release 2013.09.06.1

There could be duplicate videos or other videos if the description have links.

.travis.yml

@@ -9,6 +9,7 @@ notifications:
     - filippo.valsorda@gmail.com
     - phihag@phihag.de
     - jaime.marquinez.ferrandiz+travis@gmail.com
+    - yasoob.khld@gmail.com
 #  irc:
 #    channels:
 #      - "irc.freenode.org#youtube-dl"

README.md

@@ -16,21 +16,17 @@ which means you can modify it, redistribute it or use it however you like.
 # OPTIONS
     -h, --help                 print this help text and exit
     --version                  print program version and exit
-    -U, --update               update this program to latest version
+    -U, --update               update this program to latest version. Make sure
+                               that you have sufficient permissions (run with
+                               sudo if needed)
     -i, --ignore-errors        continue on download errors
-    -r, --rate-limit LIMIT     maximum download rate (e.g. 50k or 44.6m)
-    -R, --retries RETRIES      number of retries (default is 10)
-    --buffer-size SIZE         size of download buffer (e.g. 1024 or 16k)
-                               (default is 1024)
-    --no-resize-buffer         do not automatically adjust the buffer size. By
-                               default, the buffer size is automatically resized
-                               from an initial value of SIZE.
     --dump-user-agent          display the current browser identification
     --user-agent UA            specify a custom user agent
     --referer REF              specify a custom referer, use if the video access
                                is restricted to one domain
     --list-extractors          List all supported extractors and the URLs they
                                would handle
+    --extractor-descriptions   Output descriptions of all supported extractors
     --proxy URL                Use the specified HTTP/HTTPS proxy
     --no-check-certificate     Suppress HTTPS certificate validation.
 
@@ -50,6 +46,15 @@ which means you can modify it, redistribute it or use it however you like.
     --datebefore DATE          download only videos uploaded before this date
     --dateafter DATE           download only videos uploaded after this date
 
+## Download Options:
+    -r, --rate-limit LIMIT     maximum download rate (e.g. 50k or 44.6m)
+    -R, --retries RETRIES      number of retries (default is 10)
+    --buffer-size SIZE         size of download buffer (e.g. 1024 or 16k)
+                               (default is 1024)
+    --no-resize-buffer         do not automatically adjust the buffer size. By
+                               default, the buffer size is automatically resized
+                               from an initial value of SIZE.
+
 ## Filesystem Options:
     -t, --title                use title in file name (default)
     --id                       use only video ID in file name
@@ -108,28 +113,34 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Video Format Options:
     -f, --format FORMAT        video format code, specifiy the order of
-                               preference using slashes: "-f 22/17/18"
+                               preference using slashes: "-f 22/17/18". "-f mp4"
+                               and "-f flv" are also supported
     --all-formats              download all available video formats
     --prefer-free-formats      prefer free video formats unless a specific one
                                is requested
     --max-quality FORMAT       highest quality format to download
     -F, --list-formats         list all available formats (currently youtube
                                only)
+
+## Subtitle Options:
     --write-sub                write subtitle file (currently youtube only)
+    --write-auto-sub           write automatic subtitle file (currently youtube
+                               only)
     --only-sub                 [deprecated] alias of --skip-download
     --all-subs                 downloads all the available subtitles of the
-                               video (currently youtube only)
+                               video
     --list-subs                lists all available subtitles for the video
-                               (currently youtube only)
-    --sub-format FORMAT        subtitle format [srt/sbv] (default=srt)
-                               (currently youtube only)
-    --sub-lang LANG            language of the subtitles to download (optional)
-                               use IETF language tags like 'en'
+    --sub-format FORMAT        subtitle format (default=srt) ([sbv/vtt] youtube
+                               only)
+    --sub-lang LANGS           languages of the subtitles to download (optional)
+                               separated by commas, use IETF language tags like
+                               'en,pt'
 
 ## Authentication Options:
     -u, --username USERNAME    account username
     -p, --password PASSWORD    account password
     -n, --netrc                use .netrc authentication data
+    --video-password PASSWORD  video password (vimeo only)
 
 ## Post-processing Options:
     -x, --extract-audio        convert video files to audio-only files (requires
@@ -145,6 +156,8 @@ which means you can modify it, redistribute it or use it however you like.
                                processing; the video is erased by default
     --no-post-overwrites       do not overwrite post-processed files; the post-
                                processed files are overwritten by default
+    --embed-subs               embed subtitles in the video (only for mp4
+                               videos)
 
 # CONFIGURATION
 
@@ -165,7 +178,7 @@ The `-o` option allows users to indicate a template for the output file names. T
  - `playlist`: The name or the id of the playlist that contains the video.
  - `playlist_index`: The index of the video in the playlist, a five-digit number.
 
-The current default template is `%(id)s.%(ext)s`, but that will be switchted to `%(title)s-%(id)s.%(ext)s` (which can be requested with `-t` at the moment).
+The current default template is `%(title)s-%(id)s.%(ext)s`.
 
 In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
 
@@ -191,11 +204,11 @@ Examples:
 
 ### Can you please put the -b option back?
 
-Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the -b option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you''re interested in. In that case, simply request it with the -f option and youtube-dl will try to download it.
+Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the `-b` option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you're interested in. In that case, simply request it with the `-f` option and youtube-dl will try to download it.
 
 ### 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 webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
 
 ### I have downloaded a video but how can I play it?
 

devscripts/bash-completion.in

@@ -4,8 +4,12 @@ __youtube-dl()
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
     opts="{{flags}}"
+    keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater"
 
-    if [[ ${cur} == * ]] ; then
+    if [[ ${cur} =~ : ]]; then
+        COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) )
+        return 0
+    elif [[ ${cur} == * ]] ; then
         COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
         return 0
     fi

devscripts/gh-pages/add-version.py

@@ -6,28 +6,35 @@ import hashlib
 import urllib.request
 
 if len(sys.argv) <= 1:
-	print('Specify the version number as parameter')
-	sys.exit()
+    print('Specify the version number as parameter')
+    sys.exit()
 version = sys.argv[1]
 
 with open('update/LATEST_VERSION', 'w') as f:
-	f.write(version)
+    f.write(version)
 
 versions_info = json.load(open('update/versions.json'))
 if 'signature' in versions_info:
-	del versions_info['signature']
+    del versions_info['signature']
 
 new_version = {}
 
-filenames = {'bin': 'youtube-dl', 'exe': 'youtube-dl.exe', 'tar': 'youtube-dl-%s.tar.gz' % version}
+filenames = {
+    'bin': 'youtube-dl',
+    'exe': 'youtube-dl.exe',
+    'tar': 'youtube-dl-%s.tar.gz' % version}
+build_dir = os.path.join('..', '..', 'build', version)
 for key, filename in filenames.items():
-	print('Downloading and checksumming %s...' %filename)
-	url = 'http://youtube-dl.org/downloads/%s/%s' % (version, filename)
-	data = urllib.request.urlopen(url).read()
-	sha256sum = hashlib.sha256(data).hexdigest()
-	new_version[key] = (url, sha256sum)
+    fn = os.path.join(build_dir, filename)
+    with open(fn, 'rb') as f:
+        data = f.read()
+    if not data:
+        raise ValueError('File %s is empty!' % fn)
+    sha256sum = hashlib.sha256(data).hexdigest()
+    new_version[key] = (url, sha256sum)
 
 versions_info['versions'][version] = new_version
 versions_info['latest'] = version
 
-json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
+with open('update/versions.json', 'w') as jsonf:
+    json.dump(versions_info, jsonf, indent=4, sort_keys=True)

devscripts/gh-pages/update-feed.py

@@ -22,7 +22,7 @@ entry_template=textwrap.dedent("""
 									<atom:link href="http://rg3.github.io/youtube-dl" />
 									<atom:content type="xhtml">
 										<div xmlns="http://www.w3.org/1999/xhtml">
-											Downloads available at <a href="http://youtube-dl.org/downloads/@VERSION@/">http://youtube-dl.org/downloads/@VERSION@/</a>
+											Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
 										</div>
 									</atom:content>
 									<atom:author>
@@ -54,4 +54,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
 with open('update/releases.atom','w',encoding='utf-8') as atom_file:
 	atom_file.write(atom_template)
 
-

devscripts/gh-pages/update-sites.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python3
+
+import sys
+import os
+import textwrap
+
+# We must be able to import youtube_dl
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+import youtube_dl
+
+def main():
+    with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
+        template = tmplf.read()
+
+    ie_htmls = []
+    for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME):
+        ie_html = '<b>{}</b>'.format(ie.IE_NAME)
+        try:
+            ie_html += ': {}'.format(ie.IE_DESC)
+        except AttributeError:
+            pass
+        if ie.working() == False:
+            ie_html += ' (Currently broken)'
+        ie_htmls.append('<li>{}</li>'.format(ie_html))
+
+    template = template.replace('@SITES@', textwrap.indent('\n'.join(ie_htmls), '\t'))
+
+    with open('supportedsites.html', 'w', encoding='utf-8') as sitesf:
+        sitesf.write(template)
+
+if __name__ == '__main__':
+    main()

devscripts/release.sh

@@ -67,9 +67,11 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
 git checkout HEAD -- youtube-dl youtube-dl.exe
 
-/bin/echo -e "\n### Signing and uploading the new binaries to youtube-dl.org..."
+/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
 for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
-scp -r "build/$version" ytdl@youtube-dl.org:html/downloads/
+scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
+ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
+ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
 
 /bin/echo -e "\n### Now switching to gh-pages..."
 git clone --branch gh-pages --single-branch . build/gh-pages
@@ -83,6 +85,7 @@ ROOT=$(pwd)
     "$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem"
     "$ROOT/devscripts/gh-pages/generate-download.py"
     "$ROOT/devscripts/gh-pages/update-copyright.py"
+    "$ROOT/devscripts/gh-pages/update-sites.py"
     git add *.html *.html.in update
     git commit -m "release $version"
     git show HEAD

devscripts/youtube_genalgo.py

@@ -0,0 +1,109 @@
+#!/usr/bin/env python
+
+# Generate youtube signature algorithm from test cases
+
+import sys
+
+tests = [
+    # 92 - vflQw-fB4 2013/07/17
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~\"",
+     "mrtyuioplkjhgfdsazxcvbnq1234567890QWERTY}IOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]\"|:;"),
+    # 90
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`",
+     "mrtyuioplkjhgfdsazxcvbne1234567890QWER[YUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={`]}|"),
+    # 89 
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'",
+     "/?;:|}<[{=+-_)(*&^%$#@!MqBVCXZASDFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuyt"),
+    # 88 - vflapUV9V 2013/08/28
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
+     "ioplkjhgfdsazxcvbnm12<4567890QWERTYUIOZLKJHGFDSAeXCVBNM!@#$%^&*()_-+={[]}|:;?/>.3"),
+    # 87
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
+     "uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),
+    # 86 - vfluy6kdb 2013/09/06
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
+     "yuioplkjhgfdsazxcvbnm12345678q0QWrRTYUIOELKJHGFD-AZXCVBNM!@#$%^&*()_<+={[|};?/>.S"),
+    # 85
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
+     ".>/?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ0q876543r1mnbvcx9asdfghjklpoiuyt2"),
+    # 84 - vflg0g8PQ 2013/08/29 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
+     ">?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWq0987654321mnbvcxzasdfghjklpoiuytr"),
+    # 83
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
+     ".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
+    # 82 - vflZK4ZYR 2013/08/23
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
+     "wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>.<"),
+    # 81 - vflLC8JvQ 2013/07/25
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.",
+     "C>/?;}[{=+-(*&^%$#@!MNBVYXZASDFGHKLPOIU.TREWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
+    # 80 - vflZK4ZYR 2013/08/23 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>",
+     "wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>"),
+    # 79 - vflLC8JvQ 2013/07/25 (sporadic)
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/",
+     "Z?;}[{=+-(*&^%$#@!MNBVCXRASDFGHKLPOIUYT/EWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
+]
+
+tests_age_gate = [
+    # 86 - vflqinMWD
+    ("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
+     "ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"),
+]
+
+def find_matching(wrong, right):
+    idxs = [wrong.index(c) for c in right]
+    return compress(idxs)
+    return ('s[%d]' % i for i in idxs)
+
+def compress(idxs):
+    def _genslice(start, end, step):
+        starts = '' if start == 0 else str(start)
+        ends = ':%d' % (end+step)
+        steps = '' if step == 1 else (':%d' % step)
+        return 's[%s%s%s]' % (starts, ends, steps)
+
+    step = None
+    for i, prev in zip(idxs[1:], idxs[:-1]):
+        if step is not None:
+            if i - prev == step:
+                continue
+            yield _genslice(start, prev, step)
+            step = None
+            continue
+        if i - prev in [-1, 1]:
+            step = i - prev
+            start = prev
+            continue
+        else:
+            yield 's[%d]' % prev
+    if step is None:
+        yield 's[%d]' % i
+    else:
+        yield _genslice(start, i, step)
+
+def _assert_compress(inp, exp):
+    res = list(compress(inp))
+    if res != exp:
+        print('Got %r, expected %r' % (res, exp))
+        assert res == exp
+_assert_compress([0,2,4,6], ['s[0]', 's[2]', 's[4]', 's[6]'])
+_assert_compress([0,1,2,4,6,7], ['s[:3]', 's[4]', 's[6:8]'])
+_assert_compress([8,0,1,2,4,7,6,9], ['s[8]', 's[:3]', 's[4]', 's[7:5:-1]', 's[9]'])
+
+def gen(wrong, right, indent):
+    code = ' + '.join(find_matching(wrong, right))
+    return 'if len(s) == %d:\n%s    return %s\n' % (len(wrong), indent, code)
+
+def genall(tests):
+    indent = ' ' * 8
+    return indent + (indent + 'el').join(gen(wrong, right, indent) for wrong,right in tests)
+
+def main():
+    print(genall(tests))
+    print(u'    Age gate:')
+    print(genall(tests_age_gate))
+
+if __name__ == '__main__':
+    main()

setup.py

@@ -12,8 +12,9 @@ except ImportError:
     from distutils.core import setup
 
 try:
+    # This will create an exe that needs Microsoft Visual C++ 2008
+    # Redistributable Package
     import py2exe
-    """This will create an exe that needs Microsoft Visual C++ 2008 Redistributable Package"""
 except ImportError:
     if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
         print("Cannot import py2exe", file=sys.stderr)
@@ -26,13 +27,15 @@ py2exe_options = {
     "dist_dir": '.',
     "dll_excludes": ['w9xpopen.exe'],
 }
+
 py2exe_console = [{
     "script": "./youtube_dl/__main__.py",
     "dest_base": "youtube-dl",
 }]
+
 py2exe_params = {
     'console': py2exe_console,
-    'options': { "py2exe": py2exe_options },
+    'options': {"py2exe": py2exe_options},
     'zipfile': None
 }
 
@@ -41,30 +44,34 @@ if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
 else:
     params = {
         'scripts': ['bin/youtube-dl'],
-        'data_files': [('etc/bash_completion.d', ['youtube-dl.bash-completion']), # Installing system-wide would require sudo...
-                       ('share/doc/youtube_dl', ['README.txt']),
-                       ('share/man/man1/', ['youtube-dl.1'])]
+        'data_files': [  # Installing system-wide would require sudo...
+            ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
+            ('share/doc/youtube_dl', ['README.txt']),
+            ('share/man/man1/', ['youtube-dl.1'])
+        ]
     }
 
 # Get the version from youtube_dl/version.py without importing the package
-exec(compile(open('youtube_dl/version.py').read(), 'youtube_dl/version.py', 'exec'))
+exec(compile(open('youtube_dl/version.py').read(),
+             'youtube_dl/version.py', 'exec'))
 
 setup(
-    name = 'youtube_dl',
-    version = __version__,
-    description = 'YouTube video downloader',
-    long_description = 'Small command-line program to download videos from YouTube.com and other video sites.',
-    url = 'https://github.com/rg3/youtube-dl',
-    author = 'Ricardo Garcia',
-    maintainer = 'Philipp Hagemeister',
-    maintainer_email = 'phihag@phihag.de',
-    packages = ['youtube_dl', 'youtube_dl.extractor'],
+    name='youtube_dl',
+    version=__version__,
+    description='YouTube video downloader',
+    long_description='Small command-line program to download videos from'
+    ' YouTube.com and other video sites.',
+    url='https://github.com/rg3/youtube-dl',
+    author='Ricardo Garcia',
+    maintainer='Philipp Hagemeister',
+    maintainer_email='phihag@phihag.de',
+    packages=['youtube_dl', 'youtube_dl.extractor'],
 
     # Provokes warning on most systems (why?!)
-    #test_suite = 'nose.collector',
-    #test_requires = ['nosetest'],
+    # test_suite = 'nose.collector',
+    # test_requires = ['nosetest'],
 
-    classifiers = [
+    classifiers=[
         "Topic :: Multimedia :: Video",
         "Development Status :: 5 - Production/Stable",
         "Environment :: Console",

test/helper.py

@@ -0,0 +1,44 @@
+import io
+import json
+import os.path
+
+import youtube_dl.extractor
+from youtube_dl import YoutubeDL, YoutubeDLHandler
+from youtube_dl.utils import (
+    compat_cookiejar,
+    compat_urllib_request,
+)
+
+# General configuration (from __init__, not very elegant...)
+jar = compat_cookiejar.CookieJar()
+cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
+proxy_handler = compat_urllib_request.ProxyHandler()
+opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
+compat_urllib_request.install_opener(opener)
+
+PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
+with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+    parameters = json.load(pf)
+
+class FakeYDL(YoutubeDL):
+    def __init__(self):
+        self.result = []
+        # Different instances of the downloader can't share the same dictionary
+        # some test set the "sublang" parameter, which would break the md5 checks.
+        self.params = dict(parameters)
+    def to_screen(self, s):
+        print(s)
+    def trouble(self, s, tb=None):
+        raise Exception(s)
+    def download(self, x):
+        self.result.append(x)
+
+def get_testcases():
+    for ie in youtube_dl.extractor.gen_extractors():
+        t = getattr(ie, '_TEST', None)
+        if t:
+            t['name'] = type(ie).__name__[:-len('IE')]
+            yield t
+        for t in getattr(ie, '_TESTS', []):
+            t['name'] = type(ie).__name__[:-len('IE')]
+            yield t

test/test_all_urls.py

@@ -7,9 +7,19 @@ import unittest
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from youtube_dl.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE
+from youtube_dl.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE, gen_extractors
+from helper import get_testcases
 
 class TestAllURLsMatching(unittest.TestCase):
+    def setUp(self):
+        self.ies = gen_extractors()
+
+    def matching_ies(self, url):
+        return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']
+
+    def assertMatch(self, url, ie_list):
+        self.assertEqual(self.matching_ies(url), ie_list)
+
     def test_youtube_playlist_matching(self):
         self.assertTrue(YoutubePlaylistIE.suitable(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8'))
         self.assertTrue(YoutubePlaylistIE.suitable(u'UUBABnxM4Ar9ten8Mdjj1j0Q')) #585
@@ -23,12 +33,17 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_matching(self):
         self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
         self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+        self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
+        self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
 
     def test_youtube_channel_matching(self):
         self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM'))
         self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec'))
         self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos'))
 
+    def test_youtube_user_matching(self):
+        self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
+
     def test_justin_tv_channelid_matching(self):
         self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
         self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
@@ -49,6 +64,26 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
         self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
         self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
+        self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch_popup?v=BaW_jenozKc'), 'BaW_jenozKc')
+
+    def test_no_duplicates(self):
+        ies = gen_extractors()
+        for tc in get_testcases():
+            url = tc['url']
+            for ie in ies:
+                if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
+                    self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
+                else:
+                    self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
+
+    def test_keywords(self):
+        self.assertMatch(':ytsubs', ['youtube:subscriptions'])
+        self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
+        self.assertMatch(':thedailyshow', ['ComedyCentral'])
+        self.assertMatch(':tds', ['ComedyCentral'])
+        self.assertMatch(':colbertreport', ['ComedyCentral'])
+        self.assertMatch(':cr', ['ComedyCentral'])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -14,10 +14,8 @@ import binascii
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import youtube_dl.YoutubeDL
-import youtube_dl.extractor
 from youtube_dl.utils import *
 
-DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json')
 PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
 
 RETRIES = 3
@@ -56,8 +54,9 @@ def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
-with io.open(DEF_FILE, encoding='utf-8') as deff:
-    defs = json.load(deff)
+from helper import get_testcases
+defs = get_testcases()
+
 with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
     parameters = json.load(pf)
 
@@ -73,22 +72,23 @@ def generator(test_case):
 
     def test_template(self):
         ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
+        def print_skipping(reason):
+            print('Skipping %s: %s' % (test_case['name'], reason))
         if not ie._WORKING:
-            print('Skipping: IE marked as not _WORKING')
+            print_skipping('IE marked as not _WORKING')
             return
         if 'playlist' not in test_case and not test_case['file']:
-            print('Skipping: No output file specified')
+            print_skipping('No output file specified')
             return
         if 'skip' in test_case:
-            print('Skipping: {0}'.format(test_case['skip']))
+            print_skipping(test_case['skip'])
             return
 
         params = self.parameters.copy()
         params.update(test_case.get('params', {}))
 
         ydl = YoutubeDL(params)
-        for ie in youtube_dl.extractor.gen_extractors():
-            ydl.add_info_extractor(ie)
+        ydl.add_default_info_extractors()
         finished_hook_called = set()
         def _hook(status):
             if status['status'] == 'finished':
@@ -127,12 +127,11 @@ def generator(test_case):
                     info_dict = json.load(infof)
                 for (info_field, expected) in tc.get('info_dict', {}).items():
                     if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                        self.assertEqual(expected, 'md5:' + md5(info_dict.get(info_field)))
+                        got = 'md5:' + md5(info_dict.get(info_field))
                     else:
                         got = info_dict.get(info_field)
-                        self.assertEqual(
-                            expected, got,
-                            u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+                    self.assertEqual(expected, got,
+                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
                 # If checkable fields are missing from the test case, print the info_dict
                 test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
@@ -153,9 +152,14 @@ def generator(test_case):
     return test_template
 
 ### And add them to TestDownload
-for test_case in defs:
+for n, test_case in enumerate(defs):
     test_method = generator(test_case)
-    test_method.__name__ = "test_{0}".format(test_case["name"])
+    tname = 'test_' + str(test_case['name'])
+    i = 1
+    while hasattr(TestDownload, tname):
+        tname = 'test_'  + str(test_case['name']) + '_' + str(i)
+        i += 1
+    test_method.__name__ = tname
     setattr(TestDownload, test_method.__name__, test_method)
     del test_method
 

test/test_playlists.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python
+
+import sys
+import unittest
+import json
+
+# Allow direct execution
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.extractor import DailymotionPlaylistIE, VimeoChannelIE
+from youtube_dl.utils import *
+
+from helper import FakeYDL
+
+class TestPlaylists(unittest.TestCase):
+    def assertIsPlaylist(self, info):
+        """Make sure the info has '_type' set to 'playlist'"""
+        self.assertEqual(info['_type'], 'playlist')
+
+    def test_dailymotion_playlist(self):
+        dl = FakeYDL()
+        ie = DailymotionPlaylistIE(dl)
+        result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'SPORT')
+        self.assertTrue(len(result['entries']) > 20)
+
+    def test_vimeo_channel(self):
+        dl = FakeYDL()
+        ie = VimeoChannelIE(dl)
+        result = ie.extract('http://vimeo.com/channels/tributes')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Vimeo Tributes')
+        self.assertTrue(len(result['entries']) > 24)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_utils.py

@@ -4,6 +4,7 @@
 
 import sys
 import unittest
+import xml.etree.ElementTree
 
 # Allow direct execution
 import os
@@ -16,6 +17,7 @@ from youtube_dl.utils import unescapeHTML
 from youtube_dl.utils import orderedSet
 from youtube_dl.utils import DateRange
 from youtube_dl.utils import unified_strdate
+from youtube_dl.utils import find_xpath_attr
 
 if sys.version_info < (3, 0):
     _compat_str = lambda b: b.decode('unicode-escape')
@@ -112,5 +114,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 
+    def test_find_xpath_attr(self):
+        testxml = u'''<root>
+            <node/>
+            <node x="a"/>
+            <node x="a" y="c" />
+            <node x="b" y="d" />
+        </root>'''
+        doc = xml.etree.ElementTree.fromstring(testxml)
+
+        self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
+        self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
+        self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -8,32 +8,10 @@ import json
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE
+from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE, YoutubeShowIE
 from youtube_dl.utils import *
-from youtube_dl import YoutubeDL
 
-PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
-with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
-    parameters = json.load(pf)
-
-# General configuration (from __init__, not very elegant...)
-jar = compat_cookiejar.CookieJar()
-cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
-proxy_handler = compat_urllib_request.ProxyHandler()
-opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
-compat_urllib_request.install_opener(opener)
-
-class FakeYDL(YoutubeDL):
-    def __init__(self):
-        self.result = []
-        self.params = parameters
-    def to_screen(self, s):
-        print(s)
-    def trouble(self, s, tb=None):
-        raise Exception(s)
-    def extract_info(self, url):
-        self.result.append(url)
-        return url
+from helper import FakeYDL
 
 class TestYoutubeLists(unittest.TestCase):
     def assertIsPlaylist(self,info):
@@ -110,5 +88,11 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0]
         self.assertEqual(len(result['entries']), 2)
 
+    def test_youtube_show(self):
+        dl = FakeYDL()
+        ie = YoutubeShowIE(dl)
+        result = ie.extract('http://www.youtube.com/show/airdisasters')
+        self.assertTrue(len(result) >= 4)
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_subtitles.py

@@ -12,31 +12,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.utils import *
-from youtube_dl import YoutubeDL
-
-PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
-with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
-    parameters = json.load(pf)
-
-# General configuration (from __init__, not very elegant...)
-jar = compat_cookiejar.CookieJar()
-cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
-proxy_handler = compat_urllib_request.ProxyHandler()
-opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
-compat_urllib_request.install_opener(opener)
-
-class FakeYDL(YoutubeDL):
-    def __init__(self):
-        self.result = []
-        # Different instances of the downloader can't share the same dictionary
-        # some test set the "sublang" parameter, which would break the md5 checks.
-        self.params = dict(parameters)
-    def to_screen(self, s):
-        print(s)
-    def trouble(self, s, tb=None):
-        raise Exception(s)
-    def download(self, x):
-        self.result.append(x)
+from helper import FakeYDL
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
@@ -59,39 +35,47 @@ class TestYoutubeSubtitles(unittest.TestCase):
         DL.params['writesubtitles'] = True
         IE = YoutubeIE(DL)
         info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
+        sub = info_dict[0]['subtitles']['en']
+        self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
     def test_youtube_subtitles_it(self):
         DL = FakeYDL()
         DL.params['writesubtitles'] = True
-        DL.params['subtitleslang'] = 'it'
+        DL.params['subtitleslangs'] = ['it']
         IE = YoutubeIE(DL)
         info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d')
+        sub = info_dict[0]['subtitles']['it']
+        self.assertEqual(md5(sub), '164a51f16f260476a05b50fe4c2f161d')
     def test_youtube_onlysubtitles(self):
         DL = FakeYDL()
         DL.params['writesubtitles'] = True
         DL.params['onlysubtitles'] = True
         IE = YoutubeIE(DL)
         info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
+        sub = info_dict[0]['subtitles']['en']
+        self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
     def test_youtube_allsubtitles(self):
         DL = FakeYDL()
         DL.params['allsubtitles'] = True
         IE = YoutubeIE(DL)
         info_dict = IE.extract('QRS8MkLhQmM')
         subtitles = info_dict[0]['subtitles']
-        self.assertEqual(len(subtitles), 13)
-    def test_youtube_subtitles_format(self):
+        self.assertEqual(len(subtitles.keys()), 13)
+    def test_youtube_subtitles_sbv_format(self):
         DL = FakeYDL()
         DL.params['writesubtitles'] = True
         DL.params['subtitlesformat'] = 'sbv'
         IE = YoutubeIE(DL)
         info_dict = IE.extract('QRS8MkLhQmM')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b')
+        sub = info_dict[0]['subtitles']['en']
+        self.assertEqual(md5(sub), '13aeaa0c245a8bed9a451cb643e3ad8b')
+    def test_youtube_subtitles_vtt_format(self):
+        DL = FakeYDL()
+        DL.params['writesubtitles'] = True
+        DL.params['subtitlesformat'] = 'vtt'
+        IE = YoutubeIE(DL)
+        info_dict = IE.extract('QRS8MkLhQmM')
+        sub = info_dict[0]['subtitles']['en']
+        self.assertEqual(md5(sub), '356cdc577fde0c6783b9b822e7206ff7')
     def test_youtube_list_subtitles(self):
         DL = FakeYDL()
         DL.params['listsubtitles'] = True
@@ -100,12 +84,21 @@ class TestYoutubeSubtitles(unittest.TestCase):
         self.assertEqual(info_dict, None)
     def test_youtube_automatic_captions(self):
         DL = FakeYDL()
-        DL.params['writesubtitles'] = True
-        DL.params['subtitleslang'] = 'it'
+        DL.params['writeautomaticsub'] = True
+        DL.params['subtitleslangs'] = ['it']
         IE = YoutubeIE(DL)
         info_dict = IE.extract('8YoUxe5ncPo')
-        sub = info_dict[0]['subtitles'][0]
-        self.assertTrue(sub[2] is not None)
+        sub = info_dict[0]['subtitles']['it']
+        self.assertTrue(sub is not None)
+    def test_youtube_multiple_langs(self):
+        DL = FakeYDL()
+        DL.params['writesubtitles'] = True
+        langs = ['it', 'fr', 'de']
+        DL.params['subtitleslangs'] = langs
+        IE = YoutubeIE(DL)
+        subtitles = IE.extract('QRS8MkLhQmM')[0]['subtitles']
+        for lang in langs:
+            self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
 if __name__ == '__main__':
     unittest.main()

test/tests.json

@@ -1,664 +0,0 @@
-[
-  {
-    "name": "Youtube",
-    "url":  "http://www.youtube.com/watch?v=BaW_jenozKc",
-    "file":  "BaW_jenozKc.mp4",
-    "info_dict": {
-      "title": "youtube-dl test video \"'/\\ä↭𝕐",
-      "uploader": "Philipp Hagemeister",
-      "uploader_id": "phihag",
-      "upload_date": "20121002",
-      "description": "test chars:  \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
-    }
-  },
-  {
-    "name": "Dailymotion",
-    "md5":  "392c4b85a60a90dc4792da41ce3144eb",
-    "url":  "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech",
-    "file":  "x33vw9.mp4",
-    "info_dict": {
-      "uploader": "Alex and Van .",
-      "title": "Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
-    }
-  },
-  {
-    "name": "Metacafe",
-    "add_ie": ["Youtube"],
-    "url":  "http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
-    "file":  "_aUehQsCQtM.flv",
-    "info_dict": {
-      "upload_date": "20090102",
-      "title": "The Electric Company | \"Short I\" | PBS KIDS GO!",
-      "description": "md5:2439a8ef6d5a70e380c22f5ad323e5a8",
-      "uploader": "PBS",
-      "uploader_id": "PBS"
-    }
-  },
-  {
-    "name": "BlipTV",
-    "md5":  "b2d849efcf7ee18917e4b4d9ff37cafe",
-    "url":  "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352",
-    "file":  "5779306.m4v",
-    "info_dict": {
-      "upload_date": "20111205",
-      "description": "md5:9bc31f227219cde65e47eeec8d2dc596",
-      "uploader": "Comic Book Resources - CBR TV",
-      "title": "CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
-    }
-  },
-  {
-    "name": "XVideos",
-    "md5":  "1d0c835822f0a71a7bf011855db929d0",
-    "url":  "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
-    "file":  "939581.flv",
-    "info_dict": {
-      "title": "Funny Porns By >>>>S<<<<<< -1"
-    }
-  },
-  {
-    "name": "YouPorn",
-    "md5": "c37ddbaaa39058c76a7e86c6813423c1",
-    "url": "http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/",
-    "file": "505835.mp4",
-    "info_dict": {
-      "upload_date": "20101221",
-      "description": "Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
-      "uploader": "Ask Dan And Jennifer",
-      "title": "Sex Ed: Is It Safe To Masturbate Daily?"
-    }
-  },
-  {
-    "name": "Pornotube",
-    "md5": "374dd6dcedd24234453b295209aa69b6",
-    "url": "http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing",
-    "file": "1689755.flv",
-    "info_dict": {
-      "upload_date": "20090708",
-      "title": "Marilyn-Monroe-Bathing"
-    }
-  },
-  {
-    "name": "YouJizz",
-    "md5": "07e15fa469ba384c7693fd246905547c",
-    "url": "http://www.youjizz.com/videos/zeichentrick-1-2189178.html",
-    "file": "2189178.flv",
-    "info_dict": {
-      "title": "Zeichentrick 1"
-    }
-  },
-  {
-    "name": "Vimeo",
-    "md5":  "8879b6cc097e987f02484baf890129e5",
-    "url":  "http://vimeo.com/56015672",
-    "file": "56015672.mp4",
-    "info_dict": {
-      "title": "youtube-dl test video - ★ \" ' 幸 / \\ ä ↭ 𝕐",
-      "uploader": "Filippo Valsorda",
-      "uploader_id": "user7108434",
-      "upload_date": "20121220",
-      "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: ★ \" ' 幸 / \\ ä ↭ 𝕐"
-    }
-  },
-  {
-    "name": "Soundcloud",
-    "md5":  "ebef0a451b909710ed1d7787dddbf0d7",
-    "url":  "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy",
-    "file":  "62986583.mp3",
-    "info_dict": {
-      "upload_date": "20121011",
-      "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
-      "uploader": "E.T. ExTerrestrial Music",
-      "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
-    }
-  },
-  {
-    "name": "StanfordOpenClassroom",
-    "md5":  "544a9468546059d4e80d76265b0443b8",
-    "url":  "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
-    "file":  "PracticalUnix_intro-environment.mp4",
-    "info_dict": {
-      "title": "Intro Environment"
-    }
-  },
-  {
-    "name": "XNXX",
-    "md5":  "0831677e2b4761795f68d417e0b7b445",
-    "url":  "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_",
-    "file":  "1135332.flv",
-    "info_dict": {
-      "title": "lida » Naked Funny Actress  (5)"
-    }
-  },
-  {
-    "name": "Youku",
-    "url": "http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
-    "file": "XNDgyMDQ2NTQw_part00.flv",
-    "md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
-    "params": { "test": false },
-    "info_dict": {
-      "title": "youtube-dl test video \"'/\\ä↭𝕐"
-    }
-  },
-  {
-    "name": "NBA",
-    "url": "http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html",
-    "file": "0021200253-okc-bkn-recap.nba.mp4",
-    "md5": "c0edcfc37607344e2ff8f13c378c88a4",
-    "info_dict": {
-      "description": "Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.",
-      "title": "Thunder vs. Nets"
-    }
-  },
-  {
-    "name": "JustinTV",
-    "url": "http://www.twitch.tv/thegamedevhub/b/296128360",
-    "file": "296128360.flv",
-    "md5": "ecaa8a790c22a40770901460af191c9a",
-    "info_dict": {
-      "upload_date": "20110927",
-      "uploader_id": 25114803,
-      "uploader": "thegamedevhub",
-      "title": "Beginner Series - Scripting With Python Pt.1"
-    }
-  },
-  {
-    "name": "MyVideo",
-    "url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
-    "file": "8229274.flv",
-    "md5": "2d2753e8130479ba2cb7e0a37002053e",
-    "info_dict": {
-      "title": "bowling-fail-or-win"
-    }
-  },
-  {
-    "name": "Escapist",
-    "url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
-    "file": "6618-Breaking-Down-Baldurs-Gate.mp4",
-    "md5": "c6793dbda81388f4264c1ba18684a74d",
-    "info_dict": {
-      "description": "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
-      "uploader": "the-escapist-presents",
-      "title": "Breaking Down Baldur's Gate"
-    }
-  },
-  {
-    "name": "GooglePlus",
-    "url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
-    "file": "ZButuJc6CtH.flv",
-    "info_dict": {
-      "upload_date": "20120613",
-      "uploader": "井上ヨシマサ",
-      "title": "嘆きの天使 降臨"
-    }
-  },
-  {
-    "name": "FunnyOrDie",
-    "url": "http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version",
-    "file": "0732f586d7.mp4",
-    "md5": "f647e9e90064b53b6e046e75d0241fbd",
-    "info_dict": {
-      "description": "Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.",
-      "title": "Heart-Shaped Box: Literal Video Version"
-    }
-  },
-  {
-    "name": "Steam",
-    "url": "http://store.steampowered.com/video/105600/",
-    "playlist": [
-      {
-        "file": "81300.flv",
-        "md5": "f870007cee7065d7c76b88f0a45ecc07",
-        "info_dict": {
-            "title": "Terraria 1.1 Trailer"
-        }
-      },
-      {
-        "file": "80859.flv",
-        "md5": "61aaf31a5c5c3041afb58fb83cbb5751",
-        "info_dict": {
-          "title": "Terraria Trailer"
-        }
-      }
-    ]
-  },
-  {
-    "name": "Ustream",
-    "url": "http://www.ustream.tv/recorded/20274954",
-    "file": "20274954.flv",
-    "md5": "088f151799e8f572f84eb62f17d73e5c",
-    "info_dict": {
-        "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
-        "uploader": "Young Americans for Liberty"
-    }
-  },
-  {
-    "name": "InfoQ",
-    "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
-    "file": "12-jan-pythonthings.mp4",
-    "info_dict": {
-      "description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
-      "title": "A Few of My Favorite [Python] Things"
-    },
-    "params": {
-      "skip_download": true
-    }
-  },
-  {
-    "name": "ComedyCentral",
-    "url": "http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart",
-    "file": "422212.mp4",
-    "md5": "4e2f5cb088a83cd8cdb7756132f9739d",
-    "info_dict": {
-      "upload_date": "20121214",
-      "description": "Kristen Stewart",
-      "uploader": "thedailyshow",
-      "title": "thedailyshow-kristen-stewart part 1"
-    }
-  },
-  {
-    "name": "RBMARadio",
-    "url": "http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011",
-    "file": "ford-lopatin-live-at-primavera-sound-2011.mp3",
-    "md5": "6bc6f9bcb18994b4c983bc3bf4384d95",
-    "info_dict": {
-        "title": "Live at Primavera Sound 2011",
-        "description": "Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
-        "uploader": "Ford & Lopatin",
-        "uploader_id": "ford-lopatin",
-        "location": "Spain"
-    }
-  },
-  {
-    "name": "Facebook",
-    "url": "https://www.facebook.com/photo.php?v=120708114770723",
-    "file": "120708114770723.mp4",
-    "md5": "48975a41ccc4b7a581abd68651c1a5a8",
-    "info_dict": {
-      "title": "PEOPLE ARE AWESOME 2013",
-      "duration": 279
-    }
-  },
-  {
-    "name": "EightTracks",
-    "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
-    "playlist": [
-      {
-        "file": "11885610.m4a",
-        "md5": "96ce57f24389fc8734ce47f4c1abcc55",
-        "info_dict": {
-          "title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      },
-      {
-        "file": "11885608.m4a",
-        "md5": "4ab26f05c1f7291ea460a3920be8021f",
-        "info_dict": {
-          "title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-
-        }
-      },
-      {
-        "file": "11885679.m4a",
-        "md5": "d30b5b5f74217410f4689605c35d1fd7",
-        "info_dict": {
-          "title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      },
-      {
-        "file": "11885680.m4a",
-        "md5": "4eb0a669317cd725f6bbd336a29f923a",
-        "info_dict": {
-          "title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      },
-      {
-        "file": "11885682.m4a",
-        "md5": "1893e872e263a2705558d1d319ad19e8",
-        "info_dict": {
-          "title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      },
-      {
-        "file": "11885683.m4a",
-        "md5": "b673c46f47a216ab1741ae8836af5899",
-        "info_dict": {
-          "title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      },
-      {
-        "file": "11885684.m4a",
-        "md5": "1d74534e95df54986da7f5abf7d842b7",
-        "info_dict": {
-          "title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      },
-      {
-        "file": "11885685.m4a",
-        "md5": "f081f47af8f6ae782ed131d38b9cd1c0",
-        "info_dict": {
-          "title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
-          "uploader_id": "ytdl"
-        }
-      }
-    ]
-  },
-  {
-    "name": "Keek",
-    "url": "http://www.keek.com/ytdl/keeks/NODfbab",
-    "file": "NODfbab.mp4",
-    "md5": "9b0636f8c0f7614afa4ea5e4c6e57e83",
-    "info_dict": {
-      "uploader": "ytdl",
-      "title": "test chars: \"'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
-    }
-  },
-  {
-    "name": "TED",
-    "url": "http://www.ted.com/talks/dan_dennett_on_our_consciousness.html",
-    "file": "102.mp4",
-    "md5": "8cd9dfa41ee000ce658fd48fb5d89a61",
-    "info_dict": {
-        "title": "Dan Dennett: The illusion of consciousness",
-        "description": "md5:c6fa72e6eedbd938c9caf6b2702f5922"
-    }
-  },
-  {
-    "name": "MySpass",
-    "url": "http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/",
-    "file": "11741.mp4",
-    "md5": "0b49f4844a068f8b33f4b7c88405862b",
-    "info_dict": {
-      "description": "Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
-      "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
-    }
-  },
-  {
-    "name": "Generic",
-    "url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html",
-    "file": "13601338388002.mp4",
-    "md5": "85b90ccc9d73b4acd9138d3af4c27f89",
-    "info_dict": {
-      "uploader": "www.hodiho.fr",
-      "title": "Régis plante sa Jeep"
-    }
-  },
-  {
-    "name": "Spiegel",
-    "url": "http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html",
-    "file": "1259285.mp4",
-    "md5": "2c2754212136f35fb4b19767d242f66e",
-    "info_dict": {
-        "title": "Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
-    }
-  },
-  {
-    "name": "LiveLeak",
-    "md5":  "0813c2430bea7a46bf13acf3406992f4",
-    "url":  "http://www.liveleak.com/view?i=757_1364311680",
-    "file":  "757_1364311680.mp4",
-    "info_dict": {
-        "title": "Most unlucky car accident",
-        "description": "extremely bad day for this guy..!",
-        "uploader": "ljfriel2"
-    }
-  },
-  {
-    "name": "WorldStarHipHop",
-    "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
-    "file": "wshh6a7q1ny0G34ZwuIO.mp4",
-    "md5": "9d04de741161603bf7071bbf4e883186",
-    "info_dict": {
-        "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
-    }
-  },
-  {
-    "name": "ARD",
-    "url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640",
-    "file": "14077640.mp4",
-    "md5": "6ca8824255460c787376353f9e20bbd8",
-    "info_dict": {
-        "title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
-    },
-    "skip": "Requires rtmpdump"
-  },
-  {
-    "name": "Tumblr",
-    "url": "http://resigno.tumblr.com/post/53364321212/e-de-extrema-importancia-que-esse-video-seja",
-    "file": "53364321212.mp4",
-    "md5": "0716d3dd51baf68a28b40fdf1251494e",
-    "info_dict": {
-        "title": "Rafael Lemos | Tumblr"
-    }
-  },
-  {
-    "name": "SoundcloudSet",
-    "url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
-    "playlist":[
-      {
-        "file":"30510138.mp3",
-        "md5":"f9136bf103901728f29e419d2c70f55d",
-        "info_dict": {
-          "upload_date": "20111213",
-          "description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
-          "uploader": "The Royal Concept",
-          "title": "D-D-Dance"
-        }
-      },
-      {
-        "file":"47127625.mp3",
-        "md5":"09b6758a018470570f8fd423c9453dd8",
-        "info_dict": {
-          "upload_date": "20120521",
-          "description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
-          "uploader": "The Royal Concept",
-          "title": "The Royal Concept - Gimme Twice"
-        }
-      },
-      {
-        "file":"47127627.mp3",
-        "md5":"154abd4e418cea19c3b901f1e1306d9c",
-        "info_dict": {
-          "upload_date": "20120521",
-          "uploader": "The Royal Concept",
-          "title": "Goldrushed"
-        }
-      },
-      {
-        "file":"47127629.mp3",
-        "md5":"2f5471edc79ad3f33a683153e96a79c1",
-        "info_dict": {
-          "upload_date": "20120521",
-          "description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
-          "uploader": "The Royal Concept",
-          "title": "In the End"
-        }
-      },
-      {
-        "file":"47127631.mp3",
-        "md5":"f9ba87aa940af7213f98949254f1c6e2",
-        "info_dict": {
-          "upload_date": "20120521",
-          "description": "The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
-          "uploader": "The Royal Concept",
-          "title": "Knocked Up"
-        }
-      },
-      {
-        "file":"75206121.mp3",
-        "md5":"f9d1fe9406717e302980c30de4af9353",
-        "info_dict": {
-          "upload_date": "20130116",
-          "description": "The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central).  \r\nAs a gift to our fans we would like to offer you a free download of the track!  ",
-          "uploader": "The Royal Concept",
-          "title": "World On Fire"
-        }
-      }
-    ]
-  },
-  {
-    "name":"Bandcamp",
-    "url":"http://youtube-dl.bandcamp.com/track/youtube-dl-test-song",
-    "file":"1812978515.mp3",
-    "md5":"cdeb30cdae1921719a3cbcab696ef53c",
-    "info_dict": {
-      "title":"youtube-dl test song \"'/\\ä↭"
-    },
-    "skip": "There is a limit of 200 free downloads / month for the test song"
-  },
-  {
-    "name": "RedTube",
-    "url": "http://www.redtube.com/66418",
-    "file": "66418.mp4",
-    "md5": "7b8c22b5e7098a3e1c09709df1126d2d",
-    "info_dict":{
-      "title":"Sucked on a toilet"
-    }
-  },
-  {
-    "name": "Photobucket",
-    "url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0",
-    "file": "zpsc0c3b9fa.mp4",
-    "md5": "7dabfb92b0a31f6c16cebc0f8e60ff99",
-    "info_dict": {
-      "upload_date": "20130504",
-      "uploader": "rachaneronas",
-      "title": "Tired of Link Building? Try BacklinkMyDomain.com!"
-    }
-  },
-  {
-    "name": "Ina",
-    "url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html",
-    "file": "I12055569.mp4",
-    "md5": "a667021bf2b41f8dc6049479d9bb38a3",
-    "info_dict":{
-      "title":"François Hollande \"Je crois que c'est clair\""
-    }
-  },
-  {
-    "name": "Yahoo",
-    "url": "http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html",
-    "file": "214727115.flv",
-    "md5": "2e717f169c1be93d84d3794a00d4a325",
-    "info_dict": {
-        "title": "Julian Smith & Travis Legg Watch Julian Smith"
-    },
-    "skip": "Requires rtmpdump"
-  },
-  {
-    "name": "Howcast",
-    "url": "http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly",
-    "file": "390161.mp4",
-    "md5": "1d7ba54e2c9d7dc6935ef39e00529138",
-    "info_dict":{
-      "title":"How to Tie a Square Knot Properly",
-      "description":"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot."
-    }
-  },
-  {
-    "name": "Vine",
-    "url": "https://vine.co/v/b9KOOWX7HUx",
-    "file": "b9KOOWX7HUx.mp4",
-    "md5": "2f36fed6235b16da96ce9b4dc890940d",
-    "info_dict":{
-      "title": "Chicken.",
-      "uploader": "Jack Dorsey"
-    }
-  },
-  {
-    "name": "Flickr",
-    "url": "http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/",
-    "file": "5645318632.mp4",
-    "md5": "6fdc01adbc89d72fc9c4f15b4a4ba87b",
-    "info_dict":{
-      "title": "Dark Hollow Waterfalls",
-      "uploader_id": "forestwander-nature-pictures",
-      "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up."
-    }
-  },
-  {
-    "name": "Teamcoco",
-    "url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush",
-    "file": "19705.mp4",
-    "md5": "27b6f7527da5acf534b15f21b032656e",
-    "info_dict":{
-      "title": "Louis C.K. Interview Pt. 1 11/3/11",
-      "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
-    }
-  },
-  {
-    "name": "XHamster",
-    "url": "http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html",
-    "file": "1509445.flv",
-    "md5": "9f48e0e8d58e3076bb236ff412ab62fa",
-    "info_dict": {
-      "upload_date": "20121014",
-      "uploader_id": "Ruseful2011",
-      "title": "FemaleAgent Shy beauty takes the bait"
-    }
-  },
-  {
-    "name": "Hypem",
-    "url": "http://hypem.com/track/1v6ga/BODYWORK+-+TAME",
-    "file": "1v6ga.mp3",
-    "md5": "b9cc91b5af8995e9f0c1cee04c575828",
-    "info_dict":{
-      "title":"Tame"
-    }
-  },
-  {
-    "name": "Vbox7",
-    "url": "http://vbox7.com/play:249bb972c2",
-    "file": "249bb972c2.flv",
-    "md5": "9c70d6d956f888bdc08c124acc120cfe",
-    "info_dict":{
-      "title":"Смях! Чудо - чист за секунди - Скрита камера"
-    }
-  },
-  {
-    "name": "Gametrailers",
-    "url": "http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer",
-    "file": "zbvr8i.flv",
-    "md5": "c3edbc995ab4081976e16779bd96a878",
-    "info_dict": {
-        "title": "E3 2013: Debut Trailer"
-    },
-    "skip": "Requires rtmpdump"
-  },
-  {
-    "name": "Statigram",
-    "url": "http://statigr.am/p/484091715184808010_284179915",
-    "file": "484091715184808010_284179915.mp4",
-    "md5": "deda4ff333abe2e118740321e992605b",
-    "info_dict": {
-        "uploader_id": "videoseconds",
-        "title": "Instagram photo by @videoseconds (Videos)"
-    }
-  },
-  {
-    "name": "Break",
-    "url": "http://www.break.com/video/when-girls-act-like-guys-2468056",
-    "file": "2468056.mp4",
-    "md5": "a3513fb1547fba4fb6cfac1bffc6c46b",
-    "info_dict": {
-        "title": "When Girls Act Like D-Bags"
-    }
-  },
-  {
-    "name": "Vevo",
-    "url": "http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280",
-    "file": "GB1101300280.mp4",
-    "md5": "06bea460acb744eab74a9d7dcb4bfd61",
-    "info_dict": {
-        "title": "Somebody To Die For",
-        "upload_date": "20130624",
-        "uploader": "Hurts"
-    }
-  }
-]

youtube_dl/FileDownloader.py

@@ -63,6 +63,17 @@ class FileDownloader(object):
         converted = float(bytes) / float(1024 ** exponent)
         return '%.2f%s' % (converted, suffix)
 
+    @staticmethod
+    def format_seconds(seconds):
+        (mins, secs) = divmod(seconds, 60)
+        (hours, eta_mins) = divmod(mins, 60)
+        if hours > 99:
+            return '--:--:--'
+        if hours == 0:
+            return '%02d:%02d' % (mins, secs)
+        else:
+            return '%02d:%02d:%02d' % (hours, mins, secs)
+
     @staticmethod
     def calc_percent(byte_counter, data_len):
         if data_len is None:
@@ -78,10 +89,7 @@ class FileDownloader(object):
             return '--:--'
         rate = float(current) / dif
         eta = int((float(total) - float(current)) / rate)
-        (eta_mins, eta_secs) = divmod(eta, 60)
-        if eta_mins > 99:
-            return '--:--'
-        return '%02d:%02d' % (eta_mins, eta_secs)
+        return FileDownloader.format_seconds(eta)
 
     @staticmethod
     def calc_speed(start, now, bytes):
@@ -137,7 +145,7 @@ class FileDownloader(object):
         self.ydl.report_warning(*args, **kargs)
 
     def report_error(self, *args, **kargs):
-        self.ydl.error(*args, **kargs)
+        self.ydl.report_error(*args, **kargs)
 
     def slow_down(self, start_time, byte_counter):
         """Sleep if the download speed is over the rate limit."""
@@ -230,12 +238,14 @@ class FileDownloader(object):
         """Report it was impossible to resume download."""
         self.to_screen(u'[download] Unable to resume')
 
-    def report_finish(self):
+    def report_finish(self, data_len_str, tot_time):
         """Report download finished."""
         if self.params.get('noprogress', False):
             self.to_screen(u'[download] Download completed')
         else:
-            self.to_screen(u'')
+            clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
+            self.to_screen(u'\r%s[download] 100%% of %s in %s' %
+                (clear_line, data_len_str, self.format_seconds(tot_time)))
 
     def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
         self.report_destination(filename)
@@ -329,6 +339,35 @@ class FileDownloader(object):
             self.report_error(u'mplayer exited with code %d' % retval)
             return False
 
+    def _download_m3u8_with_ffmpeg(self, filename, url):
+        self.report_destination(filename)
+        tmpfilename = self.temp_name(filename)
+
+        args = ['ffmpeg', '-y', '-i', url, '-f', 'mp4', tmpfilename]
+        # Check for ffmpeg first
+        try:
+            subprocess.call(['ffmpeg', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+        except (OSError, IOError):
+            self.report_error(u'm3u8 download detected but "%s" could not be run' % args[0] )
+            return False
+
+        retval = subprocess.call(args)
+        if retval == 0:
+            fsize = os.path.getsize(encodeFilename(tmpfilename))
+            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
+            self.try_rename(tmpfilename, filename)
+            self._hook_progress({
+                'downloaded_bytes': fsize,
+                'total_bytes': fsize,
+                'filename': filename,
+                'status': 'finished',
+            })
+            return True
+        else:
+            self.to_stderr(u"\n")
+            self.report_error(u'ffmpeg exited with code %d' % retval)
+            return False
+
 
     def _do_download(self, filename, info_dict):
         url = info_dict['url']
@@ -354,6 +393,10 @@ class FileDownloader(object):
         if url.startswith('mms') or url.startswith('rtsp'):
             return self._download_with_mplayer(filename, url)
 
+        # m3u8 manifest are downloaded with ffmpeg
+        if determine_ext(url) == u'm3u8':
+            return self._download_m3u8_with_ffmpeg(filename, url)
+
         tmpfilename = self.temp_name(filename)
         stream = None
 
@@ -505,7 +548,7 @@ class FileDownloader(object):
             self.report_error(u'Did not get any data blocks')
             return False
         stream.close()
-        self.report_finish()
+        self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:
             raise ContentTooShortError(byte_counter, int(data_len))
         self.try_rename(tmpfilename, filename)

youtube_dl/PostProcessor.py

@@ -71,12 +71,17 @@ class FFmpegPostProcessor(PostProcessor):
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
         return dict((program, executable(program)) for program in programs)
 
-    def run_ffmpeg(self, path, out_path, opts):
+    def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
         if not self._exes['ffmpeg'] and not self._exes['avconv']:
             raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
-        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path)]
+
+        files_cmd = []
+        for path in input_paths:
+            files_cmd.extend(['-i', encodeFilename(path)])
+        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
                + opts +
                [encodeFilename(self._ffmpeg_filename_argument(out_path))])
+
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         stdout,stderr = p.communicate()
         if p.returncode != 0:
@@ -84,6 +89,9 @@ class FFmpegPostProcessor(PostProcessor):
             msg = stderr.strip().split('\n')[-1]
             raise FFmpegPostProcessorError(msg)
 
+    def run_ffmpeg(self, path, out_path, opts):
+        self.run_ffmpeg_multiple_files([path], out_path, opts)
+
     def _ffmpeg_filename_argument(self, fn):
         # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
         if fn.startswith(u'-'):
@@ -100,7 +108,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         self._nopostoverwrites = nopostoverwrites
 
     def get_audio_codec(self, path):
-        if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
+        if not self._exes['ffprobe'] and not self._exes['avprobe']:
+            raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')
         try:
             cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
             handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)
@@ -128,7 +137,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         try:
             FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
         except FFmpegPostProcessorError as err:
-            raise AudioConversionError(err.message)
+            raise AudioConversionError(err.msg)
 
     def run(self, information):
         path = information['filepath']
@@ -198,7 +207,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
         except:
             etype,e,tb = sys.exc_info()
             if isinstance(e, AudioConversionError):
-                msg = u'audio conversion failed: ' + e.message
+                msg = u'audio conversion failed: ' + e.msg
             else:
                 msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
             raise PostProcessingError(msg)
@@ -208,7 +217,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
             try:
                 os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
             except:
-                self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+                self._downloader.report_warning(u'Cannot update utime of audio file')
 
         information['filepath'] = new_path
         return self._nopostoverwrites,information
@@ -231,3 +240,227 @@ class FFmpegVideoConvertor(FFmpegPostProcessor):
         information['format'] = self._preferedformat
         information['ext'] = self._preferedformat
         return False,information
+
+
+class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
+    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+    _lang_map = {
+        'aa': 'aar',
+        'ab': 'abk',
+        'ae': 'ave',
+        'af': 'afr',
+        'ak': 'aka',
+        'am': 'amh',
+        'an': 'arg',
+        'ar': 'ara',
+        'as': 'asm',
+        'av': 'ava',
+        'ay': 'aym',
+        'az': 'aze',
+        'ba': 'bak',
+        'be': 'bel',
+        'bg': 'bul',
+        'bh': 'bih',
+        'bi': 'bis',
+        'bm': 'bam',
+        'bn': 'ben',
+        'bo': 'bod',
+        'br': 'bre',
+        'bs': 'bos',
+        'ca': 'cat',
+        'ce': 'che',
+        'ch': 'cha',
+        'co': 'cos',
+        'cr': 'cre',
+        'cs': 'ces',
+        'cu': 'chu',
+        'cv': 'chv',
+        'cy': 'cym',
+        'da': 'dan',
+        'de': 'deu',
+        'dv': 'div',
+        'dz': 'dzo',
+        'ee': 'ewe',
+        'el': 'ell',
+        'en': 'eng',
+        'eo': 'epo',
+        'es': 'spa',
+        'et': 'est',
+        'eu': 'eus',
+        'fa': 'fas',
+        'ff': 'ful',
+        'fi': 'fin',
+        'fj': 'fij',
+        'fo': 'fao',
+        'fr': 'fra',
+        'fy': 'fry',
+        'ga': 'gle',
+        'gd': 'gla',
+        'gl': 'glg',
+        'gn': 'grn',
+        'gu': 'guj',
+        'gv': 'glv',
+        'ha': 'hau',
+        'he': 'heb',
+        'hi': 'hin',
+        'ho': 'hmo',
+        'hr': 'hrv',
+        'ht': 'hat',
+        'hu': 'hun',
+        'hy': 'hye',
+        'hz': 'her',
+        'ia': 'ina',
+        'id': 'ind',
+        'ie': 'ile',
+        'ig': 'ibo',
+        'ii': 'iii',
+        'ik': 'ipk',
+        'io': 'ido',
+        'is': 'isl',
+        'it': 'ita',
+        'iu': 'iku',
+        'ja': 'jpn',
+        'jv': 'jav',
+        'ka': 'kat',
+        'kg': 'kon',
+        'ki': 'kik',
+        'kj': 'kua',
+        'kk': 'kaz',
+        'kl': 'kal',
+        'km': 'khm',
+        'kn': 'kan',
+        'ko': 'kor',
+        'kr': 'kau',
+        'ks': 'kas',
+        'ku': 'kur',
+        'kv': 'kom',
+        'kw': 'cor',
+        'ky': 'kir',
+        'la': 'lat',
+        'lb': 'ltz',
+        'lg': 'lug',
+        'li': 'lim',
+        'ln': 'lin',
+        'lo': 'lao',
+        'lt': 'lit',
+        'lu': 'lub',
+        'lv': 'lav',
+        'mg': 'mlg',
+        'mh': 'mah',
+        'mi': 'mri',
+        'mk': 'mkd',
+        'ml': 'mal',
+        'mn': 'mon',
+        'mr': 'mar',
+        'ms': 'msa',
+        'mt': 'mlt',
+        'my': 'mya',
+        'na': 'nau',
+        'nb': 'nob',
+        'nd': 'nde',
+        'ne': 'nep',
+        'ng': 'ndo',
+        'nl': 'nld',
+        'nn': 'nno',
+        'no': 'nor',
+        'nr': 'nbl',
+        'nv': 'nav',
+        'ny': 'nya',
+        'oc': 'oci',
+        'oj': 'oji',
+        'om': 'orm',
+        'or': 'ori',
+        'os': 'oss',
+        'pa': 'pan',
+        'pi': 'pli',
+        'pl': 'pol',
+        'ps': 'pus',
+        'pt': 'por',
+        'qu': 'que',
+        'rm': 'roh',
+        'rn': 'run',
+        'ro': 'ron',
+        'ru': 'rus',
+        'rw': 'kin',
+        'sa': 'san',
+        'sc': 'srd',
+        'sd': 'snd',
+        'se': 'sme',
+        'sg': 'sag',
+        'si': 'sin',
+        'sk': 'slk',
+        'sl': 'slv',
+        'sm': 'smo',
+        'sn': 'sna',
+        'so': 'som',
+        'sq': 'sqi',
+        'sr': 'srp',
+        'ss': 'ssw',
+        'st': 'sot',
+        'su': 'sun',
+        'sv': 'swe',
+        'sw': 'swa',
+        'ta': 'tam',
+        'te': 'tel',
+        'tg': 'tgk',
+        'th': 'tha',
+        'ti': 'tir',
+        'tk': 'tuk',
+        'tl': 'tgl',
+        'tn': 'tsn',
+        'to': 'ton',
+        'tr': 'tur',
+        'ts': 'tso',
+        'tt': 'tat',
+        'tw': 'twi',
+        'ty': 'tah',
+        'ug': 'uig',
+        'uk': 'ukr',
+        'ur': 'urd',
+        'uz': 'uzb',
+        've': 'ven',
+        'vi': 'vie',
+        'vo': 'vol',
+        'wa': 'wln',
+        'wo': 'wol',
+        'xh': 'xho',
+        'yi': 'yid',
+        'yo': 'yor',
+        'za': 'zha',
+        'zh': 'zho',
+        'zu': 'zul',
+    }
+
+    def __init__(self, downloader=None, subtitlesformat='srt'):
+        super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
+        self._subformat = subtitlesformat
+
+    @classmethod
+    def _conver_lang_code(cls, code):
+        """Convert language code from ISO 639-1 to ISO 639-2/T"""
+        return cls._lang_map.get(code[:2])
+
+    def run(self, information):
+        if information['ext'] != u'mp4':
+            self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
+            return True, information
+        sub_langs = [key for key in information['subtitles']]
+
+        filename = information['filepath']
+        input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]
+
+        opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
+        for (i, lang) in enumerate(sub_langs):
+            opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
+            lang_code = self._conver_lang_code(lang)
+            if lang_code is not None:
+                opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
+        opts.extend(['-f', 'mp4'])
+
+        temp_filename = filename + u'.temp'
+        self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
+        self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
+        os.remove(encodeFilename(filename))
+        os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
+        return True, information

youtube_dl/YoutubeDL.py

@@ -13,7 +13,7 @@ import time
 import traceback
 
 from .utils import *
-from .extractor import get_info_extractor
+from .extractor import get_info_extractor, gen_extractors
 from .FileDownloader import FileDownloader
 
 
@@ -46,6 +46,7 @@ class YoutubeDL(object):
 
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
+    videopassword:     Password for acces a video.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
@@ -71,10 +72,11 @@ class YoutubeDL(object):
     writeinfojson:     Write the video description to a .info.json file
     writethumbnail:    Write the thumbnail image to a file
     writesubtitles:    Write the video subtitles to a file
+    writeautomaticsub: Write the automatic subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video
     listsubtitles:     Lists all available subtitles for the video
-    subtitlesformat:   Subtitle format [sbv/srt] (default=srt)
-    subtitleslang:     Language of the subtitles to download
+    subtitlesformat:   Subtitle format [srt/sbv/vtt] (default=srt)
+    subtitleslangs:    List of languages of the subtitles to download
     keepvideo:         Keep the video file after post-processing
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
@@ -95,6 +97,7 @@ class YoutubeDL(object):
     def __init__(self, params):
         """Create a FileDownloader object with the given options."""
         self._ies = []
+        self._ies_instances = {}
         self._pps = []
         self._progress_hooks = []
         self._download_retcode = 0
@@ -109,8 +112,28 @@ class YoutubeDL(object):
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)
+        self._ies_instances[ie.ie_key()] = ie
         ie.set_downloader(self)
 
+    def get_info_extractor(self, ie_key):
+        """
+        Get an instance of an IE with name ie_key, it will try to get one from
+        the _ies list, if there's no instance it will create a new one and add
+        it to the extractor list.
+        """
+        ie = self._ies_instances.get(ie_key)
+        if ie is None:
+            ie = get_info_extractor(ie_key)()
+            self.add_info_extractor(ie)
+        return ie
+
+    def add_default_info_extractors(self):
+        """
+        Add the InfoExtractors returned by gen_extractors to the end of the list
+        """
+        for ie in gen_extractors():
+            self.add_info_extractor(ie)
+
     def add_post_processor(self, pp):
         """Add a PostProcessor object to the end of the chain."""
         self._pps.append(pp)
@@ -255,7 +278,7 @@ class YoutubeDL(object):
             self.report_error(u'Erroneous output template')
             return None
         except ValueError as err:
-            self.report_error(u'Insufficient system charset ' + repr(preferredencoding()))
+            self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
     def _match_entry(self, info_dict):
@@ -285,9 +308,7 @@ class YoutubeDL(object):
          '''
         
         if ie_key:
-            ie = get_info_extractor(ie_key)()
-            ie.set_downloader(self)
-            ies = [ie]
+            ies = [self.get_info_extractor(ie_key)]
         else:
             ies = self._ies
 
@@ -339,6 +360,7 @@ class YoutubeDL(object):
 
         result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
         if result_type == 'video':
+            ie_result.update(extra_info)
             if 'playlist' not in ie_result:
                 # It isn't part of a playlist
                 ie_result['playlist'] = None
@@ -438,7 +460,8 @@ class YoutubeDL(object):
         if self.params.get('forceid', False):
             compat_print(info_dict['id'])
         if self.params.get('forceurl', False):
-            compat_print(info_dict['url'])
+            # For RTMP URLs, also include the playpath
+            compat_print(info_dict['url'] + info_dict.get('play_path', u''))
         if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
             compat_print(info_dict['thumbnail'])
         if self.params.get('forcedescription', False) and 'description' in info_dict:
@@ -473,41 +496,28 @@ class YoutubeDL(object):
                 self.report_error(u'Cannot write description file ' + descfn)
                 return
 
-        if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
+        subtitles_are_requested = any([self.params.get('writesubtitles', False),
+                                       self.params.get('writeautomaticsub'),
+                                       self.params.get('allsubtitles', False)])
+
+        if  subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
             # subtitles download errors are already managed as troubles in relevant IE
             # that way it will silently go on when used with unsupporting IE
-            subtitle = info_dict['subtitles'][0]
-            (sub_error, sub_lang, sub) = subtitle
+            subtitles = info_dict['subtitles']
             sub_format = self.params.get('subtitlesformat')
-            if sub_error:
-                self.report_warning("Some error while getting the subtitles")
-            else:
+            for sub_lang in subtitles.keys():
+                sub = subtitles[sub_lang]
+                if sub is None:
+                    continue
                 try:
-                    sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+                    sub_filename = subtitles_filename(filename, sub_lang, sub_format)
                     self.report_writesubtitles(sub_filename)
                     with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
-                        subfile.write(sub)
+                            subfile.write(sub)
                 except (OSError, IOError):
                     self.report_error(u'Cannot write subtitles file ' + descfn)
                     return
 
-        if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
-            subtitles = info_dict['subtitles']
-            sub_format = self.params.get('subtitlesformat')
-            for subtitle in subtitles:
-                (sub_error, sub_lang, sub) = subtitle
-                if sub_error:
-                    self.report_warning("Some error while getting the subtitles")
-                else:
-                    try:
-                        sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
-                        self.report_writesubtitles(sub_filename)
-                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
-                                subfile.write(sub)
-                    except (OSError, IOError):
-                        self.report_error(u'Cannot write subtitles file ' + descfn)
-                        return
-
         if self.params.get('writeinfojson', False):
             infofn = filename + u'.info.json'
             self.report_writeinfojson(infofn)
@@ -519,10 +529,8 @@ class YoutubeDL(object):
                 return
 
         if self.params.get('writethumbnail', False):
-            if 'thumbnail' in info_dict:
-                thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2]
-                if not thumb_format:
-                    thumb_format = 'jpg'
+            if info_dict.get('thumbnail') is not None:
+                thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
                 thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
                 self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
                                (info_dict['extractor'], info_dict['id']))
@@ -539,7 +547,7 @@ class YoutubeDL(object):
                 try:
                     success = self.fd._do_download(filename, info_dict)
                 except (OSError, IOError) as err:
-                    raise UnavailableVideoError()
+                    raise UnavailableVideoError(err)
                 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                     self.report_error(u'unable to download video data: %s' % str(err))
                     return
@@ -586,7 +594,7 @@ class YoutubeDL(object):
                         # No clear decision yet, let IE decide
                         keep_video = keep_video_wish
             except PostProcessingError as e:
-                self.to_stderr(u'ERROR: ' + e.msg)
+                self.report_error(e.msg)
         if keep_video is False and not self.params.get('keepvideo', False):
             try:
                 self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename)

youtube_dl/__init__.py

@@ -25,7 +25,11 @@ __authors__  = (
     'M. Yasoob Ullah Khalid',
     'Julien Fraichard',
     'Johny Mo Swag',
-    )
+    'Axel Noack',
+    'Albert Kim',
+    'Pierre Rudloff',
+    'Huarong Huo',
+)
 
 __license__ = 'Public Domain'
 
@@ -33,6 +37,7 @@ import codecs
 import getpass
 import optparse
 import os
+import random
 import re
 import shlex
 import socket
@@ -41,6 +46,7 @@ import sys
 import warnings
 import platform
 
+
 from .utils import *
 from .update import update_self
 from .version import __version__
@@ -79,6 +85,9 @@ def parseOpts(overrideArguments=None):
 
         return "".join(opts)
 
+    def _comma_separated_values_options_callback(option, opt_str, value, parser):
+        setattr(parser.values, option.dest, value.split(','))
+
     def _find_term_columns():
         columns = os.environ.get('COLUMNS', None)
         if columns:
@@ -92,6 +101,16 @@ def parseOpts(overrideArguments=None):
             pass
         return None
 
+    def _hide_login_info(opts):
+        opts = list(opts)
+        for private_opt in ['-p', '--password', '-u', '--username']:
+            try:
+                i = opts.index(private_opt)
+                opts[i+1] = '<PRIVATE>'
+            except ValueError:
+                pass
+        return opts
+
     max_width = 80
     max_help_position = 80
 
@@ -116,6 +135,8 @@ def parseOpts(overrideArguments=None):
     selection      = optparse.OptionGroup(parser, 'Video Selection')
     authentication = optparse.OptionGroup(parser, 'Authentication Options')
     video_format   = optparse.OptionGroup(parser, 'Video Format Options')
+    subtitles      = optparse.OptionGroup(parser, 'Subtitle Options')
+    downloader     = optparse.OptionGroup(parser, 'Download Options')
     postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
     filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
     verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
@@ -125,18 +146,9 @@ def parseOpts(overrideArguments=None):
     general.add_option('-v', '--version',
             action='version', help='print program version and exit')
     general.add_option('-U', '--update',
-            action='store_true', dest='update_self', help='update this program to latest version')
+            action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
             action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
-    general.add_option('-r', '--rate-limit',
-            dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
-    general.add_option('-R', '--retries',
-            dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
-    general.add_option('--buffer-size',
-            dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is %default)', default="1024")
-    general.add_option('--no-resize-buffer',
-            action='store_true', dest='noresizebuffer',
-            help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
     general.add_option('--dump-user-agent',
             action='store_true', dest='dump_user_agent',
             help='display the current browser identification', default=False)
@@ -148,9 +160,12 @@ def parseOpts(overrideArguments=None):
     general.add_option('--list-extractors',
             action='store_true', dest='list_extractors',
             help='List all supported extractors and the URLs they would handle', default=False)
+    general.add_option('--extractor-descriptions',
+            action='store_true', dest='list_extractor_descriptions',
+            help='Output descriptions of all supported extractors', default=False)
     general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
-    general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
+
 
     selection.add_option('--playlist-start',
             dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
@@ -172,11 +187,13 @@ def parseOpts(overrideArguments=None):
             dest='password', metavar='PASSWORD', help='account password')
     authentication.add_option('-n', '--netrc',
             action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+    authentication.add_option('--video-password',
+            dest='videopassword', metavar='PASSWORD', help='video password (vimeo only)')
 
 
     video_format.add_option('-f', '--format',
             action='store', dest='format', metavar='FORMAT',
-            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18"')
+            help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -185,24 +202,40 @@ def parseOpts(overrideArguments=None):
             action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
     video_format.add_option('-F', '--list-formats',
             action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
-    video_format.add_option('--write-sub', '--write-srt',
+
+    subtitles.add_option('--write-sub', '--write-srt',
             action='store_true', dest='writesubtitles',
             help='write subtitle file (currently youtube only)', default=False)
-    video_format.add_option('--only-sub',
+    subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
+            action='store_true', dest='writeautomaticsub',
+            help='write automatic subtitle file (currently youtube only)', default=False)
+    subtitles.add_option('--only-sub',
             action='store_true', dest='skip_download',
             help='[deprecated] alias of --skip-download', default=False)
-    video_format.add_option('--all-subs',
+    subtitles.add_option('--all-subs',
             action='store_true', dest='allsubtitles',
-            help='downloads all the available subtitles of the video (currently youtube only)', default=False)
-    video_format.add_option('--list-subs',
+            help='downloads all the available subtitles of the video', default=False)
+    subtitles.add_option('--list-subs',
             action='store_true', dest='listsubtitles',
-            help='lists all available subtitles for the video (currently youtube only)', default=False)
-    video_format.add_option('--sub-format',
+            help='lists all available subtitles for the video', default=False)
+    subtitles.add_option('--sub-format',
             action='store', dest='subtitlesformat', metavar='FORMAT',
-            help='subtitle format [srt/sbv] (default=srt) (currently youtube only)', default='srt')
-    video_format.add_option('--sub-lang', '--srt-lang',
-            action='store', dest='subtitleslang', metavar='LANG',
-            help='language of the subtitles to download (optional) use IETF language tags like \'en\'')
+            help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
+    subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
+            action='callback', dest='subtitleslang', metavar='LANGS', type='str',
+            default=[], callback=_comma_separated_values_options_callback,
+            help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
+
+    downloader.add_option('-r', '--rate-limit',
+            dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
+    downloader.add_option('-R', '--retries',
+            dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
+    downloader.add_option('--buffer-size',
+            dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16k) (default is %default)', default="1024")
+    downloader.add_option('--no-resize-buffer',
+            action='store_true', dest='noresizebuffer',
+            help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False)
+    downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
 
     verbosity.add_option('-q', '--quiet',
             action='store_true', dest='quiet', help='activates quiet mode', default=False)
@@ -306,20 +339,24 @@ def parseOpts(overrideArguments=None):
             help='keeps the video file on disk after the post-processing; the video is erased by default')
     postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
             help='do not overwrite post-processed files; the post-processed files are overwritten by default')
+    postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
+            help='embed subtitles in the video (only for mp4 videos)')
 
 
     parser.add_option_group(general)
     parser.add_option_group(selection)
+    parser.add_option_group(downloader)
     parser.add_option_group(filesystem)
     parser.add_option_group(verbosity)
     parser.add_option_group(video_format)
+    parser.add_option_group(subtitles)
     parser.add_option_group(authentication)
     parser.add_option_group(postproc)
 
     if overrideArguments is not None:
         opts, args = parser.parse_args(overrideArguments)
         if opts.verbose:
-            print(u'[debug] Override config: ' + repr(overrideArguments))
+            sys.stderr.write(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
         xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
         if xdg_config_home:
@@ -328,13 +365,13 @@ def parseOpts(overrideArguments=None):
             userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
         systemConf = _readOptions('/etc/youtube-dl.conf')
         userConf = _readOptions(userConfFile)
-        commandLineConf = sys.argv[1:] 
+        commandLineConf = sys.argv[1:]
         argv = systemConf + userConf + commandLineConf
         opts, args = parser.parse_args(argv)
         if opts.verbose:
-            print(u'[debug] System config: ' + repr(systemConf))
-            print(u'[debug] User config: ' + repr(userConf))
-            print(u'[debug] Command-line args: ' + repr(commandLineConf))
+            sys.stderr.write(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
+            sys.stderr.write(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
+            sys.stderr.write(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
 
     return parser, opts, args
 
@@ -362,14 +399,14 @@ def _real_main(argv=None):
     # Set user agent
     if opts.user_agent is not None:
         std_headers['User-Agent'] = opts.user_agent
-    
+
     # Set referer
     if opts.referer is not None:
         std_headers['Referer'] = opts.referer
 
     # Dump user agent
     if opts.dump_user_agent:
-        print(std_headers['User-Agent'])
+        compat_print(std_headers['User-Agent'])
         sys.exit(0)
 
     # Batch file verification
@@ -383,6 +420,8 @@ def _real_main(argv=None):
             batchurls = batchfd.readlines()
             batchurls = [x.strip() for x in batchurls]
             batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+            if opts.verbose:
+                sys.stderr.write(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
     all_urls = batchurls + args
@@ -403,25 +442,41 @@ def _real_main(argv=None):
     proxy_handler = compat_urllib_request.ProxyHandler(proxies)
     https_handler = make_HTTPS_handler(opts)
     opener = compat_urllib_request.build_opener(https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
+    # Delete the default user-agent header, which would otherwise apply in
+    # cases where our custom HTTP handler doesn't come into play
+    # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
+    opener.addheaders =[]
     compat_urllib_request.install_opener(opener)
     socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
 
     extractors = gen_extractors()
 
     if opts.list_extractors:
-        for ie in extractors:
-            print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
+        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+            compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             all_urls = [url for url in all_urls if url not in matchedUrls]
             for mu in matchedUrls:
-                print(u'  ' + mu)
+                compat_print(u'  ' + mu)
         sys.exit(0)
+    if opts.list_extractor_descriptions:
+        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+            if not ie._WORKING:
+                continue
+            desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
+            if hasattr(ie, 'SEARCH_KEY'):
+                _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
+                _COUNTS = (u'', u'5', u'10', u'all')
+                desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
+            compat_print(desc)
+        sys.exit(0)
+
 
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
         parser.error(u'using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
-        print(u'WARNING: account username missing')
+        parser.error(u' account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error(u'using output template conflicts with using title, video ID or auto number')
     if opts.usetitle and opts.useid:
@@ -498,6 +553,7 @@ def _real_main(argv=None):
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
+        'videopassword': opts.videopassword,
         'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
@@ -533,10 +589,11 @@ def _real_main(argv=None):
         'writeinfojson': opts.writeinfojson,
         'writethumbnail': opts.writethumbnail,
         'writesubtitles': opts.writesubtitles,
+        'writeautomaticsub': opts.writeautomaticsub,
         'allsubtitles': opts.allsubtitles,
         'listsubtitles': opts.listsubtitles,
         'subtitlesformat': opts.subtitlesformat,
-        'subtitleslang': opts.subtitleslang,
+        'subtitleslangs': opts.subtitleslang,
         'matchtitle': decodeOption(opts.matchtitle),
         'rejecttitle': decodeOption(opts.rejecttitle),
         'max_downloads': opts.max_downloads,
@@ -551,27 +608,33 @@ def _real_main(argv=None):
         })
 
     if opts.verbose:
-        ydl.to_screen(u'[debug] youtube-dl version ' + __version__)
+        sys.stderr.write(u'[debug] youtube-dl version ' + __version__ + u'\n')
         try:
-            sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE, stderr=subprocess.PIPE,
-                                  cwd=os.path.dirname(os.path.abspath(__file__)))
+            sp = subprocess.Popen(
+                ['git', 'rev-parse', '--short', 'HEAD'],
+                stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+                cwd=os.path.dirname(os.path.abspath(__file__)))
             out, err = sp.communicate()
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
-                ydl.to_screen(u'[debug] Git HEAD: ' + out)
+                sys.stderr.write(u'[debug] Git HEAD: ' + out + u'\n')
         except:
-            pass
-        ydl.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()))
-        ydl.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
+            try:
+                sys.exc_clear()
+            except:
+                pass
+        sys.stderr.write(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
+        sys.stderr.write(u'[debug] Proxy map: ' + str(proxy_handler.proxies) + u'\n')
 
-    for extractor in extractors:
-        ydl.add_info_extractor(extractor)
+    ydl.add_default_info_extractors()
 
     # PostProcessors
     if opts.extractaudio:
         ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
     if opts.recodevideo:
         ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
+    if opts.embedsubtitles:
+        ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
 
     # Update version
     if opts.update_self:

youtube_dl/aes.py

@@ -0,0 +1,202 @@
+__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text']
+
+import base64
+from math import ceil
+
+from .utils import bytes_to_intlist, intlist_to_bytes
+
+BLOCK_SIZE_BYTES = 16
+
+def aes_ctr_decrypt(data, key, counter):
+    """
+    Decrypt with aes in counter mode
+    
+    @param {int[]} data        cipher
+    @param {int[]} key         16/24/32-Byte cipher key
+    @param {instance} counter  Instance whose next_value function (@returns {int[]}  16-Byte block)
+                               returns the next counter block
+    @returns {int[]}           decrypted data
+    """
+    expanded_key = key_expansion(key)
+    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
+    
+    decrypted_data=[]
+    for i in range(block_count):
+        counter_block = counter.next_value()
+        block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
+        block += [0]*(BLOCK_SIZE_BYTES - len(block))
+        
+        cipher_counter_block = aes_encrypt(counter_block, expanded_key)
+        decrypted_data += xor(block, cipher_counter_block)
+    decrypted_data = decrypted_data[:len(data)]
+    
+    return decrypted_data
+
+def key_expansion(data):
+    """
+    Generate key schedule
+    
+    @param {int[]} data  16/24/32-Byte cipher key
+    @returns {int[]}     176/208/240-Byte expanded key 
+    """
+    data = data[:] # copy
+    rcon_iteration = 1
+    key_size_bytes = len(data)
+    expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
+    
+    while len(data) < expanded_key_size_bytes:
+        temp = data[-4:]
+        temp = key_schedule_core(temp, rcon_iteration)
+        rcon_iteration += 1
+        data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        for _ in range(3):
+            temp = data[-4:]
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        if key_size_bytes == 32:
+            temp = data[-4:]
+            temp = sub_bytes(temp)
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+        
+        for _ in range(3 if key_size_bytes == 32  else 2 if key_size_bytes == 24 else 0):
+            temp = data[-4:]
+            data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
+    data = data[:expanded_key_size_bytes]
+    
+    return data
+
+def aes_encrypt(data, expanded_key):
+    """
+    Encrypt one block with aes
+    
+    @param {int[]} data          16-Byte state
+    @param {int[]} expanded_key  176/208/240-Byte expanded key 
+    @returns {int[]}             16-Byte cipher
+    """
+    rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
+    
+    data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
+    for i in range(1, rounds+1):
+        data = sub_bytes(data)
+        data = shift_rows(data)
+        if i != rounds:
+            data = mix_columns(data)
+        data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
+    
+    return data
+
+def aes_decrypt_text(data, password, key_size_bytes):
+    """
+    Decrypt text
+    - The first 8 Bytes of decoded 'data' are the 8 high Bytes of the counter
+    - The cipher key is retrieved by encrypting the first 16 Byte of 'password'
+      with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
+    - Mode of operation is 'counter'
+    
+    @param {str} data                    Base64 encoded string
+    @param {str,unicode} password        Password (will be encoded with utf-8)
+    @param {int} key_size_bytes          Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
+    @returns {str}                       Decrypted data
+    """
+    NONCE_LENGTH_BYTES = 8
+    
+    data = bytes_to_intlist(base64.b64decode(data))
+    password = bytes_to_intlist(password.encode('utf-8'))
+    
+    key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password))
+    key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
+    
+    nonce = data[:NONCE_LENGTH_BYTES]
+    cipher = data[NONCE_LENGTH_BYTES:]
+    
+    class Counter:
+        __value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
+        def next_value(self):
+            temp = self.__value
+            self.__value = inc(self.__value)
+            return temp
+    
+    decrypted_data = aes_ctr_decrypt(cipher, key, Counter())
+    plaintext = intlist_to_bytes(decrypted_data)
+    
+    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,
+        0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
+        0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
+        0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
+        0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
+        0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
+        0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
+        0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
+        0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
+        0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
+        0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
+        0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
+        0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
+        0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
+        0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
+MIX_COLUMN_MATRIX = ((2,3,1,1),
+                     (1,2,3,1),
+                     (1,1,2,3),
+                     (3,1,1,2))
+
+def sub_bytes(data):
+    return [SBOX[x] for x in data]
+
+def rotate(data):
+    return data[1:] + [data[0]]
+
+def key_schedule_core(data, rcon_iteration):
+    data = rotate(data)
+    data = sub_bytes(data)
+    data[0] = data[0] ^ RCON[rcon_iteration]
+    
+    return data
+
+def xor(data1, data2):
+    return [x^y for x, y in zip(data1, data2)]
+
+def mix_column(data):
+    data_mixed = []
+    for row in range(4):
+        mixed = 0
+        for column in range(4):
+            addend = data[column]
+            if MIX_COLUMN_MATRIX[row][column] in (2,3):
+                addend <<= 1
+                if addend > 0xff:
+                    addend &= 0xff
+                    addend ^= 0x1b
+                if MIX_COLUMN_MATRIX[row][column] == 3:
+                    addend ^= data[column]
+            mixed ^= addend & 0xff
+        data_mixed.append(mixed)
+    return data_mixed
+
+def mix_columns(data):
+    data_mixed = []
+    for i in range(4):
+        column = data[i*4 : (i+1)*4]
+        data_mixed += mix_column(column)
+    return data_mixed
+
+def shift_rows(data):
+    data_shifted = []
+    for column in range(4):
+        for row in range(4):
+            data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
+    return data_shifted
+
+def inc(data):
+    data = data[:] # copy
+    for i in range(len(data)-1,-1,-1):
+        if data[i] == 255:
+            data[i] = 0
+        else:
+            data[i] = data[i] + 1
+            break
+    return data

youtube_dl/extractor/__init__.py

@@ -1,134 +1,143 @@
-
+from .appletrailers import AppleTrailersIE
+from .addanime import AddAnimeIE
+from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE
 from .arte import ArteTvIE
+from .auengine import AUEngineIE
 from .bandcamp import BandcampIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .breakcom import BreakIE
-from .comedycentral import ComedyCentralIE
+from .brightcove import BrightcoveIE
+from .c56 import C56IE
+from .canalplus import CanalplusIE
+from .canalc2 import Canalc2IE
+from .cnn import CNNIE
 from .collegehumor import CollegeHumorIE
-from .dailymotion import DailymotionIE
+from .comedycentral import ComedyCentralIE
+from .condenast import CondeNastIE
+from .criterion import CriterionIE
+from .cspan import CSpanIE
+from .dailymotion import DailymotionIE, DailymotionPlaylistIE
+from .daum import DaumIE
 from .depositfiles import DepositFilesIE
+from .dotsub import DotsubIE
+from .dreisat import DreiSatIE
+from .defense import DefenseGouvFrIE
+from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .escapist import EscapistIE
+from .exfm import ExfmIE
 from .facebook import FacebookIE
 from .flickr import FlickrIE
+from .freesound import FreesoundIE
 from .funnyordie import FunnyOrDieIE
+from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .hark import HarkIE
+from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .hypem import HypemIE
+from .ign import IGNIE, OneUPIE
 from .ina import InaIE
 from .infoq import InfoQIE
+from .instagram import InstagramIE
+from .jeuxvideo import JeuxVideoIE
+from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
+from .kankan import KankanIE
 from .keek import KeekIE
 from .liveleak import LiveLeakIE
+from .livestream import LivestreamIE
 from .metacafe import MetacafeIE
+from .mit import TechTVMITIE, MITIE
 from .mixcloud import MixcloudIE
 from .mtv import MTVIE
+from .muzu import MuzuTVIE
 from .myspass import MySpassIE
 from .myvideo import MyVideoIE
+from .naver import NaverIE
 from .nba import NBAIE
-from .statigram import StatigramIE
+from .nbc import NBCNewsIE
+from .ooyala import OoyalaIE
+from .orf import ORFIE
+from .pbs import PBSIE
 from .photobucket import PhotobucketIE
 from .pornotube import PornotubeIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
+from .ringtv import RingTVIE
+from .ro220 import Ro220IE
+from .roxwel import RoxwelIE
+from .rtlnow import RTLnowIE
+from .sina import SinaIE
+from .slashdot import SlashdotIE
+from .sohu import SohuIE
 from .soundcloud import SoundcloudIE, SoundcloudSetIE
 from .spiegel import SpiegelIE
 from .stanfordoc import StanfordOpenClassroomIE
+from .statigram import StatigramIE
 from .steam import SteamIE
 from .teamcoco import TeamcocoIE
 from .ted import TEDIE
+from .tf1 import TF1IE
+from .thisav import ThisAVIE
+from .traileraddict import TrailerAddictIE
+from .trilulilu import TriluliluIE
+from .tudou import TudouIE
 from .tumblr import TumblrIE
+from .tutv import TutvIE
+from .unistra import UnistraIE
 from .ustream import UstreamIE
 from .vbox7 import Vbox7IE
+from .veehd import VeeHDIE
+from .veoh import VeohIE
 from .vevo import VevoIE
-from .vimeo import VimeoIE
+from .videofyme import VideofyMeIE
+from .vimeo import VimeoIE, VimeoChannelIE
 from .vine import VineIE
+from .wat import WatIE
+from .weibo import WeiboIE
+from .wimp import WimpIE
 from .worldstarhiphop import WorldStarHipHopIE
-from .xnxx import XNXXIE
 from .xhamster import XHamsterIE
+from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .yahoo import YahooIE, YahooSearchIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .youporn import YouPornIE
-from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
+from .youtube import (
+    YoutubeIE,
+    YoutubePlaylistIE,
+    YoutubeSearchIE,
+    YoutubeUserIE,
+    YoutubeChannelIE,
+    YoutubeShowIE,
+    YoutubeSubscriptionsIE,
+    YoutubeRecommendedIE,
+    YoutubeWatchLaterIE,
+    YoutubeFavouritesIE,
+)
 from .zdf import ZDFIE
 
+
+_ALL_CLASSES = [
+    klass
+    for name, klass in globals().items()
+    if name.endswith('IE') and name != 'GenericIE'
+]
+_ALL_CLASSES.append(GenericIE)
+
+
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
     The order does matter; the first extractor matched is the one handling the URL.
     """
-    return [
-        YoutubePlaylistIE(),
-        YoutubeChannelIE(),
-        YoutubeUserIE(),
-        YoutubeSearchIE(),
-        YoutubeIE(),
-        MetacafeIE(),
-        DailymotionIE(),
-        GoogleSearchIE(),
-        PhotobucketIE(),
-        YahooIE(),
-        YahooSearchIE(),
-        DepositFilesIE(),
-        FacebookIE(),
-        BlipTVIE(),
-        BlipTVUserIE(),
-        VimeoIE(),
-        MyVideoIE(),
-        ComedyCentralIE(),
-        EscapistIE(),
-        CollegeHumorIE(),
-        XVideosIE(),
-        SoundcloudSetIE(),
-        SoundcloudIE(),
-        InfoQIE(),
-        MixcloudIE(),
-        StanfordOpenClassroomIE(),
-        MTVIE(),
-        YoukuIE(),
-        XNXXIE(),
-        YouJizzIE(),
-        PornotubeIE(),
-        YouPornIE(),
-        GooglePlusIE(),
-        ArteTvIE(),
-        NBAIE(),
-        WorldStarHipHopIE(),
-        JustinTVIE(),
-        FunnyOrDieIE(),
-        SteamIE(),
-        UstreamIE(),
-        RBMARadioIE(),
-        EightTracksIE(),
-        KeekIE(),
-        TEDIE(),
-        MySpassIE(),
-        SpiegelIE(),
-        LiveLeakIE(),
-        ARDIE(),
-        ZDFIE(),
-        TumblrIE(),
-        BandcampIE(),
-        RedTubeIE(),
-        InaIE(),
-        HowcastIE(),
-        VineIE(),
-        FlickrIE(),
-        TeamcocoIE(),
-        XHamsterIE(),
-        HypemIE(),
-        Vbox7IE(),
-        GametrailersIE(),
-        StatigramIE(),
-        BreakIE(),
-        VevoIE(),
-        GenericIE()
-    ]
+    return [klass() for klass in _ALL_CLASSES]
+
 
 def get_info_extractor(ie_name):
     """Returns the info extractor class with the given ie_name"""

youtube_dl/extractor/addanime.py

@@ -0,0 +1,75 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_HTTPError,
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+
+    ExtractorError,
+)
+
+
+class AddAnimeIE(InfoExtractor):
+
+    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
+    IE_NAME = u'AddAnime'
+    _TEST = {
+        u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
+        u'file': u'24MR3YO5SAS9.flv',
+        u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1',
+        u'info_dict': {
+            u"description": u"One Piece 606",
+            u"title": u"One Piece 606"
+        }
+    }
+
+    def _real_extract(self, url):
+        try:
+            mobj = re.match(self._VALID_URL, url)
+            video_id = mobj.group('video_id')
+            webpage = self._download_webpage(url, video_id)
+        except ExtractorError as ee:
+            if not isinstance(ee.cause, compat_HTTPError):
+                raise
+
+            redir_webpage = ee.cause.read().decode('utf-8')
+            action = self._search_regex(
+                r'<form id="challenge-form" action="([^"]+)"',
+                redir_webpage, u'Redirect form')
+            vc = self._search_regex(
+                r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
+                redir_webpage, u'redirect vc value')
+            av = re.search(
+                r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
+                redir_webpage)
+            if av is None:
+                raise ExtractorError(u'Cannot find redirect math task')
+            av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
+
+            parsed_url = compat_urllib_parse_urlparse(url)
+            av_val = av_res + len(parsed_url.netloc)
+            confirm_url = (
+                parsed_url.scheme + u'://' + parsed_url.netloc +
+                action + '?' +
+                compat_urllib_parse.urlencode({
+                    'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
+            self._download_webpage(
+                confirm_url, video_id,
+                note=u'Confirming after redirect')
+            webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
+                                       webpage, u'video file URL')
+        video_title = self._og_search_title(webpage)
+        video_description = self._og_search_description(webpage)
+
+        return {
+            '_type': 'video',
+            'id':  video_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': video_title,
+            'description': video_description
+        }

youtube_dl/extractor/appletrailers.py

@@ -0,0 +1,166 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class AppleTrailersIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+    _TEST = {
+        u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
+        u"playlist": [
+            {
+                u"file": u"manofsteel-trailer4.mov",
+                u"md5": u"11874af099d480cc09e103b189805d5f",
+                u"info_dict": {
+                    u"duration": 111,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg",
+                    u"title": u"Trailer 4",
+                    u"upload_date": u"20130523",
+                    u"uploader_id": u"wb",
+                },
+            },
+            {
+                u"file": u"manofsteel-trailer3.mov",
+                u"md5": u"07a0a262aae5afe68120eed61137ab34",
+                u"info_dict": {
+                    u"duration": 182,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg",
+                    u"title": u"Trailer 3",
+                    u"upload_date": u"20130417",
+                    u"uploader_id": u"wb",
+                },
+            },
+            {
+                u"file": u"manofsteel-trailer.mov",
+                u"md5": u"e401fde0813008e3307e54b6f384cff1",
+                u"info_dict": {
+                    u"duration": 148,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg",
+                    u"title": u"Trailer",
+                    u"upload_date": u"20121212",
+                    u"uploader_id": u"wb",
+                },
+            },
+            {
+                u"file": u"manofsteel-teaser.mov",
+                u"md5": u"76b392f2ae9e7c98b22913c10a639c97",
+                u"info_dict": {
+                    u"duration": 93,
+                    u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg",
+                    u"title": u"Teaser",
+                    u"upload_date": u"20120721",
+                    u"uploader_id": u"wb",
+                },
+            }
+        ]
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        movie = mobj.group('movie')
+        uploader_id = mobj.group('company')
+
+        playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc'
+        playlist_snippet = self._download_webpage(playlist_url, movie)
+        playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet)
+        playlist_html = u'<html>' + playlist_cleaned + u'</html>'
+
+        size_cache = {}
+
+        doc = xml.etree.ElementTree.fromstring(playlist_html)
+        playlist = []
+        for li in doc.findall('./div/ul/li'):
+            title = li.find('.//h3').text
+            video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
+            thumbnail = li.find('.//img').attrib['src']
+
+            date_el = li.find('.//p')
+            upload_date = None
+            m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text)
+            if m:
+                upload_date = u'20' + m.group('year') + m.group('month') + m.group('day')
+            runtime_el = date_el.find('./br')
+            m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail)
+            duration = None
+            if m:
+                duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
+
+            formats = []
+            for formats_el in li.findall('.//a'):
+                if formats_el.attrib['class'] != 'OverlayPanel':
+                    continue
+                target = formats_el.attrib['target']
+
+                format_code = formats_el.text
+                if 'Automatic' in format_code:
+                    continue
+
+                size_q = formats_el.attrib['href']
+                size_id = size_q.rpartition('#videos-')[2]
+                if size_id not in size_cache:
+                    size_url = url + size_q
+                    sizepage_html = self._download_webpage(
+                        size_url, movie,
+                        note=u'Downloading size info %s' % size_id,
+                        errnote=u'Error while downloading size info %s' % size_id,
+                    )
+                    _doc = xml.etree.ElementTree.fromstring(sizepage_html)
+                    size_cache[size_id] = _doc
+
+                sizepage_doc = size_cache[size_id]
+                links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a')
+                for vid_a in links:
+                    href = vid_a.get('href')
+                    if not href.endswith(target):
+                        continue
+                    detail_q = href.partition('#')[0]
+                    detail_url = url + '/' + detail_q
+
+                    m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q)
+                    detail_id = m.group('detail_id')
+
+                    detail_html = self._download_webpage(
+                        detail_url, movie,
+                        note=u'Downloading detail %s %s' % (detail_id, size_id),
+                        errnote=u'Error while downloading detail %s %s' % (detail_id, size_id)
+                    )
+                    detail_doc = xml.etree.ElementTree.fromstring(detail_html)
+                    movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a')
+                    assert movie_link_el.get('class') == 'movieLink'
+                    movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h')
+                    ext = determine_ext(movie_link)
+                    assert ext == 'mov'
+
+                    formats.append({
+                        'format': format_code,
+                        'ext': ext,
+                        'url': movie_link,
+                    })
+
+            info = {
+                '_type': 'video',
+                'id': video_id,
+                'title': title,
+                'formats': formats,
+                'title': title,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'upload_date': upload_date,
+                'uploader_id': uploader_id,
+                'user_agent': 'QuickTime compatible (youtube-dl)',
+            }
+            # TODO: Remove when #980 has been merged
+            info['url'] = formats[-1]['url']
+            info['ext'] = formats[-1]['ext']
+
+            playlist.append(info)
+
+        return {
+            '_type': 'playlist',
+            'id': movie,
+            'entries': playlist,
+        }

youtube_dl/extractor/archiveorg.py

@@ -0,0 +1,67 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    unified_strdate,
+)
+
+
+class ArchiveOrgIE(InfoExtractor):
+    IE_NAME = 'archive.org'
+    IE_DESC = 'archive.org videos'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _TEST = {
+        u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
+        u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
+        u'md5': u'8af1d4cf447933ed3c7f4871162602db',
+        u'info_dict': {
+            u"title": u"1968 Demo - FJCC Conference Presentation Reel #1",
+            u"description": u"Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
+            u"upload_date": u"19681210",
+            u"uploader": u"SRI International"
+        }
+    }
+
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        json_url = url + (u'?' if u'?' in url else '&') + u'output=json'
+        json_data = self._download_webpage(json_url, video_id)
+        data = json.loads(json_data)
+
+        title = data['metadata']['title'][0]
+        description = data['metadata']['description'][0]
+        uploader = data['metadata']['creator'][0]
+        upload_date = unified_strdate(data['metadata']['date'][0])
+
+        formats = [{
+                'format': fdata['format'],
+                'url': 'http://' + data['server'] + data['dir'] + fn,
+                'file_size': int(fdata['size']),
+            }
+            for fn,fdata in data['files'].items()
+            if 'Video' in fdata['format']]
+        formats.sort(key=lambda fdata: fdata['file_size'])
+
+        info = {
+            '_type': 'video',
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'uploader': uploader,
+            'upload_date': upload_date,
+        }
+        thumbnail = data.get('misc', {}).get('image')
+        if thumbnail:
+            info['thumbnail'] = thumbnail
+
+        # TODO: Remove when #980 has been merged
+        info['url'] = formats[-1]['url']
+        info['ext'] = determine_ext(formats[-1]['url'])
+
+        return info

youtube_dl/extractor/ard.py

@@ -9,6 +9,15 @@ class ARDIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
     _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
     _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
+    _TEST = {
+        u'url': u'http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640',
+        u'file': u'14077640.mp4',
+        u'md5': u'6ca8824255460c787376353f9e20bbd8',
+        u'info_dict': {
+            u"title": u"11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
+        },
+        u'skip': u'Requires rtmpdump'
+    }
 
     def _real_extract(self, url):
         # determine video id from url
@@ -23,7 +32,7 @@ class ARDIE(InfoExtractor):
         # determine title and media streams from webpage
         html = self._download_webpage(url, video_id)
         title = re.search(self._TITLE, html).group('title')
-        streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+        streams = [mo.groupdict() for mo in re.finditer(self._MEDIA_STREAM, html)]
         if not streams:
             assert '"fsk"' in html
             raise ExtractorError(u'This video is only available after 8:00 pm')

youtube_dl/extractor/arte.py

@@ -1,54 +1,33 @@
 import re
-import socket
+import json
+import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_parse,
-    compat_urllib_request,
-
     ExtractorError,
+    find_xpath_attr,
     unified_strdate,
 )
 
 class ArteTvIE(InfoExtractor):
-    """arte.tv information extractor."""
-
-    _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
+    """
+    There are two sources of video in arte.tv: videos.arte.tv and
+    www.arte.tv/guide, the extraction process is different for each one.
+    The videos expire in 7 days, so we can't add tests.
+    """
+    _EMISSION_URL = r'(?:http://)?www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
+    _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
+    _LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
     _LIVE_URL = r'index-[0-9]+\.html$'
 
     IE_NAME = u'arte.tv'
 
-    def fetch_webpage(self, url):
-        request = compat_urllib_request.Request(url)
-        try:
-            self.report_download_webpage(url)
-            webpage = compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
-        except ValueError as err:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        return webpage
-
-    def grep_webpage(self, url, regex, regexFlags, matchTuples):
-        page = self.fetch_webpage(url)
-        mobj = re.search(regex, page, regexFlags)
-        info = {}
-
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-
-        for (i, key, err) in matchTuples:
-            if mobj.group(i) is None:
-                raise ExtractorError(err)
-            else:
-                info[key] = mobj.group(i)
-
-        return info
+    @classmethod
+    def suitable(cls, url):
+        return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL, cls._LIVEWEB_URL))
 
     # TODO implement Live Stream
+    # from ..utils import compat_urllib_parse
     # def extractLiveStream(self, url):
     #     video_lang = url.split('/')[-4]
     #     info = self.grep_webpage(
@@ -75,62 +54,121 @@ class ArteTvIE(InfoExtractor):
     #     )
     #     video_url = u'%s/%s' % (info.get('url'), info.get('path'))
 
-    def extractPlus7Stream(self, url):
-        video_lang = url.split('/')[-3]
-        info = self.grep_webpage(
-            url,
-            r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
-            0,
-            [
-                (1, 'url', u'Invalid URL: %s' % url)
-            ]
-        )
-        next_url = compat_urllib_parse.unquote(info.get('url'))
-        info = self.grep_webpage(
-            next_url,
-            r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
-            0,
-            [
-                (1, 'url', u'Could not find <video> tag: %s' % url)
-            ]
-        )
-        next_url = compat_urllib_parse.unquote(info.get('url'))
-
-        info = self.grep_webpage(
-            next_url,
-            r'<video id="(.*?)".*?>.*?' +
-                '<name>(.*?)</name>.*?' +
-                '<dateVideo>(.*?)</dateVideo>.*?' +
-                '<url quality="hd">(.*?)</url>',
-            re.DOTALL,
-            [
-                (1, 'id',    u'could not extract video id: %s' % url),
-                (2, 'title', u'could not extract video title: %s' % url),
-                (3, 'date',  u'could not extract video date: %s' % url),
-                (4, 'url',   u'could not extract video url: %s' % url)
-            ]
-        )
-
-        return {
-            'id':           info.get('id'),
-            'url':          compat_urllib_parse.unquote(info.get('url')),
-            'uploader':     u'arte.tv',
-            'upload_date':  unified_strdate(info.get('date')),
-            'title':        info.get('title').decode('utf-8'),
-            'ext':          u'mp4',
-            'format':       u'NA',
-            'player_url':   None,
-        }
-
     def _real_extract(self, url):
-        video_id = url.split('/')[-1]
-        self.report_extraction(video_id)
+        mobj = re.match(self._EMISSION_URL, url)
+        if mobj is not None:
+            lang = mobj.group('lang')
+            # This is not a real id, it can be for example AJT for the news
+            # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
+            video_id = mobj.group('id')
+            return self._extract_emission(url, video_id, lang)
+
+        mobj = re.match(self._VIDEOS_URL, url)
+        if mobj is not None:
+            id = mobj.group('id')
+            lang = mobj.group('lang')
+            return self._extract_video(url, id, lang)
+
+        mobj = re.match(self._LIVEWEB_URL, url)
+        if mobj is not None:
+            name = mobj.group('name')
+            lang = mobj.group('lang')
+            return self._extract_liveweb(url, name, lang)
 
         if re.search(self._LIVE_URL, video_id) is not None:
             raise ExtractorError(u'Arte live streams are not yet supported, sorry')
             # self.extractLiveStream(url)
             # return
-        else:
-            info = self.extractPlus7Stream(url)
 
-        return [info]
+    def _extract_emission(self, url, video_id, lang):
+        """Extract from www.arte.tv/guide"""
+        webpage = self._download_webpage(url, video_id)
+        json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+
+        json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
+        self.report_extraction(video_id)
+        info = json.loads(json_info)
+        player_info = info['videoJsonPlayer']
+
+        info_dict = {'id': player_info['VID'],
+                     'title': player_info['VTI'],
+                     'description': player_info.get('VDE'),
+                     'upload_date': unified_strdate(player_info['VDA'].split(' ')[0]),
+                     'thumbnail': player_info['programImage'],
+                     'ext': 'flv',
+                     }
+
+        formats = player_info['VSR'].values()
+        def _match_lang(f):
+            # Return true if that format is in the language of the url
+            if lang == 'fr':
+                l = 'F'
+            elif lang == 'de':
+                l = 'A'
+            regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
+            return any(re.match(r, f['versionCode']) for r in regexes)
+        # Some formats may not be in the same language as the url
+        formats = filter(_match_lang, formats)
+        # We order the formats by quality
+        formats = sorted(formats, key=lambda f: int(f['height']))
+        # Prefer videos without subtitles in the same language
+        formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f['versionCode']) is None)
+        # Pick the best quality
+        format_info = formats[-1]
+        if format_info['mediaType'] == u'rtmp':
+            info_dict['url'] = format_info['streamer']
+            info_dict['play_path'] = 'mp4:' + format_info['url']
+        else:
+            info_dict['url'] = format_info['url']
+
+        return info_dict
+
+    def _extract_video(self, url, video_id, lang):
+        """Extract from videos.arte.tv"""
+        ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
+        ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
+        ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata')
+        ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml)
+        config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
+        config_xml_url = config_node.attrib['ref']
+        config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
+
+        video_urls = list(re.finditer(r'<url quality="(?P<quality>.*?)">(?P<url>.*?)</url>', config_xml))
+        def _key(m):
+            quality = m.group('quality')
+            if quality == 'hd':
+                return 2
+            else:
+                return 1
+        # We pick the best quality
+        video_urls = sorted(video_urls, key=_key)
+        video_url = list(video_urls)[-1].group('url')
+        
+        title = self._html_search_regex(r'<name>(.*?)</name>', config_xml, 'title')
+        thumbnail = self._html_search_regex(r'<firstThumbnailUrl>(.*?)</firstThumbnailUrl>',
+                                            config_xml, 'thumbnail')
+        return {'id': video_id,
+                'title': title,
+                'thumbnail': thumbnail,
+                'url': video_url,
+                'ext': 'flv',
+                }
+
+    def _extract_liveweb(self, url, name, lang):
+        """Extract form http://liveweb.arte.tv/"""
+        webpage = self._download_webpage(url, name)
+        video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id')
+        config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
+                                            video_id, u'Downloading information')
+        config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
+        event_doc = config_doc.find('event')
+        url_node = event_doc.find('video').find('urlHd')
+        if url_node is None:
+            url_node = video_doc.find('urlSd')
+
+        return {'id': video_id,
+                'title': event_doc.find('name%s' % lang.capitalize()).text,
+                'url': url_node.text.replace('MP4', 'mp4'),
+                'ext': 'flv',
+                'thumbnail': self._og_search_thumbnail(webpage),
+                }

youtube_dl/extractor/auengine.py

@@ -0,0 +1,46 @@
+import os.path
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+)
+
+class AUEngineIE(InfoExtractor):
+    _TEST = {
+        u'url': u'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
+        u'file': u'lfvlytY6.mp4',
+        u'md5': u'48972bdbcf1a3a2f5533e62425b41d4f',
+        u'info_dict': {
+            u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
+        }
+    }
+    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
+                webpage, u'title')
+        title = title.strip()
+        links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
+        links = [compat_urllib_parse.unquote(l) for l in links]
+        for link in links:
+            root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
+            if pathext == '.png':
+                thumbnail = link
+            elif pathext == '.mp4':
+                url = link
+                ext = pathext
+        if ext == title[-len(ext):]:
+            title = title[:-len(ext)]
+        ext = ext[1:]
+        return [{
+            'id':        video_id,
+            'url':       url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail,
+        }]

youtube_dl/extractor/bandcamp.py

@@ -9,6 +9,15 @@ from ..utils import (
 
 class BandcampIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+    _TEST = {
+        u'url': u'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
+        u'file': u'1812978515.mp3',
+        u'md5': u'cdeb30cdae1921719a3cbcab696ef53c',
+        u'info_dict': {
+            u"title": u"youtube-dl test song \"'/\\\u00e4\u21ad"
+        },
+        u'skip': u'There is a limit of 200 free downloads / month for the test song'
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/bliptv.py

@@ -24,6 +24,17 @@ class BlipTVIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
     _URL_EXT = r'^.*\.([a-z0-9]+)$'
     IE_NAME = u'blip.tv'
+    _TEST = {
+        u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
+        u'file': u'5779306.m4v',
+        u'md5': u'80baf1ec5c3d2019037c1c707d676b9f',
+        u'info_dict': {
+            u"upload_date": u"20111205", 
+            u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596", 
+            u"uploader": u"Comic Book Resources - CBR TV", 
+            u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
+        }
+    }
 
     def report_direct_download(self, title):
         """Report information extraction."""
@@ -92,7 +103,12 @@ class BlipTVIE(InfoExtractor):
                     data = json_data
 
                 upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
-                video_url = data['media']['url']
+                if 'additionalMedia' in data:
+                    formats = sorted(data['additionalMedia'], key=lambda f: int(f['media_height']))
+                    best_format = formats[-1]
+                    video_url = best_format['url']
+                else:
+                    video_url = data['media']['url']
                 umobj = re.match(self._URL_EXT, video_url)
                 if umobj is None:
                     raise ValueError('Can not determine filename extension')
@@ -173,5 +189,5 @@ class BlipTVUserIE(InfoExtractor):
             pagenum += 1
 
         urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
-        url_entries = [self.url_result(url, 'BlipTV') for url in urls]
+        url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
         return [self.playlist_result(url_entries, playlist_title = username)]

youtube_dl/extractor/breakcom.py

@@ -1,25 +1,38 @@
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import determine_ext
 
 
 class BreakIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+    _TEST = {
+        u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
+        u'file': u'2468056.mp4',
+        u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
+        u'info_dict': {
+            u"title": u"When Girls Act Like D-Bags"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1).split("-")[-1]
-        webpage = self._download_webpage(url, video_id)
-        video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
-        key = re.search(r"icon: '(.+?)',",webpage).group(1)
-        final_url = str(video_url)+"?"+str(key)
-        thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
-        title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
-        ext = video_url.split('.')[-1]
+        embed_url = 'http://www.break.com/embed/%s' % video_id
+        webpage = self._download_webpage(embed_url, video_id)
+        info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
+                                       u'info json', flags=re.DOTALL)
+        info = json.loads(info_json)
+        video_url = info['videoUri']
+        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
+        if m_youtube is not None:
+            return self.url_result(m_youtube.group(1), 'Youtube')
+        final_url = video_url + '?' + info['AuthToken']
         return [{
             'id':        video_id,
             'url':       final_url,
-            'ext':       ext,
-            'title':     title,
-            'thumbnail': thumbnail_url,
+            'ext':       determine_ext(final_url),
+            'title':     info['contentName'],
+            'thumbnail': info['thumbUri'],
         }]

youtube_dl/extractor/brightcove.py

@@ -0,0 +1,86 @@
+import re
+import json
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    find_xpath_attr,
+    compat_urlparse,
+)
+
+class BrightcoveIE(InfoExtractor):
+    _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
+    _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
+    _PLAYLIST_URL_TEMPLATE = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s'
+    
+    # There is a test for Brigtcove in GenericIE, that way we test both the download
+    # and the detection of videos, and we don't have to find an URL that is always valid
+
+    @classmethod
+    def _build_brighcove_url(cls, object_str):
+        """
+        Build a Brightcove url from a xml string containing
+        <object class="BrightcoveExperience">{params}</object>
+        """
+        object_doc = xml.etree.ElementTree.fromstring(object_str)
+        assert u'BrightcoveExperience' in object_doc.attrib['class']
+        params = {'flashID': object_doc.attrib['id'],
+                  'playerID': find_xpath_attr(object_doc, './param', 'name', 'playerID').attrib['value'],
+                  }
+        playerKey = find_xpath_attr(object_doc, './param', 'name', 'playerKey')
+        # Not all pages define this value
+        if playerKey is not None:
+            params['playerKey'] = playerKey.attrib['value']
+        videoPlayer = find_xpath_attr(object_doc, './param', 'name', '@videoPlayer')
+        if videoPlayer is not None:
+            params['@videoPlayer'] = videoPlayer.attrib['value']
+        data = compat_urllib_parse.urlencode(params)
+        return cls._FEDERATED_URL_TEMPLATE % data
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        query_str = mobj.group('query')
+        query = compat_urlparse.parse_qs(query_str)
+
+        videoPlayer = query.get('@videoPlayer')
+        if videoPlayer:
+            return self._get_video_info(videoPlayer[0], query_str)
+        else:
+            player_key = query['playerKey']
+            return self._get_playlist_info(player_key[0])
+
+    def _get_video_info(self, video_id, query):
+        request_url = self._FEDERATED_URL_TEMPLATE % query
+        webpage = self._download_webpage(request_url, video_id)
+
+        self.report_extraction(video_id)
+        info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
+        info = json.loads(info)['data']
+        video_info = info['programmedContent']['videoPlayer']['mediaDTO']
+
+        return self._extract_video_info(video_info)
+
+    def _get_playlist_info(self, player_key):
+        playlist_info = self._download_webpage(self._PLAYLIST_URL_TEMPLATE % player_key,
+                                               player_key, u'Downloading playlist information')
+
+        playlist_info = json.loads(playlist_info)['videoList']
+        videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']]
+
+        return self.playlist_result(videos, playlist_id=playlist_info['id'],
+                                    playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
+
+    def _extract_video_info(self, video_info):
+        renditions = video_info['renditions']
+        renditions = sorted(renditions, key=lambda r: r['size'])
+        best_format = renditions[-1]
+
+        return {'id': video_info['id'],
+                'title': video_info['displayName'],
+                'url': best_format['defaultURL'], 
+                'ext': 'mp4',
+                'description': video_info.get('shortDescription'),
+                'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
+                'uploader': video_info.get('publisherName'),
+                }

youtube_dl/extractor/c56.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class C56IE(InfoExtractor):
+    _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
+    IE_NAME = u'56.com'
+
+    _TEST ={
+        u'url': u'http://www.56.com/u39/v_OTM0NDA3MTY.html',
+        u'file': u'93440716.flv',
+        u'md5': u'e59995ac63d0457783ea05f93f12a866',
+        u'info_dict': {
+            u'title': u'网事知多少 第32期：车怒',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        text_id = mobj.group('textid')
+        info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
+                                           text_id, u'Downloading video info')
+        info = json.loads(info_page)['info']
+        best_format = sorted(info['rfiles'], key=lambda f: int(f['filesize']))[-1]
+        video_url = best_format['url']
+
+        return {'id': info['vid'],
+                'title': info['Subject'],
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': info.get('bimg') or info.get('img'),
+                }

youtube_dl/extractor/canalc2.py

@@ -0,0 +1,35 @@
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+
+
+class Canalc2IE(InfoExtractor):
+    _IE_NAME = 'canalc2.tv'
+    _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
+
+    _TEST = {
+        u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+        u'file': u'12163.mp4',
+        u'md5': u'060158428b650f896c542dfbb3d6487f',
+        u'info_dict': {
+            u'title': u'Terrasses du Numérique'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, video_id)
+        file_name = self._search_regex(
+            r"so\.addVariable\('file','(.*?)'\);",
+            webpage, 'file name')
+        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
+
+        title = self._html_search_regex(
+            r'class="evenement8">(.*?)</a>', webpage, u'title')
+        
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': title,
+                }

youtube_dl/extractor/canalplus.py

@@ -0,0 +1,46 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+class CanalplusIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?\?vid=|player\.canalplus\.fr/#/)(?P<id>\d+)'
+    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
+    IE_NAME = u'canalplus.fr'
+
+    _TEST = {
+        u'url': u'http://www.canalplus.fr/c-divertissement/pid3351-c-le-petit-journal.html?vid=889861',
+        u'file': u'889861.flv',
+        u'md5': u'590a888158b5f0d6832f84001fbf3e99',
+        u'info_dict': {
+            u'title': u'Le Petit Journal 20/06/13 - La guerre des drone',
+            u'upload_date': u'20130620',
+        },
+        u'skip': u'Requires rtmpdump'
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_url = self._VIDEO_INFO_TEMPLATE % video_id
+        info_page = self._download_webpage(info_url,video_id, 
+                                           u'Downloading video info')
+
+        self.report_extraction(video_id)
+        doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
+        video_info = [video for video in doc if video.find('ID').text == video_id][0]
+        infos = video_info.find('INFOS')
+        media = video_info.find('MEDIA')
+        formats = [media.find('VIDEOS/%s' % format)
+            for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
+        video_url = [format.text for format in formats if format is not None][-1]
+
+        return {'id': video_id,
+                'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
+                                       infos.find('TITRAGE/SOUS_TITRE').text),
+                'url': video_url,
+                'ext': 'flv',
+                'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
+                'thumbnail': media.find('IMAGES/GRAND').text,
+                }

youtube_dl/extractor/cnn.py

@@ -0,0 +1,58 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class CNNIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
+
+    _TESTS = [{
+        u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
+        u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
+        u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
+        u'info_dict': {
+            u'title': u'Nadal wins 8th French Open title',
+            u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
+        },
+    },
+    {
+        u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
+        u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
+        u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
+        u"info_dict": {
+            u"title": "Student's epic speech stuns new freshmen",
+            u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        path = mobj.group('path')
+        page_title = mobj.group('title')
+        info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
+        info_xml = self._download_webpage(info_url, page_title)
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+
+        formats = []
+        for f in info.findall('files/file'):
+            mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
+            if mf is not None:
+                formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
+        formats = sorted(formats)
+        (_,_,_, video_path) = formats[-1]
+        video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
+
+        thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
+        thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
+
+        return {'id': info.attrib['id'],
+                'title': info.find('headline').text,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': thumbnails[-1][1],
+                'thumbnails': thumbs_dict,
+                'description': info.find('description').text,
+                }

youtube_dl/extractor/collegehumor.py

@@ -1,26 +1,36 @@
 import re
-import socket
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
     compat_urllib_parse_urlparse,
-    compat_urllib_request,
+    determine_ext,
 
     ExtractorError,
 )
 
 
 class CollegeHumorIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
 
-    def report_manifest(self, video_id):
-        """Report information extraction."""
-        self.to_screen(u'%s: Downloading XML manifest' % video_id)
+    _TESTS = [{
+        u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
+        u'file': u'6902724.mp4',
+        u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
+        u'info_dict': {
+            u'title': u'Comic-Con Cosplay Catastrophe',
+            u'description': u'Fans get creative this year at San Diego.  Too creative.  And yes, that\'s really Joss Whedon.',
+        },
+    },
+    {
+        u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
+        u'file': u'3505939.mp4',
+        u'md5': u'c51ca16b82bb456a4397987791a835f5',
+        u'info_dict': {
+            u'title': u'Font Conference',
+            u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -36,39 +46,42 @@ class CollegeHumorIE(InfoExtractor):
 
         self.report_extraction(video_id)
         xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
-        try:
-            metaXml = compat_urllib_request.urlopen(xmlUrl).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
+        metaXml = self._download_webpage(xmlUrl, video_id,
+                                         u'Downloading info XML',
+                                         u'Unable to download video info XML')
 
         mdoc = xml.etree.ElementTree.fromstring(metaXml)
         try:
             videoNode = mdoc.findall('./video')[0]
+            youtubeIdNode = videoNode.find('./youtubeID')
+            if youtubeIdNode is not None:
+                return self.url_result(youtubeIdNode.text, 'Youtube')
             info['description'] = videoNode.findall('./description')[0].text
             info['title'] = videoNode.findall('./caption')[0].text
             info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
-            manifest_url = videoNode.findall('./file')[0].text
+            next_url = videoNode.findall('./file')[0].text
         except IndexError:
             raise ExtractorError(u'Invalid metadata XML file')
 
-        manifest_url += '?hdcore=2.10.3'
-        self.report_manifest(video_id)
-        try:
-            manifestXml = compat_urllib_request.urlopen(manifest_url).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
+        if next_url.endswith(u'manifest.f4m'):
+            manifest_url = next_url + '?hdcore=2.10.3'
+            manifestXml = self._download_webpage(manifest_url, video_id,
+                                         u'Downloading XML manifest',
+                                         u'Unable to download video info XML')
 
-        adoc = xml.etree.ElementTree.fromstring(manifestXml)
-        try:
-            media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
-            node_id = media_node.attrib['url']
-            video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
-        except IndexError as err:
-            raise ExtractorError(u'Invalid manifest file')
+            adoc = xml.etree.ElementTree.fromstring(manifestXml)
+            try:
+                media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
+                node_id = media_node.attrib['url']
+                video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
+            except IndexError as err:
+                raise ExtractorError(u'Invalid manifest file')
+            url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
+            info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
+            info['ext'] = 'mp4'
+        else:
+            # Old-style direct links
+            info['url'] = next_url
+            info['ext'] = determine_ext(info['url'])
 
-        url_pr = compat_urllib_parse_urlparse(manifest_url)
-        url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
-
-        info['url'] = url
-        info['ext'] = 'f4f'
-        return [info]
+        return info

youtube_dl/extractor/comedycentral.py

@@ -12,8 +12,7 @@ from ..utils import (
 
 
 class ComedyCentralIE(InfoExtractor):
-    """Information extractor for The Daily Show and Colbert Report """
-
+    IE_DESC = u'The Daily Show / Colbert Report'
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
@@ -25,8 +24,21 @@ class ComedyCentralIE(InfoExtractor):
                          (full-episodes/(?P<episode>.*)|
                           (?P<clip>
                               (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
+                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+                          (?P<interview>
+                              extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
                      $"""
+    _TEST = {
+        u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
+        u'file': u'422212.mp4',
+        u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
+        u'info_dict': {
+            u"upload_date": u"20121214", 
+            u"description": u"Kristen Stewart", 
+            u"uploader": u"thedailyshow", 
+            u"title": u"thedailyshow-kristen-stewart part 1"
+        }
+    }
 
     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 
@@ -77,6 +89,9 @@ class ComedyCentralIE(InfoExtractor):
             else:
                 epTitle = mobj.group('cntitle')
             dlNewest = False
+        elif mobj.group('interview'):
+            epTitle = mobj.group('interview_title')
+            dlNewest = False
         else:
             dlNewest = not mobj.group('episode')
             if dlNewest:
@@ -172,7 +187,7 @@ class ComedyCentralIE(InfoExtractor):
                 'ext': 'mp4',
                 'format': format,
                 'thumbnail': None,
-                'description': officialTitle,
+                'description': compat_str(officialTitle),
             }
             results.append(info)
 

youtube_dl/extractor/common.py

@@ -3,6 +3,7 @@ import os
 import re
 import socket
 import sys
+import netrc
 
 from ..utils import (
     compat_http_client,
@@ -13,6 +14,7 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
+    unescapeHTML,
 )
 
 class InfoExtractor(object):
@@ -36,6 +38,8 @@ class InfoExtractor(object):
     The following fields are optional:
 
     format:         The video format, defaults to ext (used for --get-format)
+    thumbnails:     A list of dictionaries (with the entries "resolution" and
+                    "url") for the varying thumbnails
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
@@ -43,7 +47,9 @@ class InfoExtractor(object):
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     player_url:     SWF Player URL (used for rtmpdump).
-    subtitles:      The subtitle file contents.
+    subtitles:      The subtitle file contents as a dictionary in the format
+                    {language: subtitles}.
+    view_count:     How many users have watched the video on the platform.
     urlhandle:      [internal] The urlHandle to be used to download the file,
                     like returned by urllib.request.urlopen
 
@@ -72,7 +78,13 @@ class InfoExtractor(object):
     @classmethod
     def suitable(cls, url):
         """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url) is not None
+
+        # This does not use has/getattr intentionally - we want to know whether
+        # we have cached the regexp for *this* class, whereas getattr would also
+        # match the superclass
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        return cls._VALID_URL_RE.match(url) is not None
 
     @classmethod
     def working(cls):
@@ -102,6 +114,11 @@ class InfoExtractor(object):
         """Real extraction process. Redefine in subclasses."""
         pass
 
+    @classmethod
+    def ie_key(cls):
+        """A string for getting the InfoExtractor with get_info_extractor"""
+        return cls.__name__[:-2]
+
     @property
     def IE_NAME(self):
         return type(self).__name__[:-2]
@@ -117,18 +134,28 @@ class InfoExtractor(object):
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is None:
                 errnote = u'Unable to download webpage'
-            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
 
     def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
         """ Returns a tuple (page content as string, URL handle) """
+
+        # Strip hashes from the URL (#1038)
+        if isinstance(url_or_request, (compat_str, str)):
+            url_or_request = url_or_request.partition('#')[0]
+
         urlh = self._request_webpage(url_or_request, video_id, note, errnote)
         content_type = urlh.headers.get('Content-Type', '')
+        webpage_bytes = urlh.read()
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
         else:
-            encoding = 'utf-8'
-        webpage_bytes = urlh.read()
+            m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
+                          webpage_bytes[:1024])
+            if m:
+                encoding = m.group(1).decode('ascii')
+            else:
+                encoding = 'utf-8'
         if self._downloader.params.get('dump_intermediate_pages', False):
             try:
                 url = url_or_request.get_full_url()
@@ -160,12 +187,11 @@ class InfoExtractor(object):
         """Report attempt to confirm age."""
         self.to_screen(u'Confirming age')
 
+    def report_login(self):
+        """Report attempt to log in."""
+        self.to_screen(u'Logging in')
+
     #Methods for following #608
-    #They set the correct value of the '_type' key
-    def video_result(self, video_info):
-        """Returns a video"""
-        video_info['_type'] = 'video'
-        return video_info
     def url_result(self, url, ie=None):
         """Returns a url that points to a page that should be processed"""
         #TODO: ie should be the class used for getting the info
@@ -211,7 +237,7 @@ class InfoExtractor(object):
             raise ExtractorError(u'Unable to extract %s' % _name)
         else:
             self._downloader.report_warning(u'unable to extract %s; '
-                u'please report this issue on GitHub.' % _name)
+                u'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
     def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
@@ -224,6 +250,61 @@ class InfoExtractor(object):
         else:
             return res
 
+    def _get_login_info(self):
+        """
+        Get the the login info as (username, password)
+        It will look in the netrc file using the _NETRC_MACHINE value
+        If there's no info available, return (None, None)
+        """
+        if self._downloader is None:
+            return (None, None)
+
+        username = None
+        password = None
+        downloader_params = self._downloader.params
+
+        # Attempt to use provided username and password or .netrc data
+        if downloader_params.get('username', None) is not None:
+            username = downloader_params['username']
+            password = downloader_params['password']
+        elif downloader_params.get('usenetrc', False):
+            try:
+                info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+                if info is not None:
+                    username = info[0]
+                    password = info[2]
+                else:
+                    raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+            except (IOError, netrc.NetrcParseError) as err:
+                self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+        
+        return (username, password)
+
+    # Helper functions for extracting OpenGraph info
+    @staticmethod
+    def _og_regex(prop):
+        return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+
+    def _og_search_property(self, prop, html, name=None, **kargs):
+        if name is None:
+            name = 'OpenGraph %s' % prop
+        escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+        return unescapeHTML(escaped)
+
+    def _og_search_thumbnail(self, html, **kargs):
+        return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+
+    def _og_search_description(self, html, **kargs):
+        return self._og_search_property('description', html, fatal=False, **kargs)
+
+    def _og_search_title(self, html, **kargs):
+        return self._og_search_property('title', html, **kargs)
+
+    def _og_search_video_url(self, html, name='video url', **kargs):
+        return self._html_search_regex([self._og_regex('video:secure_url'),
+                                        self._og_regex('video')],
+                                       html, name, **kargs)
+
 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.
@@ -262,3 +343,7 @@ class SearchInfoExtractor(InfoExtractor):
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
         raise NotImplementedError("This method must be implemented by sublclasses")
+
+    @property
+    def SEARCH_KEY(self):
+        return self._SEARCH_KEY

youtube_dl/extractor/condenast.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    orderedSet,
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
+
+
+class CondeNastIE(InfoExtractor):
+    """
+    Condé Nast is a media group, some of its sites use a custom HTML5 player
+    that works the same in all of them.
+    """
+
+    # The keys are the supported sites and the values are the name to be shown
+    # to the user and in the extractor description.
+    _SITES = {'wired': u'WIRED',
+              'gq': u'GQ',
+              'vogue': u'Vogue',
+              'glamour': u'Glamour',
+              'wmagazine': u'W Magazine',
+              'vanityfair': u'Vanity Fair',
+              }
+
+    _VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
+    IE_DESC = u'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
+
+    _TEST = {
+        u'url': u'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
+        u'file': u'5171b343c2b4c00dd0c1ccb3.mp4',
+        u'md5': u'1921f713ed48aabd715691f774c451f7',
+        u'info_dict': {
+            u'title': u'3D Printed Speakers Lit With LED',
+            u'description': u'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
+        }
+    }
+
+    def _extract_series(self, url, webpage):
+        title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
+                                        webpage, u'series title', flags=re.DOTALL)
+        url_object = compat_urllib_parse_urlparse(url)
+        base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
+        m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
+                              webpage, flags=re.DOTALL)
+        paths = orderedSet(m.group(1) for m in m_paths)
+        build_url = lambda path: compat_urlparse.urljoin(base_url, path)
+        entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
+        return self.playlist_result(entries, playlist_title=title)
+
+    def _extract_video(self, webpage):
+        description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
+                                               r'<div class="video-post-content">(.+?)</div>',
+                                               ],
+                                              webpage, u'description',
+                                              fatal=False, flags=re.DOTALL)
+        params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
+                                    u'player params', flags=re.DOTALL)
+        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, u'video id')
+        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, u'player id')
+        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, u'target')
+        data = compat_urllib_parse.urlencode({'videoId': video_id,
+                                              'playerId': player_id,
+                                              'target': target,
+                                              })
+        base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
+                                           webpage, u'base info url',
+                                           default='http://player.cnevids.com/player/loader.js?')
+        info_url = base_info_url + data
+        info_page = self._download_webpage(info_url, video_id,
+                                           u'Downloading video info')
+        video_info = self._search_regex(r'var video = ({.+?});', info_page, u'video info')
+        video_info = json.loads(video_info)
+
+        def _formats_sort_key(f):
+            type_ord = 1 if f['type'] == 'video/mp4' else 0
+            quality_ord = 1 if f['quality'] == 'high' else 0
+            return (quality_ord, type_ord)
+        best_format = sorted(video_info['sources'][0], key=_formats_sort_key)[-1]
+
+        return {'id': video_id,
+                'url': best_format['src'],
+                'ext': best_format['type'].split('/')[-1],
+                'title': video_info['title'],
+                'thumbnail': video_info['poster_frame'],
+                'description': description,
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        site = mobj.group('site')
+        url_type = mobj.group('type')
+        id = mobj.group('id')
+
+        self.to_screen(u'Extracting from %s with the Condé Nast extractor' % self._SITES[site])
+        webpage = self._download_webpage(url, id)
+
+        if url_type == 'series':
+            return self._extract_series(url, webpage)
+        else:
+            return self._extract_video(webpage)

youtube_dl/extractor/criterion.py

@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class CriterionIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
+    _TEST = {
+        u'url': u'http://www.criterion.com/films/184-le-samourai',
+        u'file': u'184.mp4',
+        u'md5': u'bc51beba55685509883a9a7830919ec3',
+        u'info_dict': {
+            u"title": u"Le Samouraï",
+            u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+
+        final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
+                                webpage, 'video url')
+        title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
+                                webpage, 'video title')
+        description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
+                                webpage, 'video description')
+        thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+                                webpage, 'thumbnail url')
+
+        return {'id': video_id,
+                'url' : final_url,
+                'title': title,
+                'ext': determine_ext(final_url),
+                'description': description,
+                'thumbnail': thumbnail,
+                }

youtube_dl/extractor/cspan.py

@@ -0,0 +1,51 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+)
+
+class CSpanIE(InfoExtractor):
+    _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
+    _TEST = {
+        u'url': u'http://www.c-spanvideo.org/program/HolderonV',
+        u'file': u'315139.flv',
+        u'md5': u'74a623266956f69e4df0068ab6c80fe4',
+        u'info_dict': {
+            u"title": u"Attorney General Eric Holder on Voting Rights Act Decision"
+        },
+        u'skip': u'Requires rtmpdump'
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        prog_name = mobj.group(1)
+        webpage = self._download_webpage(url, prog_name)
+        video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
+        data = compat_urllib_parse.urlencode({'programid': video_id,
+                                              'dynamic':'1'})
+        info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data
+        video_info = self._download_webpage(info_url, video_id, u'Downloading video info')
+
+        self.report_extraction(video_id)
+
+        title = self._html_search_regex(r'<string name="title">(.*?)</string>',
+                                        video_info, 'title')
+        description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
+                                              webpage, 'description',
+                                              flags=re.MULTILINE|re.DOTALL)
+
+        url = self._search_regex(r'<string name="URL">(.*?)</string>',
+                                 video_info, 'video url')
+        url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443')
+        path = self._search_regex(r'<string name="path">(.*?)</string>',
+                            video_info, 'rtmp play path')
+
+        return {'id': video_id,
+                'title': title,
+                'ext': 'flv',
+                'url': url,
+                'play_path': path,
+                'description': description,
+                'thumbnail': self._og_search_thumbnail(webpage),
+                }

youtube_dl/extractor/dailymotion.py

@@ -1,12 +1,14 @@
 import re
+import json
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_request,
-    compat_urllib_parse,
+    get_element_by_attribute,
+    get_element_by_id,
 
     ExtractorError,
-    unescapeHTML,
 )
 
 class DailymotionIE(InfoExtractor):
@@ -14,6 +16,15 @@ class DailymotionIE(InfoExtractor):
 
     _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
     IE_NAME = u'dailymotion'
+    _TEST = {
+        u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
+        u'file': u'x33vw9.mp4',
+        u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
+        u'info_dict': {
+            u"uploader": u"Amphora Alex and Van .", 
+            u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+        }
+    }
 
     def _real_extract(self, url):
         # Extract id and simplified title from URL
@@ -30,33 +41,7 @@ class DailymotionIE(InfoExtractor):
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
-        mobj = re.search(r'\s*var flashvars = (.*)', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract media URL')
-        flashvars = compat_urllib_parse.unquote(mobj.group(1))
 
-        for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
-            if key in flashvars:
-                max_quality = key
-                self.to_screen(u'Using %s' % key)
-                break
-        else:
-            raise ExtractorError(u'Unable to extract video URL')
-
-        mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract video URL')
-
-        video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
-
-        # TODO: support choosing qualities
-
-        mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract title')
-        video_title = unescapeHTML(mobj.group('title'))
-
-        video_uploader = None
         video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
                                              # Looking for official user
                                              r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
@@ -67,11 +52,60 @@ class DailymotionIE(InfoExtractor):
         if mobj is not None:
             video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
 
+        embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
+        embed_page = self._download_webpage(embed_url, video_id,
+                                            u'Downloading embed page')
+        info = self._search_regex(r'var info = ({.*?}),$', embed_page,
+            'video info', flags=re.MULTILINE)
+        info = json.loads(info)
+
+        # TODO: support choosing qualities
+
+        for key in ['stream_h264_hd1080_url','stream_h264_hd_url',
+                    'stream_h264_hq_url','stream_h264_url',
+                    'stream_h264_ld_url']:
+            if info.get(key):#key in info and info[key]:
+                max_quality = key
+                self.to_screen(u'Using %s' % key)
+                break
+        else:
+            raise ExtractorError(u'Unable to extract video URL')
+        video_url = info[max_quality]
+
         return [{
             'id':       video_id,
             'url':      video_url,
             'uploader': video_uploader,
             'upload_date':  video_upload_date,
-            'title':    video_title,
+            'title':    self._og_search_title(webpage),
             'ext':      video_extension,
+            'thumbnail': info['thumbnail_url']
         }]
+
+
+class DailymotionPlaylistIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
+    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id =  mobj.group('id')
+        video_ids = []
+
+        for pagenum in itertools.count(1):
+            webpage = self._download_webpage('https://www.dailymotion.com/playlist/%s/%s' % (playlist_id, pagenum),
+                                             playlist_id, u'Downloading page %s' % pagenum)
+
+            playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
+            video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
+
+            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+                break
+
+        entries = [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+                   for video_id in video_ids]
+        return {'_type': 'playlist',
+                'id': playlist_id,
+                'title': get_element_by_id(u'playlist_name', webpage),
+                'entries': entries,
+                }

youtube_dl/extractor/daum.py

@@ -0,0 +1,74 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    determine_ext,
+)
+
+
+class DaumIE(InfoExtractor):
+    _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+    IE_NAME = u'daum.net'
+
+    _TEST = {
+        u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
+        u'file': u'52554690.mp4',
+        u'info_dict': {
+            u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
+            u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
+            u'upload_date': u'20130831',
+            u'duration': 3868,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
+        webpage = self._download_webpage(canonical_url, video_id)
+        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
+            webpage, u'full id')
+        query = compat_urllib_parse.urlencode({'vid': full_id})
+        info_xml = self._download_webpage(
+            'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
+            u'Downloading video info')
+        urls_xml = self._download_webpage(
+            'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
+            video_id, u'Downloading video formats info')
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
+
+        self.to_screen(u'%s: Getting video urls' % video_id)
+        formats = []
+        for format_el in urls.findall('result/output_list/output_list'):
+            profile = format_el.attrib['profile']
+            format_query = compat_urllib_parse.urlencode({
+                'vid': full_id,
+                'profile': profile,
+            })
+            url_xml = self._download_webpage(
+                'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
+                video_id, note=False)
+            url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
+            format_url = url_doc.find('result/url').text
+            formats.append({
+                'url': format_url,
+                'ext': determine_ext(format_url),
+                'format_id': profile,
+            })
+
+        info = {
+            'id': video_id,
+            'title': info.find('TITLE').text,
+            'formats': formats,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': info.find('CONTENTS').text,
+            'duration': int(info.find('DURATION').text),
+            'upload_date': info.find('REGDTTM').text[:8],
+        }
+        # TODO: Remove when #980 has been merged
+        info.update(formats[-1])
+        return info

youtube_dl/extractor/defense.py

@@ -0,0 +1,39 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class DefenseGouvFrIE(InfoExtractor):
+    _IE_NAME = 'defense.gouv.fr'
+    _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
+        r'ligthboxvideo/base-de-medias/webtv/(.*)')
+
+    _TEST = {
+        u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/'
+        u'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1'),
+        u'file': u'11213.mp4',
+        u'md5': u'75bba6124da7e63d2d60b5244ec9430c',
+        "info_dict": {
+            "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
+        }
+    }
+
+    def _real_extract(self, url):
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        video_id = self._search_regex(
+            r"flashvars.pvg_id=\"(\d+)\";",
+            webpage, 'ID')
+        
+        json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
+            + video_id)
+        info = self._download_webpage(json_url, title,
+                                                  'Downloading JSON config')
+        video_url = json.loads(info)['renditions'][0]['url']
+        
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': title,
+                }

youtube_dl/extractor/dotsub.py

@@ -0,0 +1,41 @@
+import re
+import json
+import time
+
+from .common import InfoExtractor
+
+
+class DotsubIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)'
+    _TEST = {
+        u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+        u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv',
+        u'md5': u'0914d4d69605090f623b7ac329fea66e',
+        u'info_dict': {
+            u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary",
+            u"uploader": u"4v4l0n42",
+            u'description': u'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
+            u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            u'upload_date': u'20101213',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id)
+        webpage = self._download_webpage(info_url, video_id)
+        info = json.loads(webpage)
+        date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds
+
+        return [{
+            'id':          video_id,
+            'url':         info['mediaURI'],
+            'ext':         'flv',
+            'title':       info['title'],
+            'thumbnail':   info['screenshotURI'],
+            'description': info['description'],
+            'uploader':    info['user'],
+            'view_count':  info['numberOfViews'],
+            'upload_date': u'%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
+        }]

youtube_dl/extractor/dreisat.py

@@ -0,0 +1,85 @@
+# coding: utf-8
+
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    unified_strdate,
+)
+
+
+class DreiSatIE(InfoExtractor):
+    IE_NAME = '3sat'
+    _VALID_URL = r'(?:http://)?(?:www\.)?3sat.de/mediathek/index.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+    _TEST = {
+        u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
+        u'file': u'36983.webm',
+        u'md5': u'57c97d0469d71cf874f6815aa2b7c944',
+        u'info_dict': {
+            u"title": u"Kaffeeland Schweiz",
+            u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", 
+            u"uploader": u"3sat",
+            u"upload_date": u"20130622"
+        }
+    }
+
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
+        details_xml = self._download_webpage(details_url, video_id, note=u'Downloading video details')
+        details_doc = xml.etree.ElementTree.fromstring(details_xml.encode('utf-8'))
+
+        thumbnail_els = details_doc.findall('.//teaserimage')
+        thumbnails = [{
+            'width': te.attrib['key'].partition('x')[0],
+            'height': te.attrib['key'].partition('x')[2],
+            'url': te.text,
+        } for te in thumbnail_els]
+
+        information_el = details_doc.find('.//information')
+        video_title = information_el.find('./title').text
+        video_description = information_el.find('./detail').text
+
+        details_el = details_doc.find('.//details')
+        video_uploader = details_el.find('./channel').text
+        upload_date = unified_strdate(details_el.find('./airtime').text)
+
+        format_els = details_doc.findall('.//formitaet')
+        formats = [{
+            'format_id': fe.attrib['basetype'],
+            'width': int(fe.find('./width').text),
+            'height': int(fe.find('./height').text),
+            'url': fe.find('./url').text,
+            'filesize': int(fe.find('./filesize').text),
+            'video_bitrate': int(fe.find('./videoBitrate').text),
+            '3sat_qualityname': fe.find('./quality').text,
+        } for fe in format_els
+            if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')]
+
+        def _sortkey(format):
+            qidx = ['low', 'med', 'high', 'veryhigh'].index(format['3sat_qualityname'])
+            prefer_http = 1 if 'rtmp' in format['url'] else 0
+            return (qidx, prefer_http, format['video_bitrate'])
+        formats.sort(key=_sortkey)
+
+        info = {
+            '_type': 'video',
+            'id': video_id,
+            'title': video_title,
+            'formats': formats,
+            'description': video_description,
+            'thumbnails': thumbnails,
+            'thumbnail': thumbnails[-1]['url'],
+            'uploader': video_uploader,
+            'upload_date': upload_date,
+        }
+
+        # TODO: Remove when #980 has been merged
+        info['url'] = formats[-1]['url']
+        info['ext'] = determine_ext(formats[-1]['url'])
+
+        return info

youtube_dl/extractor/ehow.py

@@ -0,0 +1,46 @@
+import re
+
+from ..utils import (
+    compat_urllib_parse,
+    determine_ext
+)
+from .common import InfoExtractor
+
+
+class EHowIE(InfoExtractor):
+    IE_NAME = u'eHow'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
+    _TEST = {
+        u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
+        u'file': u'12245069.flv',
+        u'md5': u'9809b4e3f115ae2088440bcb4efbf371',
+        u'info_dict': {
+            u"title": u"Hardwood Flooring Basics",
+            u"description": u"Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...",
+   			u"uploader": u"Erick Nathan"
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
+            webpage, u'video URL')
+        final_url = compat_urllib_parse.unquote(video_url)        
+        uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
+            webpage, u'uploader')
+        title = self._og_search_title(webpage).replace(' | eHow', '')
+        ext = determine_ext(final_url)
+
+        return {
+            '_type':       'video',
+            'id':          video_id,
+            'url':         final_url,
+            'ext':         ext,
+            'title':       title,
+            'thumbnail':   self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+            'uploader':    uploader,
+        }
+

youtube_dl/extractor/eighttracks.py

@@ -12,6 +12,77 @@ from ..utils import (
 class EightTracksIE(InfoExtractor):
     IE_NAME = '8tracks'
     _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
+    _TEST = {
+        u"name": u"EightTracks",
+        u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
+        u"playlist": [
+            {
+                u"file": u"11885610.m4a",
+                u"md5": u"96ce57f24389fc8734ce47f4c1abcc55",
+                u"info_dict": {
+                    u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885608.m4a",
+                u"md5": u"4ab26f05c1f7291ea460a3920be8021f",
+                u"info_dict": {
+                    u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885679.m4a",
+                u"md5": u"d30b5b5f74217410f4689605c35d1fd7",
+                u"info_dict": {
+                    u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885680.m4a",
+                u"md5": u"4eb0a669317cd725f6bbd336a29f923a",
+                u"info_dict": {
+                    u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885682.m4a",
+                u"md5": u"1893e872e263a2705558d1d319ad19e8",
+                u"info_dict": {
+                    u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885683.m4a",
+                u"md5": u"b673c46f47a216ab1741ae8836af5899",
+                u"info_dict": {
+                    u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885684.m4a",
+                u"md5": u"1d74534e95df54986da7f5abf7d842b7",
+                u"info_dict": {
+                    u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            },
+            {
+                u"file": u"11885685.m4a",
+                u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0",
+                u"info_dict": {
+                    u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
+                    u"uploader_id": u"ytdl"
+                }
+            }
+        ]
+    }
+
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/escapist.py

@@ -12,6 +12,16 @@ from ..utils import (
 
 class EscapistIE(InfoExtractor):
     _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _TEST = {
+        u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
+        u'md5': u'c6793dbda81388f4264c1ba18684a74d',
+        u'info_dict': {
+            u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 
+            u"uploader": u"the-escapist-presents", 
+            u"title": u"Breaking Down Baldur's Gate"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -26,11 +36,7 @@ class EscapistIE(InfoExtractor):
         videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
             webpage, u'description', fatal=False)
 
-        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
-            webpage, u'thumbnail', fatal=False)
-
-        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
-            webpage, u'player url')
+        playerUrl = self._og_search_video_url(webpage, name='player url')
 
         title = self._html_search_regex('<meta name="title" content="([^"]*)"',
             webpage, u'player url').split(' : ')[-1]
@@ -60,7 +66,7 @@ class EscapistIE(InfoExtractor):
             'upload_date': None,
             'title': title,
             'ext': 'mp4',
-            'thumbnail': imgUrl,
+            'thumbnail': self._og_search_thumbnail(webpage),
             'description': videoDesc,
             'player_url': playerUrl,
         }

youtube_dl/extractor/exfm.py

@@ -0,0 +1,54 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class ExfmIE(InfoExtractor):
+    IE_NAME = u'exfm'
+    IE_DESC = u'ex.fm'
+    _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
+    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
+    _TESTS = [
+        {
+            u'url': u'http://ex.fm/song/1bgtzg',
+            u'file': u'95223130.mp3',
+            u'md5': u'8a7967a3fef10e59a1d6f86240fd41cf',
+            u'info_dict': {
+                u"title": u"We Can't Stop - Miley Cyrus",
+                u"uploader": u"Miley Cyrus",
+                u'upload_date': u'20130603',
+                u'description': u'Download "We Can\'t Stop" \r\niTunes: http://smarturl.it/WeCantStop?IQid=SC\r\nAmazon: http://smarturl.it/WeCantStopAMZ?IQid=SC',
+            },
+            u'note': u'Soundcloud song',
+        },
+        {
+            u'url': u'http://ex.fm/song/wddt8',
+            u'file': u'wddt8.mp3',
+            u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
+            u'info_dict': {
+                u'title': u'Safe and Sound',
+                u'uploader': u'Capital Cities',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        song_id = mobj.group(1)
+        info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
+        webpage = self._download_webpage(info_url, song_id)
+        info = json.loads(webpage)
+        song_url = info['song']['url']
+        if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
+            self.to_screen('Soundcloud song detected')
+            return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
+        return [{
+            'id':          song_id,
+            'url':         song_url,
+            'ext':         'mp3',
+            'title':       info['song']['title'],
+            'thumbnail':   info['song']['image']['large'],
+            'uploader':    info['song']['artist'],
+            'view_count':  info['song']['loved_count'],
+        }]

youtube_dl/extractor/facebook.py

@@ -22,6 +22,15 @@ class FacebookIE(InfoExtractor):
     _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
     _NETRC_MACHINE = 'facebook'
     IE_NAME = u'facebook'
+    _TEST = {
+        u'url': u'https://www.facebook.com/photo.php?v=120708114770723',
+        u'file': u'120708114770723.mp4',
+        u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
+        u'info_dict': {
+            u"duration": 279, 
+            u"title": u"PEOPLE ARE AWESOME 2013"
+        }
+    }
 
     def report_login(self):
         """Report attempt to log in."""

youtube_dl/extractor/flickr.py

@@ -10,6 +10,16 @@ from ..utils import (
 class FlickrIE(InfoExtractor):
     """Information Extractor for Flickr videos"""
     _VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+    _TEST = {
+        u'url': u'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
+        u'file': u'5645318632.mp4',
+        u'md5': u'6fdc01adbc89d72fc9c4f15b4a4ba87b',
+        u'info_dict': {
+            u"description": u"Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", 
+            u"uploader_id": u"forestwander-nature-pictures", 
+            u"title": u"Dark Hollow Waterfalls"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -37,21 +47,12 @@ class FlickrIE(InfoExtractor):
             raise ExtractorError(u'Unable to extract video url')
         video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
-            webpage, u'video title')
-
-        video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
-            webpage, u'description', fatal=False)
-
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
-            webpage, u'thumbnail', fatal=False)
-
         return [{
             'id':          video_id,
             'url':         video_url,
             'ext':         'mp4',
-            'title':       video_title,
-            'description': video_description,
-            'thumbnail':   thumbnail,
+            'title':       self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail':   self._og_search_thumbnail(webpage),
             'uploader_id': video_uploader_id,
         }]

youtube_dl/extractor/freesound.py

@@ -0,0 +1,36 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class FreesoundIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _TEST = {
+        u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
+        u'file': u'194503.mp3',
+        u'md5': u'12280ceb42c81f19a515c745eae07650',
+        u'info_dict': {
+            u"title": u"gulls in the city.wav",
+            u"uploader" : u"miklovan",
+            u'description': u'the sounds of seagulls in the city',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        music_id = mobj.group('id')
+        webpage = self._download_webpage(url, music_id)
+        title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
+                                webpage, 'music title', flags=re.DOTALL)
+        music_url = self._og_search_property('audio', webpage, 'music url')
+        description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
+                                webpage, 'description', fatal=False, flags=re.DOTALL)
+
+        return [{
+            'id':       music_id,
+            'title':    title,            
+            'url':      music_url,
+            'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
+            'ext':      determine_ext(music_url),
+            'description': description,
+        }]

youtube_dl/extractor/funnyordie.py

@@ -5,6 +5,15 @@ from .common import InfoExtractor
 
 class FunnyOrDieIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
+    _TEST = {
+        u'url': u'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
+        u'file': u'0732f586d7.mp4',
+        u'md5': u'f647e9e90064b53b6e046e75d0241fbd',
+        u'info_dict': {
+            u"description": u"Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.", 
+            u"title": u"Heart-Shaped Box: Literal Video Version"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -12,20 +21,14 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
+        video_url = self._search_regex(r'type: "video/mp4", src: "(.*?)"',
             webpage, u'video URL', flags=re.DOTALL)
 
-        title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
-            r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
-
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
-            webpage, u'description', fatal=False, flags=re.DOTALL)
-
         info = {
             'id': video_id,
             'url': video_url,
             'ext': 'mp4',
-            'title': title,
-            'description': video_description,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
         }
         return [info]

youtube_dl/extractor/gamespot.py

@@ -0,0 +1,55 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+    compat_urllib_parse,
+)
+
+class GameSpotIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
+    _TEST = {
+        u"url": u"http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
+        u"file": u"6410818.mp4",
+        u"md5": u"b2a30deaa8654fcccd43713a6b6a4825",
+        u"info_dict": {
+            u"title": u"Arma III - Community Guide: SITREP I",
+            u"upload_date": u"20130627", 
+        }
+    }
+
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        page_id = mobj.group('page_id')
+        webpage = self._download_webpage(url, page_id)
+        video_id = self._html_search_regex([r'"og:video" content=".*?\?id=(\d+)"',
+                                            r'http://www\.gamespot\.com/videoembed/(\d+)'],
+                                           webpage, 'video id')
+        data = compat_urllib_parse.urlencode({'id': video_id, 'newplayer': '1'})
+        info_url = 'http://www.gamespot.com/pages/video_player/xml.php?' + data
+        info_xml = self._download_webpage(info_url, video_id)
+        doc = xml.etree.ElementTree.fromstring(info_xml)
+        clip_el = doc.find('./playList/clip')
+
+        http_urls = [{'url': node.find('filePath').text,
+                      'rate': int(node.find('rate').text)}
+            for node in clip_el.find('./httpURI')]
+        best_quality = sorted(http_urls, key=lambda f: f['rate'])[-1]
+        video_url = best_quality['url']
+        title = clip_el.find('./title').text
+        ext = video_url.rpartition('.')[2]
+        thumbnail_url = clip_el.find('./screenGrabURI').text
+        view_count = int(clip_el.find('./views').text)
+        upload_date = unified_strdate(clip_el.find('./postDate').text)
+
+        return [{
+            'id'          : video_id,
+            'url'         : video_url,
+            'ext'         : ext,
+            'title'       : title,
+            'thumbnail'   : thumbnail_url,
+            'upload_date' : upload_date,
+            'view_count'  : view_count,
+        }]

youtube_dl/extractor/gametrailers.py

@@ -1,59 +1,36 @@
 import re
 
-from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
+from .mtv import MTVIE, _media_xml_tag
 
-    ExtractorError,
-)
-
-class GametrailersIE(InfoExtractor):
+class GametrailersIE(MTVIE):
+    """
+    Gametrailers use the same videos system as MTVIE, it just changes the feed
+    url, where the uri is and the method to get the thumbnails.
+    """
     _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
+    _TEST = {
+        u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
+        u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
+        u'md5': u'4c8e67681a0ea7ec241e8c09b3ea8cf7',
+        u'info_dict': {
+            u'title': u'E3 2013: Debut Trailer',
+            u'description': u'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
+        },
+    }
+    # Overwrite MTVIE properties we don't want
+    _TESTS = []
+
+    _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
+        return itemdoc.find(search_path).attrib['url']
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group('id')
-        video_type = mobj.group('type')
         webpage = self._download_webpage(url, video_id)
-        if video_type == 'full-episodes':
-            mgid_re = r'data-video="(?P<mgid>mgid:.*?)"'
-        else:
-            mgid_re = r'data-contentId=\'(?P<mgid>mgid:.*?)\''
-        mgid = self._search_regex(mgid_re, webpage, u'mgid')
-        data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'})
-
-        info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data,
-                                           video_id, u'Downloading video info')
-        links_webpage = self._download_webpage('http://www.gametrailers.com/feeds/mediagen/?' + data,
-                                               video_id, u'Downloading video urls info')
-
-        self.report_extraction(video_id)
-        info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
-                      <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
-                      <image>.*
-                        <url>(?P<thumb>.*?)</url>.*
-                      </image>'''
-
-        m_info = re.search(info_re, info_page, re.VERBOSE|re.DOTALL)
-        if m_info is None:
-            raise ExtractorError(u'Unable to extract video info')
-        video_title = m_info.group('title')
-        video_description = m_info.group('description')
-        video_thumb = m_info.group('thumb')
-
-        m_urls = list(re.finditer(r'<src>(?P<url>.*)</src>', links_webpage))
-        if m_urls is None or len(m_urls) == 0:
-            raise ExtractorError(u'Unable to extract video url')
-        # They are sorted from worst to best quality
-        video_url = m_urls[-1].group('url')
-
-        return {'url':         video_url,
-                'id':          video_id,
-                'title':       video_title,
-                # Videos are actually flv not mp4
-                'ext':         'flv',
-                'thumbnail':   video_thumb,
-                'description': video_description,
-                }
+        mgid = self._search_regex([r'data-video="(?P<mgid>mgid:.*?)"',
+                                   r'data-contentId=\'(?P<mgid>mgid:.*?)\''],
+                                  webpage, u'mgid')
+        return self._get_videos_info(mgid)

youtube_dl/extractor/generic.py

@@ -1,3 +1,5 @@
+# encoding: utf-8
+
 import os
 import re
 
@@ -6,15 +8,39 @@ from ..utils import (
     compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
+    compat_urlparse,
 
     ExtractorError,
 )
+from .brightcove import BrightcoveIE
+
 
 class GenericIE(InfoExtractor):
-    """Generic last-resort information extractor."""
-
+    IE_DESC = u'Generic downloader that works on some sites'
     _VALID_URL = r'.*'
     IE_NAME = u'generic'
+    _TESTS = [
+        {
+            u'url': u'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
+            u'file': u'13601338388002.mp4',
+            u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89',
+            u'info_dict': {
+                u"uploader": u"www.hodiho.fr",
+                u"title": u"R\u00e9gis plante sa Jeep"
+            }
+        },
+        {
+            u'url': u'http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/',
+            u'file': u'2371591881001.mp4',
+            u'md5': u'9e80619e0a94663f0bdc849b4566af19',
+            u'note': u'Test Brightcove downloads and detection in GenericIE',
+            u'info_dict': {
+                u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
+                u'uploader': u'8TV',
+                u'description': u'md5:a950cc4285c43e44d763d036710cd9cd',
+            }
+        },
+    ]
 
     def report_download_webpage(self, video_id):
         """Report webpage download."""
@@ -83,8 +109,13 @@ class GenericIE(InfoExtractor):
         return new_url
 
     def _real_extract(self, url):
-        new_url = self._test_redirect(url)
-        if new_url: return [self.url_result(new_url)]
+        try:
+            new_url = self._test_redirect(url)
+            if new_url:
+                return [self.url_result(new_url)]
+        except compat_urllib_error.HTTPError:
+            # This may be a stupid server that doesn't like HEAD, our UA, or so
+            pass
 
         video_id = url.split('/')[-1]
         try:
@@ -95,6 +126,13 @@ class GenericIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         self.report_extraction(video_id)
+        # Look for BrightCove:
+        m_brightcove = re.search(r'<object.+?class=([\'"]).*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL)
+        if m_brightcove is not None:
+            self.to_screen(u'Brightcove video detected.')
+            bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group())
+            return self.url_result(bc_url, 'Brightcove')
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:
@@ -102,7 +140,7 @@ class GenericIE(InfoExtractor):
             mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
         if mobj is None:
             # Broaden the search a little bit: JWPlayer JS loader
-            mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
+            mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"&]*)', webpage)
         if mobj is None:
             # Try to find twitter cards info
             mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@@ -113,6 +151,9 @@ class GenericIE(InfoExtractor):
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
                 mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+        if mobj is None:
+            # HTML5 video
+            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
@@ -121,8 +162,9 @@ class GenericIE(InfoExtractor):
         if mobj.group(1) is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
-        video_url = compat_urllib_parse.unquote(mobj.group(1))
-        video_id = os.path.basename(video_url)
+        video_url = mobj.group(1)
+        video_url = compat_urlparse.urljoin(url, video_url)
+        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
         # here's a fun little line of code for you:
         video_extension = os.path.splitext(video_id)[1][1:]
@@ -135,7 +177,7 @@ class GenericIE(InfoExtractor):
         #   Video Title - Tagline | Site Name
         # and so on and so forth; it's just not practical
         video_title = self._html_search_regex(r'<title>(.*)</title>',
-            webpage, u'video title')
+            webpage, u'video title', default=u'video', flags=re.DOTALL)
 
         # video uploader is domain name
         video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',

youtube_dl/extractor/googleplus.py

@@ -1,3 +1,5 @@
+# coding: utf-8
+
 import datetime
 import re
 
@@ -8,10 +10,18 @@ from ..utils import (
 
 
 class GooglePlusIE(InfoExtractor):
-    """Information extractor for plus.google.com."""
-
+    IE_DESC = u'Google Plus'
     _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
     IE_NAME = u'plus.google'
+    _TEST = {
+        u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
+        u"file": u"ZButuJc6CtH.flv",
+        u"info_dict": {
+            u"upload_date": u"20120613",
+            u"uploader": u"井上ヨシマサ",
+            u"title": u"嘆きの天使 降臨"
+        }
+    }
 
     def _real_extract(self, url):
         # Extract id from URL
@@ -46,14 +56,18 @@ class GooglePlusIE(InfoExtractor):
         video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
             webpage, 'title', default=u'NA')
 
-        # Step 2, Stimulate clicking the image box to launch video
-        video_page = self._search_regex('"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]',
+        # Step 2, Simulate clicking the image box to launch video
+        DOMAIN = 'https://plus.google.com/'
+        video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
             webpage, u'video page URL')
+        if not video_page.startswith(DOMAIN):
+            video_page = DOMAIN + video_page
+
         webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
 
         # Extract video links on video page
         """Extract video links of all sizes"""
-        pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
+        pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
         mobj = re.findall(pattern, webpage)
         if len(mobj) == 0:
             raise ExtractorError(u'Unable to extract video links')

youtube_dl/extractor/googlesearch.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class GoogleSearchIE(SearchInfoExtractor):
-    """Information Extractor for Google Video search queries."""
+    IE_DESC = u'Google Video search'
     _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
     _MAX_RESULTS = 1000
     IE_NAME = u'video.google:search'

youtube_dl/extractor/hark.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class HarkIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
+    _TEST = {
+        u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
+        u'file': u'mmbzyhkgny.mp3',
+        u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
+        u'info_dict': {
+            u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013",
+            u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
+            u'duration': 11,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        json_url = "http://www.hark.com/clips/%s.json" %(video_id)
+        info_json = self._download_webpage(json_url, video_id)
+        info = json.loads(info_json)
+        final_url = info['url']
+
+        return {'id': video_id,
+                'url' : final_url,
+                'title': info['name'],
+                'ext': determine_ext(final_url),
+                'description': info['description'],
+                'thumbnail': info['image_original'],
+                'duration': info['duration'],
+                }

youtube_dl/extractor/hotnewhiphop.py

@@ -0,0 +1,44 @@
+import re
+import base64
+
+from .common import InfoExtractor
+
+
+class HotNewHipHopIE(InfoExtractor):
+    _VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
+    _TEST = {
+        u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html'",
+        u'file': u'1435540.mp3',
+        u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
+        u'info_dict': {
+            u"title": u"Freddie Gibbs Songs - Lay It Down"
+        }
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage_src = self._download_webpage(url, video_id)
+
+        video_url_base64 = self._search_regex(r'data-path="(.*?)"',
+            webpage_src, u'video URL', fatal=False)
+
+        if video_url_base64 == None:
+            video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
+                u'video URL')
+            return self.url_result(video_url, ie='Youtube')
+
+        video_url = base64.b64decode(video_url_base64).decode('utf-8')
+
+        video_title = self._html_search_regex(r"<title>(.*)</title>",
+            webpage_src, u'title')
+
+        results = [{
+                    'id': video_id,
+                    'url' : video_url,
+                    'title' : video_title,
+                    'thumbnail' : self._og_search_thumbnail(webpage_src),
+                    'ext' : 'mp3',
+                    }]
+        return results

youtube_dl/extractor/howcast.py

@@ -5,6 +5,15 @@ from .common import InfoExtractor
 
 class HowcastIE(InfoExtractor):
     _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
+    _TEST = {
+        u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
+        u'file': u'390161.mp4',
+        u'md5': u'1d7ba54e2c9d7dc6935ef39e00529138',
+        u'info_dict': {
+            u"description": u"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot.", 
+            u"title": u"How to Tie a Square Knot Properly"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/hypem.py

@@ -15,6 +15,14 @@ from ..utils import (
 class HypemIE(InfoExtractor):
     """Information Extractor for hypem"""
     _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+    _TEST = {
+        u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
+        u'file': u'1v6ga.mp3',
+        u'md5': u'b9cc91b5af8995e9f0c1cee04c575828',
+        u'info_dict': {
+            u"title": u"Tame"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/ign.py

@@ -0,0 +1,95 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class IGNIE(InfoExtractor):
+    """
+    Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
+    Some videos of it.ign.com are also supported
+    """
+
+    _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles)(/.+)?/(?P<name_or_id>.+)'
+    IE_NAME = u'ign.com'
+
+    _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
+    _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>',
+                       r'id="my_show_video">.*?<p>(.*?)</p>',
+                       ]
+
+    _TEST = {
+        u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
+        u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
+        u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
+        u'info_dict': {
+            u'title': u'The Last of Us Review',
+            u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
+        }
+    }
+
+    def _find_video_id(self, webpage):
+        res_id = [r'data-video-id="(.+?)"',
+                  r'<object id="vid_(.+?)"',
+                  r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
+                  ]
+        return self._search_regex(res_id, webpage, 'video id')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name_or_id = mobj.group('name_or_id')
+        page_type = mobj.group('type')
+        webpage = self._download_webpage(url, name_or_id)
+        if page_type == 'articles':
+            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
+            return self.url_result(video_url, ie='IGN')
+        video_id = self._find_video_id(webpage)
+        result = self._get_video_info(video_id)
+        description = self._html_search_regex(self._DESCRIPTION_RE,
+                                              webpage, 'video description',
+                                              flags=re.DOTALL)
+        result['description'] = description
+        return result
+
+    def _get_video_info(self, video_id):
+        config_url = self._CONFIG_URL_TEMPLATE % video_id
+        config = json.loads(self._download_webpage(config_url, video_id,
+                            u'Downloading video info'))
+        media = config['playlist']['media']
+        video_url = media['url']
+
+        return {'id': media['metadata']['videoId'],
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'title': media['metadata']['title'],
+                'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
+                }
+
+
+class OneUPIE(IGNIE):
+    """Extractor for 1up.com, it uses the ign videos system."""
+
+    _VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
+    IE_NAME = '1up.com'
+
+    _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
+
+    _TEST = {
+        u'url': u'http://gamevideos.1up.com/video/id/34976',
+        u'file': u'34976.mp4',
+        u'md5': u'68a54ce4ebc772e4b71e3123d413163d',
+        u'info_dict': {
+            u'title': u'Sniper Elite V2 - Trailer',
+            u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        id = mobj.group('name_or_id')
+        result = super(OneUPIE, self)._real_extract(url)
+        result['id'] = id
+        return result

youtube_dl/extractor/ina.py

@@ -5,7 +5,15 @@ from .common import InfoExtractor
 
 class InaIE(InfoExtractor):
     """Information Extractor for Ina.fr"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
+    _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
+    _TEST = {
+        u'url': u'www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
+        u'file': u'I12055569.mp4',
+        u'md5': u'a667021bf2b41f8dc6049479d9bb38a3',
+        u'info_dict': {
+            u"title": u"Fran\u00e7ois Hollande \"Je crois que c'est clair\""
+        }
+    }
 
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/infoq.py

@@ -11,6 +11,18 @@ from ..utils import (
 
 class InfoQIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+    _TEST = {
+        u"name": u"InfoQ",
+        u"url": u"http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
+        u"file": u"12-jan-pythonthings.mp4",
+        u"info_dict": {
+            u"description": u"Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
+            u"title": u"A Few of My Favorite [Python] Things"
+        },
+        u"params": {
+            u"skip_download": True
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/instagram.py

@@ -0,0 +1,35 @@
+import re
+
+from .common import InfoExtractor
+
+class InstagramIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/'
+    _TEST = {
+        u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        u'file': u'aye83DjauH.mp4',
+        u'md5': u'0d2da106a9d2631273e192b372806516',
+        u'info_dict': {
+            u"uploader_id": u"naomipq", 
+            u"title": u"Video by naomipq",
+            u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+        uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
+            webpage, u'uploader id', fatal=False)
+        desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description',
+            fatal=False)
+
+        return [{
+            'id':        video_id,
+            'url':       self._og_search_video_url(webpage),
+            'ext':       'mp4',
+            'title':     u'Video by %s' % uploader_id,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'uploader_id' : uploader_id,
+            'description': desc,
+        }]

youtube_dl/extractor/jeuxvideo.py

@@ -0,0 +1,47 @@
+# coding: utf-8
+
+import json
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+class JeuxVideoIE(InfoExtractor):
+    _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
+
+    _TEST = {
+        u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        u'file': u'5182.mp4',
+        u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
+        u'info_dict': {
+            u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
+
+        xml_link = m_download.group(1)
+        
+        id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
+
+        xml_config = self._download_webpage(xml_link, title,
+                                                  'Downloading XML config')
+        config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
+        info = re.search(r'<format\.json>(.*?)</format\.json>',
+                         xml_config, re.MULTILINE|re.DOTALL).group(1)
+        info = json.loads(info)['versions'][0]
+        
+        video_url = 'http://video720.jeuxvideo.com/' + info['file']
+
+        return {'id': id,
+                'title' : config.find('titre_video').text,
+                'ext' : 'mp4',
+                'url' : video_url,
+                'description': self._og_search_description(webpage),
+                'thumbnail': config.find('image').text,
+                }

youtube_dl/extractor/jukebox.py

@@ -0,0 +1,56 @@
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unescapeHTML,
+)
+
+class JukeboxIE(InfoExtractor):
+    _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html'
+    _IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
+    _VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
+    _TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
+    _IS_YOUTUBE = r'config":{"file":"(?P<youtube_url>http:[\\][/][\\][/]www[.]youtube[.]com[\\][/]watch[?]v=[^"]+)"'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
+
+        html = self._download_webpage(url, video_id)
+
+        mobj = re.search(self._IFRAME, html)
+        if mobj is None:
+            raise ExtractorError(u'Cannot extract iframe url')
+        iframe_url = unescapeHTML(mobj.group('iframe'))
+
+        iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
+        mobj = re.search(r'class="jkb_waiting"', iframe_html)
+        if mobj is not None:
+            raise ExtractorError(u'Video is not available(in your country?)!')
+
+        self.report_extraction(video_id)
+
+        mobj = re.search(self._VIDEO_URL, iframe_html)
+        if mobj is None:
+            mobj = re.search(self._IS_YOUTUBE, iframe_html)
+            if mobj is None:
+                raise ExtractorError(u'Cannot extract video url')
+            youtube_url = unescapeHTML(mobj.group('youtube_url')).replace('\/','/')
+            self.to_screen(u'Youtube video detected')
+            return self.url_result(youtube_url,ie='Youtube')
+        video_url = unescapeHTML(mobj.group('video_url')).replace('\/','/')
+        video_ext = unescapeHTML(mobj.group('video_ext'))
+
+        mobj = re.search(self._TITLE, html)
+        if mobj is None:
+            raise ExtractorError(u'Cannot extract title')
+        title = unescapeHTML(mobj.group('title'))
+        artist = unescapeHTML(mobj.group('artist'))
+
+        return [{'id': video_id,
+                 'url': video_url,
+                 'title': artist + '-' + title,
+                 'ext': video_ext
+                 }]

youtube_dl/extractor/justintv.py

@@ -26,6 +26,17 @@ class JustinTVIE(InfoExtractor):
         """
     _JUSTIN_PAGE_LIMIT = 100
     IE_NAME = u'justin.tv'
+    _TEST = {
+        u'url': u'http://www.twitch.tv/thegamedevhub/b/296128360',
+        u'file': u'296128360.flv',
+        u'md5': u'ecaa8a790c22a40770901460af191c9a',
+        u'info_dict': {
+            u"upload_date": u"20110927", 
+            u"uploader_id": 25114803, 
+            u"uploader": u"thegamedevhub", 
+            u"title": u"Beginner Series - Scripting With Python Pt.1"
+        }
+    }
 
     def report_download_page(self, channel, offset):
         """Report attempt to download a single page of videos."""

youtube_dl/extractor/kankan.py

@@ -0,0 +1,39 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class KankanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
+    
+    _TEST = {
+        u'url': u'http://yinyue.kankan.com/vod/48/48863.shtml',
+        u'file': u'48863.flv',
+        u'md5': u'29aca1e47ae68fc28804aca89f29507e',
+        u'info_dict': {
+            u'title': u'Ready To Go',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
+        surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
+        gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
+        gcid = gcids[-1]
+
+        video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
+                                                 video_id, u'Downloading video url info')
+        ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
+        path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
+        video_url = 'http://%s%s' % (ip, path)
+
+        return {'id': video_id,
+                'title': title,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                }

youtube_dl/extractor/keek.py

@@ -4,8 +4,17 @@ from .common import InfoExtractor
 
 
 class KeekIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
     IE_NAME = u'keek'
+    _TEST = {
+        u'url': u'https://www.keek.com/ytdl/keeks/NODfbab',
+        u'file': u'NODfbab.mp4',
+        u'md5': u'9b0636f8c0f7614afa4ea5e4c6e57e83',
+        u'info_dict': {
+            u"uploader": u"ytdl", 
+            u"title": u"test chars: \"'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
+        }
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
@@ -15,8 +24,7 @@ class KeekIE(InfoExtractor):
         thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
         webpage = self._download_webpage(url, video_id)
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title')
+        video_title = self._og_search_title(webpage)
 
         uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
             webpage, u'uploader', fatal=False)

youtube_dl/extractor/liveleak.py

@@ -10,6 +10,16 @@ class LiveLeakIE(InfoExtractor):
 
     _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
     IE_NAME = u'liveleak'
+    _TEST = {
+        u'url': u'http://www.liveleak.com/view?i=757_1364311680',
+        u'file': u'757_1364311680.mp4',
+        u'md5': u'0813c2430bea7a46bf13acf3406992f4',
+        u'info_dict': {
+            u"description": u"extremely bad day for this guy..!", 
+            u"uploader": u"ljfriel2", 
+            u"title": u"Most unlucky car accident"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -23,11 +33,9 @@ class LiveLeakIE(InfoExtractor):
         video_url = self._search_regex(r'file: "(.*?)",',
             webpage, u'video URL')
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title').replace('LiveLeak.com -', '').strip()
+        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
 
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
-            webpage, u'description', fatal=False)
+        video_description = self._og_search_description(webpage)
 
         video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
             webpage, u'uploader', fatal=False)

youtube_dl/extractor/livestream.py

@@ -0,0 +1,52 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_parse_urlparse, compat_urlparse
+
+
+class LivestreamIE(InfoExtractor):
+    _VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _TEST = {
+        u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
+        u'file': u'4719370.mp4',
+        u'md5': u'0d2186e3187d185a04b3cdd02b828836',
+        u'info_dict': {
+            u'title': u'Live from Webster Hall NYC',
+            u'upload_date': u'20121012',
+        }
+    }
+
+    def _extract_video_info(self, video_data):
+        video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
+        return {'id': video_data['id'],
+                'url': video_url,
+                'ext': 'mp4',
+                'title': video_data['caption'],
+                'thumbnail': video_data['thumbnail_url'],
+                'upload_date': video_data['updated_at'].replace('-','')[:8],
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        event_name = mobj.group('event_name')
+        webpage = self._download_webpage(url, video_id or event_name)
+
+        if video_id is None:
+            # This is an event page:
+            api_url = self._search_regex(r'event_design_eventId: \'(.+?)\'',
+                                         webpage, 'api url')
+            info = json.loads(self._download_webpage(api_url, event_name,
+                                                     u'Downloading event info'))
+            videos = [self._extract_video_info(video_data['data'])
+                for video_data in info['feed']['data'] if video_data['type'] == u'video']
+            return self.playlist_result(videos, info['id'], info['full_name'])
+        else:
+            og_video = self._og_search_video_url(webpage, name=u'player url')
+            query_str = compat_urllib_parse_urlparse(og_video).query
+            query = compat_urlparse.parse_qs(query_str)
+            api_url = query['play_url'][0].replace('.smil', '')
+            info = json.loads(self._download_webpage(api_url, video_id,
+                                                     u'Downloading video info'))
+            return self._extract_video_info(info)

youtube_dl/extractor/metacafe.py

@@ -9,7 +9,7 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_str,
-
+    determine_ext,
     ExtractorError,
 )
 
@@ -20,6 +20,28 @@ class MetacafeIE(InfoExtractor):
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = u'metacafe'
+    _TESTS = [{
+        u"add_ie": ["Youtube"],
+        u"url":  u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
+        u"file":  u"_aUehQsCQtM.flv",
+        u"info_dict": {
+            u"upload_date": u"20090102",
+            u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
+            u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
+            u"uploader": u"PBS",
+            u"uploader_id": u"PBS"
+        }
+    },
+    {
+        u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
+        u"file": u"an-dVVXnuY7Jh77J.mp4",
+        u"info_dict": {
+            u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
+            u"uploader": u"anyclip",
+            u"description": u"md5:38c711dd98f5bb87acf973d573442e67"
+        }
+    }]
+
 
     def report_disclaimer(self):
         """Report disclaimer retrieval."""
@@ -60,14 +82,16 @@ class MetacafeIE(InfoExtractor):
             return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
 
         # Retrieve video webpage to extract further information
-        webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id)
+        req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
+        req.headers['Cookie'] = 'flashVersion=0;'
+        webpage = self._download_webpage(req, video_id)
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
         if mobj is not None:
             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
-            video_extension = mediaURL[-3:]
+            video_ext = mediaURL[-3:]
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
@@ -77,34 +101,37 @@ class MetacafeIE(InfoExtractor):
                 gdaKey = mobj.group(1)
                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
         else:
-            mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
-            if mobj is None:
-                raise ExtractorError(u'Unable to extract media URL')
-            vardict = compat_parse_qs(mobj.group(1))
-            if 'mediaData' not in vardict:
-                raise ExtractorError(u'Unable to extract media URL')
-            mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
-            if mobj is None:
-                raise ExtractorError(u'Unable to extract media URL')
-            mediaURL = mobj.group('mediaURL').replace('\\/', '/')
-            video_extension = mediaURL[-3:]
-            video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
+            mobj = re.search(r'<video src="([^"]+)"', webpage)
+            if mobj:
+                video_url = mobj.group(1)
+                video_ext = 'mp4'
+            else:
+                mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+                if mobj is None:
+                    raise ExtractorError(u'Unable to extract media URL')
+                vardict = compat_parse_qs(mobj.group(1))
+                if 'mediaData' not in vardict:
+                    raise ExtractorError(u'Unable to extract media URL')
+                mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
+                if mobj is None:
+                    raise ExtractorError(u'Unable to extract media URL')
+                mediaURL = mobj.group('mediaURL').replace('\\/', '/')
+                video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
+                video_ext = determine_ext(video_url)
 
-        mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract title')
-        video_title = mobj.group(1).decode('utf-8')
+        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
+        description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+                r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
+                webpage, u'uploader nickname', fatal=False)
 
-        mobj = re.search(r'submitter=(.*?);', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract uploader nickname')
-        video_uploader = mobj.group(1)
-
-        return [{
-            'id':       video_id.decode('utf-8'),
-            'url':      video_url.decode('utf-8'),
-            'uploader': video_uploader.decode('utf-8'),
+        return {
+            '_type':    'video',
+            'id':       video_id,
+            'url':      video_url,
+            'description': description,
+            'uploader': video_uploader,
             'upload_date':  None,
             'title':    video_title,
-            'ext':      video_extension.decode('utf-8'),
-        }]
+            'ext':      video_ext,
+        }

youtube_dl/extractor/mit.py

@@ -0,0 +1,74 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    get_element_by_id,
+)
+
+
+class TechTVMITIE(InfoExtractor):
+    IE_NAME = u'techtv.mit.edu'
+    _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+        u'file': u'25418.mp4',
+        u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
+        u'info_dict': {
+            u'title': u'MIT DNA Learning Center Set',
+            u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        raw_page = self._download_webpage(
+            'http://techtv.mit.edu/videos/%s' % video_id, video_id)
+        clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
+
+        base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
+            raw_page, u'base url')
+        formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
+            u'video formats')
+        formats = json.loads(formats_json)
+        formats = sorted(formats, key=lambda f: f['bitrate'])
+
+        title = get_element_by_id('edit-title', clean_page)
+        description = clean_html(get_element_by_id('edit-description', clean_page))
+        thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
+            raw_page, u'thumbnail', flags=re.DOTALL)
+
+        return {'id': video_id,
+                'title': title,
+                'url': base_url + formats[-1]['url'].replace('mp4:', ''),
+                'ext': 'mp4',
+                'description': description,
+                'thumbnail': thumbnail,
+                }
+
+
+class MITIE(TechTVMITIE):
+    IE_NAME = u'video.mit.edu'
+    _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
+
+    _TEST = {
+        u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+        u'file': u'21783.mp4',
+        u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
+        u'info_dict': {
+            u'title': u'The Government is Profiling You',
+            u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        page_title = mobj.group('title')
+        webpage = self._download_webpage(url, page_title)
+        self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
+        embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
+            u'embed url')
+        return self.url_result(embed_url, ie='TechTVMIT')

youtube_dl/extractor/mtv.py

@@ -1,28 +1,110 @@
 import re
-import socket
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_request,
-
+    compat_urllib_parse,
     ExtractorError,
 )
 
+def _media_xml_tag(tag):
+    return '{http://search.yahoo.com/mrss/}%s' % tag
 
 class MTVIE(InfoExtractor):
-    _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
-    _WORKING = False
+    _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$'
+
+    _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
+
+    _TESTS = [
+        {
+            u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
+            u'file': u'853555.mp4',
+            u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
+            u'info_dict': {
+                u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
+                u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
+            },
+        },
+        {
+            u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
+            u'file': u'USCJY1331283.mp4',
+            u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
+            u'info_dict': {
+                u'title': u'Everything Has Changed',
+                u'upload_date': u'20130606',
+                u'uploader': u'Taylor Swift',
+            },
+            u'skip': u'VEVO is only available in some countries',
+        },
+    ]
+
+    @staticmethod
+    def _id_from_uri(uri):
+        return uri.split(':')[-1]
+
+    # This was originally implemented for ComedyCentral, but it also works here
+    @staticmethod
+    def _transform_rtmp_url(rtmp_video_url):
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
+        if not m:
+            raise ExtractorError(u'Cannot transform RTMP url')
+        base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+        return base + m.group('finalid')
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        return 'http://mtv.mtvnimages.com/uri/' + uri
+
+    def _extract_video_url(self, metadataXml):
+        if '/error_country_block.swf' in metadataXml:
+            raise ExtractorError(u'This video is not available from your country.', expected=True)
+        mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
+        renditions = mdoc.findall('.//rendition')
+
+        # For now, always pick the highest quality.
+        rendition = renditions[-1]
+
+        try:
+            _,_,ext = rendition.attrib['type'].partition('/')
+            format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
+            rtmp_video_url = rendition.find('./src').text
+        except KeyError:
+            raise ExtractorError('Invalid rendition field.')
+        video_url = self._transform_rtmp_url(rtmp_video_url)
+        return {'ext': ext, 'url': video_url, 'format': format}
+
+    def _get_video_info(self, itemdoc):
+        uri = itemdoc.find('guid').text
+        video_id = self._id_from_uri(uri)
+        self.report_extraction(video_id)
+        mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url']
+        if 'acceptMethods' not in mediagen_url:
+            mediagen_url += '&acceptMethods=fms'
+        mediagen_page = self._download_webpage(mediagen_url, video_id,
+                                               u'Downloading video urls')
+        video_info = self._extract_video_url(mediagen_page)
+
+        description_node = itemdoc.find('description')
+        if description_node is not None:
+            description = description_node.text
+        else:
+            description = None
+        video_info.update({'title': itemdoc.find('title').text,
+                           'id': video_id,
+                           'thumbnail': self._get_thumbnail_url(uri, itemdoc),
+                           'description': description,
+                           })
+        return video_info
+
+    def _get_videos_info(self, uri):
+        video_id = self._id_from_uri(uri)
+        data = compat_urllib_parse.urlencode({'uri': uri})
+        infoXml = self._download_webpage(self._FEED_URL +'?' + data, video_id,
+                                         u'Downloading info')
+        idoc = xml.etree.ElementTree.fromstring(infoXml.encode('utf-8'))
+        return [self._get_video_info(item) for item in idoc.findall('.//item')]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        if not mobj.group('proto'):
-            url = 'http://' + url
         video_id = mobj.group('videoid')
 
         webpage = self._download_webpage(url, video_id)
@@ -35,46 +117,5 @@ class MTVIE(InfoExtractor):
             self.to_screen(u'Vevo video detected: %s' % vevo_id)
             return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 
-        #song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
-        #    webpage, u'song name', fatal=False)
-
-        video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
-            webpage, u'title')
-
-        mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
-            webpage, u'mtvn_uri', fatal=False)
-
-        content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
-            webpage, u'content id', fatal=False)
-
-        videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
-        self.report_extraction(video_id)
-        request = compat_urllib_request.Request(videogen_url)
-        try:
-            metadataXml = compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
-
-        mdoc = xml.etree.ElementTree.fromstring(metadataXml)
-        renditions = mdoc.findall('.//rendition')
-
-        # For now, always pick the highest quality.
-        rendition = renditions[-1]
-
-        try:
-            _,_,ext = rendition.attrib['type'].partition('/')
-            format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
-            video_url = rendition.find('./src').text
-        except KeyError:
-            raise ExtractorError('Invalid rendition field.')
-
-        info = {
-            'id': video_id,
-            'url': video_url,
-            'upload_date': None,
-            'title': video_title,
-            'ext': ext,
-            'format': format,
-        }
-
-        return [info]
+        uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
+        return self._get_videos_info(uri)

youtube_dl/extractor/muzu.py

@@ -0,0 +1,64 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    determine_ext,
+)
+
+
+class MuzuTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www.muzu.tv/(.+?)/(.+?)/(?P<id>\d+)'
+    IE_NAME = u'muzu.tv'
+
+    _TEST = {
+        u'url': u'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/',
+        u'file': u'1981454.mp4',
+        u'md5': u'98f8b2c7bc50578d6a0364fff2bfb000',
+        u'info_dict': {
+            u'title': u'Cat Walk (Original Mix)',
+            u'description': u'md5:90e868994de201b2570e4e5854e19420',
+            u'uploader': u'MarcAshken featuring SOS',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        info_data = compat_urllib_parse.urlencode({'format': 'json',
+                                                   'url': url,
+                                                   })
+        video_info_page = self._download_webpage('http://www.muzu.tv/api/oembed/?%s' % info_data,
+                                                 video_id, u'Downloading video info')
+        info = json.loads(video_info_page)
+
+        player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
+                                                  video_id, u'Downloading player info')
+        video_info = json.loads(player_info_page)['videos'][0]
+        for quality in ['1080' , '720', '480', '360']:
+            if video_info.get('v%s' % quality):
+                break
+
+        data = compat_urllib_parse.urlencode({'ai': video_id,
+                                              # Even if each time you watch a video the hash changes,
+                                              # it seems to work for different videos, and it will work
+                                              # even if you use any non empty string as a hash
+                                              'viewhash': 'VBNff6djeV4HV5TRPW5kOHub2k',
+                                              'device': 'web',
+                                              'qv': quality,
+                                              })
+        video_url_page = self._download_webpage('http://player.muzu.tv/player/requestVideo?%s' % data,
+                                                video_id, u'Downloading video url')
+        video_url_info = json.loads(video_url_page)
+        video_url = video_url_info['url']
+
+        return {'id': video_id,
+                'title': info['title'],
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': info['thumbnail_url'],
+                'description': info['description'],
+                'uploader': info['author_name'],
+                }

youtube_dl/extractor/myspass.py

@@ -11,6 +11,15 @@ from ..utils import (
 
 class MySpassIE(InfoExtractor):
     _VALID_URL = r'http://www.myspass.de/.*'
+    _TEST = {
+        u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
+        u'file': u'11741.mp4',
+        u'md5': u'0b49f4844a068f8b33f4b7c88405862b',
+        u'info_dict': {
+            u"description": u"Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?", 
+            u"title": u"Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
+        }
+    }
 
     def _real_extract(self, url):
         META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'

youtube_dl/extractor/myvideo.py

@@ -2,11 +2,13 @@ import binascii
 import base64
 import hashlib
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import (
     compat_ord,
     compat_urllib_parse,
+    compat_urllib_request,
 
     ExtractorError,
 )
@@ -16,8 +18,16 @@ from ..utils import (
 class MyVideoIE(InfoExtractor):
     """Information Extractor for myvideo.de."""
 
-    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/([0-9]+)/([^?/]+).*'
     IE_NAME = u'myvideo'
+    _TEST = {
+        u'url': u'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
+        u'file': u'8229274.flv',
+        u'md5': u'2d2753e8130479ba2cb7e0a37002053e',
+        u'info_dict': {
+            u"title": u"bowling-fail-or-win"
+        }
+    }
 
     # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
     # Released into the Public Domain by Tristan Fischer on 2013-05-19
@@ -77,6 +87,20 @@ class MyVideoIE(InfoExtractor):
                 'ext':      video_ext,
             }]
 
+        mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage)
+        if mobj is not None:
+            request = compat_urllib_request.Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
+            response = self._download_webpage(request, video_id,
+                                              u'Downloading video info')
+            info = json.loads(base64.b64decode(response).decode('utf-8'))
+            return {'id': video_id,
+                    'title': info['title'],
+                    'url': info['streaming_url'].replace('rtmpe', 'rtmpt'),
+                    'play_path': info['filename'],
+                    'ext': 'flv',
+                    'thumbnail': info['thumbnail'][0]['url'],
+                    }
+
         # try encxml
         mobj = re.search('var flashvars={(.+?)}', webpage)
         if mobj is None:

youtube_dl/extractor/naver.py

@@ -0,0 +1,73 @@
+# encoding: utf-8
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    ExtractorError,
+)
+
+
+class NaverIE(InfoExtractor):
+    _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://tvcast.naver.com/v/81652',
+        u'file': u'81652.mp4',
+        u'info_dict': {
+            u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
+            u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
+            u'upload_date': u'20130903',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+        m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
+            webpage)
+        if m_id is None:
+            raise ExtractorError(u'couldn\'t extract vid and key')
+        vid = m_id.group(1)
+        key = m_id.group(2)
+        query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,})
+        query_urls = compat_urllib_parse.urlencode({
+            'masterVid': vid,
+            'protocol': 'p2p',
+            'inKey': key,
+        })
+        info_xml = self._download_webpage(
+            'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
+            video_id, u'Downloading video info')
+        urls_xml = self._download_webpage(
+            'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
+            video_id, u'Downloading video formats info')
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
+
+        formats = []
+        for format_el in urls.findall('EncodingOptions/EncodingOption'):
+            domain = format_el.find('Domain').text
+            if domain.startswith('rtmp'):
+                continue
+            formats.append({
+                'url': domain + format_el.find('uri').text,
+                'ext': 'mp4',
+                'width': int(format_el.find('width').text),
+                'height': int(format_el.find('height').text),
+            })
+
+        info = {
+            'id': video_id,
+            'title': info.find('Subject').text,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'upload_date': info.find('WriteDate').text.replace('.', ''),
+            'view_count': int(info.find('PlayCount').text),
+        }
+        # TODO: Remove when #980 has been merged
+        info.update(formats[-1])
+        return info

youtube_dl/extractor/nba.py

@@ -8,6 +8,15 @@ from ..utils import (
 
 class NBAIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
+    _TEST = {
+        u'url': u'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
+        u'file': u'0021200253-okc-bkn-recap.nba.mp4',
+        u'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
+        u'info_dict': {
+            u"description": u"Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.", 
+            u"title": u"Thunder vs. Nets"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -21,8 +30,7 @@ class NBAIE(InfoExtractor):
         video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
 
         shortened_video_id = video_id.rpartition('/')[2]
-        title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"',
-            webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
+        title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
 
         # It isn't there in the HTML it returns to us
         # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)

youtube_dl/extractor/nbc.py

@@ -0,0 +1,33 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import find_xpath_attr, compat_str
+
+
+class NBCNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
+        u'file': u'52753292.flv',
+        u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
+        u'info_dict': {
+            u'title': u'Crew emerges after four-month Mars food study',
+            u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
+
+        return {'id': video_id,
+                'title': info.find('headline').text,
+                'ext': 'flv',
+                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+                'description': compat_str(info.find('caption').text),
+                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+                }

youtube_dl/extractor/ooyala.py

@@ -0,0 +1,52 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import unescapeHTML
+
+class OoyalaIE(InfoExtractor):
+    _VALID_URL = r'https?://.+?\.ooyala\.com/.*?embedCode=(?P<id>.+?)(&|$)'
+
+    _TEST = {
+        # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
+        u'url': u'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+        u'file': u'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8.mp4',
+        u'md5': u'3f5cceb3a7bf461d6c29dc466cf8033c',
+        u'info_dict': {
+            u'title': u'Explaining Data Recovery from Hard Drives and SSDs',
+            u'description': u'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+        },
+    }
+
+    def _extract_result(self, info, more_info):
+        return {'id': info['embedCode'],
+                'ext': 'mp4',
+                'title': unescapeHTML(info['title']),
+                'url': info['url'],
+                'description': unescapeHTML(more_info['description']),
+                'thumbnail': more_info['promo'],
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        embedCode = mobj.group('id')
+        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
+        player = self._download_webpage(player_url, embedCode)
+        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
+                                        player, u'mobile player url')
+        mobile_player = self._download_webpage(mobile_url, embedCode)
+        videos_info = self._search_regex(r'eval\("\((\[{.*?stream_redirect.*?}\])\)"\);', mobile_player, u'info').replace('\\"','"')
+        videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"')
+        videos_info = json.loads(videos_info)
+        videos_more_info =json.loads(videos_more_info)
+
+        if videos_more_info.get('lineup'):
+            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
+            return {'_type': 'playlist',
+                    'id': embedCode,
+                    'title': unescapeHTML(videos_more_info['title']),
+                    'entries': videos,
+                    }
+        else:
+            return self._extract_result(videos_info[0], videos_more_info)
+        

youtube_dl/extractor/orf.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+
+import re
+import xml.etree.ElementTree
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    ExtractorError,
+    find_xpath_attr,
+)
+
+class ORFIE(InfoExtractor):
+    _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        webpage = self._download_webpage(url, playlist_id)
+
+        flash_xml = self._search_regex('ORF.flashXML = \'(.+?)\'', webpage, u'flash xml')
+        flash_xml = compat_urlparse.parse_qs('xml='+flash_xml)['xml'][0]
+        flash_config = xml.etree.ElementTree.fromstring(flash_xml.encode('utf-8'))
+        playlist_json = self._search_regex(r'playlist\': \'(\[.*?\])\'', webpage, u'playlist').replace(r'\"','"')
+        playlist = json.loads(playlist_json)
+
+        videos = []
+        ns = '{http://tempuri.org/XMLSchema.xsd}'
+        xpath = '%(ns)sPlaylist/%(ns)sItems/%(ns)sItem' % {'ns': ns}
+        webpage_description = self._og_search_description(webpage)
+        for (i, (item, info)) in enumerate(zip(flash_config.findall(xpath), playlist), 1):
+            # Get best quality url
+            rtmp_url = None
+            for q in ['Q6A', 'Q4A', 'Q1A']:
+                video_url = find_xpath_attr(item, '%sVideoUrl' % ns, 'quality', q)
+                if video_url is not None:
+                    rtmp_url = video_url.text
+                    break
+            if rtmp_url is None:
+                raise ExtractorError(u'Couldn\'t get video url: %s' % info['id'])
+            description = self._html_search_regex(
+                r'id="playlist_entry_%s".*?<p>(.*?)</p>' % i, webpage,
+                u'description', default=webpage_description, flags=re.DOTALL)
+            videos.append({
+                '_type': 'video',
+                'id': info['id'],
+                'title': info['title'],
+                'url': rtmp_url,
+                'ext': 'flv',
+                'description': description,
+                })
+
+        return videos

youtube_dl/extractor/pbs.py

@@ -0,0 +1,34 @@
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class PBSIE(InfoExtractor):
+    _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
+
+    _TEST = {
+        u'url': u'http://video.pbs.org/video/2365006249/',
+        u'file': u'2365006249.mp4',
+        u'md5': 'ce1888486f0908d555a8093cac9a7362',
+        u'info_dict': {
+            u'title': u'A More Perfect Union',
+            u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
+            u'duration': 3190,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
+        info_page = self._download_webpage(info_url, video_id)
+        info =json.loads(info_page)
+        return {'id': video_id,
+                'title': info['title'],
+                'url': info['alternate_encoding']['url'],
+                'ext': 'mp4',
+                'description': info['program'].get('description'),
+                'thumbnail': info.get('image_url'),
+                'duration': info.get('duration'),
+                }

youtube_dl/extractor/photobucket.py

@@ -16,6 +16,16 @@ class PhotobucketIE(InfoExtractor):
     # Check if it's necessary to keep the old extracion process
     _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
     IE_NAME = u'photobucket'
+    _TEST = {
+        u'url': u'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
+        u'file': u'zpsc0c3b9fa.mp4',
+        u'md5': u'7dabfb92b0a31f6c16cebc0f8e60ff99',
+        u'info_dict': {
+            u"upload_date": u"20130504", 
+            u"uploader": u"rachaneronas", 
+            u"title": u"Tired of Link Building? Try BacklinkMyDomain.com!"
+        }
+    }
 
     def _real_extract(self, url):
         # Extract id from URL

youtube_dl/extractor/pornotube.py

@@ -10,6 +10,15 @@ from ..utils import (
 
 class PornotubeIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+    _TEST = {
+        u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
+        u'file': u'1689755.flv',
+        u'md5': u'374dd6dcedd24234453b295209aa69b6',
+        u'info_dict': {
+            u"upload_date": u"20090708", 
+            u"title": u"Marilyn-Monroe-Bathing"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/rbmaradio.py

@@ -11,6 +11,18 @@ from ..utils import (
 
 class RBMARadioIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+    _TEST = {
+        u'url': u'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
+        u'file': u'ford-lopatin-live-at-primavera-sound-2011.mp3',
+        u'md5': u'6bc6f9bcb18994b4c983bc3bf4384d95',
+        u'info_dict': {
+            u"uploader_id": u"ford-lopatin", 
+            u"location": u"Spain", 
+            u"description": u"Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.", 
+            u"uploader": u"Ford & Lopatin", 
+            u"title": u"Live at Primavera Sound 2011"
+        }
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

youtube_dl/extractor/redtube.py

@@ -5,6 +5,14 @@ from .common import InfoExtractor
 
 class RedTubeIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+    _TEST = {
+        u'url': u'http://www.redtube.com/66418',
+        u'file': u'66418.mp4',
+        u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
+        u'info_dict': {
+            u"title": u"Sucked on a toilet"
+        }
+    }
 
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/ringtv.py

@@ -0,0 +1,37 @@
+import re
+
+from .common import InfoExtractor
+
+
+class RingTVIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/videos/video/([^/]+)'
+    _TEST = {
+        u"url": u"http://ringtv.craveonline.com/videos/video/746619-canelo-alvarez-talks-about-mayweather-showdown",
+        u"file": u"746619.mp4",
+        u"md5": u"7c46b4057d22de32e0a539f017e64ad3",
+        u"info_dict": {
+            u"title": u"Canelo Alvarez talks about Mayweather showdown",
+            u"description": u"Saul \\\"Canelo\\\" Alvarez spoke to the media about his Sept. 14 showdown with Floyd Mayweather after their kick-off presser in NYC. Canelo is motivated and confident that he will have the speed and gameplan to beat the pound-for-pound king."
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1).split('-')[0]
+        webpage = self._download_webpage(url, video_id)
+        title = self._search_regex(r'<title>(.+?)</title>',
+        		webpage, 'video title').replace(' | RingTV','')
+        description = self._search_regex(r'<div class="blurb">(.+?)</div>',
+        		webpage, 'Description')
+        final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" %(str(video_id))
+        thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" %(str(video_id))
+        ext = final_url.split('.')[-1]
+        return [{
+            'id'          : video_id,
+            'url'         : final_url,
+            'ext'         : ext,
+            'title'       : title,
+            'thumbnail'   : thumbnail_url,
+            'description' : description,
+        }]
+

youtube_dl/extractor/ro220.py

@@ -0,0 +1,42 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    compat_parse_qs,
+)
+
+
+class Ro220IE(InfoExtractor):
+    IE_NAME = '220.ro'
+    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
+    _TEST = {
+        u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
+        u'file': u'LYV6doKo7f.mp4',
+        u'md5': u'03af18b73a07b4088753930db7a34add',
+        u'info_dict': {
+            u"title": u"Luati-le Banii sez 4 ep 1",
+            u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
+
+        webpage = self._download_webpage(url, video_id)
+        flashVars_str = self._search_regex(
+            r'<param name="flashVars" value="([^"]+)"',
+            webpage, u'flashVars')
+        flashVars = compat_parse_qs(flashVars_str)
+
+        info = {
+            '_type': 'video',
+            'id': video_id,
+            'ext': 'mp4',
+            'url': flashVars['videoURL'][0],
+            'title': flashVars['title'][0],
+            'description': clean_html(flashVars['desc'][0]),
+            'thumbnail': flashVars['preview'][0],
+        }
+        return info

youtube_dl/extractor/roxwel.py

@@ -0,0 +1,49 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import unified_strdate, determine_ext
+
+
+class RoxwelIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)'
+
+    _TEST = {
+        u'url': u'http://www.roxwel.com/player/passionpittakeawalklive.html',
+        u'file': u'passionpittakeawalklive.flv',
+        u'md5': u'd9dea8360a1e7d485d2206db7fe13035',
+        u'info_dict': {
+            u'title': u'Take A Walk (live)',
+            u'uploader': u'Passion Pit',
+            u'description': u'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ',
+        },
+        u'skip': u'Requires rtmpdump',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        filename = mobj.group('filename')
+        info_url = 'http://www.roxwel.com/api/videos/%s' % filename
+        info_page = self._download_webpage(info_url, filename,
+                                           u'Downloading video info')
+
+        self.report_extraction(filename)
+        info = json.loads(info_page)
+        rtmp_rates = sorted([int(r.replace('flv_', '')) for r in info['media_rates'] if r.startswith('flv_')])
+        best_rate = rtmp_rates[-1]
+        url_page_url = 'http://roxwel.com/pl_one_time.php?filename=%s&quality=%s' % (filename, best_rate)
+        rtmp_url = self._download_webpage(url_page_url, filename, u'Downloading video url')
+        ext = determine_ext(rtmp_url)
+        if ext == 'f4v':
+            rtmp_url = rtmp_url.replace(filename, 'mp4:%s' % filename)
+
+        return {'id': filename,
+                'title': info['title'],
+                'url': rtmp_url,
+                'ext': 'flv',
+                'description': info['description'],
+                'thumbnail': info.get('player_image_url') or info.get('image_url_large'),
+                'uploader': info['artist'],
+                'uploader_id': info['artistname'],
+                'upload_date': unified_strdate(info['dbdate']),
+                }

youtube_dl/extractor/rtlnow.py

@@ -0,0 +1,126 @@
+# encoding: utf-8
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError,
+)
+
+class RTLnowIE(InfoExtractor):
+    """Information Extractor for RTL NOW, RTL2 NOW, SUPER RTL NOW and VOX NOW"""
+    _VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?superrtlnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
+    _TESTS = [{
+        u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
+        u'file': u'90419.flv',
+        u'info_dict': {
+            u'upload_date': u'20070416', 
+            u'title': u'Ahornallee - Folge 1 - Der Einzug',
+            u'description': u'Folge 1 - Der Einzug',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+        u'skip': u'Only works from Germany',
+    },
+    {
+        u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
+        u'file': u'69756.flv',
+        u'info_dict': {
+            u'upload_date': u'20120519', 
+            u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
+            u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
+            u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+        u'skip': u'Only works from Germany',
+    },
+    {
+        u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
+        u'file': u'13883.flv',
+        u'info_dict': {
+            u'upload_date': u'20090627', 
+            u'title': u'Voxtours - Südafrika-Reporter II',
+            u'description': u'Südafrika-Reporter II',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    },
+    {
+        u'url': u'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
+        u'file': u'99205.flv',
+        u'info_dict': {
+            u'upload_date': u'20080928', 
+            u'title': u'Medicopter 117 - Angst!',
+            u'description': u'Angst!',
+            u'thumbnail': u'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self,url):
+        mobj = re.match(self._VALID_URL, url)
+
+        webpage_url = u'http://' + mobj.group('url')
+        video_page_url = u'http://' + mobj.group('base_url')
+        video_id = mobj.group(u'video_id')
+
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        note_m = re.search(r'''(?sx)
+            <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
+            <div[ ]id="playerteaser">''', webpage)
+        if note_m:
+            msg = clean_html(note_m.group(1))
+            raise ExtractorError(msg)
+
+        video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>',
+            webpage, u'title')
+        playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
+            webpage, u'playerdata_url')
+
+        playerdata = self._download_webpage(playerdata_url, video_id)
+        mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata)
+        if mobj:
+            video_description = mobj.group(u'description')
+            if mobj.group('upload_date_Y'):
+                video_upload_date = mobj.group('upload_date_Y')
+            else:
+                video_upload_date = u'20' + mobj.group('upload_date_y')
+            video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
+        else:
+            video_description = None
+            video_upload_date = None
+            self._downloader.report_warning(u'Unable to extract description and upload date')
+
+        # Thumbnail: not every video has an thumbnail
+        mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
+        if mobj:
+            video_thumbnail = mobj.group(u'thumbnail')
+        else:
+            video_thumbnail = None
+
+        mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract media URL')
+        video_url = mobj.group(u'url')
+        video_play_path = u'mp4:' + mobj.group(u'play_path')
+        video_player_url = video_page_url + u'includes/vodplayer.swf'
+
+        return [{
+            'id':          video_id,
+            'url':         video_url,
+            'play_path':   video_play_path,
+            'page_url':    video_page_url,
+            'player_url':  video_player_url,
+            'ext':         'flv',
+            'title':       video_title,
+            'description': video_description,
+            'upload_date': video_upload_date,
+            'thumbnail':   video_thumbnail,
+        }]

youtube_dl/extractor/sina.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class SinaIE(InfoExtractor):
+    _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/
+                        (
+                            (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=))(?P<id>\d+?)($|&))))
+                            |
+                            # This is used by external sites like Weibo
+                            (api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
+                        )
+                  '''
+
+    _TEST = {
+        u'url': u'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
+        u'file': u'110028898.flv',
+        u'md5': u'd65dd22ddcf44e38ce2bf58a10c3e71f',
+        u'info_dict': {
+            u'title': u'《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
+        }
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
+
+    def _extract_video(self, video_id):
+        data = compat_urllib_parse.urlencode({'vid': video_id})
+        url_page = self._download_webpage('http://v.iask.com/v_play.php?%s' % data,
+            video_id, u'Downloading video url')
+        image_page = self._download_webpage(
+            'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
+            video_id, u'Downloading thumbnail info')
+        url_doc = xml.etree.ElementTree.fromstring(url_page.encode('utf-8'))
+
+        return {'id': video_id,
+                'url': url_doc.find('./durl/url').text,
+                'ext': 'flv',
+                'title': url_doc.find('./vname').text,
+                'thumbnail': image_page.split('=')[1],
+                }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        video_id = mobj.group('id')
+        if mobj.group('token') is not None:
+            # The video id is in the redirected url
+            self.to_screen(u'Getting video id')
+            request = compat_urllib_request.Request(url)
+            request.get_method = lambda: 'HEAD'
+            (_, urlh) = self._download_webpage_handle(request, 'NA', False)
+            return self._real_extract(urlh.geturl())
+        elif video_id is None:
+            pseudo_id = mobj.group('pseudo_id')
+            webpage = self._download_webpage(url, pseudo_id)
+            video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, u'video id')
+
+        return self._extract_video(video_id)

youtube_dl/extractor/slashdot.py

@@ -0,0 +1,23 @@
+import re
+
+from .common import InfoExtractor
+
+
+class SlashdotIE(InfoExtractor):
+    _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
+
+    _TEST = {
+        u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
+        u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
+        u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
+        u'info_dict': {
+            u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url')
+        return self.url_result(ooyala_url, 'Ooyala')

youtube_dl/extractor/sohu.py

@@ -0,0 +1,90 @@
+# encoding: utf-8
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class SohuIE(InfoExtractor):
+    _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?'
+
+    _TEST = {
+        u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
+        u'file': u'382479172.mp4',
+        u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
+        u'info_dict': {
+            u'title': u'MV：Far East Movement《The Illest》',
+        },
+    }
+
+    def _real_extract(self, url):
+
+        def _fetch_data(vid_id):
+            base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
+            data_url = base_data_url + str(vid_id)
+            data_json = self._download_webpage(
+                data_url, video_id,
+                note=u'Downloading JSON data for ' + str(vid_id))
+            return json.loads(data_json)
+
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
+                                            webpage, u'video title')
+        title = raw_title.partition('-')[0].strip()
+
+        vid = self._html_search_regex(r'var vid="(\d+)"', webpage,
+                                      u'video path')
+        data = _fetch_data(vid)
+
+        QUALITIES = ('ori', 'super', 'high', 'nor')
+        vid_ids = [data['data'][q + 'Vid']
+                   for q in QUALITIES
+                   if data['data'][q + 'Vid'] != 0]
+        if not vid_ids:
+            raise ExtractorError(u'No formats available for this video')
+
+        # For now, we just pick the highest available quality
+        vid_id = vid_ids[-1]
+
+        format_data = data if vid == vid_id else _fetch_data(vid_id)
+        part_count = format_data['data']['totalBlocks']
+        allot = format_data['allot']
+        prot = format_data['prot']
+        clipsURL = format_data['data']['clipsURL']
+        su = format_data['data']['su']
+
+        playlist = []
+        for i in range(part_count):
+            part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
+                        (allot, prot, clipsURL[i], su[i]))
+            part_str = self._download_webpage(
+                part_url, video_id,
+                note=u'Downloading part %d of %d' % (i+1, part_count))
+
+            part_info = part_str.split('|')
+            video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+
+            video_info = {
+                'id': '%s_part%02d' % (video_id, i + 1),
+                'title': title,
+                'url': video_url,
+                'ext': 'mp4',
+            }
+            playlist.append(video_info)
+
+        if len(playlist) == 1:
+            info = playlist[0]
+            info['id'] = video_id
+        else:
+            info = {
+                '_type': 'playlist',
+                'entries': playlist,
+                'id': video_id,
+            }
+
+        return info

youtube_dl/extractor/soundcloud.py

@@ -4,6 +4,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_str,
+    compat_urlparse,
 
     ExtractorError,
     unified_strdate,
@@ -19,68 +20,153 @@ class SoundcloudIE(InfoExtractor):
        of the stream token and uid
      """
 
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+    _VALID_URL = r'''^(?:https?://)?
+                    (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
+                       |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
+                       |(?P<widget>w.soundcloud.com/player/?.*?url=.*)
+                    )
+                    '''
     IE_NAME = u'soundcloud'
+    _TEST = {
+        u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
+        u'file': u'62986583.mp3',
+        u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
+        u'info_dict': {
+            u"upload_date": u"20121011", 
+            u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", 
+            u"uploader": u"E.T. ExTerrestrial Music", 
+            u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+        }
+    }
+
+    _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
+
+    @classmethod
+    def suitable(cls, url):
+        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
 
     def report_resolve(self, video_id):
         """Report information extraction."""
         self.to_screen(u'%s: Resolving id' % video_id)
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+    @classmethod
+    def _resolv_url(cls, url):
+        return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
 
-        # extract uploader (which is in the url)
-        uploader = mobj.group(1)
-        # extract simple title (uploader + slug of song title)
-        slug_title =  mobj.group(2)
-        full_title = '%s/%s' % (uploader, slug_title)
-
-        self.report_resolve(full_title)
-
-        url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
-        resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
-        info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
-
-        info = json.loads(info_json)
+    def _extract_info_dict(self, info, full_title=None):
         video_id = info['id']
-        self.report_extraction(full_title)
+        name = full_title or video_id
+        self.report_extraction(name)
 
-        streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
-        stream_json = self._download_webpage(streams_url, full_title,
-                                             u'Downloading stream definitions',
-                                             u'unable to download stream definitions')
-
-        streams = json.loads(stream_json)
-        mediaURL = streams['http_mp3_128_url']
-        upload_date = unified_strdate(info['created_at'])
-
-        return [{
+        thumbnail = info['artwork_url']
+        if thumbnail is not None:
+            thumbnail = thumbnail.replace('-large', '-t500x500')
+        return {
             'id':       info['id'],
-            'url':      mediaURL,
+            'url':      info['stream_url'] + '?client_id=' + self._CLIENT_ID,
             'uploader': info['user']['username'],
-            'upload_date': upload_date,
+            'upload_date': unified_strdate(info['created_at']),
             'title':    info['title'],
             'ext':      u'mp3',
             'description': info['description'],
-        }]
+            'thumbnail': thumbnail,
+        }
 
-class SoundcloudSetIE(InfoExtractor):
-    """Information extractor for soundcloud.com sets
-       To access the media, the uid of the song and a stream token
-       must be extracted from the page source and the script must make
-       a request to media.soundcloud.com/crossdomain.xml. Then
-       the media can be grabbed by requesting from an url composed
-       of the stream token and uid
-     """
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        if mobj is None:
+            raise ExtractorError(u'Invalid URL: %s' % url)
 
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
+        track_id = mobj.group('track_id')
+        if track_id is not None:
+            info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
+            full_title = track_id
+        elif mobj.group('widget'):
+            query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+            return self.url_result(query['url'][0], ie='Soundcloud')
+        else:
+            # extract uploader (which is in the url)
+            uploader = mobj.group(1)
+            # extract simple title (uploader + slug of song title)
+            slug_title =  mobj.group(2)
+            full_title = '%s/%s' % (uploader, slug_title)
+    
+            self.report_resolve(full_title)
+    
+            url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
+            info_json_url = self._resolv_url(url)
+        info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
+
+        info = json.loads(info_json)
+        return self._extract_info_dict(info, full_title)
+
+class SoundcloudSetIE(SoundcloudIE):
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
     IE_NAME = u'soundcloud:set'
-
-    def report_resolve(self, video_id):
-        """Report information extraction."""
-        self.to_screen(u'%s: Resolving id' % video_id)
+    _TEST = {
+        u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
+        u"playlist": [
+            {
+                u"file":"30510138.mp3",
+                u"md5":"f9136bf103901728f29e419d2c70f55d",
+                u"info_dict": {
+                    u"upload_date": u"20111213",
+                    u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
+                    u"uploader": u"The Royal Concept",
+                    u"title": u"D-D-Dance"
+                }
+            },
+            {
+                u"file":"47127625.mp3",
+                u"md5":"09b6758a018470570f8fd423c9453dd8",
+                u"info_dict": {
+                    u"upload_date": u"20120521",
+                    u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
+                    u"uploader": u"The Royal Concept",
+                    u"title": u"The Royal Concept - Gimme Twice"
+                }
+            },
+            {
+                u"file":"47127627.mp3",
+                u"md5":"154abd4e418cea19c3b901f1e1306d9c",
+                u"info_dict": {
+                    u"upload_date": u"20120521",
+                    u"uploader": u"The Royal Concept",
+                    u"title": u"Goldrushed"
+                }
+            },
+            {
+                u"file":"47127629.mp3",
+                u"md5":"2f5471edc79ad3f33a683153e96a79c1",
+                u"info_dict": {
+                    u"upload_date": u"20120521",
+                    u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
+                    u"uploader": u"The Royal Concept",
+                    u"title": u"In the End"
+                }
+            },
+            {
+                u"file":"47127631.mp3",
+                u"md5":"f9ba87aa940af7213f98949254f1c6e2",
+                u"info_dict": {
+                    u"upload_date": u"20120521",
+                    u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
+                    u"uploader": u"The Royal Concept",
+                    u"title": u"Knocked Up"
+                }
+            },
+            {
+                u"file":"75206121.mp3",
+                u"md5":"f9d1fe9406717e302980c30de4af9353",
+                u"info_dict": {
+                    u"upload_date": u"20130116",
+                    u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central).  \r\nAs a gift to our fans we would like to offer you a free download of the track!  ",
+                    u"uploader": u"The Royal Concept",
+                    u"title": u"World On Fire"
+                }
+            }
+        ]
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -96,7 +182,7 @@ class SoundcloudSetIE(InfoExtractor):
         self.report_resolve(full_title)
 
         url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
-        resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
+        resolv_url = self._resolv_url(url)
         info_json = self._download_webpage(resolv_url, full_title)
 
         videos = []
@@ -107,23 +193,8 @@ class SoundcloudSetIE(InfoExtractor):
             return
 
         self.report_extraction(full_title)
-        for track in info['tracks']:
-            video_id = track['id']
-
-            streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
-            stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
-
-            self.report_extraction(video_id)
-            streams = json.loads(stream_json)
-            mediaURL = streams['http_mp3_128_url']
-
-            videos.append({
-                'id':       video_id,
-                'url':      mediaURL,
-                'uploader': track['user']['username'],
-                'upload_date':  unified_strdate(track['created_at']),
-                'title':    track['title'],
-                'ext':      u'mp3',
-                'description': track['description'],
-            })
-        return videos
+        return {'_type': 'playlist',
+                'entries': [self._extract_info_dict(track) for track in info['tracks']],
+                'id': info['id'],
+                'title': info['title'],
+                }