release 2014.02.08

[Tube8] Extended valid urls schema

README.md

@@ -53,6 +53,12 @@ which means you can modify it, redistribute it or use it however you like.
                                      from google videos for  youtube-dl "large
                                      apple". By default (with value "auto")
                                      youtube-dl guesses.
+    --ignore-config                  Do not read configuration files. When given
+                                     in the global configuration file /etc
+                                     /youtube-dl.conf: do not read the user
+                                     configuration in ~/.config/youtube-dl.conf
+                                     (%APPDATA%/youtube-dl/config.txt on
+                                     Windows)
 
 ## Video Selection:
     --playlist-start NUMBER          playlist video to start at (default is 1)
@@ -325,7 +331,7 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
 
 To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
 
-# BUILD INSTRUCTIONS
+# 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.
 
@@ -347,6 +353,10 @@ If you want to create a build of youtube-dl yourself, you'll need
 * zip
 * nosetests
 
+### Adding support for a new site
+
+If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py Test_Download.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
+
 # BUGS
 
 Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email.

test/test_all_urls.py

@@ -37,6 +37,8 @@ class TestAllURLsMatching(unittest.TestCase):
         assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
         assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
         self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
+        # Top tracks
+        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
 
     def test_youtube_matching(self):
         self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))

test/test_download.py

@@ -22,6 +22,7 @@ import socket
 
 import youtube_dl.YoutubeDL
 from youtube_dl.utils import (
+    compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_HTTPError,
@@ -110,7 +111,7 @@ def generator(test_case):
                     ydl.download([test_case['url']])
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
+                    if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
                         raise
 
                     if try_num == RETRIES:

test/test_playlists.py

@@ -34,6 +34,8 @@ from youtube_dl.extractor import (
     KhanAcademyIE,
     EveryonesMixtapeIE,
     RutubeChannelIE,
+    GoogleSearchIE,
+    GenericIE,
 )
 
 
@@ -229,6 +231,24 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], '1409')
         self.assertTrue(len(result['entries']) >= 34)
 
+    def test_multiple_brightcove_videos(self):
+        # https://github.com/rg3/youtube-dl/issues/2283
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'always-never-nuclear-command-and-control')
+        self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
+        self.assertEqual(len(result['entries']), 3)
+
+    def test_GoogleSearch(self):
+        dl = FakeYDL()
+        ie = GoogleSearchIE(dl)
+        result = ie.extract('gvsearch15:python language')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'python language')
+        self.assertEqual(result['title'], 'python language')
+        self.assertTrue(len(result['entries']) == 15)
 
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -10,9 +10,11 @@ from test.helper import FakeYDL, md5
 
 
 from youtube_dl.extractor import (
+    BlipTVIE,
     YoutubeIE,
     DailymotionIE,
     TEDIE,
+    VimeoIE,
 )
 
 
@@ -202,5 +204,80 @@ class TestTedSubtitles(BaseTestSubtitles):
         for lang in langs:
             self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
 
+
+class TestBlipTVSubtitles(BaseTestSubtitles):
+    url = 'http://blip.tv/a/a-6603250'
+    IE = BlipTVIE
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_allsubtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), '5b75c300af65fe4476dff79478bb93e4')
+
+
+class TestVimeoSubtitles(BaseTestSubtitles):
+    url = 'http://vimeo.com/76979871'
+    IE = VimeoIE
+
+    def test_no_writesubtitles(self):
+        subtitles = self.getSubtitles()
+        self.assertEqual(subtitles, None)
+
+    def test_subtitles(self):
+        self.DL.params['writesubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
+
+    def test_subtitles_lang(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['subtitleslangs'] = ['fr']
+        subtitles = self.getSubtitles()
+        self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
+
+    def test_list_subtitles(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['listsubtitles'] = True
+        info_dict = self.getInfoDict()
+        self.assertEqual(info_dict, None)
+
+    def test_automatic_captions(self):
+        self.DL.expect_warning(u'Automatic Captions not supported by this server')
+        self.DL.params['writeautomaticsub'] = True
+        self.DL.params['subtitleslang'] = ['en']
+        subtitles = self.getSubtitles()
+        self.assertTrue(len(subtitles.keys()) == 0)
+
+    def test_nosubtitles(self):
+        self.DL.expect_warning(u'video doesn\'t have subtitles')
+        self.url = 'http://vimeo.com/56015672'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(len(subtitles), 0)
+
+    def test_multiple_langs(self):
+        self.DL.params['writesubtitles'] = True
+        langs = ['es', 'fr', 'de']
+        self.DL.params['subtitleslangs'] = langs
+        subtitles = self.getSubtitles()
+        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/test_youtube_lists.py

@@ -117,6 +117,13 @@ class TestYoutubeLists(unittest.TestCase):
         original_video = entries[0]
         self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
 
+    def test_youtube_toptracks(self):
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+        entries = result['entries']
+        self.assertEqual(len(entries), 100)
+
     def test_youtube_toplist(self):
         dl = FakeYDL()
         ie = YoutubeTopListIE(dl)

test/test_youtube_signature.py

@@ -27,6 +27,12 @@ _TESTS = [
         85,
         u'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
+    (
+        u'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
+        u'js',
+        90,
+        u']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
+    ),
 ]
 
 

youtube-dl.plugin.zsh

@@ -0,0 +1,24 @@
+# This allows the youtube-dl command to be installed in ZSH using antigen.
+# Antigen is a bundle manager. It allows you to enhance the functionality of
+# your zsh session by installing bundles and themes easily.
+
+# Antigen documentation:
+# http://antigen.sharats.me/
+# https://github.com/zsh-users/antigen
+
+# Install youtube-dl:
+# antigen bundle rg3/youtube-dl
+# Bundles installed by antigen are available for use immediately.
+
+# Update youtube-dl (and all other antigen bundles):
+# antigen update
+
+# The antigen command will download the git repository to a folder and then
+# execute an enabling script (this file). The complete process for loading the
+# code is documented here:
+# https://github.com/zsh-users/antigen#notes-on-writing-plugins
+
+# This specific script just aliases youtube-dl to the python script that this
+# library provides. This requires updating the PYTHONPATH to ensure that the
+# full set of code can be located.
+alias youtube-dl="PYTHONPATH=$(dirname $0) $(dirname $0)/bin/youtube-dl"

youtube_dl/__init__.py

@@ -41,6 +41,7 @@ __authors__  = (
     'Chris Gahan',
     'Saimadhav Heblikar',
     'Mike Col',
+    'Andreas Schmitz',
 )
 
 __license__ = 'Public Domain'
@@ -100,6 +101,43 @@ def parseOpts(overrideArguments=None):
             optionf.close()
         return res
 
+    def _readUserConf():
+        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+        if xdg_config_home:
+            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
+        else:
+            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
+            if not os.path.isfile(userConfFile):
+                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+        userConf = _readOptions(userConfFile, None)
+
+        if userConf is None:
+            appdata_dir = os.environ.get('appdata')
+            if appdata_dir:
+                userConf = _readOptions(
+                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
+                    default=None)
+                if userConf is None:
+                    userConf = _readOptions(
+                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
+                        default=None)
+
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
+                default=None)
+        if userConf is None:
+            userConf = _readOptions(
+                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
+                default=None)
+
+        if userConf is None:
+            userConf = []
+
+        return userConf
+
     def _format_option_string(option):
         ''' ('-o', '--option') -> -o, --format METAVAR'''
 
@@ -203,6 +241,11 @@ def parseOpts(overrideArguments=None):
     general.add_option('--default-search',
             dest='default_search', metavar='PREFIX',
             help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
+    general.add_option(
+        '--ignore-config',
+        action='store_true',
+        help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
+
 
     selection.add_option(
         '--playlist-start',
@@ -457,44 +500,18 @@ def parseOpts(overrideArguments=None):
         if opts.verbose:
             write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
-        systemConf = _readOptions('/etc/youtube-dl.conf')
-
-        xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
-        if xdg_config_home:
-            userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
-        else:
-            userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
-            if not os.path.isfile(userConfFile):
-                userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
-        userConf = _readOptions(userConfFile, None)
-
-        if userConf is None:
-            appdata_dir = os.environ.get('appdata')
-            if appdata_dir:
-                userConf = _readOptions(
-                    os.path.join(appdata_dir, 'youtube-dl', 'config'),
-                    default=None)
-                if userConf is None:
-                    userConf = _readOptions(
-                        os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
-                        default=None)
-
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
-                default=None)
-        if userConf is None:
-            userConf = _readOptions(
-                os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
-                default=None)
-
-        if userConf is None:
-            userConf = []
-
         commandLineConf = sys.argv[1:]
+        if '--ignore-config' in commandLineConf:
+            systemConf = []
+            userConf = []
+        else:
+            systemConf = _readOptions('/etc/youtube-dl.conf')
+            if '--ignore-config' in systemConf:
+                userConf = []
+            else:
+                userConf = _readUserConf()
         argv = systemConf + userConf + commandLineConf
+
         opts, args = parser.parse_args(argv)
         if opts.verbose:
             write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')

youtube_dl/downloader/rtmp.py

@@ -87,8 +87,10 @@ class RtmpFD(FileDownloader):
         url = info_dict['url']
         player_url = info_dict.get('player_url', None)
         page_url = info_dict.get('page_url', None)
+        app = info_dict.get('app', None)
         play_path = info_dict.get('play_path', None)
         tc_url = info_dict.get('tc_url', None)
+        flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
 
@@ -111,12 +113,16 @@ class RtmpFD(FileDownloader):
             basic_args += ['--swfVfy', player_url]
         if page_url is not None:
             basic_args += ['--pageUrl', page_url]
+        if app is not None:
+            basic_args += ['--app', app]
         if play_path is not None:
             basic_args += ['--playpath', play_path]
         if tc_url is not None:
             basic_args += ['--tcUrl', url]
         if test:
             basic_args += ['--stop', '1']
+        if flash_version is not None:
+            basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
         if conn:

youtube_dl/extractor/__init__.py

@@ -15,6 +15,7 @@ from .arte import (
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
+from .bbccouk import BBCCoUkIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
@@ -25,6 +26,7 @@ from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
 from .channel9 import Channel9IE
+from .chilloutzone import ChilloutzoneIE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
@@ -54,12 +56,14 @@ from .ebaumsworld import EbaumsWorldIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
+from .elpais import ElPaisIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .firstpost import FirstpostIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
@@ -96,6 +100,7 @@ from .ina import InaIE
 from .infoq import InfoQIE
 from .instagram import InstagramIE
 from .internetvideoarchive import InternetVideoArchiveIE
+from .iprima import IPrimaIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -110,12 +115,14 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .la7 import LA7IE
+from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import LivestreamIE, LivestreamOriginalIE
 from .lynda import (
     LyndaIE,
     LyndaCourseIE
 )
+from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
@@ -125,6 +132,7 @@ from .mit import TechTVMITIE, MITIE
 from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
+from .mooshare import MooshareIE
 from .mtv import (
     MTVIE,
     MTVIggyIE,
@@ -136,11 +144,14 @@ from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import NBCNewsIE
+from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
+from .normalboots import NormalbootsIE
 from .novamov import NovamovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
@@ -198,6 +209,7 @@ from .ted import TEDIE
 from .tf1 import TF1IE
 from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
+from .tinypic import TinyPicIE
 from .toutv import TouTvIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
@@ -228,6 +240,7 @@ from .vimeo import (
 from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
+from .vube import VubeIE
 from .wat import WatIE
 from .weibo import WeiboIE
 from .wimp import WimpIE

youtube_dl/extractor/bbccouk.py

@@ -0,0 +1,116 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class BBCCoUkIE(InfoExtractor):
+    IE_NAME = 'bbc.co.uk'
+    IE_DESC = 'BBC - iPlayer Radio'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>[\da-z]{8})'
+
+    _TEST = {
+        'url': 'http://www.bbc.co.uk/programmes/p01q7wz1',
+        'info_dict': {
+            'id': 'p01q7wz4',
+            'ext': 'flv',
+            'title': 'Friction: Blu Mar Ten guest mix: Blu Mar Ten - Guest Mix',
+            'description': 'Blu Mar Ten deliver a Guest Mix for Friction.',
+            'duration': 1936,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        group_id = mobj.group('id')
+
+        playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
+            'Downloading playlist XML')
+
+        item = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}item')
+        if item is None:
+            no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+            if no_items is not None:
+                reason = no_items.get('reason')
+                if reason == 'preAvailability':
+                    msg = 'Episode %s is not yet available' % group_id
+                elif reason == 'postAvailability':
+                    msg = 'Episode %s is no longer available' % group_id
+                else:
+                    msg = 'Episode %s is not available: %s' % (group_id, reason)
+                raise ExtractorError(msg, expected=True)
+            raise ExtractorError('Failed to extract media for episode %s' % group_id, expected=True)
+
+        title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+        description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+
+        radio_programme_id = item.get('identifier')
+        duration = int(item.get('duration'))
+
+        media_selection = self._download_xml(
+            'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % radio_programme_id,
+            radio_programme_id, 'Downloading media selection XML')
+
+        formats = []
+        for media in media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media'):
+            bitrate = int(media.get('bitrate'))
+            encoding = media.get('encoding')
+            service = media.get('service')
+            connection = media.find('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
+            protocol = connection.get('protocol')
+            priority = connection.get('priority')
+            supplier = connection.get('supplier')
+            if protocol == 'http':
+                href = connection.get('href')
+                # ASX playlist
+                if supplier == 'asx':
+                    asx = self._download_xml(href, radio_programme_id, 'Downloading %s ASX playlist' % service)
+                    for i, ref in enumerate(asx.findall('./Entry/ref')):
+                        formats.append({
+                            'url': ref.get('href'),
+                            'format_id': '%s_ref%s' % (service, i),
+                            'abr': bitrate,
+                            'acodec': encoding,
+                            'preference': priority,
+                        })
+                    continue
+                # Direct link
+                formats.append({
+                    'url': href,
+                    'format_id': service,
+                    'abr': bitrate,
+                    'acodec': encoding,
+                    'preference': priority,
+                })
+            elif protocol == 'rtmp':
+                application = connection.get('application', 'ondemand')
+                auth_string = connection.get('authString')
+                identifier = connection.get('identifier')
+                server = connection.get('server')
+                formats.append({
+                    'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                    'play_path': identifier,
+                    'app': '%s?%s' % (application, auth_string),
+                    'rtmp_live': False,
+                    'ext': 'flv',
+                    'format_id': service,
+                    'abr': bitrate,
+                    'acodec': encoding,
+                    'preference': priority,
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': radio_programme_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/bliptv.py

@@ -1,128 +1,137 @@
 from __future__ import unicode_literals
 
 import datetime
-import json
 import re
-import socket
 
 from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
-    compat_http_client,
     compat_str,
-    compat_urllib_error,
     compat_urllib_request,
 
-    ExtractorError,
     unescapeHTML,
 )
 
 
-class BlipTVIE(InfoExtractor):
+class BlipTVIE(SubtitlesInfoExtractor):
     """Information extractor for blip.tv"""
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
+    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(?P<presumptive_id>.+)$'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
-        'file': '5779306.mov',
         'md5': 'c6934ad0b6acf2bd920720ec888eb812',
         'info_dict': {
+            'id': '5779306',
+            'ext': 'mov',
             'upload_date': '20111205',
             'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
             'uploader': 'Comic Book Resources - CBR TV',
             'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
         }
-    }
-
-    def report_direct_download(self, title):
-        """Report information extraction."""
-        self.to_screen('%s: Direct download detected' % title)
+    }, {
+        # https://github.com/rg3/youtube-dl/pull/2274
+        'note': 'Video with subtitles',
+        'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
+        'md5': '309f9d25b820b086ca163ffac8031806',
+        'info_dict': {
+            'id': '6586561',
+            'ext': 'mp4',
+            'uploader': 'Red vs. Blue',
+            'description': 'One-Zero-One',
+            'upload_date': '20130614',
+            'title': 'Red vs. Blue Season 11 Episode 1',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
+        presumptive_id = mobj.group('presumptive_id')
 
         # See https://github.com/rg3/youtube-dl/issues/857
-        embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
+        embed_mobj = re.match(r'https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
         if embed_mobj:
             info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
             info_page = self._download_webpage(info_url, embed_mobj.group(1))
-            video_id = self._search_regex(r'data-episode-id="(\d+)', info_page,  'video_id')
+            video_id = self._search_regex(
+                r'data-episode-id="([0-9]+)', info_page, 'video_id')
             return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV')
-
-        if '?' in url:
-            cchar = '&'
-        else:
-            cchar = '?'
+        
+        cchar = '&' if '?' in url else '?'
         json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
         request = compat_urllib_request.Request(json_url)
         request.add_header('User-Agent', 'iTunes/10.6.1')
-        self.report_extraction(mobj.group(1))
-        urlh = self._request_webpage(request, None, False,
-            'unable to download video info webpage')
 
-        try:
-            json_code_bytes = urlh.read()
-            json_code = json_code_bytes.decode('utf-8')
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError('Unable to read video info webpage: %s' % compat_str(err))
+        json_data = self._download_json(request, video_id=presumptive_id)
 
-        try:
-            json_data = json.loads(json_code)
-            if 'Post' in json_data:
-                data = json_data['Post']
-            else:
-                data = json_data
+        if 'Post' in json_data:
+            data = json_data['Post']
+        else:
+            data = json_data
 
-            upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
-            formats = []
-            if 'additionalMedia' in data:
-                for f in sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])):
-                    if not int(f['media_width']): # filter m3u8
-                        continue
-                    formats.append({
-                        'url': f['url'],
-                        'format_id': f['role'],
-                        'width': int(f['media_width']),
-                        'height': int(f['media_height']),
-                    })
-            else:
+        video_id = compat_str(data['item_id'])
+        upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+        subtitles = {}
+        formats = []
+        if 'additionalMedia' in data:
+            for f in data['additionalMedia']:
+                if f.get('file_type_srt') == 1:
+                    LANGS = {
+                        'english': 'en',
+                    }
+                    lang = f['role'].rpartition('-')[-1].strip().lower()
+                    langcode = LANGS.get(lang, lang)
+                    subtitles[langcode] = f['url']
+                    continue
+                if not int(f['media_width']):  # filter m3u8
+                    continue
                 formats.append({
-                    'url': data['media']['url'],
-                    'width': int(data['media']['width']),
-                    'height': int(data['media']['height']),
+                    'url': f['url'],
+                    'format_id': f['role'],
+                    'width': int(f['media_width']),
+                    'height': int(f['media_height']),
                 })
+        else:
+            formats.append({
+                'url': data['media']['url'],
+                'width': int(data['media']['width']),
+                'height': int(data['media']['height']),
+            })
+        self._sort_formats(formats)
 
-            self._sort_formats(formats)
+        # subtitles
+        video_subtitles = self.extract_subtitles(video_id, subtitles)
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
 
-            return {
-                'id': compat_str(data['item_id']),
-                'uploader': data['display_name'],
-                'upload_date': upload_date,
-                'title': data['title'],
-                'thumbnail': data['thumbnailUrl'],
-                'description': data['description'],
-                'user_agent': 'iTunes/10.6.1',
-                'formats': formats,
-            }
-        except (ValueError, KeyError) as err:
-            raise ExtractorError('Unable to parse video information: %s' % repr(err))
+        return {
+            'id': video_id,
+            'uploader': data['display_name'],
+            'upload_date': upload_date,
+            'title': data['title'],
+            'thumbnail': data['thumbnailUrl'],
+            'description': data['description'],
+            'user_agent': 'iTunes/10.6.1',
+            'formats': formats,
+            'subtitles': video_subtitles,
+        }
+
+    def _download_subtitle_url(self, sub_lang, url):
+        # For some weird reason, blip.tv serves a video instead of subtitles
+        # when we request with a common UA
+        req = compat_urllib_request.Request(url)
+        req.add_header('Youtubedl-user-agent', 'youtube-dl')
+        return self._download_webpage(req, None, note=False)
 
 
 class BlipTVUserIE(InfoExtractor):
-    """Information Extractor for blip.tv users."""
-
     _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
     _PAGE_SIZE = 12
     IE_NAME = 'blip.tv:user'
 
     def _real_extract(self, url):
-        # Extract username
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
-
         username = mobj.group(1)
 
         page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
@@ -131,7 +140,6 @@ class BlipTVUserIE(InfoExtractor):
         mobj = re.search(r'data-users-id="([^"]+)"', page)
         page_base = page_base % mobj.group(1)
 
-
         # Download video ids using BlipTV Ajax calls. Result size per
         # query is limited (currently to 12 videos) so we need to query
         # page by page until there are no video ids - it means we got
@@ -142,8 +150,8 @@ class BlipTVUserIE(InfoExtractor):
 
         while True:
             url = page_base + "&page=" + str(pagenum)
-            page = self._download_webpage(url, username,
-                                          'Downloading video ids from page %d' % pagenum)
+            page = self._download_webpage(
+                url, username, 'Downloading video ids from page %d' % pagenum)
 
             # Extract video identifiers
             ids_in_page = []
@@ -167,4 +175,4 @@ class BlipTVUserIE(InfoExtractor):
 
         urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
         url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
-        return [self.playlist_result(url_entries, playlist_title = username)]
+        return [self.playlist_result(url_entries, playlist_title=username)]

youtube_dl/extractor/bloomberg.py

@@ -24,5 +24,5 @@ class BloombergIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        ooyala_code = self._search_regex(r'<source src="http://player.ooyala.com/player/[^/]+/([^".]+)', webpage, u'ooyala url')
-        return OoyalaIE._build_url_result(ooyala_code)
+        ooyala_url = self._twitter_search_player(webpage)
+        return self.url_result(ooyala_url, OoyalaIE.ie_key())

youtube_dl/extractor/brightcove.py

@@ -127,25 +127,28 @@ class BrightcoveIE(InfoExtractor):
 
     @classmethod
     def _extract_brightcove_url(cls, webpage):
-        """Try to extract the brightcove url from the wepbage, returns None
+        """Try to extract the brightcove url from the webpage, returns None
         if it can't be found
         """
+        urls = cls._extract_brightcove_urls(webpage)
+        return urls[0] if urls else None
+
+    @classmethod
+    def _extract_brightcove_urls(cls, webpage):
+        """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
         if url_m:
-            return url_m.group(1)
+            return [url_m.group(1)]
 
-        m_brightcove = re.search(
+        matches = re.findall(
             r'''(?sx)<object
             (?:
-                [^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1 |
+                [^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
             ).+?</object>''',
             webpage)
-        if m_brightcove is not None:
-            return cls._build_brighcove_url(m_brightcove.group())
-        else:
-            return None
+        return [cls._build_brighcove_url(m) for m in matches]
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})

youtube_dl/extractor/channel9.py

@@ -15,14 +15,15 @@ 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>.+)/?'
 
     _TESTS = [
         {
             'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-            'file': 'Events_TechEd_Australia_2013_KOS002.mp4',
             'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
             'info_dict': {
+                'id': 'Events/TechEd/Australia/2013/KOS002',
+                'ext': 'mp4',
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
@@ -35,9 +36,10 @@ class Channel9IE(InfoExtractor):
         },
         {
             'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            'file': 'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
             'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
             'info_dict': {
+                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+                'ext': 'mp4',
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,

youtube_dl/extractor/chilloutzone.py

@@ -0,0 +1,97 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError
+)
+
+
+class ChilloutzoneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
+        'md5': 'a76f3457e813ea0037e5244f509e66d1',
+        'info_dict': {
+            'id': 'enemene-meck-alle-katzen-weg',
+            'ext': 'mp4',
+            'title': 'Enemene Meck - Alle Katzen weg',
+            'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
+        },
+    }, {
+        'note': 'Video hosted at YouTube',
+        'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
+        'info_dict': {
+            'id': '1YVQaAgHyRU',
+            'ext': 'mp4',
+            'title': '16 Photos Taken 1 Second Before Disaster',
+            'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
+            'uploader': 'BuzzFeedVideo',
+            'uploader_id': 'BuzzFeedVideo',
+            'upload_date': '20131105',
+        },
+    }, {
+        'note': 'Video hosted at Vimeo',
+        'url': 'http://www.chilloutzone.net/video/icon-blending.html',
+        'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
+        'info_dict': {
+            'id': '85523671',
+            'ext': 'mp4',
+            'title': 'The Sunday Times - Icons',
+            'description': 'md5:3e5e8e839f076a637c6b9406c8f25c4c',
+            'uploader': 'Us',
+            'uploader_id': 'usfilms',
+            'upload_date': '20140131'
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        base64_video_info = self._html_search_regex(
+            r'var cozVidData = "(.+?)";', webpage, 'video data')
+        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        video_info_dict = json.loads(decoded_video_info)
+
+        # get video information from dict
+        video_url = video_info_dict['mediaUrl']
+        description = clean_html(video_info_dict.get('description'))
+        title = video_info_dict['title']
+        native_platform = video_info_dict['nativePlatform']
+        native_video_id = video_info_dict['nativeVideoId']
+        source_priority = video_info_dict['sourcePriority']
+
+        # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
+        if native_platform is None:
+            youtube_url = self._html_search_regex(
+                r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+                webpage, 'fallback video URL', default=None)
+            if youtube_url is not None:
+                return self.url_result(youtube_url, ie='Youtube')
+
+        # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
+        # the own CDN
+        if source_priority == 'native':
+            if native_platform == 'youtube':
+                return self.url_result(native_video_id, ie='Youtube')
+            if native_platform == 'vimeo':
+                return self.url_result(
+                    'http://vimeo.com/' + native_video_id, ie='Vimeo')
+
+        if not video_url:
+            raise ExtractorError('No video found')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/cliphunter.py

@@ -1,12 +1,9 @@
 from __future__ import unicode_literals
 
 import re
-import string
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+
 
 translation_table = {
     'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',

youtube_dl/extractor/collegehumor.py

@@ -4,6 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class CollegeHumorIE(InfoExtractor):
@@ -11,24 +12,45 @@ class CollegeHumorIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
-        'file': '6902724.mp4',
         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
         'info_dict': {
+            'id': '6902724',
+            'ext': 'mp4',
             'title': 'Comic-Con Cosplay Catastrophe',
-            'description': 'Fans get creative this year at San Diego.  Too',
+            'description': 'Fans get creative this year',
             'age_limit': 13,
         },
     },
     {
         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
-        'file': '3505939.mp4',
         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
         'info_dict': {
+            'id': '3505939',
+            'ext': 'mp4',
             'title': 'Font Conference',
-            'description': 'This video wasn\'t long enough, so we made it double-spaced.',
+            'description': 'This video wasn\'t long enough,',
             'age_limit': 10,
+            'duration': 179,
         },
-    }]
+    },
+    # embedded youtube video
+    {
+        'url': 'http://www.collegehumor.com/embed/6950457',
+        'info_dict': {
+            'id': 'W5gMp3ZjYg4',
+            'ext': 'mp4',
+            'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]',
+            'uploader': 'Funnyplox TV',
+            'uploader_id': 'funnyploxtv',
+            'description': 'md5:11812366244110c3523968aa74f02521',
+            'upload_date': '20140128',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Youtube'],
+    },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -38,6 +60,12 @@ class CollegeHumorIE(InfoExtractor):
         data = json.loads(self._download_webpage(
             jsonUrl, video_id, 'Downloading info JSON'))
         vdata = data['video']
+        if vdata.get('youtubeId') is not None:
+            return {
+                '_type': 'url',
+                'url': vdata['youtubeId'],
+                'ie_key': 'Youtube',
+            }
 
         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
         rating = vdata.get('rating')
@@ -49,7 +77,7 @@ class CollegeHumorIE(InfoExtractor):
         PREFS = {'high_quality': 2, 'low_quality': 0}
         formats = []
         for format_key in ('mp4', 'webm'):
-            for qname, qurl in vdata[format_key].items():
+            for qname, qurl in vdata.get(format_key, {}).items():
                 formats.append({
                     'format_id': format_key + '_' + qname,
                     'url': qurl,
@@ -58,6 +86,8 @@ class CollegeHumorIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        duration = int_or_none(vdata.get('duration'), 1000)
+
         return {
             'id': video_id,
             'title': vdata['title'],
@@ -65,4 +95,5 @@ class CollegeHumorIE(InfoExtractor):
             'thumbnail': vdata.get('thumbnail'),
             'formats': formats,
             'age_limit': age_limit,
+            'duration': duration,
         }

youtube_dl/extractor/comedycentral.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
         (video-clips|episodes|cc-studios|video-collections)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
@@ -86,7 +86,7 @@ class ComedyCentralShowsIE(InfoExtractor):
 
     @staticmethod
     def _transform_rtmp_url(rtmp_video_url):
-        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
         if not m:
             raise ExtractorError('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/'

youtube_dl/extractor/common.py

@@ -399,7 +399,7 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
         property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
@@ -465,6 +465,10 @@ class InfoExtractor(object):
         }
         return RATING_TABLE.get(rating.lower(), None)
 
+    def _twitter_search_player(self, html):
+        return self._html_search_meta('twitter:player', html,
+            'twitter card player')
+
     def _sort_formats(self, formats):
         if not formats:
             raise ExtractorError(u'No video formats found')

youtube_dl/extractor/crunchyroll.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re, base64, zlib
 from hashlib import sha1
 from math import pow, sqrt, floor
@@ -18,29 +20,29 @@ from ..aes import (
 )
 
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?(?P<url>crunchyroll\.com/[^/]*/[^/?&]*?(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'(?:https?://)?(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
-        u'url': u'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        u'file': u'645513.flv',
-        #u'md5': u'b1639fd6ddfaa43788c85f6d1dddd412',
-        u'info_dict': {
-            u'title': u'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
-            u'description': u'md5:2d17137920c64f2f49981a7797d275ef',
-            u'thumbnail': u'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
-            u'uploader': u'Yomiuri Telecasting Corporation (YTV)',
-            u'upload_date': u'20131013',
+        'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
+        'file': '645513.flv',
+        #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
+        'info_dict': {
+            'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
+            'description': 'md5:2d17137920c64f2f49981a7797d275ef',
+            'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
+            'uploader': 'Yomiuri Telecasting Corporation (YTV)',
+            'upload_date': '20131013',
         },
-        u'params': {
+        'params': {
             # rtmp
-            u'skip_download': True,
+            'skip_download': True,
         },
     }]
 
     _FORMAT_IDS = {
-        u'360': (u'60', u'106'),
-        u'480': (u'61', u'106'),
-        u'720': (u'62', u'106'),
-        u'1080': (u'80', u'108'),
+        '360': ('60', '106'),
+        '480': ('61', '106'),
+        '720': ('62', '106'),
+        '1080': ('80', '108'),
     }
 
     def _decrypt_subtitles(self, data, iv, id):
@@ -63,7 +65,7 @@ class CrunchyrollIE(InfoExtractor):
             num3 = key ^ num1
             num4 = num3 ^ (num3 >> 3) ^ num2
             prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
-            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode(u'ascii')).digest())
+            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
             # Extend 160 Bit hash to 256 Bit
             return shaHash + [0] * 12
         
@@ -79,93 +81,98 @@ class CrunchyrollIE(InfoExtractor):
 
     def _convert_subtitles_to_srt(self, subtitles):
         i=1
-        output = u''
+        output = ''
         for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
-            start = start.replace(u'.', u',')
-            end = end.replace(u'.', u',')
+            start = start.replace('.', ',')
+            end = end.replace('.', ',')
             text = clean_html(text)
-            text = text.replace(u'\\N', u'\n')
+            text = text.replace('\\N', '\n')
             if not text:
                 continue
-            output += u'%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
+            output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
             i+=1
         return output
 
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
 
-        webpage_url = u'http://www.' + mobj.group('url')
-        video_id = mobj.group(u'video_id')
-        webpage = self._download_webpage(webpage_url, video_id)
-        note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, u'trailer-notice', default=u'')
+        if mobj.group('prefix') == 'm':
+            mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
+            webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
+        else:
+            webpage_url = 'http://www.' + mobj.group('url')
+
+        webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
+        note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='')
         if note_m:
             raise ExtractorError(note_m)
 
-        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, u'video_title', flags=re.DOTALL)
-        video_title = re.sub(r' {2,}', u' ', video_title)
-        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, u'video_description', default=u'')
+        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
+        video_title = re.sub(r' {2,}', ' ', video_title)
+        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
         if not video_description:
             video_description = None
-        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, u'video_upload_date', fatal=False, flags=re.DOTALL)
+        video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
         if video_upload_date:
             video_upload_date = unified_strdate(video_upload_date)
-        video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, u'video_uploader', fatal=False, flags=re.DOTALL)
+        video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
 
-        playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, u'playerdata_url'))
+        playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
         playerdata_req = compat_urllib_request.Request(playerdata_url)
-        playerdata_req.data = compat_urllib_parse.urlencode({u'current_page': webpage_url})
-        playerdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded')
-        playerdata = self._download_webpage(playerdata_req, video_id, note=u'Downloading media info')
+        playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
+        playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
         
-        stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, u'stream_id')
-        video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, u'thumbnail', fatal=False)
+        stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
+        video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
 
         formats = []
         for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
-            video_format = fmt+u'p'
-            streamdata_req = compat_urllib_request.Request(u'http://www.crunchyroll.com/xml/')
+            video_format = fmt+'p'
+            streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
             # urlencode doesn't work!
-            streamdata_req.data = u'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+u'&media%5Fid='+stream_id+u'&video%5Fformat='+stream_format
-            streamdata_req.add_header(u'Content-Type', u'application/x-www-form-urlencoded')
-            streamdata_req.add_header(u'Content-Length', str(len(streamdata_req.data)))
-            streamdata = self._download_webpage(streamdata_req, video_id, note=u'Downloading media info for '+video_format)
-            video_url = self._search_regex(r'<host>([^<]+)', streamdata, u'video_url')
-            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, u'video_play_path')
+            streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
+            streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
+            streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
+            streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
+            video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
+            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
             formats.append({
-                u'url': video_url,
-                u'play_path':   video_play_path,
-                u'ext': 'flv',
-                u'format': video_format,
-                u'format_id': video_format,
+                'url': video_url,
+                'play_path':   video_play_path,
+                'ext': 'flv',
+                'format': video_format,
+                'format_id': video_format,
             })
 
         subtitles = {}
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
-            sub_page = self._download_webpage(u'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
-                                              video_id, note=u'Downloading subtitles for '+sub_name)
-            id = self._search_regex(r'id=\'([0-9]+)', sub_page, u'subtitle_id', fatal=False)
-            iv = self._search_regex(r'<iv>([^<]+)', sub_page, u'subtitle_iv', fatal=False)
-            data = self._search_regex(r'<data>([^<]+)', sub_page, u'subtitle_data', fatal=False)
+            sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
+                                              video_id, note='Downloading subtitles for '+sub_name)
+            id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
+            iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
+            data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
             if not id or not iv or not data:
                 continue
             id = int(id)
             iv = base64.b64decode(iv)
             data = base64.b64decode(data)
 
-            subtitle = self._decrypt_subtitles(data, iv, id).decode(u'utf-8')
-            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, u'subtitle_lang_code', fatal=False)
+            subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
+            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
             subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
 
         return {
-            u'id':          video_id,
-            u'title':       video_title,
-            u'description': video_description,
-            u'thumbnail':   video_thumbnail,
-            u'uploader':    video_uploader,
-            u'upload_date': video_upload_date,
-            u'subtitles':   subtitles,
-            u'formats':     formats,
+            'id':          video_id,
+            'title':       video_title,
+            'description': video_description,
+            'thumbnail':   video_thumbnail,
+            'uploader':    video_uploader,
+            'upload_date': video_upload_date,
+            'subtitles':   subtitles,
+            'formats':     formats,
         }

youtube_dl/extractor/cspan.py

@@ -1,49 +1,60 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     unescapeHTML,
+    find_xpath_attr,
 )
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P<name>.*)'
+    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>\d+)'
     IE_DESC = 'C-SPAN'
     _TEST = {
-        'url': 'http://www.c-spanvideo.org/program/HolderonV',
-        'file': '315139.mp4',
+        'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
         'md5': '8e44ce11f0f725527daccc453f553eb0',
         'info_dict': {
+            'id': '315139',
+            'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
+            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
         },
         'skip': 'Regularly fails on travis, for unknown reasons',
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        prog_name = mobj.group('name')
-        webpage = self._download_webpage(url, prog_name)
-        video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id')
+        page_id = mobj.group('id')
+        webpage = self._download_webpage(url, page_id)
+        video_id = self._search_regex(r'data-progid=\'(\d+)\'>', webpage, 'video id')
 
-        title = self._html_search_regex(
-            r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
-        description = self._og_search_description(webpage)
+        description = self._html_search_regex(
+            [
+                # The full description
+                r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
+                # If the description is small enough the other div is not
+                # present, otherwise this is a stripped version
+                r'<p class=\'initial\'>(.*?)</p>'
+            ],
+            webpage, 'description', flags=re.DOTALL)
 
         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
-        data_json = self._download_webpage(
-            info_url, video_id, 'Downloading video info')
-        data = json.loads(data_json)
+        data = self._download_json(info_url, video_id)
 
         url = unescapeHTML(data['video']['files'][0]['path']['#text'])
 
+        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+            video_id)
+
+        def find_string(s):
+            return find_xpath_attr(doc, './/string', 'name', s).text
+
         return {
             'id': video_id,
-            'title': title,
+            'title': find_string('title'),
             'url': url,
             'description': description,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': find_string('poster'),
         }

youtube_dl/extractor/elpais.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class ElPaisIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
+    IE_DESC = 'El País'
+
+    _TEST = {
+        'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
+        'md5': '98406f301f19562170ec071b83433d55',
+        'info_dict': {
+            'id': 'tiempo-nuevo-recetas-viejas',
+            'ext': 'mp4',
+            'title': 'Tiempo nuevo, recetas viejas',
+            'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
+            'upload_date': '20140206',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        prefix = self._html_search_regex(
+            r'var url_cache = "([^"]+)";', webpage, 'URL prefix')
+        video_suffix = self._search_regex(
+            r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL')
+        video_url = prefix + video_suffix
+        thumbnail_suffix = self._search_regex(
+            r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL',
+            fatal=False)
+        thumbnail = (
+            None if thumbnail_suffix is None
+            else prefix + thumbnail_suffix)
+        title = self._html_search_regex(
+            '<h2 class="entry-header entry-title.*?>(.*?)</h2>',
+            webpage, 'title')
+        date_str = self._search_regex(
+            r'<p class="date-header date-int updated"\s+title="([^"]+)">',
+            webpage, 'upload date', fatal=False)
+        upload_date = (None if date_str is None else unified_strdate(date_str))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/firstpost.py

@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class FirstpostIE(InfoExtractor):
+    IE_NAME = 'Firstpost.com'
+    _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
+        'md5': 'ee9114957692f01fb1263ed87039112a',
+        'info_dict': {
+            'id': '1025403',
+            'ext': 'mp4',
+            'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+            'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
+        }
+    }
+
+    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._html_search_regex(
+            r'<div.*?name="div_video".*?flashvars="([^"]+)">',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/francetv.py

@@ -1,4 +1,7 @@
 # encoding: utf-8
+
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -30,7 +33,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
 
 
 class PluzzIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'pluzz.francetv.fr'
+    IE_NAME = 'pluzz.francetv.fr'
     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
 
     # Can't use tests, videos expire in 7 days
@@ -44,17 +47,17 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'francetvinfo.fr'
+    IE_NAME = 'francetvinfo.fr'
     _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html'
 
     _TEST = {
-        u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
-        u'file': u'84981923.mp4',
-        u'info_dict': {
-            u'title': u'Soir 3',
+        'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+        'file': '84981923.mp4',
+        'info_dict': {
+            'title': 'Soir 3',
         },
-        u'params': {
-            u'skip_download': True,
+        'params': {
+            'skip_download': True,
         },
     }
 
@@ -62,13 +65,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
+        video_id = self._search_regex(r'id-video=(\d+?)[@"]', webpage, 'video id')
         return self._extract_video(video_id)
 
 
 class FranceTVIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'francetv'
-    IE_DESC = u'France 2, 3, 4, 5 and Ô'
+    IE_NAME = 'francetv'
+    IE_DESC = 'France 2, 3, 4, 5 and Ô'
     _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
         (?:
             emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
@@ -78,73 +81,73 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
     _TESTS = [
         # france2
         {
-            u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
-            u'file': u'75540104.mp4',
-            u'info_dict': {
-                u'title': u'13h15, le samedi...',
-                u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+            'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+            'file': '75540104.mp4',
+            'info_dict': {
+                'title': '13h15, le samedi...',
+                'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d',
             },
-            u'params': {
+            'params': {
                 # m3u8 download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # france3
         {
-            u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
-            u'info_dict': {
-                u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
-                u'ext': u'flv',
-                u'title': u'Le scandale du prix des médicaments',
-                u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
+            'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+            'info_dict': {
+                'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
+                'ext': 'flv',
+                'title': 'Le scandale du prix des médicaments',
+                'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
             },
-            u'params': {
+            'params': {
                 # rtmp download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # france4
         {
-            u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
-            u'info_dict': {
-                u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
-                u'ext': u'flv',
-                u'title': u'Hero Corp Making of - Extrait 1',
-                u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+            'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+            'info_dict': {
+                'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+                'ext': 'flv',
+                'title': 'Hero Corp Making of - Extrait 1',
+                'description': 'md5:c87d54871b1790679aec1197e73d650a',
             },
-            u'params': {
+            'params': {
                 # rtmp download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # france5
         {
-            u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
-            u'info_dict': {
-                u'id': u'92837968',
-                u'ext': u'mp4',
-                u'title': u'C à dire ?!',
-                u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+            'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+            'info_dict': {
+                'id': '92837968',
+                'ext': 'mp4',
+                'title': 'C à dire ?!',
+                'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
             },
-            u'params': {
+            'params': {
                 # m3u8 download
-                u'skip_download': True,
+                'skip_download': True,
             },
         },
         # franceo
         {
-            u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
-            u'info_dict': {
-                u'id': u'92327925',
-                u'ext': u'mp4',
-                u'title': u'Infô-Afrique',
-                u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+            'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+            'info_dict': {
+                'id': '92327925',
+                'ext': 'mp4',
+                'title': 'Infô-Afrique',
+                'description': 'md5:ebf346da789428841bee0fd2a935ea55',
             },
-            u'params': {
+            'params': {
                 # m3u8 download
-                u'skip_download': True,
+                'skip_download': True,
             },
-            u'skip': u'The id changes frequently',
+            'skip': 'The id changes frequently',
         },
     ]
 
@@ -160,26 +163,26 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
                  '\.fr/\?id-video=([^"/&]+)'),
                 (r'<a class="video" id="ftv_player_(.+?)"'),
             ]
-            video_id = self._html_search_regex(id_res, webpage, u'video ID')
+            video_id = self._html_search_regex(id_res, webpage, 'video ID')
         else:
             video_id = mobj.group('id')
         return self._extract_video(video_id)
 
 
 class GenerationQuoiIE(InfoExtractor):
-    IE_NAME = u'france2.fr:generation-quoi'
+    IE_NAME = 'france2.fr:generation-quoi'
     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 
     _TEST = {
-        u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous',
-        u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4',
-        u'info_dict': {
-            u'title': u'Génération Quoi - Garde à Vous',
-            u'uploader': u'Génération Quoi',
+        'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
+        'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
+        'info_dict': {
+            'title': 'Génération Quoi - Garde à Vous',
+            'uploader': 'Génération Quoi',
         },
-        u'params': {
+        'params': {
             # It uses Dailymotion
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -194,20 +197,20 @@ class GenerationQuoiIE(InfoExtractor):
 
 
 class CultureboxIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'culturebox.francetvinfo.fr'
+    IE_NAME = 'culturebox.francetvinfo.fr'
     _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
-        u'url': u'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
-        u'info_dict': {
-            u'id': u'EV_6785',
-            u'ext': u'mp4',
-            u'title': u'Einstein on the beach au Théâtre du Châtelet',
-            u'description': u'md5:9ce2888b1efefc617b5e58b3f6200eeb',
+        'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
+        'info_dict': {
+            'id': 'EV_6785',
+            'ext': 'mp4',
+            'title': 'Einstein on the beach au Théâtre du Châtelet',
+            'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb',
         },
-        u'params': {
+        'params': {
             # m3u8 download
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
@@ -215,5 +218,5 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, u'video id')
+        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id')
         return self._extract_video(video_id)

youtube_dl/extractor/generic.py

@@ -38,18 +38,6 @@ class GenericIE(InfoExtractor):
                 'title': 'R\u00e9gis plante sa Jeep',
             }
         },
-        # embedded vimeo video
-        {
-            'add_ie': ['Vimeo'],
-            'url': 'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references',
-            'file': '22444065.mp4',
-            'md5': '2903896e23df39722c33f015af0666e2',
-            'info_dict': {
-                'title': 'ACCU 2011: Move Semantics,Perfect Forwarding, and Rvalue references- Scott Meyers- 13/04/2011',
-                'uploader_id': 'skillsmatter',
-                'uploader': 'Skills Matter',
-            }
-        },
         # bandcamp page with custom domain
         {
             'add_ie': ['Bandcamp'],
@@ -246,15 +234,25 @@ class GenericIE(InfoExtractor):
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
 
         # Look for BrightCove:
-        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
-        if bc_url is not None:
+        bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
+        if bc_urls:
             self.to_screen('Brightcove video detected.')
-            surl = smuggle_url(bc_url, {'Referer': url})
-            return self.url_result(surl, 'Brightcove')
+            entries = [{
+                '_type': 'url',
+                'url': smuggle_url(bc_url, {'Referer': url}),
+                'ie_key': 'Brightcove'
+            } for bc_url in bc_urls]
+
+            return {
+                '_type': 'playlist',
+                'title': video_title,
+                'id': video_id,
+                'entries': entries,
+            }
 
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
-            r'<iframe[^>]+?src="((?:https?:)?//player.vimeo.com/video/.+?)"', webpage)
+            r'<iframe[^>]+?src="((?:https?:)?//player\.vimeo\.com/video/.+?)"', webpage)
         if mobj:
             player_url = unescapeHTML(mobj.group(1))
             surl = smuggle_url(player_url, {'Referer': url})
@@ -262,7 +260,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded (swf embed) Vimeo player
         mobj = re.search(
-            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage)
+            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
         if mobj:
             return self.url_result(mobj.group(1), 'Vimeo')
 
@@ -332,7 +330,7 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group(1), 'Aparat')
 
         # Look for MPORA videos
-        mobj = re.search(r'<iframe .*?src="(http://mpora\.com/videos/[^"]+)"', webpage)
+        mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 
@@ -350,7 +348,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded Huffington Post player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live.huffingtonpost\.com/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'HuffPost')
 
@@ -358,7 +356,7 @@ class GenericIE(InfoExtractor):
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:
             # Look for gorilla-vid style embedding
-            mobj = re.search(r'(?s)jw_plugins.*?file:\s*["\'](.*?)["\']', webpage)
+            mobj = re.search(r'(?s)(?:jw_plugins|JWPlayerOptions).*?file\s*:\s*["\'](.*?)["\']', webpage)
         if mobj is None:
             # Broaden the search a little bit
             mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)

youtube_dl/extractor/googlesearch.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import itertools
 import re
 
@@ -8,32 +10,42 @@ from ..utils import (
 
 
 class GoogleSearchIE(SearchInfoExtractor):
-    IE_DESC = u'Google Video search'
-    _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
+    IE_DESC = 'Google Video search'
     _MAX_RESULTS = 1000
-    IE_NAME = u'video.google:search'
+    IE_NAME = 'video.google:search'
     _SEARCH_KEY = 'gvsearch'
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
 
+        entries = []
         res = {
             '_type': 'playlist',
             'id': query,
-            'entries': []
+            'title': query,
         }
 
-        for pagenum in itertools.count(1):
-            result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
-            webpage = self._download_webpage(result_url, u'gvsearch:' + query,
-                                             note='Downloading result page ' + str(pagenum))
+        for pagenum in itertools.count():
+            result_url = (
+                'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en'
+                % (compat_urllib_parse.quote_plus(query), pagenum * 10))
 
-            for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
-                e = {
+            webpage = self._download_webpage(
+                result_url, 'gvsearch:' + query,
+                note='Downloading result page ' + str(pagenum + 1))
+
+            for hit_idx, mobj in enumerate(re.finditer(
+                    r'<h3 class="r"><a href="([^"]+)"', webpage)):
+
+                # Skip playlists
+                if not re.search(r'id="vidthumb%d"' % (hit_idx + 1), webpage):
+                    continue
+
+                entries.append({
                     '_type': 'url',
                     'url': mobj.group(1)
-                }
-                res['entries'].append(e)
+                })
 
-            if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
+            if (len(entries) >= n) or not re.search(r'class="pn" id="pnnext"', webpage):
+                res['entries'] = entries[:n]
                 return res

youtube_dl/extractor/ina.py

@@ -1,39 +1,36 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class InaIE(InfoExtractor):
-    """Information Extractor for Ina.fr"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
+    _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
     _TEST = {
-        u'url': u'http://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\""
+        'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
+        'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
+        'info_dict': {
+            'id': 'I12055569',
+            'ext': 'mp4',
+            'title': 'François Hollande "Je crois que c\'est clair"',
         }
     }
 
-    def _real_extract(self,url):
+    def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
         video_id = mobj.group('id')
-        mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
-        video_extension = 'mp4'
-        webpage = self._download_webpage(mrss_url, video_id)
+        mrss_url = 'http://player.ina.fr/notices/%s.mrss' % video_id
+        info_doc = self._download_xml(mrss_url, video_id)
 
         self.report_extraction(video_id)
 
-        video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
-            webpage, u'video URL')
+        video_url = info_doc.find('.//{http://search.yahoo.com/mrss/}player').attrib['url']
 
-        video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
-            webpage, u'title')
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      video_extension,
-            'title':    video_title,
-        }]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': info_doc.find('.//title').text,
+        }

youtube_dl/extractor/infoq.py

@@ -1,62 +1,55 @@
+from __future__ import unicode_literals
+
 import base64
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
-
-    ExtractorError,
 )
 
 
 class InfoQIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+    _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
     _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"
+        "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,
         },
-        u"params": {
-            u"skip_download": True
-        }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, video_id=url)
-        self.report_extraction(url)
+        webpage = self._download_webpage(url, video_id)
 
         # Extract video URL
-        mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract video url')
-        real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
+        encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
+        real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
         video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
 
         # Extract title
         video_title = self._search_regex(r'contentTitle = "(.*?)";',
-            webpage, u'title')
+            webpage, 'title')
 
         # Extract description
         video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
         video_filename = video_url.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
-        info = {
+        return {
             'id': video_id,
             'url': video_url,
-            'uploader': None,
-            'upload_date': None,
             'title': video_title,
-            'ext': extension, # Extension is always(?) mp4, but seems to be flv
-            'thumbnail': None,
+            'ext': extension,  # Extension is always(?) mp4, but seems to be flv
             'description': video_description,
         }
-
-        return [info]

youtube_dl/extractor/iprima.py

@@ -0,0 +1,85 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+from random import random
+from math import floor
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_request
+
+
+class IPrimaIE(InfoExtractor):
+    _VALID_URL = r'https?://play\.iprima\.cz/(?P<videogroup>.+)/(?P<videoid>.+)'
+
+    _TESTS = [{
+        'url': 'http://play.iprima.cz/particka/particka-92',
+        'info_dict': {
+            'id': '39152',
+            'ext': 'flv',
+            'title': 'Partička (92)',
+            'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+            'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('videoid')
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
+                         floor(random()*1073741824),
+                         floor(random()*1073741824))
+
+        req = compat_urllib_request.Request(player_url)
+        req.add_header('Referer', url)
+        playerpage = self._download_webpage(req, video_id)
+
+        base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
+
+        zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
+
+        if zoneGEO != '0':
+            base_url = base_url.replace('token', 'token_'+zoneGEO)
+
+        formats = []
+        for format_id in ['lq', 'hq', 'hd']:
+            filename = self._html_search_regex(r'"%s_id":(.+?),' % format_id, webpage, 'filename')
+
+            if filename == 'null':
+                continue
+
+            real_id = self._search_regex(r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
+
+            if format_id == 'lq':
+                quality = 0
+            elif format_id == 'hq':
+                quality = 1
+            elif format_id == 'hd':
+                quality = 2
+                filename = 'hq/'+filename
+
+            formats.append({
+                'format_id': format_id,
+                'url': base_url,
+                'quality': quality,
+                'play_path': 'mp4:'+filename.replace('"', '')[:-4],
+                'rtmp_live': True,
+                'ext': 'flv',
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': real_id,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/ivi.py

@@ -14,15 +14,16 @@ from ..utils import (
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
 
     _TESTS = [
         # Single movie
         {
             'url': 'http://www.ivi.ru/watch/53141',
-            'file': '53141.mp4',
             'md5': '6ff5be2254e796ed346251d117196cf4',
             'info_dict': {
+                'id': '53141',
+                'ext': 'mp4',
                 'title': 'Иван Васильевич меняет профессию',
                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                 'duration': 5498,
@@ -33,9 +34,10 @@ class IviIE(InfoExtractor):
         # Serial's serie
         {
             'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
-            'file': '74791.mp4',
             'md5': '3e6cc9a848c1d2ebcc6476444967baa9',
             'info_dict': {
+                'id': '74791',
+                'ext': 'mp4',
                 'title': 'Дежурный ангел - 1 серия',
                 'duration': 2490,
                 'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
@@ -124,7 +126,7 @@ class IviIE(InfoExtractor):
 class IviCompilationIE(InfoExtractor):
     IE_DESC = 'ivi.ru compilations'
     IE_NAME = 'ivi:compilation'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
 
     def _extract_entries(self, html, compilation_id):
         return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')

youtube_dl/extractor/lifenews.py

@@ -0,0 +1,63 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class LifeNewsIE(InfoExtractor):
+    IE_NAME = 'lifenews'
+    IE_DESC = 'LIFE | NEWS'
+    _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
+    
+    _TEST = {
+        'url': 'http://lifenews.ru/news/126342',
+        'file': '126342.mp4',
+        'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
+        'info_dict': {
+            'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
+            'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
+            'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
+            'upload_date': '20140130',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(
+            r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
+        
+        thumbnail = self._html_search_regex(
+            r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
+
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
+
+        description = self._og_search_description(webpage)
+
+        view_count = self._html_search_regex(
+            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count')
+        comment_count = self._html_search_regex(
+            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count')
+
+        upload_date = self._html_search_regex(
+            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'upload_date': unified_strdate(upload_date),
+        }

youtube_dl/extractor/liveleak.py

@@ -1,16 +1,14 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class LiveLeakIE(InfoExtractor):
     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
         'file': '757_1364311680.mp4',
         'md5': '0813c2430bea7a46bf13acf3406992f4',
@@ -19,15 +17,37 @@ class LiveLeakIE(InfoExtractor):
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
         }
-    }
+    },
+    {
+        'url': 'http://www.liveleak.com/view?i=f93_1390833151',
+        'file': 'f93_1390833151.mp4',
+        'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
+        'info_dict': {
+            'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
+            'uploader': 'ARD_Stinkt',
+            'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
+        }
+    }]
 
     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)
-        video_url = self._search_regex(
-            r'file: "(.*?)",', webpage, 'video URL')
+        sources_raw = self._search_regex(
+            r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
+        if sources_raw is None:
+            sources_raw = '[{ %s}]' % (
+                self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
+
+        sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
+        sources = json.loads(sources_json)
+
+        formats = [{
+            'format_note': s.get('label'),
+            'url': s['file'],
+        } for s in sources]
+        self._sort_formats(formats)
 
         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
         video_description = self._og_search_description(webpage)
@@ -36,9 +56,8 @@ class LiveLeakIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
             'title': video_title,
             'description': video_description,
-            'uploader': video_uploader
+            'uploader': video_uploader,
+            'formats': formats,
         }

youtube_dl/extractor/m6.py

@@ -0,0 +1,56 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class M6IE(InfoExtractor):
+    IE_NAME = 'm6'
+    _VALID_URL = r'http://(?:www\.)?m6\.fr/[^/]+/videos/(?P<id>\d+)-[^\.]+\.html'
+
+    _TEST = {
+        'url': 'http://www.m6.fr/emission-les_reines_du_shopping/videos/11323908-emeline_est_la_reine_du_shopping_sur_le_theme_ma_fete_d_8217_anniversaire.html',
+        'md5': '242994a87de2c316891428e0176bcb77',
+        'info_dict': {
+            'id': '11323908',
+            'ext': 'mp4',
+            'title': 'Emeline est la Reine du Shopping sur le thème « Ma fête d’anniversaire ! »',
+            'description': 'md5:1212ae8fb4b7baa4dc3886c5676007c2',
+            'duration': 100,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        rss = self._download_xml('http://ws.m6.fr/v1/video/info/m6/bonus/%s' % video_id, video_id,
+            'Downloading video RSS')
+
+        title = rss.find('./channel/item/title').text
+        description = rss.find('./channel/item/description').text
+        thumbnail = rss.find('./channel/item/visuel_clip_big').text
+        duration = int(rss.find('./channel/item/duration').text)
+        view_count = int(rss.find('./channel/item/nombre_vues').text)
+
+        formats = []
+        for format_id in ['lq', 'sd', 'hq', 'hd']:
+            video_url = rss.find('./channel/item/url_video_%s' % format_id)
+            if video_url is None:
+                continue
+            formats.append({
+                'url': video_url.text,
+                'format_id': format_id,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/malemotion.py

@@ -16,7 +16,8 @@ class MalemotionIE(InfoExtractor):
         'info_dict': {
             "title": "Bien dur",
             "age_limit": 18,
-        }
+        },
+        'skip': 'This video has been deleted.'
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/mooshare.py

@@ -0,0 +1,114 @@
+from __future__ import unicode_literals
+
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class MooshareIE(InfoExtractor):
+    IE_NAME = 'mooshare'
+    IE_DESC = 'Mooshare.biz'
+    _VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})'
+
+    _TESTS = [
+        {
+            'url': 'http://mooshare.biz/8dqtk4bjbp8g',
+            'md5': '4e14f9562928aecd2e42c6f341c8feba',
+            'info_dict': {
+                'id': '8dqtk4bjbp8g',
+                'ext': 'mp4',
+                'title': 'Comedy Football 2011 - (part 1-2)',
+                'duration': 893,
+            },
+        },
+        {
+            'url': 'http://mooshare.biz/aipjtoc4g95j',
+            'info_dict': {
+                'id': 'aipjtoc4g95j',
+                'ext': 'mp4',
+                'title': 'Orange Caramel  Dashing Through the Snow',
+                'duration': 212,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        if re.search(r'>Video Not Found or Deleted<', page) is not None:
+            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+
+        hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
+        title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')
+
+        download_form = {
+            'op': 'download1',
+            'id': video_id,
+            'hash': hash_key,
+        }
+
+        request = compat_urllib_request.Request(
+            'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+
+        self.to_screen('%s: Waiting for timeout' % video_id)
+        time.sleep(5)
+
+        video_page = self._download_webpage(request, video_id, 'Downloading video page')
+
+        thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
+        duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
+        duration = int(duration_str) if duration_str is not None else None
+
+        formats = []
+
+        # SD video
+        mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
+        if mobj is not None:
+            formats.append({
+                'url': mobj.group('url'),
+                'format_id': 'sd',
+                'format': 'SD',
+            })
+
+        # HD video
+        mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
+        if mobj is not None:
+            formats.append({
+                'url': mobj.group('url'),
+                'format_id': 'hd',
+                'format': 'HD',
+            })
+
+        # rtmp video
+        mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
+        if mobj is not None:
+            formats.append({
+                'url': mobj.group('rtmpurl'),
+                'play_path': mobj.group('playpath'),
+                'rtmp_live': False,
+                'ext': 'mp4',
+                'format_id': 'rtmp',
+                'format': 'HD',
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/mtv.py

@@ -82,10 +82,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
             title_el = find_xpath_attr(
                 itemdoc, './/{http://search.yahoo.com/mrss/}category',
                 'scheme', 'urn:mtvn:video_title')
-        if title_el is None:
-            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:
             title_el = itemdoc.find('.//title')
+            if title_el.text is None:
+                title_el = None
+        if title_el is None:
+            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
+
         title = title_el.text
         if title is None:
             raise ExtractorError('Could not find video title')
@@ -119,7 +122,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             if mgid.endswith('.swf'):
                 mgid = mgid[:-4]
         except RegexNotFoundError:
-            mgid = self._search_regex(r'data-mgid="(.*?)"', webpage, u'mgid')
+            mgid = self._search_regex(
+                [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
+                webpage, u'mgid')
         return self._get_videos_info(mgid)
 
 

youtube_dl/extractor/myspass.py

@@ -1,3 +1,4 @@
+from __future__ import unicode_literals
 import os.path
 
 from .common import InfoExtractor
@@ -11,13 +12,13 @@ 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"
-        }
+        '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 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?",
+            "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2",
+        },
     }
 
     def _real_extract(self, url):
@@ -37,12 +38,11 @@ class MySpassIE(InfoExtractor):
         # extract values from metadata
         url_flv_el = metadata.find('url_flv')
         if url_flv_el is None:
-            raise ExtractorError(u'Unable to extract download url')
+            raise ExtractorError('Unable to extract download url')
         video_url = url_flv_el.text
-        extension = os.path.splitext(video_url)[1][1:]
         title_el = metadata.find('title')
         if title_el is None:
-            raise ExtractorError(u'Unable to extract title')
+            raise ExtractorError('Unable to extract title')
         title = title_el.text
         format_id_el = metadata.find('format_id')
         if format_id_el is None:
@@ -59,13 +59,12 @@ class MySpassIE(InfoExtractor):
             thumbnail = imagePreview_el.text
         else:
             thumbnail = None
-        info = {
+
+        return {
             'id': video_id,
             'url': video_url,
             'title': title,
-            'ext': extension,
             'format': format,
             'thumbnail': thumbnail,
-            'description': description
+            'description': description,
         }
-        return [info]

youtube_dl/extractor/nba.py

@@ -1,48 +1,39 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 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"
-        }
+        'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
+        'file': u'0021200253-okc-bkn-recap.nba.mp4',
+        'md5': u'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',
+        },
     }
 
     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(1)
 
         webpage = self._download_webpage(url, video_id)
 
-        video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+        video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
 
         shortened_video_id = video_id.rpartition('/')[2]
         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)
-
         description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
 
-        info = {
+        return {
             'id': shortened_video_id,
             'url': video_url,
             'ext': 'mp4',
             'title': title,
-            # 'uploader_date': uploader_date,
             'description': description,
         }
-        return [info]

youtube_dl/extractor/ndr.py

@@ -0,0 +1,89 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NDRIE(InfoExtractor):
+    IE_NAME = 'ndr'
+    IE_DESC = 'NDR.de - Mediathek'
+    _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+
+    _TESTS = [
+        # video
+        {
+            'url': 'http://www.ndr.de/fernsehen/sendungen/hallo_niedersachsen/media/hallonds19925.html',
+            'md5': '20eba151ff165f386643dad9c1da08f7',
+            'info_dict': {
+                'id': '19925',
+                'ext': 'mp4',
+                'title': 'Hallo Niedersachsen  ',
+                'description': 'Bei Hallo Niedersachsen um 19:30 Uhr erfahren Sie alles, was am Tag in Niedersachsen los war.',
+                'duration': 1722,
+            },
+        },
+        # audio
+        {
+            'url': 'http://www.ndr.de/903/audio191719.html',
+            'md5': '41ed601768534dd18a9ae34d84798129',
+            'info_dict': {
+                'id': '191719',
+                'ext': 'mp3',
+                'title': '"Es war schockierend"',
+                'description': 'md5:ed7ff8364793545021a6355b97e95f10',
+                'duration': 112,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        title = self._og_search_title(page)
+        description = self._og_search_description(page)
+
+        mobj = re.search(
+            r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
+            page)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        formats = []
+
+        mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+        if mp3_url:
+            formats.append({
+                'url': mp3_url.group('audio'),
+                'format_id': 'mp3',
+            })
+
+        thumbnail = None
+
+        video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        if video_url:
+            thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
+                page, 'thumbnail', fatal=False)
+            if thumbnail:
+                thumbnail = 'http://www.ndr.de' + thumbnail
+            for format_id in ['lo', 'hi', 'hq']:
+                formats.append({
+                    'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
+                    'format_id': format_id,
+                })
+
+        if not formats:
+            raise ExtractorError('No media links available for %s' % video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/newgrounds.py

@@ -4,18 +4,18 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class NewgroundsIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.newgrounds.com/audio/listen/549479',
-        'file': '549479.mp3',
         'md5': 'fe6033d297591288fa1c1f780386f07a',
         'info_dict': {
-            "title": "B7 - BusMode",
-            "uploader": "Burn7",
+            'id': '549479',
+            'ext': 'mp3',
+            'title': 'B7 - BusMode',
+            'uploader': 'Burn7',
         }
     }
 

youtube_dl/extractor/nfb.py

@@ -0,0 +1,93 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class NFBIE(InfoExtractor):
+    IE_NAME = 'nfb'
+    IE_DESC = 'National Film Board of Canada'
+    _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+
+    _TEST = {
+        'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
+        'info_dict': {
+            'id': 'qallunaat_why_white_people_are_funny',
+            'ext': 'mp4',
+            'title': 'Qallunaat! Why White People Are Funny ',
+            'description': 'md5:836d8aff55e087d04d9f6df554d4e038',
+            'duration': 3128,
+            'uploader': 'Mark Sandiford',
+            'uploader_id': 'mark-sandiford',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+
+        uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
+            page, 'director id', fatal=False)
+        uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
+            page, 'director name', fatal=False)
+
+        request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id,
+            compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')
+
+        config = self._download_xml(request, video_id, 'Downloading player config XML')
+
+        title = None
+        description = None
+        thumbnail = None
+        duration = None
+        formats = []
+
+        def extract_thumbnail(media):
+            thumbnails = {}
+            for asset in media.findall('assets/asset'):
+                thumbnails[asset.get('quality')] = asset.find('default/url').text
+            if not thumbnails:
+                return None
+            if 'high' in thumbnails:
+                return thumbnails['high']
+            return list(thumbnails.values())[0]
+
+        for media in config.findall('./player/stream/media'):
+            if media.get('type') == 'posterImage':
+                thumbnail = extract_thumbnail(media)
+            elif media.get('type') == 'video':
+                duration = int(media.get('duration'))
+                title = media.find('title').text
+                description = media.find('description').text
+                # It seems assets always go from lower to better quality, so no need to sort
+                formats = [{
+                    'url': x.find('default/streamerURI').text + '/',
+                    'play_path': x.find('default/url').text,
+                    'rtmp_live': False,
+                    'ext': 'mp4',
+                    'format_id': x.get('quality'),
+                } for x in media.findall('assets/asset')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/normalboots.py

@@ -0,0 +1,61 @@
+import re
+
+from .common import InfoExtractor
+
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
+
+class NormalbootsIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+    _TEST = {
+        u'url': u'http://normalboots.com/video/home-alone-games-jontron/',
+        u'file': u'home-alone-games-jontron.mp4',
+        u'md5': u'8bf6de238915dd501105b44ef5f1e0f6',
+        u'info_dict': {
+            u'title': u'Home Alone Games - JonTron - NormalBoots',
+            u'description': u'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/',
+            u'uploader': u'JonTron',
+            u'upload_date': u'20140125',
+        }
+    }
+    
+    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('videoid')
+        
+        info = {
+            'id': video_id,
+            'uploader': None,
+            'upload_date': None,
+        }
+        
+        if url[:4] != 'http':
+            url = 'http://' + url
+        
+        webpage = self._download_webpage(url, video_id)
+        video_title = self._og_search_title(webpage)
+        video_description = self._og_search_description(webpage)
+        video_thumbnail = self._og_search_thumbnail(webpage)
+        video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
+            webpage, 'uploader')
+        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', 
+            webpage, 'date')
+        video_upload_date = unified_strdate(raw_upload_date)
+        video_upload_date = unified_strdate(raw_upload_date)
+            
+        player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
+        player_page = self._download_webpage(player_url, video_id)
+        video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P<file>[0-9A-Za-z-_\.]+)'", player_page, 'file')
+        
+        info['url'] = video_url
+        info['title'] = video_title
+        info['description'] = video_description
+        info['thumbnail'] = video_thumbnail
+        info['uploader'] = video_uploader
+        info['upload_date'] = video_upload_date
+        
+        return info

youtube_dl/extractor/ooyala.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 from ..utils import unescapeHTML
 
 class OoyalaIE(InfoExtractor):
-    _VALID_URL = r'https?://.+?\.ooyala\.com/.*?embedCode=(?P<id>.+?)(&|$)'
+    _VALID_URL = r'https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=(?P<id>.+?)(&|$)'
 
     _TEST = {
         # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video

youtube_dl/extractor/pbs.py

@@ -1,34 +1,68 @@
+from __future__ import unicode_literals
+
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class PBSIE(InfoExtractor):
-    _VALID_URL = r'https?://video\.pbs\.org/video/(?P<id>\d+)/?'
+    _VALID_URL = r'''(?x)https?://
+        (?:
+            # Direct video URL
+            video\.pbs\.org/video/(?P<id>[0-9]+)/? |
+            # Article with embedded player
+           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) |
+           # Player
+           video\.pbs\.org/partnerplayer/(?P<player_id>[^/]+)/
+        )
+    '''
 
     _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,
+        'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
+        'md5': 'ce1888486f0908d555a8093cac9a7362',
+        'info_dict': {
+            'id': '2365006249',
+            'ext': 'mp4',
+            'title': 'A More Perfect Union',
+            'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
+            'duration': 3190,
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+
+        presumptive_id = mobj.group('presumptive_id')
+        display_id = presumptive_id
+        if presumptive_id:
+            webpage = self._download_webpage(url, display_id)
+            url = self._search_regex(
+                r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                webpage, 'player URL')
+            mobj = re.match(self._VALID_URL, url)
+
+        player_id = mobj.group('player_id')
+        if not display_id:
+            display_id = player_id
+        if player_id:
+            player_page = self._download_webpage(
+                url, display_id, note='Downloading player page',
+                errnote='Could not download player page')
+            video_id = self._search_regex(
+                r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
+        else:
+            video_id = mobj.group('id')
+            display_id = video_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'),
-                }
+        info = self._download_json(info_url, display_id)
+
+        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/rbmaradio.py

@@ -1,10 +1,11 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse_urlparse,
-
     ExtractorError,
 )
 
@@ -12,16 +13,17 @@ 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"
-        }
+        'url': 'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
+        'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
+        'info_dict': {
+            'id': 'ford-lopatin-live-at-primavera-sound-2011',
+            'ext': 'mp3',
+            "uploader_id": "ford-lopatin",
+            "location": "Spain",
+            "description": "Joel Ford and Daniel ’Oneohtrix Point Never’ Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
+            "uploader": "Ford & Lopatin",
+            "title": "Live at Primavera Sound 2011",
+        },
     }
 
     def _real_extract(self, url):
@@ -31,26 +33,23 @@ class RBMARadioIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
-            webpage, u'json data', flags=re.MULTILINE)
+            webpage, 'json data', flags=re.MULTILINE)
 
         try:
             data = json.loads(json_data)
         except ValueError as e:
-            raise ExtractorError(u'Invalid JSON: ' + str(e))
+            raise ExtractorError('Invalid JSON: ' + str(e))
 
         video_url = data['akamai_url'] + '&cbr=256'
-        url_parts = compat_urllib_parse_urlparse(video_url)
-        video_ext = url_parts.path.rpartition('.')[2]
-        info = {
-                'id': video_id,
-                'url': video_url,
-                'ext': video_ext,
-                'title': data['title'],
-                'description': data.get('teaser_text'),
-                'location': data.get('country_of_origin'),
-                'uploader': data.get('host', {}).get('name'),
-                'uploader_id': data.get('host', {}).get('slug'),
-                'thumbnail': data.get('image', {}).get('large_url_2x'),
-                'duration': data.get('duration'),
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': data['title'],
+            'description': data.get('teaser_text'),
+            'location': data.get('country_of_origin'),
+            'uploader': data.get('host', {}).get('name'),
+            'uploader_id': data.get('host', {}).get('slug'),
+            'thumbnail': data.get('image', {}).get('large_url_2x'),
+            'duration': data.get('duration'),
         }
-        return [info]

youtube_dl/extractor/ro220.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -11,12 +13,12 @@ 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.",
+        "url": "http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
+        'file': 'LYV6doKo7f.mp4',
+        'md5': '03af18b73a07b4088753930db7a34add',
+        'info_dict': {
+            "title": "Luati-le Banii sez 4 ep 1",
+            "description": "Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
         }
     }
 
@@ -27,10 +29,10 @@ class Ro220IE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         flashVars_str = self._search_regex(
             r'<param name="flashVars" value="([^"]+)"',
-            webpage, u'flashVars')
+            webpage, 'flashVars')
         flashVars = compat_parse_qs(flashVars_str)
 
-        info = {
+        return {
             '_type': 'video',
             'id': video_id,
             'ext': 'mp4',
@@ -39,4 +41,3 @@ class Ro220IE(InfoExtractor):
             'description': clean_html(flashVars['desc'][0]),
             'thumbnail': flashVars['preview'][0],
         }
-        return info

youtube_dl/extractor/southparkstudios.py

@@ -1,34 +1,36 @@
-import re
+from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
 
 
 class SouthParkStudiosIE(MTVServicesInfoExtractor):
-    IE_NAME = u'southparkstudios.com'
-    _VALID_URL = r'(https?://)?(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    IE_NAME = 'southparkstudios.com'
+    _VALID_URL = r'https?://(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
 
     _TESTS = [{
-        u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
-        u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4',
-        u'info_dict': {
-            u'title': u'Bat Daded',
-            u'description': u'Randy disqualifies South Park by getting into a fight with Bat Dad.',
+        'url': 'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
+        'info_dict': {
+            'id': 'a7bff6c2-ed00-11e0-aca6-0026b9414f30',
+            'ext': 'mp4',
+            'title': 'Bat Daded',
+            'description': 'Randy disqualifies South Park by getting into a fight with Bat Dad.',
         },
     }]
 
 
 class SouthparkDeIE(SouthParkStudiosIE):
-    IE_NAME = u'southpark.de'
-    _VALID_URL = r'(https?://)?(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
+    IE_NAME = 'southpark.de'
+    _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
     _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
 
     _TESTS = [{
-        u'url': u'http://www.southpark.de/clips/uygssh/the-government-wont-respect-my-privacy#tab=featured',
-        u'file': u'85487c96-b3b9-4e39-9127-ad88583d9bf2.mp4',
-        u'info_dict': {
-            u'title': u'The Government Won\'t Respect My Privacy',
-            u'description': u'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
+        'url': 'http://www.southpark.de/clips/uygssh/the-government-wont-respect-my-privacy#tab=featured',
+        'info_dict': {
+            'id': '85487c96-b3b9-4e39-9127-ad88583d9bf2',
+            'ext': 'mp4',
+            'title': 'The Government Won\'t Respect My Privacy',
+            'description': 'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
         },
     }]

youtube_dl/extractor/spiegel.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -6,20 +8,20 @@ from .common import InfoExtractor
 class SpiegelIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
     _TESTS = [{
-        u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
-        u'file': u'1259285.mp4',
-        u'md5': u'2c2754212136f35fb4b19767d242f66e',
-        u'info_dict': {
-            u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
-        }
+        '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',
+        },
     },
     {
-        u'url': u'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
-        u'file': u'1309159.mp4',
-        u'md5': u'f2cdf638d7aa47654e251e1aee360af1',
-        u'info_dict': {
-            u'title': u'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers'
-        }
+        'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
+        'file': '1309159.mp4',
+        'md5': 'f2cdf638d7aa47654e251e1aee360af1',
+        'info_dict': {
+            'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
+        },
     }]
 
     def _real_extract(self, url):
@@ -29,17 +31,17 @@ class SpiegelIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._html_search_regex(
-            r'<div class="module-title">(.*?)</div>', webpage, u'title')
+            r'<div class="module-title">(.*?)</div>', webpage, 'title')
 
-        xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
+        xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml'
         idoc = self._download_xml(
             xml_url, video_id,
-            note=u'Downloading XML', errnote=u'Failed to download XML')
+            note='Downloading XML', errnote='Failed to download XML')
 
         formats = [
             {
                 'format_id': n.tag.rpartition('type')[2],
-                'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text,
+                'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text,
                 'width': int(n.find('./width').text),
                 'height': int(n.find('./height').text),
                 'abr': int(n.find('./audiobitrate').text),
@@ -55,10 +57,9 @@ class SpiegelIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        info = {
+        return {
             'id': video_id,
             'title': video_title,
             'duration': duration,
             'formats': formats,
         }
-        return info

youtube_dl/extractor/statigram.py

@@ -1,36 +1,38 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
+
 class StatigramIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
+    _VALID_URL = r'https?://(www\.)?statigr\.am/p/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://statigr.am/p/522207370455279102_24101272',
-        u'file': u'522207370455279102_24101272.mp4',
-        u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
-        u'info_dict': {
-            u'uploader_id': u'aguynamedpatrick',
-            u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+        'url': 'http://statigr.am/p/522207370455279102_24101272',
+        'md5': '6eb93b882a3ded7c378ee1d6884b1814',
+        'info_dict': {
+            'id': '522207370455279102_24101272',
+            'ext': 'mp4',
+            'uploader_id': 'aguynamedpatrick',
+            'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         html_title = self._html_search_regex(
             r'<title>(.+?)</title>',
-            webpage, u'title')
+            webpage, 'title')
         title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
         uploader_id = self._html_search_regex(
-            r'@([^ ]+)', title, u'uploader name', fatal=False)
-        ext = 'mp4'
+            r'@([^ ]+)', title, 'uploader name', fatal=False)
 
-        return [{
-            'id':        video_id,
-            'url':       self._og_search_video_url(webpage),
-            'ext':       ext,
-            'title':     title,
+        return {
+            'id': video_id,
+            'url': self._og_search_video_url(webpage),
+            'title': title,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id' : uploader_id
-        }]
+            'uploader_id': uploader_id
+        }

youtube_dl/extractor/subtitles.py

@@ -62,10 +62,13 @@ class SubtitlesInfoExtractor(InfoExtractor):
                 subtitles[sub_lang] = subtitle
         return subtitles
 
+    def _download_subtitle_url(self, sub_lang, url):
+        return self._download_webpage(url, None, note=False)
+
     def _request_subtitle_url(self, sub_lang, url):
         """ makes the http request for the subtitle """
         try:
-            sub = self._download_webpage(url, None, note=False)
+            sub = self._download_subtitle_url(sub_lang, url)
         except ExtractorError as err:
             self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
             return
@@ -79,7 +82,11 @@ class SubtitlesInfoExtractor(InfoExtractor):
         returns {sub_lang: url} or {} if not available
         Must be redefined by the subclasses
         """
-        pass
+
+        # By default, allow implementations to simply pass in the result
+        assert isinstance(webpage, dict), \
+            '_get_available_subtitles not implemented'
+        return webpage
 
     def _get_available_automatic_caption(self, video_id, webpage):
         """

youtube_dl/extractor/thisav.py

@@ -1,22 +1,23 @@
 #coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-)
+from ..utils import determine_ext
+
 
 class ThisAVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
     _TEST = {
-        u"url": u"http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html",
-        u"file": u"47734.flv",
-        u"md5": u"0480f1ef3932d901f0e0e719f188f19b",
-        u"info_dict": {
-            u"title": u"高樹マリア - Just fit",
-            u"uploader": u"dj7970",
-            u"uploader_id": u"dj7970"
+        'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
+        'md5': '0480f1ef3932d901f0e0e719f188f19b',
+        'info_dict': {
+            'id': '47734',
+            'ext': 'flv',
+            'title': '高樹マリア - Just fit',
+            'uploader': 'dj7970',
+            'uploader_id': 'dj7970'
         }
     }
 
@@ -25,19 +26,18 @@ class ThisAVIE(InfoExtractor):
 
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, u'title')
+        title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
         video_url = self._html_search_regex(
-            r"addVariable\('file','([^']+)'\);", webpage, u'video url')
+            r"addVariable\('file','([^']+)'\);", webpage, 'video url')
         uploader = self._html_search_regex(
             r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
-            webpage, u'uploader name', fatal=False)
+            webpage, 'uploader name', fatal=False)
         uploader_id = self._html_search_regex(
             r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
-            webpage, u'uploader id', fatal=False)
+            webpage, 'uploader id', fatal=False)
         ext = determine_ext(video_url)
         
         return {
-            '_type':       'video',
             'id':          video_id,
             'url':         video_url,
             'uploader':    uploader,

youtube_dl/extractor/tinypic.py

@@ -0,0 +1,50 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from youtube_dl.utils import ExtractorError
+
+
+class TinyPicIE(InfoExtractor):
+    IE_NAME = 'tinypic'
+    IE_DESC = 'tinypic.com videos'
+    _VALID_URL = r'http://tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
+
+    _TEST = {
+        'url': 'http://tinypic.com/player.php?v=6xw7tc%3E&s=5#.UtqZmbRFCM8',
+        'md5': '609b74432465364e72727ebc6203f044',
+        'info_dict': {
+            'id': '6xw7tc',
+            'ext': 'flv',
+            'title': 'shadow phenomenon weird',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+        
+        mobj = re.search(r'(?m)fo\.addVariable\("file",\s"(?P<fileid>[\da-z]+)"\);\n'
+            '\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage)
+        if mobj is None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        file_id = mobj.group('fileid')
+        server_id = mobj.group('serverid')
+
+        KEYWORDS_SUFFIX = ', Video, images, photos, videos, myspace, ebay, video hosting, photo hosting'
+        keywords = self._html_search_meta('keywords', webpage, 'title')
+        title = keywords[:-len(KEYWORDS_SUFFIX)] if keywords.endswith(KEYWORDS_SUFFIX) else ''
+
+        video_url = 'http://v%s.tinypic.com/%s.flv' % (server_id, file_id)
+        thumbnail = 'http://v%s.tinypic.com/%s_th.jpg' % (server_id, file_id)
+
+        return {
+            'id': file_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title
+        }

youtube_dl/extractor/toutv.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,25 +11,25 @@ from ..utils import (
 
 
 class TouTvIE(InfoExtractor):
-    IE_NAME = u'tou.tv'
+    IE_NAME = 'tou.tv'
     _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
 
     _TEST = {
-        u'url': u'http://www.tou.tv/30-vies/S04E41',
-        u'file': u'30-vies_S04E41.mp4',
-        u'info_dict': {
-            u'title': u'30 vies Saison 4 / Épisode 41',
-            u'description': u'md5:da363002db82ccbe4dafeb9cab039b09',
-            u'age_limit': 8,
-            u'uploader': u'Groupe des Nouveaux Médias',
-            u'duration': 1296,
-            u'upload_date': u'20131118',
-            u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
+        'url': 'http://www.tou.tv/30-vies/S04E41',
+        'file': '30-vies_S04E41.mp4',
+        'info_dict': {
+            'title': '30 vies Saison 4 / Épisode 41',
+            'description': 'md5:da363002db82ccbe4dafeb9cab039b09',
+            'age_limit': 8,
+            'uploader': 'Groupe des Nouveaux Médias',
+            'duration': 1296,
+            'upload_date': '20131118',
+            'thumbnail': 'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
         },
-        u'params': {
-            u'skip_download': True,  # Requires rtmpdump
+        'params': {
+            'skip_download': True,  # Requires rtmpdump
         },
-        u'skip': 'Only available in Canada'
+        'skip': 'Only available in Canada'
     }
 
     def _real_extract(self, url):
@@ -36,25 +38,25 @@ class TouTvIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         mediaId = self._search_regex(
-            r'"idMedia":\s*"([^"]+)"', webpage, u'media ID')
+            r'"idMedia":\s*"([^"]+)"', webpage, 'media ID')
 
-        streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId
+        streams_url = 'http://release.theplatform.com/content.select?pid=' + mediaId
         streams_doc = self._download_xml(
-            streams_url, video_id, note=u'Downloading stream list')
+            streams_url, video_id, note='Downloading stream list')
 
         video_url = next(n.text
                          for n in streams_doc.findall('.//choice/url')
-                         if u'//ad.doubleclick' not in n.text)
+                         if '//ad.doubleclick' not in n.text)
         if video_url.endswith('/Unavailable.flv'):
             raise ExtractorError(
-                u'Access to this video is blocked from outside of Canada',
+                'Access to this video is blocked from outside of Canada',
                 expected=True)
 
         duration_str = self._html_search_meta(
-            'video:duration', webpage, u'duration')
+            'video:duration', webpage, 'duration')
         duration = int(duration_str) if duration_str else None
         upload_date_str = self._html_search_meta(
-            'video:release_date', webpage, u'upload date')
+            'video:release_date', webpage, 'upload date')
         upload_date = unified_strdate(upload_date_str) if upload_date_str else None
 
         return {

youtube_dl/extractor/traileraddict.py

@@ -1,17 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class TrailerAddictIE(InfoExtractor):
+    _WORKING = False
     _VALID_URL = r'(?:http://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
     _TEST = {
-        u'url': u'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
-        u'file': u'76184.mp4',
-        u'md5': u'57e39dbcf4142ceb8e1f242ff423fd71',
-        u'info_dict': {
-            u"title": u"Prince Avalanche Trailer",
-            u"description": u"Trailer for Prince Avalanche.Two highway road workers spend the summer of 1988 away from their city lives. The isolated landscape becomes a place of misadventure as the men find themselves at odds with each other and the women they left behind."
+        'url': 'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
+        'md5': '41365557f3c8c397d091da510e73ceb4',
+        'info_dict': {
+            'id': '76184',
+            'ext': 'mp4',
+            'title': 'Prince Avalanche Trailer',
+            'description': 'Trailer for Prince Avalanche.\n\nTwo highway road workers spend the summer of 1988 away from their city lives. The isolated landscape becomes a place of misadventure as the men find themselves at odds with each other and the women they left behind.',
         }
     }
 
@@ -22,9 +26,15 @@ class TrailerAddictIE(InfoExtractor):
 
         title = self._search_regex(r'<title>(.+?)</title>',
                 webpage, 'video title').replace(' - Trailer Addict','')
-        view_count = self._search_regex(r'Views: (.+?)<br />',
-                webpage, 'Views Count')
-        video_id = self._og_search_property('video', webpage, 'Video id').split('=')[1]
+        view_count_str = self._search_regex(
+            r'<span class="views_n">([0-9,.]+)</span>',
+            webpage, 'view count', fatal=False)
+        view_count = (
+            None if view_count_str is None
+            else int(view_count_str.replace(',', '')))
+        video_id = self._search_regex(
+            r'<param\s+name="movie"\s+value="/emb/([0-9]+)"\s*/>',
+            webpage, 'video id')
 
         # Presence of (no)watchplus function indicates HD quality is available
         if re.search(r'function (no)?watchplus()', webpage):
@@ -39,14 +49,16 @@ class TrailerAddictIE(InfoExtractor):
                 info_webpage, 'Download url').replace('%3F','?')
         thumbnail_url = self._search_regex(r'&image=(.+?)&',
                 info_webpage, 'thumbnail url')
-        ext = final_url.split('.')[-1].split('?')[0]
 
-        return [{
-            'id'          : video_id,
-            'url'         : final_url,
-            'ext'         : ext,
-            'title'       : title,
-            'thumbnail'   : thumbnail_url,
-            'description' : self._og_search_description(webpage),
-            'view_count'  : view_count,
-        }]
+        description = self._html_search_regex(
+            r'(?s)<div class="synopsis">.*?<div class="movie_label_info"[^>]*>(.*?)</div>',
+            webpage, 'description', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': title,
+            'thumbnail': thumbnail_url,
+            'description': description,
+            'view_count': view_count,
+        }

youtube_dl/extractor/tube8.py

@@ -11,7 +11,7 @@ from ..aes import (
 )
 
 class Tube8IE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/.+?/(?P<videoid>\d+)/?)$'
     _TEST = {
         u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/',
         u'file': u'229795.mp4',

youtube_dl/extractor/tutv.py

@@ -1,3 +1,4 @@
+from __future__ import unicode_literals
 import base64
 import re
 
@@ -6,15 +7,16 @@ from ..utils import (
     compat_parse_qs,
 )
 
+
 class TutvIE(InfoExtractor):
-    _VALID_URL=r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
+    _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
     _TEST = {
-        u'url': u'http://tu.tv/videos/noah-en-pabellon-cuahutemoc',
-        u'file': u'2742556.flv',
-        u'md5': u'5eb766671f69b82e528dc1e7769c5cb2',
-        u'info_dict': {
-            u"title": u"Noah en pabellon cuahutemoc"
-        }
+        'url': 'http://tu.tv/videos/noah-en-pabellon-cuahutemoc',
+        'file': '2742556.flv',
+        'md5': '5eb766671f69b82e528dc1e7769c5cb2',
+        'info_dict': {
+            'title': 'Noah en pabellon cuahutemoc',
+        },
     }
 
     def _real_extract(self, url):
@@ -22,18 +24,15 @@ class TutvIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, u'internal video ID')
+        internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
 
-        data_url = u'http://tu.tv/flvurl.php?codVideo=' + str(internal_id)
-        data_content = self._download_webpage(data_url, video_id, note=u'Downloading video info')
+        data_url = 'http://tu.tv/flvurl.php?codVideo=' + str(internal_id)
+        data_content = self._download_webpage(data_url, video_id, note='Downloading video info')
         data = compat_parse_qs(data_content)
         video_url = base64.b64decode(data['kpt'][0]).decode('utf-8')
-        ext = video_url.partition(u'?')[0].rpartition(u'.')[2]
 
-        info = {
+        return {
             'id': internal_id,
             'url': video_url,
-            'ext': ext,
             'title': self._og_search_title(webpage),
         }
-        return [info]

youtube_dl/extractor/ustream.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -10,48 +12,48 @@ from ..utils import (
 
 class UstreamIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
-    IE_NAME = u'ustream'
+    IE_NAME = 'ustream'
     _TEST = {
-        u'url': u'http://www.ustream.tv/recorded/20274954',
-        u'file': u'20274954.flv',
-        u'md5': u'088f151799e8f572f84eb62f17d73e5c',
-        u'info_dict': {
-            u"uploader": u"Young Americans for Liberty", 
-            u"title": u"Young Americans for Liberty February 7, 2012 2:28 AM"
-        }
+        'url': 'http://www.ustream.tv/recorded/20274954',
+        'file': '20274954.flv',
+        'md5': '088f151799e8f572f84eb62f17d73e5c',
+        'info_dict': {
+            "uploader": "Young Americans for Liberty",
+            "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
+        },
     }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
         video_id = m.group('videoID')
 
-        video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
+        video_url = 'http://tcdn.ustream.tv/video/%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
         self.report_extraction(video_id)
 
         video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
-            webpage, u'title')
+            webpage, 'title')
 
         uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
-            webpage, u'uploader', fatal=False, flags=re.DOTALL)
+            webpage, 'uploader', fatal=False, flags=re.DOTALL)
 
         thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
-            webpage, u'thumbnail', fatal=False)
+            webpage, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': video_title,
+            'uploader': uploader,
+            'thumbnail': thumbnail,
+        }
 
-        info = {
-                'id': video_id,
-                'url': video_url,
-                'ext': 'flv',
-                'title': video_title,
-                'uploader': uploader,
-                'thumbnail': thumbnail,
-               }
-        return info
 
 class UstreamChannelIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
-    IE_NAME = u'ustream:channel'
+    IE_NAME = 'ustream:channel'
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

youtube_dl/extractor/vbox7.py

@@ -1,3 +1,6 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -10,45 +13,44 @@ from ..utils import (
 
 
 class Vbox7IE(InfoExtractor):
-    """Information Extractor for Vbox7"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
+    _VALID_URL = r'http://(www\.)?vbox7\.com/play:(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://vbox7.com/play:249bb972c2',
-        u'file': u'249bb972c2.flv',
-        u'md5': u'99f65c0c9ef9b682b97313e052734c3f',
-        u'info_dict': {
-            u"title": u"\u0421\u043c\u044f\u0445! \u0427\u0443\u0434\u043e - \u0447\u0438\u0441\u0442 \u0437\u0430 \u0441\u0435\u043a\u0443\u043d\u0434\u0438 - \u0421\u043a\u0440\u0438\u0442\u0430 \u043a\u0430\u043c\u0435\u0440\u0430"
-        }
+        'url': 'http://vbox7.com/play:249bb972c2',
+        'md5': '99f65c0c9ef9b682b97313e052734c3f',
+        'info_dict': {
+            'id': '249bb972c2',
+            'ext': 'flv',
+            'title': 'Смях! Чудо - чист за секунди - Скрита камера',
+        },
     }
 
-    def _real_extract(self,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(1)
+        video_id = mobj.group('id')
 
         redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
+        new_location = self._search_regex(r'window\.location = \'(.*)\';',
+            redirect_page, 'redirect location')
         redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
+        webpage = self._download_webpage(redirect_url, video_id,
+            'Downloading redirect page')
 
         title = self._html_search_regex(r'<title>(.*)</title>',
-            webpage, u'title').split('/')[0].strip()
+            webpage, 'title').split('/')[0].strip()
 
-        ext = "flv"
         info_url = "http://vbox7.com/play/magare.do"
-        data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
+        data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id})
         info_request = compat_urllib_request.Request(info_url, data)
         info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
+        info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
         if info_response is None:
-            raise ExtractorError(u'Unable to extract the media url')
+            raise ExtractorError('Unable to extract the media url')
         (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
 
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       ext,
-            'title':     title,
+        return {
+            'id': video_id,
+            'url': final_url,
+            'ext': 'flv',
+            'title': title,
             'thumbnail': thumbnail_url,
-        }]
+        }

youtube_dl/extractor/vevo.py

@@ -1,5 +1,6 @@
+from __future__ import unicode_literals
+
 import re
-import json
 import xml.etree.ElementTree
 import datetime
 
@@ -22,16 +23,16 @@ class VevoIE(InfoExtractor):
            vevo:)
         (?P<id>[^&?#]+)'''
     _TESTS = [{
-        u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
-        u'file': u'GB1101300280.mp4',
-        u"md5": u"06bea460acb744eab74a9d7dcb4bfd61",
-        u'info_dict': {
-            u"upload_date": u"20130624",
-            u"uploader": u"Hurts",
-            u"title": u"Somebody to Die For",
-            u"duration": 230.12,
-            u"width": 1920,
-            u"height": 1080,
+        'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
+        'file': 'GB1101300280.mp4',
+        "md5": "06bea460acb744eab74a9d7dcb4bfd61",
+        'info_dict': {
+            "upload_date": "20130624",
+            "uploader": "Hurts",
+            "title": "Somebody to Die For",
+            "duration": 230.12,
+            "width": 1920,
+            "height": 1080,
         }
     }]
     _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/'
@@ -44,7 +45,7 @@ class VevoIE(InfoExtractor):
                 if version['version'] > last_version['version']:
                     last_version = version
         if last_version['version'] == -1:
-            raise ExtractorError(u'Unable to extract last version of the video')
+            raise ExtractorError('Unable to extract last version of the video')
 
         renditions = xml.etree.ElementTree.fromstring(last_version['data'])
         formats = []
@@ -85,7 +86,7 @@ class VevoIE(InfoExtractor):
             format_url = self._SMIL_BASE_URL + m.group('path')
             formats.append({
                 'url': format_url,
-                'format_id': u'SMIL_' + m.group('cbr'),
+                'format_id': 'SMIL_' + m.group('cbr'),
                 'vcodec': m.group('vcodec'),
                 'acodec': m.group('acodec'),
                 'vbr': int(m.group('vbr')),
@@ -101,26 +102,25 @@ class VevoIE(InfoExtractor):
         video_id = mobj.group('id')
 
         json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
-        info_json = self._download_webpage(json_url, video_id, u'Downloading json info')
-        video_info = json.loads(info_json)['video']
+        video_info = self._download_json(json_url, video_id)['video']
 
         formats = self._formats_from_json(video_info)
         try:
             smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
                 self._SMIL_BASE_URL, video_id, video_id.lower())
             smil_xml = self._download_webpage(smil_url, video_id,
-                                              u'Downloading SMIL info')
+                                              'Downloading SMIL info')
             formats.extend(self._formats_from_smil(smil_xml))
         except ExtractorError as ee:
             if not isinstance(ee.cause, compat_HTTPError):
                 raise
             self._downloader.report_warning(
-                u'Cannot download SMIL information, falling back to JSON ..')
+                'Cannot download SMIL information, falling back to JSON ..')
 
         timestamp_ms = int(self._search_regex(
-            r'/Date\((\d+)\)/', video_info['launchDate'], u'launch date'))
+            r'/Date\((\d+)\)/', video_info['launchDate'], 'launch date'))
         upload_date = datetime.datetime.fromtimestamp(timestamp_ms // 1000)
-        info = {
+        return {
             'id': video_id,
             'title': video_info['title'],
             'formats': formats,
@@ -129,5 +129,3 @@ class VevoIE(InfoExtractor):
             'uploader': video_info['mainArtists'][0]['artistName'],
             'duration': video_info['duration'],
         }
-
-        return info

youtube_dl/extractor/vimeo.py

@@ -6,10 +6,10 @@ import re
 import itertools
 
 from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
-
     clean_html,
     get_element_by_attribute,
     ExtractorError,
@@ -19,7 +19,7 @@ from ..utils import (
 )
 
 
-class VimeoIE(InfoExtractor):
+class VimeoIE(SubtitlesInfoExtractor):
     """Information extractor for vimeo.com."""
 
     # _VALID_URL matches Vimeo URLs
@@ -84,6 +84,20 @@ class VimeoIE(InfoExtractor):
                 'videopassword': 'youtube-dl',
             },
         },
+        {
+            'url': 'http://vimeo.com/76979871',
+            'md5': '3363dd6ffebe3784d56f4132317fd446',
+            'note': 'Video with subtitles',
+            'info_dict': {
+                'id': '76979871',
+                'ext': 'mp4',
+                'title': 'The New Vimeo Player (You Know, For Videos)',
+                'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
+                'upload_date': '20131015',
+                'uploader_id': 'staff',
+                'uploader': 'Vimeo Staff',
+            }
+        },
     ]
 
     def _login(self):
@@ -273,19 +287,31 @@ class VimeoIE(InfoExtractor):
         if len(formats) == 0:
             raise ExtractorError('No known codec found')
 
+        subtitles = {}
+        text_tracks = config['request'].get('text_tracks')
+        if text_tracks:
+            for tt in text_tracks:
+                subtitles[tt['lang']] = 'http://vimeo.com' + tt['url']
+
+        video_subtitles = self.extract_subtitles(video_id, subtitles)
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
         return {
-            'id':       video_id,
+            'id': video_id,
             'uploader': video_uploader,
             'uploader_id': video_uploader_id,
-            'upload_date':  video_upload_date,
-            'title':    video_title,
-            'thumbnail':    video_thumbnail,
-            'description':  video_description,
+            'upload_date': video_upload_date,
+            'title': video_title,
+            'thumbnail': video_thumbnail,
+            'description': video_description,
             'formats': formats,
             'webpage_url': url,
             'view_count': view_count,
             'like_count': like_count,
             'comment_count': comment_count,
+            'subtitles': video_subtitles,
         }
 
 

youtube_dl/extractor/vine.py

@@ -1,18 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class VineIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?vine\.co/v/(?P<id>\w+)'
     _TEST = {
-        u'url': u'https://vine.co/v/b9KOOWX7HUx',
-        u'file': u'b9KOOWX7HUx.mp4',
-        u'md5': u'2f36fed6235b16da96ce9b4dc890940d',
-        u'info_dict': {
-            u"uploader": u"Jack Dorsey", 
-            u"title": u"Chicken."
-        }
+        'url': 'https://vine.co/v/b9KOOWX7HUx',
+        'md5': '2f36fed6235b16da96ce9b4dc890940d',
+        'info_dict': {
+            'id': 'b9KOOWX7HUx',
+            'ext': 'mp4',
+            'uploader': 'Jack Dorsey',
+            'title': 'Chicken.',
+        },
     }
 
     def _real_extract(self, url):
@@ -24,17 +27,17 @@ class VineIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
-        video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
-            webpage, u'video URL')
+        video_url = self._html_search_meta('twitter:player:stream', webpage,
+            'video URL')
 
         uploader = self._html_search_regex(r'<p class="username">(.*?)</p>',
-            webpage, u'uploader', fatal=False, flags=re.DOTALL)
+            webpage, 'uploader', fatal=False, flags=re.DOTALL)
 
-        return [{
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       'mp4',
-            'title':     self._og_search_title(webpage),
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader':  uploader,
-        }]
+            'uploader': uploader,
+        }

youtube_dl/extractor/vube.py

@@ -0,0 +1,80 @@
+from __future__ import unicode_literals
+
+import re
+import datetime
+
+from .common import InfoExtractor
+
+
+class VubeIE(InfoExtractor):
+    IE_NAME = 'vube'
+    IE_DESC = 'Vube.com'
+    _VALID_URL = r'http://vube\.com/[^/]+/(?P<id>[\da-zA-Z]{10})'
+
+    _TEST = {
+        'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
+        'md5': 'f81dcf6d0448e3291f54380181695821',
+        'info_dict': {
+            'id': 'YL2qNPkqon',
+            'ext': 'mp4',
+            'title': 'Chiara Grispo - Price Tag by Jessie J',
+            'description': 'md5:8ea652a1f36818352428cb5134933313',
+            'thumbnail': 'http://frame.thestaticvube.com/snap/228x128/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f.jpg',
+            'uploader': 'Chiara.Grispo',
+            'uploader_id': '1u3hX0znhP',
+            'upload_date': '20140103',
+            'duration': 170.56
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        video = self._download_json('http://vube.com/api/v2/video/%s' % video_id,
+            video_id, 'Downloading video JSON')
+
+        public_id = video['public_id']
+
+        formats = [{'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (fmt['media_resolution_id'], public_id),
+                   'height': int(fmt['height']),
+                   'abr': int(fmt['audio_bitrate']),
+                   'vbr': int(fmt['video_bitrate']),
+                   'format_id': fmt['media_resolution_id']
+                   } for fmt in video['mtm'] if fmt['transcoding_status'] == 'processed']
+
+        self._sort_formats(formats)
+
+        title = video['title']
+        description = video.get('description')
+        thumbnail = video['thumbnail_src']
+        if thumbnail.startswith('//'):
+            thumbnail = 'http:' + thumbnail
+        uploader = video['user_alias']
+        uploader_id = video['user_url_id']
+        upload_date = datetime.datetime.fromtimestamp(int(video['upload_time'])).strftime('%Y%m%d')
+        duration = video['duration']
+        view_count = video['raw_view_count']
+        like_count = video['total_likes']
+        dislike_count= video['total_hates']
+
+        comment = self._download_json('http://vube.com/api/video/%s/comment' % video_id,
+            video_id, 'Downloading video comment JSON')
+
+        comment_count = comment['total']
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+        }

youtube_dl/extractor/xhamster.py

@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
-    unescapeHTML,
     ExtractorError,
 )
 

youtube_dl/extractor/youjizz.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,12 +11,12 @@ from ..utils import (
 class YouJizzIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
     _TEST = {
-        u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
-        u'file': u'2189178.flv',
-        u'md5': u'07e15fa469ba384c7693fd246905547c',
-        u'info_dict': {
-            u"title": u"Zeichentrick 1",
-            u"age_limit": 18,
+        'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
+        'file': '2189178.flv',
+        'md5': '07e15fa469ba384c7693fd246905547c',
+        'info_dict': {
+            "title": "Zeichentrick 1",
+            "age_limit": 18,
         }
     }
 
@@ -30,12 +32,12 @@ class YouJizzIE(InfoExtractor):
 
         # Get the video title
         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
-            webpage, u'title').strip()
+            webpage, 'title').strip()
 
         # Get the embed page
         result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
         if result is None:
-            raise ExtractorError(u'ERROR: unable to extract embed page')
+            raise ExtractorError('ERROR: unable to extract embed page')
 
         embed_page_url = result.group(0).strip()
         video_id = result.group('videoid')
@@ -47,23 +49,23 @@ class YouJizzIE(InfoExtractor):
         if m_playlist is not None:
             playlist_url = m_playlist.group('playlist')
             playlist_page = self._download_webpage(playlist_url, video_id,
-                                                   u'Downloading playlist page')
+                                                   'Downloading playlist page')
             m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
             if len(m_levels) == 0:
-                raise ExtractorError(u'Unable to extract video url')
+                raise ExtractorError('Unable to extract video url')
             videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
             (_, video_url) = sorted(videos)[0]
             video_url = video_url.replace('%252F', '%2F')
         else:
             video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
-                                           webpage, u'video URL')
+                                           webpage, 'video URL')
 
-        info = {'id': video_id,
-                'url': video_url,
-                'title': video_title,
-                'ext': 'flv',
-                'format': 'flv',
-                'player_url': embed_page_url,
-                'age_limit': age_limit}
-
-        return [info]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'ext': 'flv',
+            'format': 'flv',
+            'player_url': embed_page_url,
+            'age_limit': age_limit,
+        }

youtube_dl/extractor/youtube.py

@@ -502,7 +502,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 return a % b
 
             m = re.match(
-                r'^(?P<func>[a-zA-Z]+)\((?P<args>[a-z0-9,]+)\)$', expr)
+                r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr)
             if m:
                 fname = m.group('func')
                 if fname not in functions:
@@ -1422,7 +1422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
 class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     IE_DESC = u'YouTube.com playlists'
-    _VALID_URL = r"""(?:
+    _VALID_URL = r"""(?x)(?:
                         (?:https?://)?
                         (?:\w+\.)?
                         youtube\.com/
@@ -1431,7 +1431,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                            \? (?:.*?&)*? (?:p|a|list)=
                         |  p/
                         )
-                        ((?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,})
+                        (
+                            (?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
+                            # Top tracks, they can also include dots 
+                            |(?:MC)[\w\.]*
+                        )
                         .*
                      |
                         ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
@@ -1441,11 +1445,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     _VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
     IE_NAME = u'youtube:playlist'
 
-    @classmethod
-    def suitable(cls, url):
-        """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
     def _real_initialize(self):
         self._login()
 
@@ -1469,7 +1468,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
 
     def _real_extract(self, url):
         # Extract playlist id
-        mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+        mobj = re.match(self._VALID_URL, url)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
         playlist_id = mobj.group(1) or mobj.group(2)

youtube_dl/utils.py

@@ -751,13 +751,14 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     https_request = http_request
     https_response = http_response
 
+
 def unified_strdate(date_str):
     """Return a string with the date in the format YYYYMMDD"""
     upload_date = None
     #Replace commas
     date_str = date_str.replace(',',' ')
     # %z (UTC offset) is only supported in python>=3.2
-    date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
+    date_str = re.sub(r' ?(\+|-)[0-9:]*$', '', date_str)
     format_expressions = [
         '%d %B %Y',
         '%B %d %Y',
@@ -771,11 +772,12 @@ def unified_strdate(date_str):
         '%Y-%m-%dT%H:%M:%S.%fZ',
         '%Y-%m-%dT%H:%M:%S.%f0Z',
         '%Y-%m-%dT%H:%M:%S',
+        '%Y-%m-%dT%H:%M',
     ]
     for expression in format_expressions:
         try:
             upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
-        except:
+        except ValueError:
             pass
     if upload_date is None:
         timetuple = email.utils.parsedate_tz(date_str)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.01.29'
+__version__ = '2014.02.08'