AENetworksBaseIE):
             'id': 'world-war-i-history',
             'title': 'World War I History',
         },
-        'playlist_mincount': 24,
+        'playlist_mincount': 23,
     }, {
         'url': 'http://www.history.com/topics/world-war-i-history/videos',
         'only_matching': True,
@@ -193,7 +193,8 @@ class HistoryTopicIE(AENetworksBaseIE):
             return self.theplatform_url_result(
                 release_url, video_id, {
                     'mbr': 'true',
-                    'switch': 'hls'
+                    'switch': 'hls',
+                    'assetTypes': 'high_video_ak',
                 })
         else:
             webpage = self._download_webpage(url, topic_id)
@@ -203,6 +204,7 @@ class HistoryTopicIE(AENetworksBaseIE):
                 entries.append(self.theplatform_url_result(
                     video_attributes['data-release-url'], video_attributes['data-id'], {
                         'mbr': 'true',
-                        'switch': 'hls'
+                        'switch': 'hls',
+                        'assetTypes': 'high_video_ak',
                     }))
             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))

youtube_dl/extractor/amcnetworks.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class AMCNetworksIE(ThePlatformIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?[^/]+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
         'md5': '',
@@ -41,6 +41,9 @@ class AMCNetworksIE(ThePlatformIE):
     }, {
         'url': 'http://www.ifc.com/movies/chaos',
         'only_matching': True,
+    }, {
+        'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/arkena.py

@@ -4,8 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
+    ExtractorError,
     float_or_none,
     int_or_none,
     mimetype2ext,
@@ -15,7 +17,13 @@ from ..utils import (
 
 
 class ArkenaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:
+                                video\.arkena\.com/play2/embed/player\?|
+                                play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
+                            )
+                        '''
     _TESTS = [{
         'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
         'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
@@ -37,6 +45,9 @@ class ArkenaIE(InfoExtractor):
     }, {
         'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
         'only_matching': True,
+    }, {
+        'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -53,6 +64,14 @@ class ArkenaIE(InfoExtractor):
         video_id = mobj.group('id')
         account_id = mobj.group('account_id')
 
+        # Handle http://video.arkena.com/play2/embed/player URL
+        if not video_id:
+            qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+            video_id = qs.get('mediaId', [None])[0]
+            account_id = qs.get('accountId', [None])[0]
+            if not video_id or not account_id:
+                raise ExtractorError('Invalid URL', expected=True)
+
         playlist = self._download_json(
             'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_'
             % (video_id, account_id),

youtube_dl/extractor/azubu.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class AzubuIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/[^/]+#!/play/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
@@ -103,12 +103,15 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/(?P<id>[^/]+)$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.azubu.tv/MarsTVMDLen',
         'only_matching': True,
-    }
+    }, {
+        'url': 'http://azubu.uol.com.br/adolfz',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         user = self._match_id(url)

youtube_dl/extractor/bandcamp.py

@@ -1,7 +1,9 @@
 from __future__ import unicode_literals
 
 import json
+import random
 import re
+import time
 
 from .common import InfoExtractor
 from ..compat import (
@@ -12,6 +14,9 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    parse_filesize,
+    unescapeHTML,
+    update_url_query,
 )
 
 
@@ -81,35 +86,68 @@ class BandcampIE(InfoExtractor):
             r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
             webpage, 'video id')
 
-        download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
-        # We get the dictionary of the track from some javascript code
-        all_info = self._parse_json(self._search_regex(
-            r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
-        info = all_info[0]
-        # We pick mp3-320 for now, until format selection can be easily implemented.
-        mp3_info = info['downloads']['mp3-320']
-        # If we try to use this url it says the link has expired
-        initial_url = mp3_info['url']
-        m_url = re.match(
-            r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
-            initial_url)
-        # We build the url we will use to get the final track url
-        # This url is build in Bandcamp in the script download_bunde_*.js
-        request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
-        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._proto_relative_url(self._search_regex(
-            r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
+        download_webpage = self._download_webpage(
+            download_link, video_id, 'Downloading free downloads page')
+
+        blob = self._parse_json(
+            self._search_regex(
+                r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
+                'blob', group='blob'),
+            video_id, transform_source=unescapeHTML)
+
+        info = blob['digital_items'][0]
+
+        downloads = info['downloads']
+        track = info['title']
+
+        artist = info.get('artist')
+        title = '%s - %s' % (artist, track) if artist else track
+
+        download_formats = {}
+        for f in blob['download_formats']:
+            name, ext = f.get('name'), f.get('file_extension')
+            if all(isinstance(x, compat_str) for x in (name, ext)):
+                download_formats[name] = ext.strip('.')
+
+        formats = []
+        for format_id, f in downloads.items():
+            format_url = f.get('url')
+            if not format_url:
+                continue
+            # Stat URL generation algorithm is reverse engineered from
+            # download_*_bundle_*.js
+            stat_url = update_url_query(
+                format_url.replace('/download/', '/statdownload/'), {
+                    '.rand': int(time.time() * 1000 * random.random()),
+                })
+            format_id = f.get('encoding_name') or format_id
+            stat = self._download_json(
+                stat_url, video_id, 'Downloading %s JSON' % format_id,
+                transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
+                fatal=False)
+            if not stat:
+                continue
+            retry_url = stat.get('retry_url')
+            if not isinstance(retry_url, compat_str):
+                continue
+            formats.append({
+                'url': self._proto_relative_url(retry_url, 'http:'),
+                'ext': download_formats.get(format_id),
+                'format_id': format_id,
+                'format_note': f.get('description'),
+                'filesize': parse_filesize(f.get('size_mb')),
+                'vcodec': 'none',
+            })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': info['title'],
-            'ext': 'mp3',
-            'vcodec': 'none',
-            'url': final_url,
+            'title': title,
             'thumbnail': info.get('thumb_url'),
             'uploader': info.get('artist'),
+            'artist': artist,
+            'track': track,
+            'formats': formats,
         }
 
 

youtube_dl/extractor/bloomberg.py

@@ -45,7 +45,8 @@ class BloombergIE(InfoExtractor):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
         video_id = self._search_regex(
-            r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
+            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
+             r'videoId\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
             webpage, 'id', group='url', default=None)
         if not video_id:
             bplayer_data = self._parse_json(self._search_regex(

youtube_dl/extractor/brightcove.py

@@ -232,13 +232,16 @@ class BrightcoveLegacyIE(InfoExtractor):
         """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(
-            r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
-            webpage)
+            r'''(?x)
+                <meta\s+
+                    (?:property|itemprop)=([\'"])(?:og:video|embedURL)\1[^>]+
+                    content=([\'"])(?P<url>https?://(?:secure|c)\.brightcove.com/(?:(?!\2).)+)\2
+            ''', webpage)
         if url_m:
-            url = unescapeHTML(url_m.group(1))
+            url = unescapeHTML(url_m.group('url'))
             # Some sites don't add it, we can't download with this url, for example:
             # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
-            if 'playerKey' in url or 'videoId' in url:
+            if 'playerKey' in url or 'videoId' in url or 'idVideo' in url:
                 return [url]
 
         matches = re.findall(
@@ -259,7 +262,7 @@ class BrightcoveLegacyIE(InfoExtractor):
         url, smuggled_data = unsmuggle_url(url, {})
 
         # Change the 'videoId' and others field to '@videoPlayer'
-        url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
+        url = re.sub(r'(?<=[?&])(videoI(d|D)|idVideo|bctid)', '%40videoPlayer', url)
         # Change bckey (used by bcove.me urls) to playerKey
         url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
         mobj = re.match(self._VALID_URL, url)
@@ -548,7 +551,7 @@ class BrightcoveNewIE(InfoExtractor):
             container = source.get('container')
             ext = mimetype2ext(source.get('type'))
             src = source.get('src')
-            if ext == 'ism':
+            if ext == 'ism' or container == 'WVM':
                 continue
             elif ext == 'm3u8' or container == 'M2TS':
                 if not src:

youtube_dl/extractor/canalplus.py

@@ -105,7 +105,8 @@ class CanalplusIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
         video_id = self._search_regex(
             [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
-             r'id=["\']canal_video_player(?P<id>\d+)'],
+             r'id=["\']canal_video_player(?P<id>\d+)',
+             r'data-video=["\'](?P<id>\d+)'],
             webpage, 'video id', group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)

youtube_dl/extractor/canvas.py

@@ -89,6 +89,9 @@ class CanvasIE(InfoExtractor):
             elif format_type == 'HDS':
                 formats.extend(self._extract_f4m_formats(
                     format_url, display_id, f4m_id=format_type, fatal=False))
+            elif format_type == 'MPEG_DASH':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, display_id, mpd_id=format_type, fatal=False))
             else:
                 formats.append({
                     'format_id': format_type,

youtube_dl/extractor/cbc.py

@@ -283,11 +283,6 @@ class CBCWatchVideoIE(CBCWatchBaseIE):
         formats = self._extract_m3u8_formats(re.sub(r'/([^/]+)/[^/?]+\.m3u8', r'/\1/\1.m3u8', m3u8_url), video_id, 'mp4', fatal=False)
         if len(formats) < 2:
             formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
-        # Despite metadata in m3u8 all video+audio formats are
-        # actually video-only (no audio)
-        for f in formats:
-            if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
-                f['acodec'] = 'none'
         self._sort_formats(formats)
 
         info = {

youtube_dl/extractor/cbslocal.py

@@ -4,11 +4,14 @@ from __future__ import unicode_literals
 from .anvato import AnvatoIE
 from .sendtonews import SendtoNewsIE
 from ..compat import compat_urlparse
-from ..utils import unified_timestamp
+from ..utils import (
+    parse_iso8601,
+    unified_timestamp,
+)
 
 
 class CBSLocalIE(AnvatoIE):
-    _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/(?:\d+/\d+/\d+|video)/(?P<id>[0-9a-z-]+)'
 
     _TESTS = [{
         # Anvato backend
@@ -49,6 +52,31 @@ class CBSLocalIE(AnvatoIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/',
+        'info_dict': {
+            'id': '3580809',
+            'ext': 'mp4',
+            'title': 'A Very Blue Anniversary',
+            'description': 'CBS2’s Cindy Hsu has more.',
+            'thumbnail': 're:^https?://.*',
+            'timestamp': 1479962220,
+            'upload_date': '20161124',
+            'uploader': 'CBS',
+            'subtitles': {
+                'en': 'mincount:5',
+            },
+            'categories': [
+                'Stations\\Spoken Word\\WCBSTV',
+                'Syndication\\AOL',
+                'Syndication\\MSN',
+                'Syndication\\NDN',
+                'Syndication\\Yahoo',
+                'Content\\News',
+                'Content\\News\\Local News',
+            ],
+            'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'],
+        },
     }]
 
     def _real_extract(self, url):
@@ -64,8 +92,11 @@ class CBSLocalIE(AnvatoIE):
         info_dict = self._extract_anvato_videos(webpage, display_id)
 
         time_str = self._html_search_regex(
-            r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)
-        timestamp = unified_timestamp(time_str)
+            r'class="entry-date">([^<]+)<', webpage, 'released date', default=None)
+        if time_str:
+            timestamp = unified_timestamp(time_str)
+        else:
+            timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage))
 
         info_dict.update({
             'display_id': display_id,

youtube_dl/extractor/ccma.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    clean_html,
+)
+
+
+class CCMAIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
+        'md5': '7296ca43977c8ea4469e719c609b0871',
+        'info_dict': {
+            'id': '5630208',
+            'ext': 'mp4',
+            'title': 'L\'espot de La Marató de TV3',
+            'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
+            'timestamp': 1470918540,
+            'upload_date': '20160811',
+        }
+    }, {
+        'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
+        'md5': 'fa3e38f269329a278271276330261425',
+        'info_dict': {
+            'id': '943685',
+            'ext': 'mp3',
+            'title': 'El Consell de Savis analitza el derbi',
+            'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
+            'upload_date': '20171205',
+            'timestamp': 1512507300,
+        }
+    }]
+
+    def _real_extract(self, url):
+        media_type, media_id = re.match(self._VALID_URL, url).groups()
+        media_data = {}
+        formats = []
+        profiles = ['pc'] if media_type == 'audio' else ['mobil', 'pc']
+        for i, profile in enumerate(profiles):
+            md = self._download_json('http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
+                'media': media_type,
+                'idint': media_id,
+                'profile': profile,
+            }, fatal=False)
+            if md:
+                media_data = md
+                media_url = media_data.get('media', {}).get('url')
+                if media_url:
+                    formats.append({
+                        'format_id': profile,
+                        'url': media_url,
+                        'quality': i,
+                    })
+        self._sort_formats(formats)
+
+        informacio = media_data['informacio']
+        title = informacio['titol']
+        durada = informacio.get('durada', {})
+        duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
+        timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
+
+        subtitles = {}
+        subtitols = media_data.get('subtitols', {})
+        if subtitols:
+            sub_url = subtitols.get('url')
+            if sub_url:
+                subtitles.setdefault(
+                    subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
+                        'url': sub_url,
+                    })
+
+        thumbnails = []
+        imatges = media_data.get('imatges', {})
+        if imatges:
+            thumbnail_url = imatges.get('url')
+            if thumbnail_url:
+                thumbnails = [{
+                    'url': thumbnail_url,
+                    'width': int_or_none(imatges.get('amplada')),
+                    'height': int_or_none(imatges.get('alcada')),
+                }]
+
+        return {
+            'id': media_id,
+            'title': title,
+            'description': clean_html(informacio.get('descripcio')),
+            'duration': duration,
+            'timestamp': timestamp,
+            'thumnails': thumbnails,
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/cctv.py

@@ -4,27 +4,84 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    try_get,
+    unified_timestamp,
+)
 
 
 class CCTVIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:.+?\.)?
-        (?:
-            cctv\.(?:com|cn)|
-            cntv\.cn
-        )/
-        (?:
-            video/[^/]+/(?P<id>[0-9a-f]{32})|
-            \d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
-        )'''
+    IE_DESC = '央视网'
+    _VALID_URL = r'https?://(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)'
     _TESTS = [{
-        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
-        'md5': '819c7b49fc3927d529fb4cd555621823',
+        'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
+        'md5': 'd61ec00a493e09da810bf406a078f691',
         'info_dict': {
-            'id': '454368eb19ad44a1925bf1eb96140a61',
+            'id': '5ecdbeab623f4973b40ff25f18b174e8',
             'ext': 'mp4',
-            'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
-        }
+            'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕（快讯）',
+            'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95',
+            'duration': 98,
+            'uploader': 'songjunjie',
+            'timestamp': 1455279956,
+            'upload_date': '20160212',
+        },
+    }, {
+        'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
+        'info_dict': {
+            'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
+            'ext': 'mp4',
+            'title': '[赛车]“车王”舒马赫恢复情况成谜（快讯）',
+            'description': '2月4日，蒙特泽莫罗透露了关于“车王”舒马赫恢复情况，但情况是否属实遭到了质疑。',
+            'duration': 37,
+            'uploader': 'shujun',
+            'timestamp': 1454677291,
+            'upload_date': '20160205',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml',
+        'info_dict': {
+            'id': '4bb9bb4db7a6471ba85fdeda5af0381e',
+            'ext': 'mp4',
+            'title': 'NHnews008 ANNUAL POLITICAL SEASON',
+            'description': 'Four Comprehensives',
+            'duration': 60,
+            'uploader': 'zhangyunlei',
+            'timestamp': 1425385521,
+            'upload_date': '20150303',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://cctv.cntv.cn/lm/tvseries_russian/yilugesanghua/index.shtml',
+        'info_dict': {
+            'id': 'b15f009ff45c43968b9af583fc2e04b2',
+            'ext': 'mp4',
+            'title': 'Путь，усыпанный космеями Серия 1',
+            'description': 'Путь, усыпанный космеями',
+            'duration': 2645,
+            'uploader': 'renxue',
+            'timestamp': 1477479241,
+            'upload_date': '20161026',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44',
+        'only_matching': True,
+    }, {
+        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
+        'only_matching': True,
     }, {
         'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
         'only_matching': True,
@@ -34,20 +91,63 @@ class CCTVIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id, display_id = re.match(self._VALID_URL, url).groups()
-        if not video_id:
-            webpage = self._download_webpage(url, display_id)
-            video_id = self._search_regex(
-                r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
-                webpage, 'video_id')
-        api_data = self._download_json(
-            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
-        m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
+             r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)',
+             r'"changePlayer\s*\(\s*["\']([\da-fA-F]+)',
+             r'"load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)'],
+            webpage, 'video id')
+
+        data = self._download_json(
+            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do', video_id,
+            query={
+                'pid': video_id,
+                'url': url,
+                'idl': 32,
+                'idlr': 32,
+                'modifyed': 'false',
+            })
+
+        title = data['title']
+
+        formats = []
+
+        video = data.get('video')
+        if isinstance(video, dict):
+            for quality, chapters_key in enumerate(('lowChapters', 'chapters')):
+                video_url = try_get(
+                    video, lambda x: x[chapters_key][0]['url'], compat_str)
+                if video_url:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'http',
+                        'quality': quality,
+                        'preference': -1,
+                    })
+
+        hls_url = try_get(data, lambda x: x['hls_url'], compat_str)
+        if hls_url:
+            hls_url = re.sub(r'maxbr=\d+&?', '', hls_url)
+            formats.extend(self._extract_m3u8_formats(
+                hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        self._sort_formats(formats)
+
+        uploader = data.get('editer_name')
+        description = self._html_search_meta('description', webpage)
+        timestamp = unified_timestamp(data.get('f_pgmtime'))
+        duration = float_or_none(try_get(video, lambda x: x['totalLength']))
 
         return {
             'id': video_id,
-            'title': api_data['title'],
-            'formats': self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
-            'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
         }

youtube_dl/extractor/comedycentral.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
+        (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
@@ -27,6 +27,40 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     }]
 
 
+class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
+        (?:full-episodes|shows(?=/[^/]+/full-episodes))
+        /(?P<id>[^?]+)'''
+    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
+
+    _TESTS = [{
+        'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
+        'info_dict': {
+            'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
+            'title': 'November 28, 2016 - Ryan Speedo Green',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
+        feed = self._parse_json(feed_json, playlist_id)
+        zones = feed['manifest']['zones']
+
+        video_zone = zones['t2_lc_promo1']
+        feed = self._download_json(video_zone['feed'], playlist_id)
+        mgid = feed['result']['data']['id']
+
+        videos_info = self._get_videos_info(mgid)
+        return videos_info
+
+
 class ToshIE(MTVServicesInfoExtractor):
     IE_DESC = 'Tosh.0'
     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'

youtube_dl/extractor/common.py

@@ -59,6 +59,7 @@ from ..utils import (
     parse_m3u8_attributes,
     extract_attributes,
     parse_codecs,
+    urljoin,
 )
 
 
@@ -188,9 +189,10 @@ class InfoExtractor(object):
     uploader_url:   Full URL to a personal webpage of the video uploader.
     location:       Physical location where the video was filmed.
     subtitles:      The available subtitles as a dictionary in the format
-                    {language: subformats}. "subformats" is a list sorted from
-                    lower to higher preference, each element is a dictionary
-                    with the "ext" entry and one of:
+                    {tag: subformats}. "tag" is usually a language code, and
+                    "subformats" is a list sorted from 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
                     "ext" will be calculated from URL if missing
@@ -1224,6 +1226,7 @@ class InfoExtractor(object):
                 'protocol': entry_protocol,
                 'preference': preference,
             }]
+        audio_in_video_stream = {}
         last_info = {}
         last_media = {}
         for line in m3u8_doc.splitlines():
@@ -1233,25 +1236,32 @@ class InfoExtractor(object):
                 media = parse_m3u8_attributes(line)
                 media_type = media.get('TYPE')
                 if media_type in ('VIDEO', 'AUDIO'):
+                    group_id = media.get('GROUP-ID')
                     media_url = media.get('URI')
                     if media_url:
                         format_id = []
-                        for v in (media.get('GROUP-ID'), media.get('NAME')):
+                        for v in (group_id, media.get('NAME')):
                             if v:
                                 format_id.append(v)
-                        formats.append({
+                        f = {
                             'format_id': '-'.join(format_id),
                             'url': format_url(media_url),
                             'language': media.get('LANGUAGE'),
-                            'vcodec': 'none' if media_type == 'AUDIO' else None,
                             'ext': ext,
                             'protocol': entry_protocol,
                             'preference': preference,
-                        })
+                        }
+                        if media_type == 'AUDIO':
+                            f['vcodec'] = 'none'
+                            if group_id and not audio_in_video_stream.get(group_id):
+                                audio_in_video_stream[group_id] = False
+                        formats.append(f)
                     else:
                         # When there is no URI in EXT-X-MEDIA let this tag's
                         # data be used by regular URI lines below
                         last_media = media
+                        if media_type == 'AUDIO' and group_id:
+                            audio_in_video_stream[group_id] = True
             elif line.startswith('#') or not line.strip():
                 continue
             else:
@@ -1295,6 +1305,9 @@ class InfoExtractor(object):
                         'abr': abr,
                     })
                 f.update(parse_codecs(last_info.get('CODECS')))
+                if audio_in_video_stream.get(last_info.get('AUDIO')) is False:
+                    # TODO: update acodec for for audio only formats with the same GROUP-ID
+                    f['acodec'] = 'none'
                 formats.append(f)
                 last_info = {}
                 last_media = {}
@@ -1624,11 +1637,6 @@ class InfoExtractor(object):
                         extract_Initialization(segment_template)
             return ms_info
 
-        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)
-
         mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
         formats = []
         for period in mpd_doc.findall(_add_ns('Period')):
@@ -1678,12 +1686,11 @@ class InfoExtractor(object):
                             'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),
                             'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
                             'fps': int_or_none(representation_attrib.get('frameRate')),
-                            'vcodec': 'none' if content_type == 'audio' else representation_attrib.get('codecs'),
-                            'acodec': 'none' if content_type == 'video' else representation_attrib.get('codecs'),
                             'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
                             'format_note': 'DASH %s' % content_type,
                             'filesize': filesize,
                         }
+                        f.update(parse_codecs(representation_attrib.get('codecs')))
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
                         if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
 
@@ -1767,7 +1774,7 @@ class InfoExtractor(object):
                                 f['fragments'].append({'url': initialization_url})
                             f['fragments'].extend(representation_ms_info['fragments'])
                             for fragment in f['fragments']:
-                                fragment['url'] = combine_url(base_url, fragment['url'])
+                                fragment['url'] = urljoin(base_url, fragment['url'])
                         try:
                             existing_format = next(
                                 fo for fo in formats
@@ -1881,7 +1888,7 @@ class InfoExtractor(object):
                 })
         return formats
 
-    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'):
+    def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None):
         def absolute_url(video_url):
             return compat_urlparse.urljoin(base_url, video_url)
 
@@ -1898,11 +1905,16 @@ class InfoExtractor(object):
 
         def _media_formats(src, cur_media_type):
             full_url = absolute_url(src)
-            if determine_ext(full_url) == 'm3u8':
+            ext = determine_ext(full_url)
+            if ext == 'm3u8':
                 is_plain_url = False
                 formats = self._extract_m3u8_formats(
                     full_url, video_id, ext='mp4',
                     entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id)
+            elif ext == 'mpd':
+                is_plain_url = False
+                formats = self._extract_mpd_formats(
+                    full_url, video_id, mpd_id=mpd_id)
             else:
                 is_plain_url = True
                 formats = [{

youtube_dl/extractor/crunchyroll.py

@@ -236,7 +236,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
         output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
         output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
-        output += """ScaledBorderAndShadow: yes
+        output += """ScaledBorderAndShadow: no
 
 [V4+ Styles]
 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding

youtube_dl/extractor/ctvnews.py

@@ -8,7 +8,7 @@ from ..utils import orderedSet
 
 
 class CTVNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
+    _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
     _TESTS = [{
         'url': 'http://www.ctvnews.ca/video?clipId=901995',
         'md5': '10deb320dc0ccb8d01d34d12fc2ea672',
@@ -40,6 +40,9 @@ class CTVNewsIE(InfoExtractor):
     }, {
         'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231',
         'only_matching': True,
+    }, {
+        'url': 'http://vancouverisland.ctvnews.ca/video?clipId=761241',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/dplay.py

@@ -8,6 +8,7 @@ import time
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
+    USER_AGENTS,
     int_or_none,
     update_url_query,
 )
@@ -102,10 +103,16 @@ class DPlayIE(InfoExtractor):
                     manifest_url, video_id, ext='mp4',
                     entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)
                 # Sometimes final URLs inside m3u8 are unsigned, let's fix this
-                # ourselves
+                # ourselves. Also fragments' URLs are only served signed for
+                # Safari user agent.
                 query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query)
                 for m3u8_format in m3u8_formats:
-                    m3u8_format['url'] = update_url_query(m3u8_format['url'], query)
+                    m3u8_format.update({
+                        'url': update_url_query(m3u8_format['url'], query),
+                        'http_headers': {
+                            'User-Agent': USER_AGENTS['Safari'],
+                        },
+                    })
                 formats.extend(m3u8_formats)
             elif protocol == 'hds':
                 formats.extend(self._extract_f4m_formats(

youtube_dl/extractor/extractors.py

@@ -150,6 +150,7 @@ from .cbsnews import (
 )
 from .cbssports import CBSSportsIE
 from .ccc import CCCIE
+from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
 from .ceskatelevize import CeskaTelevizeIE
@@ -180,6 +181,7 @@ from .cnn import (
 from .coub import CoubIE
 from .collegerama import CollegeRamaIE
 from .comedycentral import (
+    ComedyCentralFullEpisodesIE,
     ComedyCentralIE,
     ComedyCentralShortnameIE,
     ComedyCentralTVIE,
@@ -318,7 +320,6 @@ from .francetv import (
 )
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
-from .freevideo import FreeVideoIE
 from .funimation import FunimationIE
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
@@ -445,7 +446,10 @@ from .kuwo import (
     KuwoMvIE,
 )
 from .la7 import LA7IE
-from .laola1tv import Laola1TvIE
+from .laola1tv import (
+    Laola1TvEmbedIE,
+    Laola1TvIE,
+)
 from .lci import LCIIE
 from .lcp import (
     LcpPlayIE,
@@ -497,6 +501,8 @@ from .mangomolo import (
 )
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
+from .meipai import MeipaiIE
+from .melonvod import MelonVODIE
 from .meta import METAIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
@@ -648,6 +654,8 @@ from .nrk import (
     NRKPlaylistIE,
     NRKSkoleIE,
     NRKTVIE,
+    NRKTVDirekteIE,
+    NRKTVEpisodesIE,
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
@@ -660,6 +668,7 @@ from .nzz import NZZIE
 from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .ondemandkorea import OnDemandKoreaIE
 from .onet import (
     OnetIE,
     OnetChannelIE,
@@ -690,6 +699,7 @@ from .periscope import (
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .piksel import PikselIE
 from .pinkbike import PinkbikeIE
 from .pladform import PladformIE
 from .playfm import PlayFMIE
@@ -804,7 +814,6 @@ from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
 from .screenjunkies import ScreenJunkiesIE
-from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
 from .seeker import SeekerIE
 from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
@@ -816,6 +825,7 @@ from .shared import (
     VivoIE,
 )
 from .sharesix import ShareSixIE
+from .showroomlive import ShowRoomLiveIE
 from .sina import SinaIE
 from .sixplay import SixPlayIE
 from .skynewsarabia import (
@@ -897,6 +907,7 @@ from .teachertube import (
 )
 from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
+from .teamfourstar import TeamFourStarIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .tele13 import Tele13IE
@@ -965,6 +976,10 @@ from .tv2 import (
 )
 from .tv3 import TV3IE
 from .tv4 import TV4IE
+from .tvanouvelles import (
+    TVANouvellesIE,
+    TVANouvellesArticleIE,
+)
 from .tvc import (
     TVCIE,
     TVCArticleIE,
@@ -993,7 +1008,10 @@ from .twitch import (
     TwitchChapterIE,
     TwitchVodIE,
     TwitchProfileIE,
+    TwitchAllVideosIE,
+    TwitchUploadsIE,
     TwitchPastBroadcastsIE,
+    TwitchHighlightsIE,
     TwitchStreamIE,
     TwitchClipsIE,
 )
@@ -1007,6 +1025,7 @@ from .udemy import (
     UdemyCourseIE
 )
 from .udn import UDNEmbedIE
+from .uktvplay import UKTVPlayIE
 from .digiteka import DigitekaIE
 from .unistra import UnistraIE
 from .uol import UOLIE
@@ -1046,6 +1065,7 @@ from .vice import (
 from .viceland import VicelandIE
 from .vidbit import VidbitIE
 from .viddler import ViddlerIE
+from .videa import VideaIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
@@ -1090,6 +1110,11 @@ from .viki import (
     VikiIE,
     VikiChannelIE,
 )
+from .viu import (
+    ViuIE,
+    ViuPlaylistIE,
+    ViuOTTIE,
+)
 from .vk import (
     VKIE,
     VKUserVideosIE,
@@ -1104,6 +1129,7 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vvvvid import VVVVIDIE
 from .vyborymos import VyboryMosIE
 from .vzaar import VzaarIE
 from .walla import WallaIE
@@ -1117,6 +1143,10 @@ from .wdr import (
     WDRIE,
     WDRMobileIE,
 )
+from .webcaster import (
+    WebcasterIE,
+    WebcasterFeedIE,
+)
 from .webofstories import (
     WebOfStoriesIE,
     WebOfStoriesPlaylistIE,

youtube_dl/extractor/facebook.py

@@ -27,7 +27,7 @@ class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                 (?:
                     https?://
-                        (?:[\w-]+\.)?facebook\.com/
+                        (?:[\w-]+\.)?(?:facebook\.com|facebookcorewwwi\.onion)/
                         (?:[^#]*?\#!/)?
                         (?:
                             (?:
@@ -150,6 +150,9 @@ class FacebookIE(InfoExtractor):
     }, {
         'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -244,8 +247,10 @@ class FacebookIE(InfoExtractor):
             r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
         for item in server_js_data.get('instances', []):
             if item[1][0] == 'VideoConfig':
-                video_data = item[2][0]['videoData']
-                break
+                video_item = item[2][0]
+                if video_item.get('video_id') == video_id:
+                    video_data = video_item['videoData']
+                    break
 
         if not video_data:
             if not fatal_if_no_video:
@@ -255,6 +260,8 @@ class FacebookIE(InfoExtractor):
                 raise ExtractorError(
                     'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)
+            elif '>You must log in to continue' in webpage:
+                self.raise_login_required()
             else:
                 raise ExtractorError('Cannot parse data')
 

youtube_dl/extractor/firsttv.py

@@ -2,7 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     int_or_none,
     qualities,
@@ -22,8 +25,7 @@ class FirstTVIE(InfoExtractor):
         'info_dict': {
             'id': '40049',
             'ext': 'mp4',
-            'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
-            'description': 'md5:36a39c1d19618fec57d12efe212a8370',
+            'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20150212',
             'duration': 2694,
@@ -34,8 +36,7 @@ class FirstTVIE(InfoExtractor):
         'info_dict': {
             'id': '364746',
             'ext': 'mp4',
-            'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
-            'description': 'md5:a242eea0031fd180a4497d52640a9572',
+            'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'upload_date': '20160407',
             'duration': 179,
@@ -44,6 +45,17 @@ class FirstTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.1tv.ru/news/issue/2016-12-01/14:00',
+        'info_dict': {
+            'id': '14:00',
+            'title': 'Выпуск новостей в 14:00   1 декабря 2016 года. Новости. Первый канал',
+            'description': 'md5:2e921b948f8c1ff93901da78ebdb1dfd',
+        },
+        'playlist_count': 13,
+    }, {
+        'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -51,43 +63,66 @@ class FirstTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
         playlist_url = compat_urlparse.urljoin(url, self._search_regex(
-            r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
+            r'data-playlist-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'playlist url', group='url'))
 
-        item = self._download_json(playlist_url, display_id)[0]
-        video_id = item['id']
-        quality = qualities(('ld', 'sd', 'hd', ))
-        formats = []
-        for f in item.get('mbr', []):
-            src = f.get('src')
-            if not src:
-                continue
-            fname = f.get('name')
-            formats.append({
-                'url': src,
-                'format_id': fname,
-                'quality': quality(fname),
+        parsed_url = compat_urlparse.urlparse(playlist_url)
+        qs = compat_urlparse.parse_qs(parsed_url.query)
+        item_ids = qs.get('videos_ids[]') or qs.get('news_ids[]')
+
+        items = self._download_json(playlist_url, display_id)
+
+        if item_ids:
+            items = [
+                item for item in items
+                if item.get('uid') and compat_str(item['uid']) in item_ids]
+        else:
+            items = [items[0]]
+
+        entries = []
+        QUALITIES = ('ld', 'sd', 'hd', )
+
+        for item in items:
+            title = item['title']
+            quality = qualities(QUALITIES)
+            formats = []
+            for f in item.get('mbr', []):
+                src = f.get('src')
+                if not src or not isinstance(src, compat_str):
+                    continue
+                tbr = int_or_none(self._search_regex(
+                    r'_(\d{3,})\.mp4', src, 'tbr', default=None))
+                formats.append({
+                    'url': src,
+                    'format_id': f.get('name'),
+                    'tbr': tbr,
+                    'quality': quality(f.get('name')),
+                })
+            self._sort_formats(formats)
+
+            thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)
+            duration = int_or_none(item.get('duration') or self._html_search_meta(
+                'video:duration', webpage, 'video duration', fatal=False))
+            upload_date = unified_strdate(self._html_search_meta(
+                'ya:ovs:upload_date', webpage, 'upload date', default=None))
+
+            entries.append({
+                'id': compat_str(item.get('id') or item['uid']),
+                'thumbnail': thumbnail,
+                'title': title,
+                'upload_date': upload_date,
+                'duration': int_or_none(duration),
+                'formats': formats
             })
-        self._sort_formats(formats)
 
         title = self._html_search_regex(
             (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
              r"'title'\s*:\s*'([^']+)'"),
-            webpage, 'title', default=None) or item['title']
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage, default=None)
         description = self._html_search_regex(
             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
             webpage, 'description', default=None) or self._html_search_meta(
-            'description', webpage, 'description')
-        duration = int_or_none(self._html_search_meta(
-            'video:duration', webpage, 'video duration', fatal=False))
-        upload_date = unified_strdate(self._html_search_meta(
-            'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
+            'description', webpage, 'description', default=None)
 
-        return {
-            'id': video_id,
-            'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
-            'title': title,
-            'description': description,
-            'upload_date': upload_date,
-            'duration': int_or_none(duration),
-            'formats': formats
-        }
+        return self.playlist_result(entries, display_id, title, description)

youtube_dl/extractor/freevideo.py

@@ -1,38 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import ExtractorError
-
-
-class FreeVideoIE(InfoExtractor):
-    _VALID_URL = r'^https?://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
-
-    _TEST = {
-        'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
-        'info_dict': {
-            'id': 'vysukany-zadecek-22033',
-            'ext': 'mp4',
-            'title': 'vysukany-zadecek-22033',
-            'age_limit': 18,
-        },
-        'skip': 'Blocked outside .cz',
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage, handle = self._download_webpage_handle(url, video_id)
-        if '//www.czechav.com/' in handle.geturl():
-            raise ExtractorError(
-                'Access to freevideo is blocked from your location',
-                expected=True)
-
-        video_url = self._search_regex(
-            r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"',
-            webpage, 'video URL')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': video_id,
-            'age_limit': 18,
-        }

youtube_dl/extractor/funnyordie.py

@@ -28,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor):
             'description': 'Please use this to sell something.  www.jonlajoie.com',
             'thumbnail': 're:^http:.*\.jpg$',
         },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
         'only_matching': True,
@@ -51,19 +54,45 @@ class FunnyOrDieIE(InfoExtractor):
 
         formats = []
 
-        formats.extend(self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+        m3u8_formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', 'm3u8_native',
+            m3u8_id='hls', fatal=False)
+        source_formats = list(filter(
+            lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            m3u8_formats))
 
-        bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
+        bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
         bitrates.sort()
 
-        for bitrate in bitrates:
-            for link in links:
-                formats.append({
-                    'url': self._proto_relative_url('%s%d.%s' % (link[0], bitrate, link[1])),
-                    'format_id': '%s-%d' % (link[1], bitrate),
-                    'vbr': bitrate,
-                })
+        if source_formats:
+            self._sort_formats(source_formats)
+
+        for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)):
+            for path, ext in links:
+                ff = f.copy()
+                if ff:
+                    if ext != 'mp4':
+                        ff = dict(
+                            [(k, v) for k, v in ff.items()
+                             if k in ('height', 'width', 'format_id')])
+                    ff.update({
+                        'format_id': ff['format_id'].replace('hls', ext),
+                        'ext': ext,
+                        'protocol': 'http',
+                    })
+                else:
+                    ff.update({
+                        'format_id': '%s-%d' % (ext, bitrate),
+                        'vbr': bitrate,
+                    })
+                ff['url'] = self._proto_relative_url(
+                    '%s%d.%s' % (path, bitrate, ext))
+                formats.append(ff)
+        self._check_formats(formats, video_id)
+
+        formats.extend(m3u8_formats)
+        self._sort_formats(
+            formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 
         subtitles = {}
         for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):

youtube_dl/extractor/fusion.py

@@ -29,7 +29,7 @@ class FusionIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         ooyala_code = self._search_regex(
-            r'data-video-id=(["\'])(?P<code>.+?)\1',
+            r'data-ooyala-id=(["\'])(?P<code>(?:(?!\1).)+)\1',
             webpage, 'ooyala code', group='code')
 
         return OoyalaIE._build_url_result(ooyala_code)

youtube_dl/extractor/generic.py

@@ -56,10 +56,10 @@ from .dailymotion import (
 )
 from .onionstudios import OnionStudiosIE
 from .viewlift import ViewLiftEmbedIE
-from .screenwavemedia import ScreenwaveMediaIE
 from .mtv import MTVServicesEmbeddedIE
 from .pladform import PladformIE
 from .videomore import VideomoreIE
+from .webcaster import WebcasterFeedIE
 from .googledrive import GoogleDriveIE
 from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
@@ -75,6 +75,8 @@ from .facebook import FacebookIE
 from .soundcloud import SoundcloudIE
 from .vbox7 import Vbox7IE
 from .dbtv import DBTVIE
+from .piksel import PikselIE
+from .videa import VideaIE
 
 
 class GenericIE(InfoExtractor):
@@ -343,10 +345,10 @@ class GenericIE(InfoExtractor):
             },
             'skip': 'There is a limit of 200 free downloads / month for the test song',
         },
-        # embedded brightcove video
-        # it also tests brightcove videos that need to set the 'Referer' in the
-        # http requests
         {
+            # embedded brightcove video
+            # it also tests brightcove videos that need to set the 'Referer'
+            # in the http requests
             'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
             'info_dict': {
@@ -360,6 +362,24 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # embedded with itemprop embedURL and video id spelled as `idVideo`
+            'add_id': ['BrightcoveLegacy'],
+            'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
+            'info_dict': {
+                'id': '5255628253001',
+                'ext': 'mp4',
+                'title': 'md5:37c519b1128915607601e75a87995fc0',
+                'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
+                'uploader': 'BFM BUSINESS',
+                'uploader_id': '876450612001',
+                'timestamp': 1482255315,
+                'upload_date': '20161220',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # https://github.com/rg3/youtube-dl/issues/2253
             'url': 'http://bcove.me/i6nfkrc3',
@@ -972,6 +992,20 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
+        {
+            # Kaltura embedded, some fileExt broken (#11480)
+            'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
+            'info_dict': {
+                'id': '1_sgtvehim',
+                'ext': 'mp4',
+                'title': 'Our "Standard Models" of particle physics and cosmology',
+                'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
+                'timestamp': 1321158993,
+                'upload_date': '20111113',
+                'uploader_id': 'kps1',
+            },
+            'add_ie': ['Kaltura'],
+        },
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -1189,16 +1223,6 @@ class GenericIE(InfoExtractor):
                 'duration': 248.667,
             },
         },
-        # ScreenwaveMedia embed
-        {
-            'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
-            'md5': '24ace5baba0d35d55c6810b51f34e9e0',
-            'info_dict': {
-                'id': 'cinemasnob-55d26273809dd',
-                'ext': 'mp4',
-                'title': 'cinemasnob',
-            },
-        },
         # BrightcoveInPageEmbed embed
         {
             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
@@ -1399,6 +1423,15 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 3,
         },
+        {
+            # Videa embeds
+            'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
+            'info_dict': {
+                'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
+                'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
+            },
+            'playlist_mincount': 2,
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2140,6 +2173,11 @@ class GenericIE(InfoExtractor):
         if videomore_url:
             return self.url_result(videomore_url)
 
+        # Look for Webcaster embeds
+        webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
+        if webcaster_url:
+            return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
+
         # Look for Playwire embeds
         mobj = re.search(
             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
@@ -2206,11 +2244,6 @@ class GenericIE(InfoExtractor):
         if jwplatform_url:
             return self.url_result(jwplatform_url, 'JWPlatform')
 
-        # Look for ScreenwaveMedia embeds
-        mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
-        if mobj is not None:
-            return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
-
         # Look for Digiteka embeds
         digiteka_url = DigitekaIE._extract_url(webpage)
         if digiteka_url:
@@ -2221,6 +2254,11 @@ class GenericIE(InfoExtractor):
         if arkena_url:
             return self.url_result(arkena_url, ArkenaIE.ie_key())
 
+        # Look for Piksel embeds
+        piksel_url = PikselIE._extract_url(webpage)
+        if piksel_url:
+            return self.url_result(piksel_url, PikselIE.ie_key())
+
         # Look for Limelight embeds
         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
         if mobj:
@@ -2232,6 +2270,16 @@ class GenericIE(InfoExtractor):
             return self.url_result('limelight:%s:%s' % (
                 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
 
+        mobj = re.search(
+            r'''(?sx)
+                <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
+                    <param[^>]+
+                        name=(["\'])flashVars\2[^>]+
+                        value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
+            ''', webpage)
+        if mobj:
+            return self.url_result('limelight:media:%s' % mobj.group('id'))
+
         # Look for AdobeTVVideo embeds
         mobj = re.search(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
@@ -2320,6 +2368,11 @@ class GenericIE(InfoExtractor):
         if dbtv_urls:
             return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
 
+        # Look for Videa embeds
+        videa_urls = VideaIE._extract_urls(webpage)
+        if videa_urls:
+            return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')

youtube_dl/extractor/hellporno.py

@@ -6,12 +6,13 @@ from .common import InfoExtractor
 from ..utils import (
     js_to_json,
     remove_end,
+    determine_ext,
 )
 
 
 class HellPornoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
+    _TESTS = [{
         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
         'md5': '1fee339c610d2049699ef2aa699439f1',
         'info_dict': {
@@ -22,7 +23,10 @@ class HellPornoIE(InfoExtractor):
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://hellporno.net/v/186271/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -38,7 +42,7 @@ class HellPornoIE(InfoExtractor):
 
         video_id = flashvars.get('video_id')
         thumbnail = flashvars.get('preview_url')
-        ext = flashvars.get('postfix', '.mp4')[1:]
+        ext = determine_ext(flashvars.get('postfix'), 'mp4')
 
         formats = []
         for video_url_key in ['video_url', 'video_alt_url']:

youtube_dl/extractor/jwplatform.py

@@ -11,6 +11,7 @@ from ..utils import (
     int_or_none,
     js_to_json,
     mimetype2ext,
+    urljoin,
 )
 
 
@@ -110,10 +111,14 @@ class JWPlatformBaseIE(InfoExtractor):
             tracks = video_data.get('tracks')
             if tracks and isinstance(tracks, list):
                 for track in tracks:
-                    if track.get('file') and track.get('kind') == 'captions':
-                        subtitles.setdefault(track.get('label') or 'en', []).append({
-                            'url': self._proto_relative_url(track['file'])
-                        })
+                    if track.get('kind') != 'captions':
+                        continue
+                    track_url = urljoin(base_url, track.get('file'))
+                    if not track_url:
+                        continue
+                    subtitles.setdefault(track.get('label') or 'en', []).append({
+                        'url': self._proto_relative_url(track_url)
+                    })
 
             entries.append({
                 'id': this_video_id,
@@ -121,7 +126,7 @@ class JWPlatformBaseIE(InfoExtractor):
                 'description': video_data.get('description'),
                 'thumbnail': self._proto_relative_url(video_data.get('image')),
                 'timestamp': int_or_none(video_data.get('pubdate')),
-                'duration': float_or_none(jwplayer_data.get('duration')),
+                'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
                 'subtitles': subtitles,
                 'formats': formats,
             })

youtube_dl/extractor/kaltura.py

@@ -107,7 +107,7 @@ class KalturaIE(InfoExtractor):
                         (?P<q1>['\"])wid(?P=q1)\s*:\s*
                         (?P<q2>['\"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
                         (?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*
-                        (?P<q4>['\"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4),
+                        (?P<q4>['\"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
                 """, webpage) or
             re.search(
                 r'''(?xs)
@@ -266,6 +266,9 @@ class KalturaIE(InfoExtractor):
             # skip for now.
             if f.get('fileExt') == 'chun':
                 continue
+            if not f.get('fileExt') and f.get('containerFormat') == 'qt':
+                # QT indicates QuickTime; some videos have broken fileExt
+                f['fileExt'] = 'mov'
             video_url = sign_url(
                 '%s/flavorId/%s' % (data_url, f['id']))
             # audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g

youtube_dl/extractor/laola1tv.py

@@ -1,25 +1,115 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlencode,
-    compat_urlparse,
-)
 from ..utils import (
     ExtractorError,
-    sanitized_Request,
     unified_strdate,
     urlencode_postdata,
     xpath_element,
     xpath_text,
+    urljoin,
+    update_url_query,
 )
 
 
+class Laola1TvEmbedIE(InfoExtractor):
+    IE_NAME = 'laola1tv:embed'
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
+    _TEST = {
+        # flashvars.premium = "false";
+        'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024',
+        'info_dict': {
+            'id': '708065',
+            'ext': 'mp4',
+            'title': 'MA Long CHN - FAN Zhendong CHN',
+            'uploader': 'ITTF - International Table Tennis Federation',
+            'upload_date': '20161211',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        flash_vars = self._search_regex(
+            r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars')
+
+        def get_flashvar(x, *args, **kwargs):
+            flash_var = self._search_regex(
+                r'%s\s*:\s*"([^"]+)"' % x,
+                flash_vars, x, default=None)
+            if not flash_var:
+                flash_var = self._search_regex([
+                    r'flashvars\.%s\s*=\s*"([^"]+)"' % x,
+                    r'%s\s*=\s*"([^"]+)"' % x],
+                    webpage, x, *args, **kwargs)
+            return flash_var
+
+        hd_doc = self._download_xml(
+            'http://www.laola1.tv/server/hd_video.php', video_id, query={
+                'play': get_flashvar('streamid'),
+                'partner': get_flashvar('partnerid'),
+                'portal': get_flashvar('portalid'),
+                'lang': get_flashvar('sprache'),
+                'v5ident': '',
+            })
+
+        _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
+        title = _v('title', fatal=True)
+
+        token_url = None
+        premium = get_flashvar('premium', default=None)
+        if premium:
+            token_url = update_url_query(
+                _v('url', fatal=True), {
+                    'timestamp': get_flashvar('timestamp'),
+                    'auth': get_flashvar('auth'),
+                })
+        else:
+            data_abo = urlencode_postdata(
+                dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
+            token_url = self._download_json(
+                'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access',
+                video_id, query={
+                    'videoId': _v('id'),
+                    'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
+                    'label': _v('label'),
+                    'area': _v('area'),
+                }, data=data_abo)['data']['stream-access'][0]
+
+        token_doc = self._download_xml(
+            token_url, video_id, 'Downloading token',
+            headers=self.geo_verification_headers())
+
+        token_attrib = xpath_element(token_doc, './/token').attrib
+
+        if token_attrib['status'] != '0':
+            raise ExtractorError(
+                'Token error: %s' % token_attrib['comment'], expected=True)
+
+        formats = self._extract_akamai_formats(
+            '%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
+            video_id)
+        self._sort_formats(formats)
+
+        categories_str = _v('meta_sports')
+        categories = categories_str.split(',') if categories_str else []
+        is_live = _v('islive') == 'true'
+
+        return {
+            'id': video_id,
+            'title': self._live_title(title) if is_live else title,
+            'upload_date': unified_strdate(_v('time_date')),
+            'uploader': _v('meta_organisation'),
+            'categories': categories,
+            'is_live': is_live,
+            'formats': formats,
+        }
+
+
 class Laola1TvIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/(?P<kind>[^/]+)/(?P<slug>[^/?#&]+)'
+    IE_NAME = 'laola1tv'
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
@@ -67,85 +157,20 @@ class Laola1TvIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('slug')
-        kind = mobj.group('kind')
-        lang = mobj.group('lang')
-        portal = mobj.group('portal')
+        display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
         if 'Dieser Livestream ist bereits beendet.' in webpage:
             raise ExtractorError('This live stream has already finished.', expected=True)
 
-        iframe_url = self._search_regex(
+        iframe_url = urljoin(url, self._search_regex(
             r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
-            webpage, 'iframe url')
-
-        video_id = self._search_regex(
-            r'videoid=(\d+)', iframe_url, 'video id')
-
-        iframe = self._download_webpage(compat_urlparse.urljoin(
-            url, iframe_url), display_id, 'Downloading iframe')
-
-        partner_id = self._search_regex(
-            r'partnerid\s*:\s*(["\'])(?P<partner_id>.+?)\1',
-            iframe, 'partner id', group='partner_id')
-
-        hd_doc = self._download_xml(
-            'http://www.laola1.tv/server/hd_video.php?%s'
-            % compat_urllib_parse_urlencode({
-                'play': video_id,
-                'partner': partner_id,
-                'portal': portal,
-                'lang': lang,
-                'v5ident': '',
-            }), display_id)
-
-        _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
-        title = _v('title', fatal=True)
-
-        VS_TARGETS = {
-            'video': '2',
-            'livestream': '17',
-        }
-
-        req = sanitized_Request(
-            'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
-            compat_urllib_parse_urlencode({
-                'videoId': video_id,
-                'target': VS_TARGETS.get(kind, '2'),
-                'label': _v('label'),
-                'area': _v('area'),
-            }),
-            urlencode_postdata(
-                dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
-
-        token_url = self._download_json(req, display_id)['data']['stream-access'][0]
-        token_doc = self._download_xml(token_url, display_id, 'Downloading token')
-
-        token_attrib = xpath_element(token_doc, './/token').attrib
-        token_auth = token_attrib['auth']
-
-        if token_auth in ('blocked', 'restricted', 'error'):
-            raise ExtractorError(
-                'Token error: %s' % token_attrib['comment'], expected=True)
-
-        formats = self._extract_f4m_formats(
-            '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
-            video_id, f4m_id='hds')
-        self._sort_formats(formats)
-
-        categories_str = _v('meta_sports')
-        categories = categories_str.split(',') if categories_str else []
+            webpage, 'iframe url'))
 
         return {
-            'id': video_id,
+            '_type': 'url',
             'display_id': display_id,
-            'title': title,
-            'upload_date': unified_strdate(_v('time_date')),
-            'uploader': _v('meta_organisation'),
-            'categories': categories,
-            'is_live': _v('islive') == 'true',
-            'formats': formats,
+            'url': iframe_url,
+            'ie_key': 'Laola1TvEmbed',
         }

youtube_dl/extractor/liveleak.py

@@ -54,6 +54,22 @@ class LiveLeakIE(InfoExtractor):
             'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
             'thumbnail': 're:^https?://.*\.jpg$'
         }
+    }, {
+        # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521
+        'url': 'http://m.liveleak.com/view?i=763_1473349649',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': '763_1473349649',
+            'ext': 'mp4',
+            'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty',
+            'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.',
+            'uploader': 'Ziz',
+            'upload_date': '20160908',
+            'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw'
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     @staticmethod
@@ -87,7 +103,7 @@ class LiveLeakIE(InfoExtractor):
             else:
                 # Maybe an embed?
                 embed_url = self._search_regex(
-                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
+                    r'<iframe[^>]+src="(https?://(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
                     webpage, 'embed URL')
                 return {
                     '_type': 'url_transparent',
@@ -107,6 +123,7 @@ class LiveLeakIE(InfoExtractor):
             'format_note': s.get('label'),
             'url': s['file'],
         } for i, s in enumerate(sources)]
+
         for i, s in enumerate(sources):
             # Removing '.h264_*.mp4' gives the raw video, which is essentially
             # the same video without the LiveLeak logo at the top (see

youtube_dl/extractor/meipai.py

@@ -0,0 +1,104 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    unified_timestamp,
+)
+
+
+class MeipaiIE(InfoExtractor):
+    IE_DESC = '美拍'
+    _VALID_URL = r'https?://(?:www\.)?meipai.com/media/(?P<id>[0-9]+)'
+    _TESTS = [{
+        # regular uploaded video
+        'url': 'http://www.meipai.com/media/531697625',
+        'md5': 'e3e9600f9e55a302daecc90825854b4f',
+        'info_dict': {
+            'id': '531697625',
+            'ext': 'mp4',
+            'title': '#葉子##阿桑##余姿昀##超級女聲#',
+            'description': '#葉子##阿桑##余姿昀##超級女聲#',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 152,
+            'timestamp': 1465492420,
+            'upload_date': '20160609',
+            'view_count': 35511,
+            'creator': '她她-TATA',
+            'tags': ['葉子', '阿桑', '余姿昀', '超級女聲'],
+        }
+    }, {
+        # record of live streaming
+        'url': 'http://www.meipai.com/media/585526361',
+        'md5': 'ff7d6afdbc6143342408223d4f5fb99a',
+        'info_dict': {
+            'id': '585526361',
+            'ext': 'mp4',
+            'title': '姿昀和善願 練歌練琴啦😁😁😁',
+            'description': '姿昀和善願 練歌練琴啦😁😁😁',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 5975,
+            'timestamp': 1474311799,
+            'upload_date': '20160919',
+            'view_count': 1215,
+            'creator': '她她-TATA',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(
+            webpage, default=None) or self._html_search_regex(
+            r'<title[^>]*>([^<]+)</title>', webpage, 'title')
+
+        formats = []
+
+        # recorded playback of live streaming
+        m3u8_url = self._html_search_regex(
+            r'file:\s*encodeURIComponent\((["\'])(?P<url>(?:(?!\1).)+)\1\)',
+            webpage, 'm3u8 url', group='url', default=None)
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        if not formats:
+            # regular uploaded video
+            video_url = self._search_regex(
+                r'data-video=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'video url',
+                group='url', default=None)
+            if video_url:
+                formats.append({
+                    'url': video_url,
+                    'format_id': 'http',
+                })
+
+        timestamp = unified_timestamp(self._og_search_property(
+            'video:release_date', webpage, 'release date', fatal=False))
+
+        tags = self._og_search_property(
+            'video:tag', webpage, 'tags', default='').split(',')
+
+        view_count = int_or_none(self._html_search_meta(
+            'interactionCount', webpage, 'view count'))
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration'))
+        creator = self._og_search_property(
+            'video:director', webpage, 'creator', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'creator': creator,
+            'tags': tags,
+            'formats': formats,
+        }

youtube_dl/extractor/melonvod.py

@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    urljoin,
+)
+
+
+class MelonVODIE(InfoExtractor):
+    _VALID_URL = r'https?://vod\.melon\.com/video/detail2\.html?\?.*?mvId=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://vod.melon.com/video/detail2.htm?mvId=50158734',
+        'info_dict': {
+            'id': '50158734',
+            'ext': 'mp4',
+            'title': "Jessica 'Wonderland' MV Making Film",
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'artist': 'Jessica (제시카)',
+            'upload_date': '20161212',
+            'duration': 203,
+        },
+        'params': {
+            'skip_download': 'm3u8 download',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        play_info = self._download_json(
+            'http://vod.melon.com/video/playerInfo.json', video_id,
+            note='Downloading player info JSON', query={'mvId': video_id})
+
+        title = play_info['mvInfo']['MVTITLE']
+
+        info = self._download_json(
+            'http://vod.melon.com/delivery/streamingInfo.json', video_id,
+            note='Downloading streaming info JSON',
+            query={
+                'contsId': video_id,
+                'contsType': 'VIDEO',
+            })
+
+        stream_info = info['streamingInfo']
+
+        formats = self._extract_m3u8_formats(
+            stream_info['encUrl'], video_id, 'mp4', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        artist_list = play_info.get('artistList')
+        artist = None
+        if isinstance(artist_list, list):
+            artist = ', '.join(
+                [a['ARTISTNAMEWEBLIST']
+                 for a in artist_list if a.get('ARTISTNAMEWEBLIST')])
+
+        thumbnail = urljoin(info.get('staticDomain'), stream_info.get('imgPath'))
+
+        duration = int_or_none(stream_info.get('playTime'))
+        upload_date = stream_info.get('mvSvcOpenDt', '')[:8] or None
+
+        return {
+            'id': video_id,
+            'title': title,
+            'artist': artist,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'formats': formats
+        }

youtube_dl/extractor/mitele.py

@@ -75,7 +75,7 @@ class MiTeleBaseIE(InfoExtractor):
 
 class MiTeleIE(InfoExtractor):
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://(?:www\.)?mitele\.es/programas-tv/(?:[^/]+/)(?P<id>[^/]+)/player'
+    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
 
     _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
@@ -86,7 +86,10 @@ class MiTeleIE(InfoExtractor):
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
             'series': 'Diario de',
             'season': 'La redacción',
+            'season_number': 14,
+            'season_id': 'diario_de_t14_11981',
             'episode': 'Programa 144',
+            'episode_number': 3,
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
             'duration': 2913,
         },
@@ -101,7 +104,10 @@ class MiTeleIE(InfoExtractor):
             'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
             'series': 'Cuarto Milenio',
             'season': 'Temporada 6',
+            'season_number': 6,
+            'season_id': 'cuarto_milenio_t06_12715',
             'episode': 'Programa 226',
+            'episode_number': 24,
             'thumbnail': 're:(?i)^https?://.*\.jpg$',
             'duration': 7313,
         },
@@ -109,41 +115,77 @@ class MiTeleIE(InfoExtractor):
             'skip_download': True,
         },
         'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        gigya_url = self._search_regex(r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s*src="([^"]*)">[^>]*</script>', webpage, 'gigya', default=None)
-        gigya_sc = self._download_webpage(compat_urlparse.urljoin(r'http://www.mitele.es/', gigya_url), video_id, 'Downloading gigya script')
+        gigya_url = self._search_regex(
+            r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>',
+            webpage, 'gigya', default=None)
+        gigya_sc = self._download_webpage(
+            compat_urlparse.urljoin('http://www.mitele.es/', gigya_url),
+            video_id, 'Downloading gigya script')
+
         # Get a appKey/uuid for getting the session key
-        appKey_var = self._search_regex(r'value\("appGridApplicationKey",([0-9a-f]+)\)', gigya_sc, 'appKey variable')
-        appKey = self._search_regex(r'var %s="([0-9a-f]+)"' % appKey_var, gigya_sc, 'appKey')
-        uid = compat_str(uuid.uuid4())
-        session_url = 'https://appgrid-api.cloud.accedo.tv/session?appKey=%s&uuid=%s' % (appKey, uid)
-        session_json = self._download_json(session_url, video_id, 'Downloading session keys')
-        sessionKey = compat_str(session_json['sessionKey'])
+        appKey_var = self._search_regex(
+            r'value\s*\(\s*["\']appGridApplicationKey["\']\s*,\s*([0-9a-f]+)',
+            gigya_sc, 'appKey variable')
+        appKey = self._search_regex(
+            r'var\s+%s\s*=\s*["\']([0-9a-f]+)' % appKey_var, gigya_sc, 'appKey')
+
+        session_json = self._download_json(
+            'https://appgrid-api.cloud.accedo.tv/session',
+            video_id, 'Downloading session keys', query={
+                'appKey': appKey,
+                'uuid': compat_str(uuid.uuid4()),
+            })
+
+        paths = self._download_json(
+            'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration',
+            video_id, 'Downloading paths JSON',
+            query={'sessionKey': compat_str(session_json['sessionKey'])})
 
-        paths_url = 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration?sessionKey=' + sessionKey
-        paths = self._download_json(paths_url, video_id, 'Downloading paths JSON')
         ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
-        data_p = (
-            'http://' + ooyala_s['base_url'] + ooyala_s['full_path'] + ooyala_s['provider_id'] +
-            '/docs/' + video_id + '?include_titles=Series,Season&product_name=test&format=full')
-        data = self._download_json(data_p, video_id, 'Downloading data JSON')
-        source = data['hits']['hits'][0]['_source']
-        embedCode = source['offers'][0]['embed_codes'][0]
+        source = self._download_json(
+            'http://%s%s%s/docs/%s' % (
+                ooyala_s['base_url'], ooyala_s['full_path'],
+                ooyala_s['provider_id'], video_id),
+            video_id, 'Downloading data JSON', query={
+                'include_titles': 'Series,Season',
+                'product_name': 'test',
+                'format': 'full',
+            })['hits']['hits'][0]['_source']
 
+        embedCode = source['offers'][0]['embed_codes'][0]
         titles = source['localizable_titles'][0]
+
         title = titles.get('title_medium') or titles['title_long']
-        episode = titles['title_sort_name']
-        description = titles['summary_long']
-        titles_series = source['localizable_titles_series'][0]
-        series = titles_series['title_long']
-        titles_season = source['localizable_titles_season'][0]
-        season = titles_season['title_medium']
-        duration = parse_duration(source['videos'][0]['duration'])
+
+        description = titles.get('summary_long') or titles.get('summary_medium')
+
+        def get(key1, key2):
+            value1 = source.get(key1)
+            if not value1 or not isinstance(value1, list):
+                return
+            if not isinstance(value1[0], dict):
+                return
+            return value1[0].get(key2)
+
+        series = get('localizable_titles_series', 'title_medium')
+
+        season = get('localizable_titles_season', 'title_medium')
+        season_number = int_or_none(source.get('season_number'))
+        season_id = source.get('season_id')
+
+        episode = titles.get('title_sort_name')
+        episode_number = int_or_none(source.get('episode_number'))
+
+        duration = parse_duration(get('videos', 'duration'))
 
         return {
             '_type': 'url_transparent',
@@ -154,7 +196,10 @@ class MiTeleIE(InfoExtractor):
             'description': description,
             'series': series,
             'season': season,
+            'season_number': season_number,
+            'season_id': season_id,
             'episode': episode,
+            'episode_number': episode_number,
             'duration': duration,
-            'thumbnail': source['images'][0]['url'],
+            'thumbnail': get('images', 'url'),
         }

youtube_dl/extractor/mixcloud.py

@@ -22,7 +22,7 @@ from ..utils import (
 
 
 class MixcloudIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
+    _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
     IE_NAME = 'mixcloud'
 
     _TESTS = [{
@@ -51,6 +51,9 @@ class MixcloudIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
+    }, {
+        'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
+        'only_matching': True,
     }]
 
     # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js

youtube_dl/extractor/msn.py

@@ -78,11 +78,6 @@ class MSNIE(InfoExtractor):
                 m3u8_formats = self._extract_m3u8_formats(
                     format_url, display_id, 'mp4',
                     m3u8_id='hls', fatal=False)
-                # Despite metadata in m3u8 all video+audio formats are
-                # actually video-only (no audio)
-                for f in m3u8_formats:
-                    if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
-                        f['acodec'] = 'none'
                 formats.extend(m3u8_formats)
             else:
                 formats.append({

youtube_dl/extractor/mtv.py

@@ -13,6 +13,7 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     HEADRequest,
+    NO_DEFAULT,
     RegexNotFoundError,
     sanitized_Request,
     strip_or_none,
@@ -201,7 +202,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             [self._get_video_info(item) for item in idoc.findall('.//item')],
             playlist_title=title, playlist_description=description)
 
-    def _extract_mgid(self, webpage):
+    def _extract_mgid(self, webpage, default=NO_DEFAULT):
         try:
             # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
             # or http://media.mtvnservices.com/{mgid}
@@ -221,7 +222,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             sm4_embed = self._html_search_meta(
                 'sm4:video:embed', webpage, 'sm4 embed', default='')
             mgid = self._search_regex(
-                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid')
+                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
         return mgid
 
     def _real_extract(self, url):

youtube_dl/extractor/nbc.py

@@ -9,6 +9,7 @@ from ..utils import (
     lowercase_escape,
     smuggle_url,
     unescapeHTML,
+    update_url_query,
 )
 
 
@@ -208,7 +209,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
             'md5': 'af1adfa51312291a017720403826bb64',
             'info_dict': {
-                'id': '269389891880',
+                'id': 'p_tweet_snow_140529',
                 'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
@@ -232,7 +233,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
             'info_dict': {
-                'id': '394064451844',
+                'id': 'nn_netcast_150204',
                 'ext': 'mp4',
                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
@@ -245,7 +246,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
             'md5': 'a49e173825e5fcd15c13fc297fced39d',
             'info_dict': {
-                'id': '529953347624',
+                'id': 'x_lon_vwhorn_150922',
                 'ext': 'mp4',
                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
@@ -258,7 +259,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
             'md5': '118d7ca3f0bea6534f119c68ef539f71',
             'info_dict': {
-                'id': '669831235788',
+                'id': 'tdy_al_space_160420',
                 'ext': 'mp4',
                 'title': 'See the aurora borealis from space in stunning new NASA video',
                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
@@ -271,7 +272,7 @@ class NBCNewsIE(ThePlatformIE):
             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
             'info_dict': {
-                'id': '314487875924',
+                'id': 'n_hayes_Aimm_140801_272214',
                 'ext': 'mp4',
                 'title': 'The chaotic GOP immigration vote',
                 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
@@ -279,7 +280,6 @@ class NBCNewsIE(ThePlatformIE):
                 'timestamp': 1406937606,
                 'upload_date': '20140802',
                 'uploader': 'NBCU-NEWS',
-                'categories': ['MSNBC/Topics/Franchise/Best of last night', 'MSNBC/Topics/General/Congress'],
             },
         },
         {
@@ -311,28 +311,41 @@ class NBCNewsIE(ThePlatformIE):
         else:
             # "feature" and "nightly-news" pages use theplatform.com
             video_id = mobj.group('mpx_id')
-            if not video_id.isdigit():
-                webpage = self._download_webpage(url, video_id)
-                info = None
-                bootstrap_json = self._search_regex(
-                    [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
-                     r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"'],
-                    webpage, 'bootstrap json', default=None)
+            webpage = self._download_webpage(url, video_id)
+
+            filter_param = 'byId'
+            bootstrap_json = self._search_regex(
+                [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
+                 r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
+                 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
+                webpage, 'bootstrap json', default=None)
+            if bootstrap_json:
                 bootstrap = self._parse_json(
                     bootstrap_json, video_id, transform_source=unescapeHTML)
+
+                info = None
                 if 'results' in bootstrap:
                     info = bootstrap['results'][0]['video']
                 elif 'video' in bootstrap:
                     info = bootstrap['video']
+                elif 'msnbcVideoInfo' in bootstrap:
+                    info = bootstrap['msnbcVideoInfo']['meta']
+                elif 'msnbcThePlatform' in bootstrap:
+                    info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
                 else:
                     info = bootstrap
-                video_id = info['mpxId']
+
+                if 'guid' in info:
+                    video_id = info['guid']
+                    filter_param = 'byGuid'
+                elif 'mpxId' in info:
+                    video_id = info['mpxId']
 
             return {
                 '_type': 'url_transparent',
                 'id': video_id,
                 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
-                'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byId=%s' % video_id,
+                'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
                 'ie_key': 'ThePlatformFeed',
             }
 

youtube_dl/extractor/normalboots.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from .screenwavemedia import ScreenwaveMediaIE
+from .jwplatform import JWPlatformIE
 
 from ..utils import (
     unified_strdate,
@@ -25,7 +25,7 @@ class NormalbootsIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
-        'add_ie': ['ScreenwaveMedia'],
+        'add_ie': ['JWPlatform'],
     }
 
     def _real_extract(self, url):
@@ -39,15 +39,13 @@ class NormalbootsIE(InfoExtractor):
             r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
             webpage, 'date', fatal=False))
 
-        screenwavemedia_url = self._html_search_regex(
-            ScreenwaveMediaIE.EMBED_PATTERN, webpage, 'screenwave URL',
-            group='url')
+        jwplatform_url = JWPlatformIE._extract_url(webpage)
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'url': screenwavemedia_url,
-            'ie_key': ScreenwaveMediaIE.ie_key(),
+            'url': jwplatform_url,
+            'ie_key': JWPlatformIE.ie_key(),
             'title': self._og_search_title(webpage),
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),

youtube_dl/extractor/nrk.py

@@ -48,6 +48,13 @@ class NRKBaseIE(InfoExtractor):
 
         entries = []
 
+        conviva = data.get('convivaStatistics') or {}
+        live = (data.get('mediaElementType') == 'Live' or
+                data.get('isLive') is True or conviva.get('isLive'))
+
+        def make_title(t):
+            return self._live_title(t) if live else t
+
         media_assets = data.get('mediaAssets')
         if media_assets and isinstance(media_assets, list):
             def video_id_and_title(idx):
@@ -61,6 +68,13 @@ class NRKBaseIE(InfoExtractor):
                 if not formats:
                     continue
                 self._sort_formats(formats)
+
+                # Some f4m streams may not work with hdcore in fragments' URLs
+                for f in formats:
+                    extra_param = f.get('extra_param_to_segment_url')
+                    if extra_param and 'hdcore' in extra_param:
+                        del f['extra_param_to_segment_url']
+
                 entry_id, entry_title = video_id_and_title(num)
                 duration = parse_duration(asset.get('duration'))
                 subtitles = {}
@@ -72,7 +86,7 @@ class NRKBaseIE(InfoExtractor):
                         })
                 entries.append({
                     'id': asset.get('carrierId') or entry_id,
-                    'title': entry_title,
+                    'title': make_title(entry_title),
                     'duration': duration,
                     'subtitles': subtitles,
                     'formats': formats,
@@ -87,7 +101,7 @@ class NRKBaseIE(InfoExtractor):
                 duration = parse_duration(data.get('duration'))
                 entries = [{
                     'id': video_id,
-                    'title': title,
+                    'title': make_title(title),
                     'duration': duration,
                     'formats': formats,
                 }]
@@ -111,7 +125,6 @@ class NRKBaseIE(InfoExtractor):
                     message_type, message_type)),
                 expected=True)
 
-        conviva = data.get('convivaStatistics') or {}
         series = conviva.get('seriesName') or data.get('seriesTitle')
         episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
 
@@ -194,7 +207,15 @@ class NRKIE(NRKBaseIE):
 
 class NRKTVIE(NRKBaseIE):
     IE_DESC = 'NRK TV and NRK Radio'
-    _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
+    _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:tv|radio)\.nrk(?:super)?\.no/
+                            (?:serie/[^/]+|program)/
+                            (?![Ee]pisodes)%s
+                            (?:/\d{2}-\d{2}-\d{4})?
+                            (?:\#del=(?P<part_id>\d+))?
+                    ''' % _EPISODE_RE
     _API_HOST = 'psapi-we.nrk.no'
 
     _TESTS = [{
@@ -260,9 +281,43 @@ class NRKTVIE(NRKBaseIE):
     }]
 
 
-class NRKPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
+class NRKTVDirekteIE(NRKTVIE):
+    IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
+    _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
 
+    _TESTS = [{
+        'url': 'https://tv.nrk.no/direkte/nrk1',
+        'only_matching': True,
+    }, {
+        'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
+        'only_matching': True,
+    }]
+
+
+class NRKPlaylistBaseIE(InfoExtractor):
+    def _extract_description(self, webpage):
+        pass
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
+            for video_id in re.findall(self._ITEM_RE, webpage)
+        ]
+
+        playlist_title = self. _extract_title(webpage)
+        playlist_description = self._extract_description(webpage)
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)
+
+
+class NRKPlaylistIE(NRKPlaylistBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
+    _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
         'info_dict': {
@@ -281,23 +336,28 @@ class NRKPlaylistIE(InfoExtractor):
         'playlist_count': 5,
     }]
 
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+    def _extract_title(self, webpage):
+        return self._og_search_title(webpage, fatal=False)
 
-        webpage = self._download_webpage(url, playlist_id)
+    def _extract_description(self, webpage):
+        return self._og_search_description(webpage)
 
-        entries = [
-            self.url_result('nrk:%s' % video_id, 'NRK')
-            for video_id in re.findall(
-                r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
-                webpage)
-        ]
 
-        playlist_title = self._og_search_title(webpage)
-        playlist_description = self._og_search_description(webpage)
+class NRKTVEpisodesIE(NRKPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
+    _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
+    _TESTS = [{
+        'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
+        'info_dict': {
+            'id': '69031',
+            'title': 'Nytt på nytt, sesong: 201210',
+        },
+        'playlist_count': 4,
+    }]
 
-        return self.playlist_result(
-            entries, playlist_id, playlist_title, playlist_description)
+    def _extract_title(self, webpage):
+        return self._html_search_regex(
+            r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 
 
 class NRKSkoleIE(InfoExtractor):

youtube_dl/extractor/ondemandkorea.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    ExtractorError,
+    js_to_json,
+)
+
+
+class OnDemandKoreaIE(JWPlatformBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
+    _TEST = {
+        'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html',
+        'info_dict': {
+            'id': 'ask-us-anything-e43',
+            'ext': 'mp4',
+            'title': 'Ask Us Anything : E43',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': 'm3u8 download'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id, fatal=False)
+
+        if not webpage:
+            # Page sometimes returns captcha page with HTTP 403
+            raise ExtractorError(
+                'Unable to access page. You may have been blocked.',
+                expected=True)
+
+        if 'msg_block_01.png' in webpage:
+            self.raise_geo_restricted(
+                'This content is not available in your region')
+
+        if 'This video is only available to ODK PLUS members.' in webpage:
+            raise ExtractorError(
+                'This video is only available to ODK PLUS members.',
+                expected=True)
+
+        title = self._og_search_title(webpage)
+
+        jw_config = self._parse_json(
+            self._search_regex(
+                r'(?s)jwplayer\(([\'"])(?:(?!\1).)+\1\)\.setup\s*\((?P<options>.+?)\);',
+                webpage, 'jw config', group='options'),
+            video_id, transform_source=js_to_json)
+        info = self._parse_jwplayer_data(
+            jw_config, video_id, require_title=False, m3u8_id='hls',
+            base_url=url)
+
+        info.update({
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        })
+        return info

youtube_dl/extractor/openload.py

@@ -1,11 +1,8 @@
 # coding: utf-8
-from __future__ import unicode_literals, division
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_chr,
-    compat_ord,
-)
+from ..compat import compat_chr
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -13,7 +10,7 @@ from ..utils import (
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://openload\.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -54,6 +51,9 @@ class OpenloadIE(InfoExtractor):
         # for title and ext
         'url': 'https://openload.co/embed/Sxz5sADo82g/',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -63,29 +63,20 @@ class OpenloadIE(InfoExtractor):
         if 'File not found' in webpage or 'deleted by the owner' in webpage:
             raise ExtractorError('File not found', expected=True)
 
-        # The following decryption algorithm is written by @yokrysty and
-        # declared to be freely used in youtube-dl
-        # See https://github.com/rg3/youtube-dl/issues/10408
-        enc_data = self._html_search_regex(
-            r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"',
-            webpage, 'encrypted data')
+        ol_id = self._search_regex(
+            '<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
+            webpage, 'openload ID')
 
-        magic = compat_ord(enc_data[-1])
-        video_url_chars = []
+        first_two_chars = int(float(ol_id[0:][:2]))
+        urlcode = ''
+        num = 2
 
-        for idx, c in enumerate(enc_data):
-            j = compat_ord(c)
-            if j == magic:
-                j -= 1
-            elif j == magic - 1:
-                j += 1
-            if j >= 33 and j <= 126:
-                j = ((j + 14) % 94) + 33
-            if idx == len(enc_data) - 1:
-                j += 3
-            video_url_chars += compat_chr(j)
+        while num < len(ol_id):
+            urlcode += compat_chr(int(float(ol_id[num:][:3])) -
+                                  first_two_chars * int(float(ol_id[num + 3:][:2])))
+            num += 5
 
-        video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
+        video_url = 'https://openload.co/stream/' + urlcode
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@@ -104,5 +95,4 @@ class OpenloadIE(InfoExtractor):
             'ext': determine_ext(title),
             'subtitles': subtitles,
         }
-
         return info_dict

youtube_dl/extractor/pandoratv.py

@@ -11,6 +11,7 @@ from ..utils import (
     float_or_none,
     parse_duration,
     str_to_int,
+    urlencode_postdata,
 )
 
 
@@ -56,6 +57,22 @@ class PandoraTVIE(InfoExtractor):
                 r'^v(\d+)[Uu]rl$', format_id, 'height', default=None)
             if not height:
                 continue
+
+            play_url = self._download_json(
+                'http://m.pandora.tv/?c=api&m=play_url', video_id,
+                data=urlencode_postdata({
+                    'prgid': video_id,
+                    'runtime': info.get('runtime'),
+                    'vod_url': format_url,
+                }),
+                headers={
+                    'Origin': url,
+                    'Content-Type': 'application/x-www-form-urlencoded',
+                })
+            format_url = play_url.get('url')
+            if not format_url:
+                continue
+
             formats.append({
                 'format_id': '%sp' % height,
                 'url': format_url,

youtube_dl/extractor/pbs.py

@@ -350,6 +350,15 @@ class PBSIE(InfoExtractor):
         410: 'This video has expired and is no longer available for online streaming.',
     }
 
+    def _real_initialize(self):
+        cookie = (self._download_json(
+            'http://localization.services.pbs.org/localize/auto/cookie/',
+            None, headers=self.geo_verification_headers(), fatal=False) or {}).get('cookie')
+        if cookie:
+            station = self._search_regex(r'#?s=\["([^"]+)"', cookie, 'station')
+            if station:
+                self._set_cookie('.pbs.org', 'pbsol.station', station)
+
     def _extract_webpage(self, url):
         mobj = re.match(self._VALID_URL, url)
 
@@ -476,7 +485,8 @@ class PBSIE(InfoExtractor):
 
             redirect_info = self._download_json(
                 '%s?format=json' % redirect['url'], display_id,
-                'Downloading %s video url info' % (redirect_id or num))
+                'Downloading %s video url info' % (redirect_id or num),
+                headers=self.geo_verification_headers())
 
             if redirect_info['status'] == 'error':
                 raise ExtractorError(

youtube_dl/extractor/piksel.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    dict_get,
+    int_or_none,
+    unescapeHTML,
+    parse_iso8601,
+)
+
+
+class PikselIE(InfoExtractor):
+    _VALID_URL = r'https?://player\.piksel\.com/v/(?P<id>[a-z0-9]+)'
+    _TEST = {
+        'url': 'http://player.piksel.com/v/nv60p12f',
+        'md5': 'd9c17bbe9c3386344f9cfd32fad8d235',
+        'info_dict': {
+            'id': 'nv60p12f',
+            'ext': 'mp4',
+            'title': 'فن الحياة  - الحلقة 1',
+            'description': 'احدث برامج الداعية الاسلامي " مصطفي حسني " فى رمضان 2016علي النهار نور',
+            'timestamp': 1465231790,
+            'upload_date': '20160606',
+        }
+    }
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//player\.piksel\.com/v/[a-z0-9]+)',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        app_token = self._search_regex(
+            r'clientAPI\s*:\s*"([^"]+)"', webpage, 'app token')
+        response = self._download_json(
+            'http://player.piksel.com/ws/ws_program/api/%s/mode/json/apiv/5' % app_token,
+            video_id, query={
+                'v': video_id
+            })['response']
+        failure = response.get('failure')
+        if failure:
+            raise ExtractorError(response['failure']['reason'], expected=True)
+        video_data = response['WsProgramResponse']['program']['asset']
+        title = video_data['title']
+
+        formats = []
+
+        m3u8_url = dict_get(video_data, [
+            'm3u8iPadURL',
+            'ipadM3u8Url',
+            'm3u8AndroidURL',
+            'm3u8iPhoneURL',
+            'iphoneM3u8Url'])
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        asset_type = dict_get(video_data, ['assetType', 'asset_type'])
+        for asset_file in video_data.get('assetFiles', []):
+            # TODO: extract rtmp formats
+            http_url = asset_file.get('http_url')
+            if not http_url:
+                continue
+            tbr = None
+            vbr = int_or_none(asset_file.get('videoBitrate'), 1024)
+            abr = int_or_none(asset_file.get('audioBitrate'), 1024)
+            if asset_type == 'video':
+                tbr = vbr + abr
+            elif asset_type == 'audio':
+                tbr = abr
+
+            format_id = ['http']
+            if tbr:
+                format_id.append(compat_str(tbr))
+
+            formats.append({
+                'format_id': '-'.join(format_id),
+                'url': unescapeHTML(http_url),
+                'vbr': vbr,
+                'abr': abr,
+                'width': int_or_none(asset_file.get('videoWidth')),
+                'height': int_or_none(asset_file.get('videoHeight')),
+                'filesize': int_or_none(asset_file.get('filesize')),
+                'tbr': tbr,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnailUrl'),
+            'timestamp': parse_iso8601(video_data.get('dateadd')),
+            'formats': formats,
+        }

youtube_dl/extractor/prosiebensat1.py

@@ -85,6 +85,9 @@ class ProSiebenSat1BaseIE(InfoExtractor):
                     formats.extend(self._extract_m3u8_formats(
                         source_url, clip_id, 'mp4', 'm3u8_native',
                         m3u8_id='hls', fatal=False))
+                elif mimetype == 'application/dash+xml':
+                    formats.extend(self._extract_mpd_formats(
+                        source_url, clip_id, mpd_id='dash', fatal=False))
                 else:
                     tbr = fix_bitrate(source['bitrate'])
                     if protocol in ('rtmp', 'rtmpe'):

youtube_dl/extractor/puls4.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class Puls4IE(ProSiebenSat1BaseIE):
-    _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)'
     _TESTS = [{
         'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
         'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
@@ -22,6 +22,12 @@ class Puls4IE(ProSiebenSat1BaseIE):
             'upload_date': '20160830',
             'uploader': 'PULS_4',
         },
+    }, {
+        'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598',
+        'only_matching': True,
     }]
     _TOKEN = 'puls4'
     _SALT = '01!kaNgaiNgah1Ie4AeSha'

youtube_dl/extractor/rte.py

@@ -4,118 +4,31 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     float_or_none,
     parse_iso8601,
     unescapeHTML,
+    ExtractorError,
 )
 
 
-class RteIE(InfoExtractor):
-    IE_NAME = 'rte'
-    IE_DESC = 'Raidió Teilifís Éireann TV'
-    _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
-        'info_dict': {
-            'id': '10478715',
-            'ext': 'flv',
-            'title': 'Watch iWitness  online',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
-            'duration': 60.046,
-        },
-        'params': {
-            'skip_download': 'f4m fails with --test atm'
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._og_search_title(webpage)
-        description = self._html_search_meta('description', webpage, 'description')
-        duration = float_or_none(self._html_search_meta(
-            'duration', webpage, 'duration', fatal=False), 1000)
-
-        thumbnail = None
-        thumbnail_meta = self._html_search_meta('thumbnail', webpage)
-        if thumbnail_meta:
-            thumbnail_id = self._search_regex(
-                r'uri:irus:(.+)', thumbnail_meta,
-                'thumbnail id', fatal=False)
-            if thumbnail_id:
-                thumbnail = 'http://img.rasset.ie/%s.jpg' % thumbnail_id
-
-        feeds_url = self._html_search_meta('feeds-prefix', webpage, 'feeds url') + video_id
-        json_string = self._download_json(feeds_url, video_id)
-
-        # f4m_url = server + relative_url
-        f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
-        f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
-        self._sort_formats(f4m_formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': f4m_formats,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-        }
-
-
-class RteRadioIE(InfoExtractor):
-    IE_NAME = 'rte:radio'
-    IE_DESC = 'Raidió Teilifís Éireann radio'
-    # Radioplayer URLs have two distinct specifier formats,
-    # the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>:
-    # the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_
-    # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated.
-    # An <id> uniquely defines an individual recording, and is the only part we require.
-    _VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)'
-
-    _TESTS = [{
-        # Old-style player URL; HLS and RTMPE formats
-        'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
-        'info_dict': {
-            'id': '10507902',
-            'ext': 'mp4',
-            'title': 'Gloria',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:9ce124a7fb41559ec68f06387cabddf0',
-            'timestamp': 1451203200,
-            'upload_date': '20151227',
-            'duration': 7230.0,
-        },
-        'params': {
-            'skip_download': 'f4m fails with --test atm'
-        }
-    }, {
-        # New-style player URL; RTMPE formats only
-        'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_',
-        'info_dict': {
-            'id': '3250678',
-            'ext': 'flv',
-            'title': 'The Lyric Concert with Paul Herriott',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'description': '',
-            'timestamp': 1333742400,
-            'upload_date': '20120406',
-            'duration': 7199.016,
-        },
-        'params': {
-            'skip_download': 'f4m fails with --test atm'
-        }
-    }]
-
+class RteBaseIE(InfoExtractor):
     def _real_extract(self, url):
         item_id = self._match_id(url)
 
-        json_string = self._download_json(
-            'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
-            item_id)
+        try:
+            json_string = self._download_json(
+                'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id,
+                item_id)
+        except ExtractorError as ee:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False)
+                if error_info:
+                    raise ExtractorError(
+                        '%s said: %s' % (self.IE_NAME, error_info['message']),
+                        expected=True)
+            raise
 
         # NB the string values in the JSON are stored using XML escaping(!)
         show = json_string['shows'][0]
@@ -163,3 +76,67 @@ class RteRadioIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
         }
+
+
+class RteIE(RteBaseIE):
+    IE_NAME = 'rte'
+    IE_DESC = 'Raidió Teilifís Éireann TV'
+    _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
+        'md5': '4a76eb3396d98f697e6e8110563d2604',
+        'info_dict': {
+            'id': '10478715',
+            'ext': 'mp4',
+            'title': 'iWitness',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'The spirit of Ireland, one voice and one minute at a time.',
+            'duration': 60.046,
+            'upload_date': '20151012',
+            'timestamp': 1444694160,
+        },
+    }
+
+
+class RteRadioIE(RteBaseIE):
+    IE_NAME = 'rte:radio'
+    IE_DESC = 'Raidió Teilifís Éireann radio'
+    # Radioplayer URLs have two distinct specifier formats,
+    # the old format #!rii=<channel_id>:<id>:<playable_item_id>:<date>:
+    # the new format #!rii=b<channel_id>_<id>_<playable_item_id>_<date>_
+    # where the IDs are int/empty, the date is DD-MM-YYYY, and the specifier may be truncated.
+    # An <id> uniquely defines an individual recording, and is the only part we require.
+    _VALID_URL = r'https?://(?:www\.)?rte\.ie/radio/utils/radioplayer/rteradioweb\.html#!rii=(?:b?[0-9]*)(?:%3A|:|%5F|_)(?P<id>[0-9]+)'
+
+    _TESTS = [{
+        # Old-style player URL; HLS and RTMPE formats
+        'url': 'http://www.rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=16:10507902:2414:27-12-2015:',
+        'md5': 'c79ccb2c195998440065456b69760411',
+        'info_dict': {
+            'id': '10507902',
+            'ext': 'mp4',
+            'title': 'Gloria',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'md5:9ce124a7fb41559ec68f06387cabddf0',
+            'timestamp': 1451203200,
+            'upload_date': '20151227',
+            'duration': 7230.0,
+        },
+    }, {
+        # New-style player URL; RTMPE formats only
+        'url': 'http://rte.ie/radio/utils/radioplayer/rteradioweb.html#!rii=b16_3250678_8861_06-04-2012_',
+        'info_dict': {
+            'id': '3250678',
+            'ext': 'flv',
+            'title': 'The Lyric Concert with Paul Herriott',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': '',
+            'timestamp': 1333742400,
+            'upload_date': '20120406',
+            'duration': 7199.016,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }]

youtube_dl/extractor/rtl2.py

@@ -2,7 +2,9 @@
 from __future__ import unicode_literals
 
 import re
+
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class RTL2IE(InfoExtractor):
@@ -13,7 +15,7 @@ class RTL2IE(InfoExtractor):
             'id': 'folge-203-0',
             'ext': 'f4v',
             'title': 'GRIP sucht den Sommerkönig',
-            'description': 'Matthias, Det und Helge treten gegeneinander an.'
+            'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f'
         },
         'params': {
             # rtmp download
@@ -25,7 +27,7 @@ class RTL2IE(InfoExtractor):
             'id': '21040-anna-erwischt-alex',
             'ext': 'mp4',
             'title': 'Anna erwischt Alex!',
-            'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
+            'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.'
         },
         'params': {
             # rtmp download
@@ -52,34 +54,47 @@ class RTL2IE(InfoExtractor):
                 r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
             vivi_id = self._html_search_regex(
                 r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
-        info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
 
-        info = self._download_json(info_url, video_id)
+        info = self._download_json(
+            'http://www.rtl2.de/sites/default/modules/rtl2/mediathek/php/get_video_jw.php',
+            video_id, query={
+                'vico_id': vico_id,
+                'vivi_id': vivi_id,
+            })
         video_info = info['video']
         title = video_info['titel']
-        description = video_info.get('beschreibung')
-        thumbnail = video_info.get('image')
 
-        download_url = video_info['streamurl']
-        download_url = download_url.replace('\\', '')
-        stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
-        rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
+        formats = []
+
+        rtmp_url = video_info.get('streamurl')
+        if rtmp_url:
+            rtmp_url = rtmp_url.replace('\\', '')
+            stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL')
+            rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
+
+            formats.append({
+                'format_id': 'rtmp',
+                'url': rtmp_url,
+                'play_path': stream_url,
+                'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
+                'page_url': url,
+                'flash_version': 'LNX 11,2,202,429',
+                'rtmp_conn': rtmp_conn,
+                'no_resume': True,
+                'preference': 1,
+            })
+
+        m3u8_url = video_info.get('streamurl_hls')
+        if m3u8_url:
+            formats.extend(self._extract_akamai_formats(m3u8_url, video_id))
 
-        formats = [{
-            'url': download_url,
-            'play_path': stream_url,
-            'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
-            'page_url': url,
-            'flash_version': 'LNX 11,2,202,429',
-            'rtmp_conn': rtmp_conn,
-            'no_resume': True,
-        }]
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': thumbnail,
-            'description': description,
+            'thumbnail': video_info.get('image'),
+            'description': video_info.get('beschreibung'),
+            'duration': int_or_none(video_info.get('duration')),
             'formats': formats,
         }

youtube_dl/extractor/rts.py

@@ -4,27 +4,24 @@ from __future__ import unicode_literals
 import re
 
 from .srgssr import SRGSSRIE
-from ..compat import (
-    compat_str,
-    compat_urllib_parse_urlparse,
-)
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
-    xpath_text,
+    determine_ext,
 )
 
 
 class RTSIE(SRGSSRIE):
     IE_DESC = 'RTS.ch'
-    _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
+    _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
 
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
-            'md5': 'f254c4b26fb1d3c183793d52bc40d3e7',
+            'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',
             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',
@@ -38,35 +35,17 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': 're:^https?://.*\.image',
                 'view_count': int,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            }
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
-            'md5': 'f1077ac5af686c76528dc8d7c5df29ba',
             'info_dict': {
-                'id': '5742494',
-                'display_id': '5742494',
-                'ext': 'mp4',
-                'duration': 3720,
-                'title': 'Les yeux dans les cieux - Mon homard au Canada',
-                'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
-                'uploader': 'Passe-moi les jumelles',
-                'upload_date': '20140404',
-                'timestamp': 1396635300,
-                'thumbnail': 're:^https?://.*\.image',
-                'view_count': int,
+                'id': '5624065',
+                'title': 'Passe-moi les jumelles',
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            }
+            'playlist_mincount': 4,
         },
         {
             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
-            'md5': 'b4326fecd3eb64a458ba73c73e91299d',
             'info_dict': {
                 'id': '5745975',
                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
@@ -80,11 +59,15 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': 're:^https?://.*\.image',
                 'view_count': int,
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
-            'md5': '9f713382f15322181bb366cc8c3a4ff0',
+            'md5': '1bae984fe7b1f78e94abc74e802ed99f',
             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',
@@ -92,16 +75,12 @@ class RTSIE(SRGSSRIE):
                 'duration': 33,
                 'title': 'Londres cachée par un épais smog',
                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
-                'uploader': 'Le Journal en continu',
+                'uploader': 'L\'actu en vidéo',
                 'upload_date': '20140403',
                 'timestamp': 1396537322,
                 'thumbnail': 're:^https?://.*\.image',
                 'view_count': int,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            }
         },
         {
             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
@@ -125,6 +104,10 @@ class RTSIE(SRGSSRIE):
                 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
             },
             'playlist_mincount': 5,
+        },
+        {
+            'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
+            'only_matching': True,
         }
     ]
 
@@ -142,19 +125,32 @@ class RTSIE(SRGSSRIE):
 
         # media_id extracted out of URL is not always a real id
         if 'video' not in all_info and 'audio' not in all_info:
-            page = self._download_webpage(url, display_id)
+            entries = []
 
-            # article with videos on rhs
-            videos = re.findall(
-                r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
-                page)
-            if not videos:
+            for item in all_info.get('items', []):
+                item_url = item.get('url')
+                if not item_url:
+                    continue
+                entries.append(self.url_result(item_url, 'RTS'))
+
+            if not entries:
+                page, urlh = self._download_webpage_handle(url, display_id)
+                if re.match(self._VALID_URL, urlh.geturl()).group('id') != media_id:
+                    return self.url_result(urlh.geturl(), 'RTS')
+
+                # article with videos on rhs
                 videos = re.findall(
-                    r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
+                    r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
                     page)
-            if videos:
-                entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
-                return self.playlist_result(entries, media_id, self._og_search_title(page))
+                if not videos:
+                    videos = re.findall(
+                        r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
+                        page)
+                if videos:
+                    entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
+
+            if entries:
+                return self.playlist_result(entries, media_id, all_info.get('title'))
 
             internal_id = self._html_search_regex(
                 r'<(?:video|audio) data-id="([0-9]+)"', page,
@@ -168,36 +164,29 @@ class RTSIE(SRGSSRIE):
 
         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
-        upload_timestamp = parse_iso8601(info.get('broadcast_date'))
-        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
-        if isinstance(duration, compat_str):
-            duration = parse_duration(duration)
-        view_count = info.get('plays')
-        thumbnail = unescapeHTML(info.get('preview_image_url'))
+        title = info['title']
 
         def extract_bitrate(url):
             return int_or_none(self._search_regex(
                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 
         formats = []
-        for format_id, format_url in info['streams'].items():
-            if format_id == 'hds_sd' and 'hds' in info['streams']:
+        streams = info.get('streams', {})
+        for format_id, format_url in streams.items():
+            if format_id == 'hds_sd' and 'hds' in streams:
                 continue
-            if format_id == 'hls_sd' and 'hls' in info['streams']:
+            if format_id == 'hls_sd' and 'hls' in streams:
                 continue
-            if format_url.endswith('.f4m'):
-                token = self._download_xml(
-                    'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
-                    media_id, 'Downloading %s token' % format_id)
-                auth_params = xpath_text(token, './/authparams', 'auth params')
-                if not auth_params:
-                    continue
-                formats.extend(self._extract_f4m_formats(
-                    '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
-                    media_id, f4m_id=format_id, fatal=False))
-            elif format_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
+            ext = determine_ext(format_url)
+            if ext in ('m3u8', 'f4m'):
+                format_url = self._get_tokenized_src(format_url, media_id, format_id)
+                if ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
+                        media_id, f4m_id=format_id, fatal=False))
+                else:
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
             else:
                 formats.append({
                     'format_id': format_id,
@@ -205,25 +194,37 @@ class RTSIE(SRGSSRIE):
                     'tbr': extract_bitrate(format_url),
                 })
 
-        if 'media' in info:
-            formats.extend([{
-                'format_id': '%s-%sk' % (media['ext'], media['rate']),
-                'url': 'http://download-video.rts.ch/%s' % media['url'],
-                'tbr': media['rate'] or extract_bitrate(media['url']),
-            } for media in info['media'] if media.get('rate')])
+        for media in info.get('media', []):
+            media_url = media.get('url')
+            if not media_url or re.match(r'https?://', media_url):
+                continue
+            rate = media.get('rate')
+            ext = media.get('ext') or determine_ext(media_url, 'mp4')
+            format_id = ext
+            if rate:
+                format_id += '-%dk' % rate
+            formats.append({
+                'format_id': format_id,
+                'url': 'http://download-video.rts.ch/' + media_url,
+                'tbr': rate or extract_bitrate(media_url),
+            })
 
         self._check_formats(formats, media_id)
         self._sort_formats(formats)
 
+        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
+        if isinstance(duration, compat_str):
+            duration = parse_duration(duration)
+
         return {
             'id': media_id,
             'display_id': display_id,
             'formats': formats,
-            'title': info['title'],
+            'title': title,
             'description': info.get('intro'),
             'duration': duration,
-            'view_count': view_count,
+            'view_count': int_or_none(info.get('plays')),
             'uploader': info.get('programName'),
-            'timestamp': upload_timestamp,
-            'thumbnail': thumbnail,
+            'timestamp': parse_iso8601(info.get('broadcast_date')),
+            'thumbnail': unescapeHTML(info.get('preview_image_url')),
         }

youtube_dl/extractor/rtve.py

@@ -209,7 +209,10 @@ class RTVELiveIE(InfoExtractor):
         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         vidplayer_id = self._search_regex(
-            r'playerId=player([0-9]+)', webpage, 'internal video ID')
+            (r'playerId=player([0-9]+)',
+             r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
+             r'data-id=["\'](\d+)'),
+            webpage, 'internal video ID')
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
         m3u8_url = _decrypt_url(png)

youtube_dl/extractor/ruutu.py

@@ -5,6 +5,7 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     determine_ext,
+    ExtractorError,
     int_or_none,
     xpath_attr,
     xpath_text,
@@ -101,6 +102,11 @@ class RuutuIE(InfoExtractor):
                         })
 
         extract_formats(video_xml.find('./Clip'))
+
+        drm = xpath_text(video_xml, './Clip/DRM', default=None)
+        if not formats and drm:
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/screenwavemedia.py

@@ -1,146 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    js_to_json,
-)
-
-
-class ScreenwaveMediaIE(InfoExtractor):
-    _VALID_URL = r'(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)'
-    EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1'
-    _TESTS = [{
-        'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        playerdata = self._download_webpage(
-            'http://player.screenwavemedia.com/player.php?id=%s' % video_id,
-            video_id, 'Downloading player webpage')
-
-        vidtitle = self._search_regex(
-            r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
-
-        playerconfig = self._download_webpage(
-            'http://player.screenwavemedia.com/player.js',
-            video_id, 'Downloading playerconfig webpage')
-
-        videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver')
-
-        sources = self._parse_json(
-            js_to_json(
-                re.sub(
-                    r'(?s)/\*.*?\*/', '',
-                    self._search_regex(
-                        r'sources\s*:\s*(\[[^\]]+?\])', playerconfig,
-                        'sources',
-                    ).replace(
-                        "' + thisObj.options.videoserver + '",
-                        videoserver
-                    ).replace(
-                        "' + playerVidId + '",
-                        video_id
-                    )
-                )
-            ),
-            video_id, fatal=False
-        )
-
-        # Fallback to hardcoded sources if JS changes again
-        if not sources:
-            self.report_warning('Falling back to a hardcoded list of streams')
-            sources = [{
-                'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id),
-                'type': 'mp4',
-                'label': format_label,
-            } for format_id, format_label in (
-                ('low', '144p Low'), ('med', '160p Med'), ('high', '360p High'), ('hd1', '720p HD1'))]
-            sources.append({
-                'file': 'http://%s/vod/smil:%s.smil/playlist.m3u8' % (videoserver, video_id),
-                'type': 'hls',
-            })
-
-        formats = []
-        for source in sources:
-            file_ = source.get('file')
-            if not file_:
-                continue
-            if source.get('type') == 'hls':
-                formats.extend(self._extract_m3u8_formats(file_, video_id, ext='mp4'))
-            else:
-                format_id = self._search_regex(
-                    r'_(.+?)\.[^.]+$', file_, 'format id', default=None)
-                if not self._is_valid_url(file_, video_id, format_id or 'video'):
-                    continue
-                format_label = source.get('label')
-                height = int_or_none(self._search_regex(
-                    r'^(\d+)[pP]', format_label, 'height', default=None))
-                formats.append({
-                    'url': file_,
-                    'format_id': format_id,
-                    'format': format_label,
-                    'ext': source.get('type'),
-                    'height': height,
-                })
-        self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
-
-        return {
-            'id': video_id,
-            'title': vidtitle,
-            'formats': formats,
-        }
-
-
-class TeamFourIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
-    _TEST = {
-        'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
-        'info_dict': {
-            'id': 'TeamFourStar-5292a02f20bfa',
-            'ext': 'mp4',
-            'upload_date': '20130401',
-            'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
-            'title': 'A Moment With TFS Episode 4',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-
-        playerdata_url = self._search_regex(
-            r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
-            webpage, 'player data URL')
-
-        video_title = self._html_search_regex(
-            r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
-            webpage, 'title')
-        video_date = unified_strdate(self._html_search_regex(
-            r'<div class="heroheadingdate">(?P<date>.+?)</div>',
-            webpage, 'date', fatal=False))
-        video_description = self._html_search_regex(
-            r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
-            webpage, 'description', fatal=False)
-        video_thumbnail = self._og_search_thumbnail(webpage)
-
-        return {
-            '_type': 'url_transparent',
-            'display_id': display_id,
-            'title': video_title,
-            'description': video_description,
-            'upload_date': video_date,
-            'thumbnail': video_thumbnail,
-            'url': playerdata_url,
-        }

youtube_dl/extractor/showroomlive.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    urljoin,
+)
+
+
+class ShowRoomLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?showroom-live\.com/(?!onlive|timetable|event|campaign|news|ranking|room)(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.showroom-live.com/48_Nana_Okada',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        broadcaster_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, broadcaster_id)
+
+        room_id = self._search_regex(
+            (r'SrGlobal\.roomId\s*=\s*(\d+)',
+             r'(?:profile|room)\?room_id\=(\d+)'), webpage, 'room_id')
+
+        room = self._download_json(
+            urljoin(url, '/api/room/profile?room_id=%s' % room_id),
+            broadcaster_id)
+
+        is_live = room.get('is_onlive')
+        if is_live is not True:
+            raise ExtractorError('%s is offline' % broadcaster_id, expected=True)
+
+        uploader = room.get('performer_name') or broadcaster_id
+        title = room.get('room_name') or room.get('main_name') or uploader
+
+        streaming_url_list = self._download_json(
+            urljoin(url, '/api/live/streaming_url?room_id=%s' % room_id),
+            broadcaster_id)['streaming_url_list']
+
+        formats = []
+        for stream in streaming_url_list:
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            stream_type = stream.get('type')
+            if stream_type == 'hls':
+                m3u8_formats = self._extract_m3u8_formats(
+                    stream_url, broadcaster_id, ext='mp4', m3u8_id='hls',
+                    live=True)
+                for f in m3u8_formats:
+                    f['quality'] = int_or_none(stream.get('quality', 100))
+                formats.extend(m3u8_formats)
+            elif stream_type == 'rtmp':
+                stream_name = stream.get('stream_name')
+                if not stream_name:
+                    continue
+                formats.append({
+                    'url': stream_url,
+                    'play_path': stream_name,
+                    'page_url': url,
+                    'player_url': 'https://www.showroom-live.com/assets/swf/v3/ShowRoomLive.swf',
+                    'rtmp_live': True,
+                    'ext': 'flv',
+                    'format_id': 'rtmp',
+                    'format_note': stream.get('label'),
+                    'quality': int_or_none(stream.get('quality', 100)),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': compat_str(room.get('live_id') or broadcaster_id),
+            'title': self._live_title(title),
+            'description': room.get('description'),
+            'timestamp': int_or_none(room.get('current_live_started_at')),
+            'uploader': uploader,
+            'uploader_id': broadcaster_id,
+            'view_count': int_or_none(room.get('view_num')),
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/soundcloud.py

@@ -121,7 +121,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = '02gUJC0hH2ct1EGOcYXQIzRFU91c72Ea'
+    _CLIENT_ID = 'fDoItMDbsbZz8dY16ZzARCZmzgHBPotA'
     _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
 
     @staticmethod

youtube_dl/extractor/spike.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .mtv import MTVServicesInfoExtractor
 
 
@@ -16,6 +18,15 @@ class SpikeIE(MTVServicesInfoExtractor):
             'timestamp': 1388120400,
             'upload_date': '20131227',
         },
+    }, {
+        'url': 'http://www.spike.com/full-episodes/j830qm/lip-sync-battle-joel-mchale-vs-jim-rash-season-2-ep-209',
+        'md5': 'b25c6f16418aefb9ad5a6cae2559321f',
+        'info_dict': {
+            'id': '37ace3a8-1df6-48be-85b8-38df8229e241',
+            'ext': 'mp4',
+            'title': 'Lip Sync Battle|April 28, 2016|2|209|Joel McHale Vs. Jim Rash|Act 1',
+            'description': 'md5:a739ca8f978a7802f67f8016d27ce114',
+        },
     }, {
         'url': 'http://www.spike.com/video-clips/lhtu8m/',
         'only_matching': True,
@@ -32,3 +43,12 @@ class SpikeIE(MTVServicesInfoExtractor):
 
     _FEED_URL = 'http://www.spike.com/feeds/mrss/'
     _MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s'
+    _CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)')
+
+    def _extract_mgid(self, webpage):
+        mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None)
+        if mgid is None:
+            url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
+            video_type, episode_id = url_parts.split('/', 1)
+            mgid = 'mgid:arc:{0}:spike.com:{1}'.format(video_type, episode_id)
+        return mgid

youtube_dl/extractor/srgssr.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     ExtractorError,
     parse_iso8601,
@@ -23,6 +24,16 @@ class SRGSSRIE(InfoExtractor):
         'STARTDATE': 'This video is not yet available. Please try again later.',
     }
 
+    def _get_tokenized_src(self, url, video_id, format_id):
+        sp = compat_urllib_parse_urlparse(url).path.split('/')
+        token = self._download_json(
+            'http://tp.srgssr.ch/akahd/token?acl=/%s/%s/*' % (sp[1], sp[2]),
+            video_id, 'Downloading %s token' % format_id, fatal=False) or {}
+        auth_params = token.get('token', {}).get('authparams')
+        if auth_params:
+            url += '?' + auth_params
+        return url
+
     def get_media_data(self, bu, media_type, media_id):
         media_data = self._download_json(
             'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
@@ -61,14 +72,16 @@ class SRGSSRIE(InfoExtractor):
                 asset_url = asset['text']
                 quality = asset['@quality']
                 format_id = '%s-%s' % (protocol, quality)
-                if protocol == 'HTTP-HDS':
-                    formats.extend(self._extract_f4m_formats(
-                        asset_url + '?hdcore=3.4.0', media_id,
-                        f4m_id=format_id, fatal=False))
-                elif protocol == 'HTTP-HLS':
-                    formats.extend(self._extract_m3u8_formats(
-                        asset_url, media_id, 'mp4', 'm3u8_native',
-                        m3u8_id=format_id, fatal=False))
+                if protocol.startswith('HTTP-HDS') or protocol.startswith('HTTP-HLS'):
+                    asset_url = self._get_tokenized_src(asset_url, media_id, format_id)
+                    if protocol.startswith('HTTP-HDS'):
+                        formats.extend(self._extract_f4m_formats(
+                            asset_url + ('?' if '?' not in asset_url else '&') + 'hdcore=3.4.0',
+                            media_id, f4m_id=format_id, fatal=False))
+                    elif protocol.startswith('HTTP-HLS'):
+                        formats.extend(self._extract_m3u8_formats(
+                            asset_url, media_id, 'mp4', 'm3u8_native',
+                            m3u8_id=format_id, fatal=False))
                 else:
                     formats.append({
                         'format_id': format_id,
@@ -94,10 +107,10 @@ class SRGSSRPlayIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
-        'md5': '4cd93523723beff51bb4bee974ee238d',
+        'md5': 'da6b5b3ac9fa4761a942331cef20fcb3',
         'info_dict': {
             'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
-            'ext': 'm4v',
+            'ext': 'mp4',
             'upload_date': '20130701',
             'title': 'Snowden beantragt Asyl in Russland',
             'timestamp': 1372713995,

youtube_dl/extractor/teamfourstar.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
+from ..utils import unified_strdate
+
+
+class TeamFourStarIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/(?P<id>[a-z0-9\-]+)'
+    _TEST = {
+        'url': 'http://teamfourstar.com/tfs-abridged-parody-episode-1-2/',
+        'info_dict': {
+            'id': '0WdZO31W',
+            'title': 'TFS Abridged Parody Episode 1',
+            'description': 'md5:d60bc389588ebab2ee7ad432bda953ae',
+            'ext': 'mp4',
+            'timestamp': 1394168400,
+            'upload_date': '20080508',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        jwplatform_url = JWPlatformIE._extract_url(webpage)
+
+        video_title = self._html_search_regex(
+            r'<h1[^>]+class="entry-title"[^>]*>(?P<title>.+?)</h1>',
+            webpage, 'title')
+        video_date = unified_strdate(self._html_search_regex(
+            r'<span[^>]+class="meta-date date updated"[^>]*>(?P<date>.+?)</span>',
+            webpage, 'date', fatal=False))
+        video_description = self._html_search_regex(
+            r'(?s)<div[^>]+class="content-inner"[^>]*>.*?(?P<description><p>.+?)</div>',
+            webpage, 'description', fatal=False)
+        video_thumbnail = self._og_search_thumbnail(webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'display_id': display_id,
+            'title': video_title,
+            'description': video_description,
+            'upload_date': video_date,
+            'thumbnail': video_thumbnail,
+            'url': jwplatform_url,
+        }

youtube_dl/extractor/telebruxelles.py

@@ -7,33 +7,30 @@ from .common import InfoExtractor
 
 
 class TeleBruxellesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)'
     _TESTS = [{
-        'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
-        'md5': '59439e568c9ee42fb77588b2096b214f',
+        'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
+        'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
         'info_dict': {
-            'id': '11942',
-            'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
-            'ext': 'flv',
-            'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition',
-            'description': 're:Les auditions des ministres se poursuivent*'
-        },
-        'params': {
-            'skip_download': 'requires rtmpdump'
+            'id': '158856',
+            'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
+            'ext': 'mp4',
+            'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?',
+            'description': 'md5:3cf8df235d44ebc5426373050840e466',
         },
     }, {
-        'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
-        'md5': '181d3fbdcf20b909309e5aef5c6c6047',
+        'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
+        'md5': 'dfe07ecc9c153ceba8582ac912687675',
         'info_dict': {
-            'id': '10091',
-            'display_id': 'basket-brussels-bat-mons-80-74',
-            'ext': 'flv',
-            'title': 'Basket : le Brussels bat Mons 80-74',
-            'description': 're:^Ils l\u2019on fait ! En basket, le B*',
-        },
-        'params': {
-            'skip_download': 'requires rtmpdump'
+            'id': '158433',
+            'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
+            'ext': 'mp4',
+            'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin',
+            'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
         },
+    }, {
+        'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -50,13 +47,13 @@ class TeleBruxellesIE(InfoExtractor):
             r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
             webpage, 'RTMP url')
         rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
+        formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
+        self._sort_formats(formats)
 
         return {
             'id': article_id or display_id,
             'display_id': display_id,
             'title': title,
             'description': description,
-            'url': rtmp_url,
-            'ext': 'flv',
-            'rtmp_live': True  # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
+            'formats': formats,
         }

youtube_dl/extractor/theplatform.py

@@ -33,7 +33,9 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns})
 
 class ThePlatformBaseIE(OnceIE):
     def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
-        meta = self._download_xml(smil_url, video_id, note=note, query={'format': 'SMIL'})
+        meta = self._download_xml(
+            smil_url, video_id, note=note, query={'format': 'SMIL'},
+            headers=self.geo_verification_headers())
         error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src')
         if error_element is not None and error_element.attrib['src'].startswith(
                 'http://link.theplatform.com/s/errorFiles/Unavailable.'):

youtube_dl/extractor/thisoldhouse.py

@@ -5,10 +5,10 @@ from .common import InfoExtractor
 
 
 class ThisOldHouseIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to)/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
-        'md5': '568acf9ca25a639f0c4ff905826b662f',
+        'md5': '946f05bbaa12a33f9ae35580d2dfcfe3',
         'info_dict': {
             'id': '2REGtUDQ',
             'ext': 'mp4',
@@ -20,6 +20,9 @@ class ThisOldHouseIE(InfoExtractor):
     }, {
         'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
         'only_matching': True,
+    }, {
+        'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/toutv.py

@@ -56,7 +56,7 @@ class TouTvIE(InfoExtractor):
                 'state': state,
             })
         login_form = self._search_regex(
-            r'(?s)(<form[^>]+id="Form-login".+?</form>)', login_webpage, 'login form')
+            r'(?s)(<form[^>]+(?:id|name)="Form-login".+?</form>)', login_webpage, 'login form')
         form_data = self._hidden_inputs(login_form)
         form_data.update({
             'login-email': email,