Merge branch 'master' of https://github.com/rg3/youtube-dl

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.03*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.02**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.06.03**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.06.02
+[debug] youtube-dl version 2016.06.03
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

README.md

@@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 
 To install it right away for all UNIX users (Linux, OS X, etc.), type:
 
-    sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
+    sudo curl -L https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
     sudo chmod a+rx /usr/local/bin/youtube-dl
 
 If you do not have curl, you can alternatively use a recent wget:
@@ -27,13 +27,19 @@ If you do not have curl, you can alternatively use a recent wget:
 
 Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`).
 
-OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/).
+You can also use pip:
+
+    sudo pip install --upgrade youtube-dl
+    
+This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
+
+OS X users can install youtube-dl with [Homebrew](http://brew.sh/):
 
     brew install youtube-dl
 
-You can also use pip:
+Or with [MacPorts](https://www.macports.org/):
 
-    sudo pip install youtube-dl
+    sudo port install youtube-dl
 
 Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
@@ -842,6 +848,12 @@ It is *not* possible to detect whether a URL is supported or not. That's because
 
 If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program.
 
+# Why do I need to go through that much red tape when filing bugs?
+
+Before we had the issue template, despite our extensive [bug reporting instructions](#bugs), about 80% of the issue reports we got were useless, for instance because people used ancient versions hundreds of releases old, because of simple syntactic errors (not in youtube-dl but in general shell usage), because the problem was alrady reported multiple times before, because people did not actually read an error message, even if it said "please install ffmpeg", because people did not mention the URL they were trying to download and many more simple, easy-to-avoid problems, many of whom were totally unrelated to youtube-dl.
+
+youtube-dl is an open-source project manned by too few volunteers, so we'd rather spend time fixing bugs where we are certain none of those simple problems apply, and where we can be reasonably confident to be able to reproduce the issue without asking the reporter repeatedly. As such, the output of `youtube-dl -v YOUR_URL_HERE` is really all that's required to file an issue. The issue template also guides you through some basic steps you can do, such as checking that your version of youtube-dl is current.
+
 # DEVELOPER INSTRUCTIONS
 
 Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.

devscripts/buildserver.py

@@ -13,6 +13,7 @@ import os.path
 
 sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__)))))
 from youtube_dl.compat import (
+    compat_input,
     compat_http_server,
     compat_str,
     compat_urlparse,
@@ -30,11 +31,6 @@ try:
 except ImportError:  # Python 2
     import SocketServer as compat_socketserver
 
-try:
-    compat_input = raw_input
-except NameError:  # Python 3
-    compat_input = input
-
 
 class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer):
     allow_reuse_address = True

devscripts/create-github-release.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+import base64
+import json
+import mimetypes
+import netrc
+import optparse
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.compat import (
+    compat_basestring,
+    compat_input,
+    compat_getpass,
+    compat_print,
+    compat_urllib_request,
+)
+from youtube_dl.utils import (
+    make_HTTPS_handler,
+    sanitized_Request,
+)
+
+
+class GitHubReleaser(object):
+    _API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases'
+    _UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s'
+    _NETRC_MACHINE = 'github.com'
+
+    def __init__(self, debuglevel=0):
+        self._init_github_account()
+        https_handler = make_HTTPS_handler({}, debuglevel=debuglevel)
+        self._opener = compat_urllib_request.build_opener(https_handler)
+
+    def _init_github_account(self):
+        try:
+            info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+            if info is not None:
+                self._username = info[0]
+                self._password = info[2]
+                compat_print('Using GitHub credentials found in .netrc...')
+                return
+            else:
+                compat_print('No GitHub credentials found in .netrc')
+        except (IOError, netrc.NetrcParseError):
+            compat_print('Unable to parse .netrc')
+        self._username = compat_input(
+            'Type your GitHub username or email address and press [Return]: ')
+        self._password = compat_getpass(
+            'Type your GitHub password and press [Return]: ')
+
+    def _call(self, req):
+        if isinstance(req, compat_basestring):
+            req = sanitized_Request(req)
+        # Authorizing manually since GitHub does not response with 401 with
+        # WWW-Authenticate header set (see
+        # https://developer.github.com/v3/#basic-authentication)
+        b64 = base64.b64encode(
+            ('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii')
+        req.add_header('Authorization', 'Basic %s' % b64)
+        response = self._opener.open(req).read().decode('utf-8')
+        return json.loads(response)
+
+    def list_releases(self):
+        return self._call(self._API_URL)
+
+    def create_release(self, tag_name, name=None, body='', draft=False, prerelease=False):
+        data = {
+            'tag_name': tag_name,
+            'target_commitish': 'master',
+            'name': name,
+            'body': body,
+            'draft': draft,
+            'prerelease': prerelease,
+        }
+        req = sanitized_Request(self._API_URL, json.dumps(data).encode('utf-8'))
+        return self._call(req)
+
+    def create_asset(self, release_id, asset):
+        asset_name = os.path.basename(asset)
+        url = self._UPLOADS_URL % (release_id, asset_name)
+        # Our files are small enough to be loaded directly into memory.
+        data = open(asset, 'rb').read()
+        req = sanitized_Request(url, data)
+        mime_type, _ = mimetypes.guess_type(asset_name)
+        req.add_header('Content-Type', mime_type or 'application/octet-stream')
+        return self._call(req)
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH')
+    options, args = parser.parse_args()
+    if len(args) != 2:
+        parser.error('Expected a version and a build directory')
+
+    version, build_path = args
+
+    releaser = GitHubReleaser()
+
+    new_release = releaser.create_release(version, name='youtube-dl %s' % version)
+    release_id = new_release['id']
+
+    for asset in os.listdir(build_path):
+        compat_print('Uploading %s...' % asset)
+        releaser.create_asset(release_id, os.path.join(build_path, asset))
+
+
+if __name__ == '__main__':
+    main()

devscripts/release.sh

@@ -95,15 +95,16 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS)
 (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
 
-/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
+/bin/echo -e "\n### Signing and uploading the new binaries to GitHub..."
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
-scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
+
-ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
+ROOT=$(pwd)
+python devscripts/create-github-release.py $version "$ROOT/build/$version"
+
 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
-ROOT=$(pwd)
 (
     set -e
     ORIGIN_URL=$(git config --get remote.origin.url)

docs/supportedsites.md

@@ -43,8 +43,8 @@
  - **appletrailers:section**
  - **archive.org**: archive.org videos
  - **ARD**
- - **ARD:mediathek**
  - **ARD:mediathek**: Saarländischer Rundfunk
+ - **ARD:mediathek**
  - **arte.tv**
  - **arte.tv:+7**
  - **arte.tv:cinema**
@@ -339,6 +339,7 @@
  - **livestream**
  - **livestream:original**
  - **LnkGo**
+ - **loc**: Library of Congress
  - **LocalNews8**
  - **LoveHomePorn**
  - **lrt.lt**
@@ -528,7 +529,8 @@
  - **Restudy**
  - **Reuters**
  - **ReverbNation**
- - **Revision3**
+ - **revision**
+ - **revision3:embed**
  - **RICE**
  - **RingTV**
  - **RottenTomatoes**
@@ -567,6 +569,7 @@
  - **ScreencastOMatic**
  - **ScreenJunkies**
  - **ScreenwaveMedia**
+ - **Seeker**
  - **SenateISVP**
  - **SendtoNews**
  - **ServingSys**

youtube_dl/__init__.py

@@ -18,7 +18,6 @@ from .options import (
 from .compat import (
     compat_expanduser,
     compat_getpass,
-    compat_print,
     compat_shlex_split,
     workaround_optparse_bug9161,
 )
@@ -76,7 +75,7 @@ def _real_main(argv=None):
 
     # Dump user agent
     if opts.dump_user_agent:
-        compat_print(std_headers['User-Agent'])
+        write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
         sys.exit(0)
 
     # Batch file verification
@@ -101,10 +100,10 @@ def _real_main(argv=None):
 
     if opts.list_extractors:
         for ie in list_extractors(opts.age_limit):
-            compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
+            write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:
-                compat_print('  ' + mu)
+                write_string('  ' + mu + '\n', out=sys.stdout)
         sys.exit(0)
     if opts.list_extractor_descriptions:
         for ie in list_extractors(opts.age_limit):
@@ -117,7 +116,7 @@ def _real_main(argv=None):
                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
                 _COUNTS = ('', '5', '10', 'all')
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
-            compat_print(desc)
+            write_string(desc + '\n', out=sys.stdout)
         sys.exit(0)
 
     # Conflicting, missing and erroneous options

youtube_dl/compat.py

@@ -482,6 +482,11 @@ if sys.version_info < (3, 0) and sys.platform == 'win32':
 else:
     compat_getpass = getpass.getpass
 
+try:
+    compat_input = raw_input
+except NameError:  # Python 3
+    compat_input = input
+
 # Python < 2.6.5 require kwargs to be bytes
 try:
     def _testfunc(x):
@@ -623,6 +628,7 @@ __all__ = [
     'compat_html_entities',
     'compat_http_client',
     'compat_http_server',
+    'compat_input',
     'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',

youtube_dl/downloader/hls.py

@@ -23,11 +23,17 @@ class HlsFD(FragmentFD):
         UNSUPPORTED_FEATURES = (
             r'#EXT-X-KEY:METHOD=(?!NONE)',  # encrypted streams [1]
             r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
+
             # Live streams heuristic does not always work (e.g. geo restricted to Germany
             # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
             # r'#EXT-X-MEDIA-SEQUENCE:(?!0$)',  # live streams [3]
-            r'#EXT-X-PLAYLIST-TYPE:EVENT',  # media segments may be appended to the end of
+
-                                            # event media playlists [4]
+            # This heuristic also is not correct since segments may not be appended as well.
+            # Twitch vods of finished streams have EXT-X-PLAYLIST-TYPE:EVENT despite
+            # no segments will definitely be appended to the end of the playlist.
+            # r'#EXT-X-PLAYLIST-TYPE:EVENT',  # media segments may be appended to the end of
+            #                                 # event media playlists [4]
+
             # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4
             # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
             # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2

youtube_dl/extractor/canalplus.py

@@ -4,11 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     ExtractorError,
     HEADRequest,
     unified_strdate,
-    url_basename,
     qualities,
     int_or_none,
 )
@@ -16,24 +16,38 @@ from ..utils import (
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
-    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:
+                                (?:
+                                    (?:(?:www|m)\.)?canalplus\.fr|
+                                    (?:www\.)?piwiplus\.fr|
+                                    (?:www\.)?d8\.tv|
+                                    (?:www\.)?d17\.tv|
+                                    (?:www\.)?itele\.fr
+                                )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
+                                player\.canalplus\.fr/#/(?P<id>\d+)
+                            )
+
+                    '''
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
     _SITE_ID_MAP = {
-        'canalplus.fr': 'cplus',
+        'canalplus': 'cplus',
-        'piwiplus.fr': 'teletoon',
+        'piwiplus': 'teletoon',
-        'd8.tv': 'd8',
+        'd8': 'd8',
-        'itele.fr': 'itele',
+        'd17': 'd17',
+        'itele': 'itele',
     }
 
     _TESTS = [{
-        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
-        'md5': '12164a6f14ff6df8bd628e8ba9b10b78',
+        'md5': '41f438a4904f7664b91b4ed0dec969dc',
         'info_dict': {
-            'id': '1263092',
+            'id': '1192814',
             'ext': 'mp4',
-            'title': 'Le Zapping - 13/05/15',
+            'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
-            'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+            'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
-            'upload_date': '20150513',
+            'upload_date': '20150105',
         },
     }, {
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
@@ -46,35 +60,45 @@ class CanalplusIE(InfoExtractor):
         },
         'skip': 'Only works from France',
     }, {
-        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+        'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
         'info_dict': {
-            'id': '966289',
+            'id': '1390231',
-            'ext': 'flv',
-            'title': 'Campagne intime - Documentaire exceptionnel',
-            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
-            'upload_date': '20131108',
-        },
-        'skip': 'videos get deleted after a while',
-    }, {
-        'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
-        'md5': '38b8f7934def74f0d6f3ba6c036a5f82',
-        'info_dict': {
-            'id': '1213714',
             'ext': 'mp4',
-            'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
+            'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
-            'description': 'md5:8216206ec53426ea6321321f3b3c16db',
+            'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
-            'upload_date': '20150211',
+            'upload_date': '20160512',
         },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
+        'info_dict': {
+            'id': '1398334',
+            'ext': 'mp4',
+            'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
+            'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
+            'upload_date': '20160607',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://m.canalplus.fr/?vid=1398231',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.groupdict().get('id')
+        video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')
 
-        site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
+        site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 
         # Beware, some subclasses do not define an id group
-        display_id = url_basename(mobj.group('path'))
+        display_id = mobj.group('display_id') or video_id
 
         if video_id is None:
             webpage = self._download_webpage(url, display_id)

youtube_dl/extractor/channel9.py

@@ -20,54 +20,64 @@ class Channel9IE(InfoExtractor):
     '''
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
-    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
 
-    _TESTS = [
+    _TESTS = [{
-        {
+        'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-            'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
+        'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
-            'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
+        'info_dict': {
-            'info_dict': {
+            'id': 'Events/TechEd/Australia/2013/KOS002',
-                'id': 'Events/TechEd/Australia/2013/KOS002',
+            'ext': 'mp4',
-                'ext': 'mp4',
+            'title': 'Developer Kick-Off Session: Stuff We Love',
-                'title': 'Developer Kick-Off Session: Stuff We Love',
+            'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
-                'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
+            'duration': 4576,
-                'duration': 4576,
+            'thumbnail': 're:http://.*\.jpg',
-                'thumbnail': 're:http://.*\.jpg',
+            'session_code': 'KOS002',
-                'session_code': 'KOS002',
+            'session_day': 'Day 1',
-                'session_day': 'Day 1',
+            'session_room': 'Arena 1A',
-                'session_room': 'Arena 1A',
+            'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug',
-                'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'],
+                                 'Mads Kristensen'],
-            },
         },
-        {
+    }, {
-            'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
+        'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
+        'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
-            'info_dict': {
+        'info_dict': {
-                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+            'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
-                'ext': 'mp4',
+            'ext': 'mp4',
-                'title': 'Self-service BI with Power BI - nuclear testing',
+            'title': 'Self-service BI with Power BI - nuclear testing',
-                'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+            'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
-                'duration': 1540,
+            'duration': 1540,
-                'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': 're:http://.*\.jpg',
-                'authors': ['Mike Wilmot'],
+            'authors': ['Mike Wilmot'],
-            },
         },
-        {
+    }, {
-            # low quality mp4 is best
+        # low quality mp4 is best
-            'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+        'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
-            'info_dict': {
+        'info_dict': {
-                'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+            'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
-                'ext': 'mp4',
+            'ext': 'mp4',
-                'title': 'Ranges for the Standard Library',
+            'title': 'Ranges for the Standard Library',
-                'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
+            'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
-                'duration': 5646,
+            'duration': 5646,
-                'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': 're:http://.*\.jpg',
-            },
+        },
-            'params': {
+        'params': {
-                'skip_download': True,
+            'skip_download': True,
-            },
+        },
-        }
+    }, {
-    ]
+        'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS',
+        'info_dict': {
+            'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b',
+            'title': 'Channel 9',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
+        'only_matching': True,
+    }, {
+        'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman',
+        'only_matching': True,
+    }]
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
@@ -254,22 +264,30 @@ class Channel9IE(InfoExtractor):
 
         return self.playlist_result(contents)
 
-    def _extract_list(self, content_path):
+    def _extract_list(self, video_id, rss_url=None):
-        rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')
+        if not rss_url:
+            rss_url = self._RSS_URL % video_id
+        rss = self._download_xml(rss_url, video_id, 'Downloading RSS')
         entries = [self.url_result(session_url.text, 'Channel9')
                    for session_url in rss.findall('./channel/item/link')]
         title_text = rss.find('./channel/title').text
-        return self.playlist_result(entries, content_path, title_text)
+        return self.playlist_result(entries, video_id, title_text)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         content_path = mobj.group('contentpath')
+        rss = mobj.group('rss')
 
-        webpage = self._download_webpage(url, content_path, 'Downloading web page')
+        if rss:
+            return self._extract_list(content_path, url)
 
-        page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage)
+        webpage = self._download_webpage(
-        if page_type_m is not None:
+            url, content_path, 'Downloading web page')
-            page_type = page_type_m.group('pagetype')
+
+        page_type = self._search_regex(
+            r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2',
+            webpage, 'page type', default=None, group='pagetype')
+        if page_type:
             if page_type == 'Entry':      # Any 'item'-like page, may contain downloadable content
                 return self._extract_entry_item(webpage, content_path)
             elif page_type == 'Session':  # Event session page, may contain downloadable content
@@ -278,6 +296,5 @@ class Channel9IE(InfoExtractor):
                 return self._extract_list(content_path)
             else:
                 raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
-
         else:  # Assuming list
             return self._extract_list(content_path)

youtube_dl/extractor/common.py

@@ -45,6 +45,7 @@ from ..utils import (
     unescapeHTML,
     unified_strdate,
     url_basename,
+    xpath_element,
     xpath_text,
     xpath_with_ns,
     determine_protocol,
@@ -1030,7 +1031,7 @@ class InfoExtractor(object):
         if base_url:
             base_url = base_url.strip()
 
-        bootstrap_info = xpath_text(
+        bootstrap_info = xpath_element(
             manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'],
             'bootstrap info', default=None)
 
@@ -1085,7 +1086,7 @@ class InfoExtractor(object):
             formats.append({
                 'format_id': format_id,
                 'url': manifest_url,
-                'ext': 'flv' if bootstrap_info else None,
+                'ext': 'flv' if bootstrap_info is not None else None,
                 'tbr': tbr,
                 'width': width,
                 'height': height,

youtube_dl/extractor/extractors.py

@@ -382,6 +382,7 @@ from .leeco import (
     LePlaylistIE,
     LetvCloudIE,
 )
+from .libraryofcongress import LibraryOfCongressIE
 from .libsyn import LibsynIE
 from .lifenews import (
     LifeNewsIE,
@@ -909,6 +910,7 @@ from .videomore import (
 )
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
+from .vidio import VidioIE
 from .vidme import (
     VidmeIE,
     VidmeUserIE,
@@ -965,7 +967,6 @@ from .watchindianporn import WatchIndianPornIE
 from .wdr import (
     WDRIE,
     WDRMobileIE,
-    WDRMausIE,
 )
 from .webofstories import (
     WebOfStoriesIE,

youtube_dl/extractor/libraryofcongress.py

@@ -0,0 +1,143 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+from ..utils import (
+    determine_ext,
+    float_or_none,
+    int_or_none,
+    parse_filesize,
+)
+
+
+class LibraryOfCongressIE(InfoExtractor):
+    IE_NAME = 'loc'
+    IE_DESC = 'Library of Congress'
+    _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)'
+    _TESTS = [{
+        # embedded via <div class="media-player"
+        'url': 'http://loc.gov/item/90716351/',
+        'md5': '353917ff7f0255aa6d4b80a034833de8',
+        'info_dict': {
+            'id': '90716351',
+            'ext': 'mp4',
+            'title': "Pa's trip to Mars",
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 0,
+            'view_count': int,
+        },
+    }, {
+        # webcast embedded via mediaObjectId
+        'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
+        'info_dict': {
+            'id': '5578',
+            'ext': 'mp4',
+            'title': 'Help! Preservation Training Needs Here, There & Everywhere',
+            'duration': 3765,
+            'view_count': int,
+            'subtitles': 'mincount:1',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # with direct download links
+        'url': 'https://www.loc.gov/item/78710669/',
+        'info_dict': {
+            'id': '78710669',
+            'ext': 'mp4',
+            'title': 'La vie et la passion de Jesus-Christ',
+            'duration': 0,
+            'view_count': int,
+            'formats': 'mincount:4',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        media_id = self._search_regex(
+            (r'id=(["\'])media-player-(?P<id>.+?)\1',
+             r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
+             r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
+             r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1'),
+            webpage, 'media id', group='id')
+
+        data = self._download_json(
+            'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
+            video_id)['mediaObject']
+
+        derivative = data['derivatives'][0]
+        media_url = derivative['derivativeUrl']
+
+        title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
+            webpage)
+
+        # Following algorithm was extracted from setAVSource js function
+        # found in webpage
+        media_url = media_url.replace('rtmp', 'https')
+
+        is_video = data.get('mediaType', 'v').lower() == 'v'
+        ext = determine_ext(media_url)
+        if ext not in ('mp4', 'mp3'):
+            media_url += '.mp4' if is_video else '.mp3'
+
+        if 'vod/mp4:' in media_url:
+            formats = [{
+                'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8',
+                'format_id': 'hls',
+                'ext': 'mp4',
+                'protocol': 'm3u8_native',
+                'quality': 1,
+            }]
+        elif 'vod/mp3:' in media_url:
+            formats = [{
+                'url': media_url.replace('vod/mp3:', ''),
+                'vcodec': 'none',
+            }]
+
+        download_urls = set()
+        for m in re.finditer(
+                r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
+            format_id = m.group('id').lower()
+            if format_id == 'gif':
+                continue
+            download_url = m.group('url')
+            if download_url in download_urls:
+                continue
+            download_urls.add(download_url)
+            formats.append({
+                'url': download_url,
+                'format_id': format_id,
+                'filesize_approx': parse_filesize(m.group('size')),
+            })
+
+        self._sort_formats(formats)
+
+        duration = float_or_none(data.get('duration'))
+        view_count = int_or_none(data.get('viewCount'))
+
+        subtitles = {}
+        cc_url = data.get('ccUrl')
+        if cc_url:
+            subtitles.setdefault('en', []).append({
+                'url': cc_url,
+                'ext': 'ttml',
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/livestream.py

@@ -203,9 +203,10 @@ class LivestreamIE(InfoExtractor):
             if not videos_info:
                 break
             for v in videos_info:
+                v_id = compat_str(v['id'])
                 entries.append(self.url_result(
-                    'http://livestream.com/accounts/%s/events/%s/videos/%s' % (account_id, event_id, v['id']),
+                    'http://livestream.com/accounts/%s/events/%s/videos/%s' % (account_id, event_id, v_id),
-                    'Livestream', v['id'], v['caption']))
+                    'Livestream', v_id, v.get('caption')))
             last_video = videos_info[-1]['id']
         return self.playlist_result(entries, event_id, event_data['full_name'])
 

youtube_dl/extractor/thesixtyone.py

@@ -12,7 +12,7 @@ class TheSixtyOneIE(InfoExtractor):
             s|
             song/comments/list|
             song
-        )/(?P<id>[A-Za-z0-9]+)/?$'''
+        )/(?:[^/]+/)?(?P<id>[A-Za-z0-9]+)/?$'''
     _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
     _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream'
     _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
@@ -45,6 +45,10 @@ class TheSixtyOneIE(InfoExtractor):
             'url': 'http://www.thesixtyone.com/song/SrE3zD7s1jt/',
             'only_matching': True,
         },
+        {
+            'url': 'http://www.thesixtyone.com/maryatmidnight/song/StrawberriesandCream/yvWtLp0c4GQ/',
+            'only_matching': True,
+        },
     ]
 
     _DECODE_MAP = {

youtube_dl/extractor/twitch.py

@@ -260,7 +260,7 @@ class TwitchVodIE(TwitchItemBaseIE):
                     'nauth': access_token['token'],
                     'nauthsig': access_token['sig'],
                 })),
-            item_id, 'mp4')
+            item_id, 'mp4', entry_protocol='m3u8_native')
 
         self._prefer_source(formats)
         info['formats'] = formats

youtube_dl/extractor/vidio.py

@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class VidioIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vidio\.com/watch/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
+        'md5': 'cd2801394afc164e9775db6a140b91fe',
+        'info_dict': {
+            'id': '165683',
+            'display_id': 'dj_ambred-booyah-live-2015',
+            'ext': 'mp4',
+            'title': 'DJ_AMBRED - Booyah (Live 2015)',
+            'description': 'md5:27dc15f819b6a78a626490881adbadf8',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 149,
+            'like_count': int,
+        },
+    }, {
+        'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id, display_id = mobj.group('id', 'display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._og_search_title(webpage)
+
+        m3u8_url, duration, thumbnail = [None] * 3
+
+        clips = self._parse_json(
+            self._html_search_regex(
+                r'data-json-clips\s*=\s*(["\'])(?P<data>\[.+?\])\1',
+                webpage, 'video data', default='[]', group='data'),
+            display_id, fatal=False)
+        if clips:
+            clip = clips[0]
+            m3u8_url = clip.get('sources', [{}])[0].get('file')
+            duration = clip.get('clip_duration')
+            thumbnail = clip.get('image')
+
+        m3u8_url = m3u8_url or self._search_regex(
+            r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>.+?)\1', webpage, 'hls url')
+        formats = self._extract_m3u8_formats(m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native')
+
+        duration = int_or_none(duration or self._search_regex(
+            r'data-video-duration=(["\'])(?P<duartion>\d+)\1', webpage, 'duration'))
+        thumbnail = thumbnail or self._og_search_thumbnail(webpage)
+
+        like_count = int_or_none(self._search_regex(
+            (r'<span[^>]+data-comment-vote-count=["\'](\d+)',
+             r'<span[^>]+class=["\'].*?\blike(?:__|-)count\b.*?["\'][^>]*>\s*(\d+)'),
+            webpage, 'like count', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'like_count': like_count,
+            'formats': formats,
+        }

youtube_dl/extractor/vlive.py

@@ -9,6 +9,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    remove_start,
 )
 from ..compat import compat_urllib_parse_urlencode
 
@@ -39,6 +40,7 @@ class VLiveIE(InfoExtractor):
             webpage, 'video params')
         status, _, _, live_params, long_video_id, key = re.split(
             r'"\s*,\s*"', video_params)[2:8]
+        status = remove_start(status, 'PRODUCT_')
 
         if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
             live_params = self._parse_json('"%s"' % live_params, video_id)

youtube_dl/extractor/wdr.py

@@ -1,214 +1,200 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import itertools
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_urlparse,
-)
 from ..utils import (
+    determine_ext,
+    js_to_json,
+    strip_jsonp,
     unified_strdate,
-    qualities,
+    ExtractorError,
 )
 
 
 class WDRIE(InfoExtractor):
-    _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
+    _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
-    _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
+    _PAGE_REGEX = r'/mediathek/(?P<media_type>[^/]+)/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
+    _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
 
     _TESTS = [
         {
-            'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
+            'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
+            # HDS download, MD5 is unstable
             'info_dict': {
-                'id': 'mdb-362427',
+                'id': 'mdb-1058683',
                 'ext': 'flv',
-                'title': 'Servicezeit',
+                'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
-                'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
+                'title': 'Geheimnis Aachener Dom',
-                'upload_date': '20140310',
+                'alt_title': 'Doku am Freitag',
-                'is_live': False
+                'upload_date': '20160304',
+                'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
+                'is_live': False,
+                'subtitles': {'de': [{
+                    'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml'
+                }]},
             },
-            'params': {
-                'skip_download': True,
-            },
-            'skip': 'Page Not Found',
         },
         {
-            'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
+            'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
+            'md5': 'f4c1f96d01cf285240f53ea4309663d8',
             'info_dict': {
-                'id': 'mdb-363194',
+                'id': 'mdb-1072000',
-                'ext': 'flv',
-                'title': 'Marga Spiegel ist tot',
-                'description': 'md5:2309992a6716c347891c045be50992e4',
-                'upload_date': '20140311',
-                'is_live': False
-            },
-            'params': {
-                'skip_download': True,
-            },
-            'skip': 'Page Not Found',
-        },
-        {
-            'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
-            'md5': '83e9e8fefad36f357278759870805898',
-            'info_dict': {
-                'id': 'mdb-194332',
                 'ext': 'mp3',
-                'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
+                'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
-                'description': 'md5:2309992a6716c347891c045be50992e4',
+                'title': 'Schriftstellerin Juli Zeh',
-                'upload_date': '20091129',
+                'alt_title': 'WDR 3 Gespräch am Samstag',
-                'is_live': False
+                'upload_date': '20160312',
+                'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
+                'is_live': False,
+                'subtitles': {}
             },
         },
         {
-            'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
+            'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
-            'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
-            'info_dict': {
-                'id': 'mdb-478135',
-                'ext': 'mp3',
-                'title': 'Flavia Coelho: Amar é Amar',
-                'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
-                'upload_date': '20140717',
-                'is_live': False
-            },
-            'skip': 'Page Not Found',
-        },
-        {
-            'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
-            'playlist_mincount': 146,
-            'info_dict': {
-                'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
-            }
-        },
-        {
-            'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
             'info_dict': {
                 'id': 'mdb-103364',
-                'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'ext': 'mp4',
+                'display_id': 'index',
+                'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'alt_title': 'WDR Fernsehen Live',
+                'upload_date': None,
                 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
-                'ext': 'flv',
+                'is_live': True,
-                'upload_date': '20150101',
+                'subtitles': {}
-                'is_live': True
             },
             'params': {
-                'skip_download': True,
+                'skip_download': True,  # m3u8 download
             },
-        }
+        },
+        {
+            'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
+            'playlist_mincount': 8,
+            'info_dict': {
+                'id': 'aktuelle-stunde/aktuelle-stunde-120',
+            },
+        },
+        {
+            'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
+            'info_dict': {
+                'id': 'mdb-1096487',
+                'ext': 'flv',
+                'upload_date': 're:^[0-9]{8}$',
+                'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
+                'description': '- Die Sendung mit der Maus -',
+            },
+            'skip': 'The id changes from week to week because of the new episode'
+        },
+        {
+            'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
+            # HDS download, MD5 is unstable
+            'info_dict': {
+                'id': 'mdb-186083',
+                'ext': 'flv',
+                'upload_date': '20130919',
+                'title': 'Sachgeschichte - Achterbahn ',
+                'description': '- Die Sendung mit der Maus -',
+            },
+        },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        page_url = mobj.group('url')
+        url_type = mobj.group('type')
-        page_id = mobj.group('id')
+        page_url = mobj.group('page_url')
+        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, display_id)
 
-        webpage = self._download_webpage(url, page_id)
+        # for wdr.de the data-extension is in a tag with the class "mediaLink"
+        # for wdrmaus its in a link to the page in a multiline "videoLink"-tag
+        json_metadata = self._html_search_regex(
+            r'class=(?:"mediaLink\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
+            webpage, 'media link', default=None, flags=re.MULTILINE)
 
-        if mobj.group('player') is None:
+        if not json_metadata:
             entries = [
-                self.url_result(page_url + href, 'WDR')
+                self.url_result(page_url + href[0], 'WDR')
                 for href in re.findall(
-                    r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX,
+                    r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX,
                     webpage)
             ]
 
             if entries:  # Playlist page
-                return self.playlist_result(entries, page_id)
+                return self.playlist_result(entries, playlist_id=display_id)
 
-            # Overview page
+            raise ExtractorError('No downloadable streams found', expected=True)
-            entries = []
-            for page_num in itertools.count(2):
-                hrefs = re.findall(
-                    r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
-                    webpage)
-                entries.extend(
-                    self.url_result(page_url + href, 'WDR')
-                    for href in hrefs)
-                next_url_m = re.search(
-                    r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
-                if not next_url_m:
-                    break
-                next_url = page_url + next_url_m.group(1)
-                webpage = self._download_webpage(
-                    next_url, page_id,
-                    note='Downloading playlist page %d' % page_num)
-            return self.playlist_result(entries, page_id)
 
-        flashvars = compat_parse_qs(self._html_search_regex(
+        media_link_obj = self._parse_json(json_metadata, display_id,
-            r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
+                                          transform_source=js_to_json)
+        jsonp_url = media_link_obj['mediaObj']['url']
 
-        page_id = flashvars['trackerClipId'][0]
+        metadata = self._download_json(
-        video_url = flashvars['dslSrc'][0]
+            jsonp_url, 'metadata', transform_source=strip_jsonp)
-        title = flashvars['trackerClipTitle'][0]
+
-        thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
+        metadata_tracker_data = metadata['trackerData']
-        is_live = flashvars.get('isLive', ['0'])[0] == '1'
+        metadata_media_resource = metadata['mediaResource']
+
+        formats = []
+
+        # check if the metadata contains a direct URL to a file
+        metadata_media_alt = metadata_media_resource.get('alt')
+        if metadata_media_alt:
+            for tag_name in ['videoURL', 'audioURL']:
+                if tag_name in metadata_media_alt:
+                    alt_url = metadata_media_alt[tag_name]
+                    if determine_ext(alt_url) == 'm3u8':
+                        m3u_fmt = self._extract_m3u8_formats(
+                            alt_url, display_id, 'mp4', 'm3u8_native',
+                            m3u8_id='hls')
+                        formats.extend(m3u_fmt)
+                    else:
+                        formats.append({
+                            'url': alt_url
+                        })
+
+        # check if there are flash-streams for this video
+        if 'dflt' in metadata_media_resource and 'videoURL' in metadata_media_resource['dflt']:
+            video_url = metadata_media_resource['dflt']['videoURL']
+            if video_url.endswith('.f4m'):
+                full_video_url = video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
+                formats.extend(self._extract_f4m_formats(full_video_url, display_id, f4m_id='hds', fatal=False))
+            elif video_url.endswith('.smil'):
+                formats.extend(self._extract_smil_formats(video_url, 'stream', fatal=False))
+
+        subtitles = {}
+        caption_url = metadata_media_resource.get('captionURL')
+        if caption_url:
+            subtitles['de'] = [{
+                'url': caption_url
+            }]
+
+        title = metadata_tracker_data.get('trackerClipTitle')
+        is_live = url_type == 'live'
 
         if is_live:
             title = self._live_title(title)
-
+            upload_date = None
-        if 'trackerClipAirTime' in flashvars:
+        elif 'trackerClipAirTime' in metadata_tracker_data:
-            upload_date = flashvars['trackerClipAirTime'][0]
+            upload_date = metadata_tracker_data['trackerClipAirTime']
         else:
-            upload_date = self._html_search_meta(
+            upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
-                'DC.Date', webpage, 'upload date')
 
         if upload_date:
             upload_date = unified_strdate(upload_date)
 
-        formats = []
-        preference = qualities(['S', 'M', 'L', 'XL'])
-
-        if video_url.endswith('.f4m'):
-            formats.extend(self._extract_f4m_formats(
-                video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id,
-                f4m_id='hds', fatal=False))
-        elif video_url.endswith('.smil'):
-            formats.extend(self._extract_smil_formats(
-                video_url, page_id, False, {
-                    'hdcore': '3.3.0',
-                    'plugin': 'aasp-3.3.0.99.43',
-                }))
-        else:
-            formats.append({
-                'url': video_url,
-                'http_headers': {
-                    'User-Agent': 'mobile',
-                },
-            })
-
-        m3u8_url = self._search_regex(
-            r'rel="adaptiv"[^>]+href="([^"]+)"',
-            webpage, 'm3u8 url', default=None)
-        if m3u8_url:
-            formats.extend(self._extract_m3u8_formats(
-                m3u8_url, page_id, 'mp4', 'm3u8_native',
-                m3u8_id='hls', fatal=False))
-
-        direct_urls = re.findall(
-            r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage)
-        if direct_urls:
-            for quality, video_url in direct_urls:
-                formats.append({
-                    'url': video_url,
-                    'preference': preference(quality),
-                    'http_headers': {
-                        'User-Agent': 'mobile',
-                    },
-                })
-
         self._sort_formats(formats)
 
-        description = self._html_search_meta('Description', webpage, 'description')
-
         return {
-            'id': page_id,
+            'id': metadata_tracker_data.get('trackerClipId', display_id),
-            'formats': formats,
+            'display_id': display_id,
             'title': title,
-            'description': description,
+            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
-            'thumbnail': thumbnail,
+            'formats': formats,
             'upload_date': upload_date,
-            'is_live': is_live
+            'description': self._html_search_meta('Description', webpage),
+            'is_live': is_live,
+            'subtitles': subtitles,
         }
 
 
@@ -241,81 +227,3 @@ class WDRMobileIE(InfoExtractor):
                 'User-Agent': 'mobile',
             },
         }
-
-
-class WDRMausIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
-    IE_DESC = 'Sendung mit der Maus'
-    _TESTS = [{
-        'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
-        'info_dict': {
-            'id': 'aktuelle-sendung',
-            'ext': 'mp4',
-            'thumbnail': 're:^http://.+\.jpg',
-            'upload_date': 're:^[0-9]{8}$',
-            'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
-        }
-    }, {
-        'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
-        'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
-        'info_dict': {
-            'id': '40_jahre_maus',
-            'ext': 'mp4',
-            'thumbnail': 're:^http://.+\.jpg',
-            'upload_date': '20131007',
-            'title': '12.03.2011 - 40 Jahre Maus',
-        }
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        param_code = self._html_search_regex(
-            r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
-
-        title_date = self._search_regex(
-            r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
-            webpage, 'air date')
-        title_str = self._html_search_regex(
-            r'<h1>(.*?)</h1>', webpage, 'title')
-        title = '%s - %s' % (title_date, title_str)
-        upload_date = unified_strdate(
-            self._html_search_meta('dc.date', webpage))
-
-        fields = compat_parse_qs(param_code)
-        video_url = fields['firstVideo'][0]
-        thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
-
-        formats = [{
-            'format_id': 'rtmp',
-            'url': video_url,
-        }]
-
-        jscode = self._download_webpage(
-            'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
-            video_id, fatal=False,
-            note='Downloading URL translation table',
-            errnote='Could not download URL translation table')
-        if jscode:
-            for m in re.finditer(
-                    r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
-                    jscode):
-                if video_url.startswith(m.group('stream')):
-                    http_url = video_url.replace(
-                        m.group('stream'), m.group('dl'))
-                    formats.append({
-                        'format_id': 'http',
-                        'url': http_url,
-                    })
-                    break
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-        }

youtube_dl/extractor/youtube.py

@@ -344,6 +344,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
         '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
         '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
+        '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
+        '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
 
         # Dash webm
         '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},

youtube_dl/options.py

@@ -668,7 +668,7 @@ def parseOpts(overrideArguments=None):
         action='store_true', dest='writeannotations', default=False,
         help='Write video annotations to a .annotations.xml file')
     filesystem.add_option(
-        '--load-info',
+        '--load-info-json', '--load-info',
         dest='load_info_filename', metavar='FILE',
         help='JSON file containing the video information (created with the "--write-info-json" option)')
     filesystem.add_option(

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.06.02'
+__version__ = '2016.06.03'