release 2015.07.07

Python 2.x does not work without it.

AUTHORS

@@ -124,3 +124,9 @@ Mohammad Teimori Pabandi
 Roman Le Négrate
 Matthias Küch
 Julian Richen
+Ping O.
+Mister Hat
+Peter Ding
+jackyzy823
+George Brighton
+Remita Amine

README.md

@@ -17,12 +17,12 @@ youtube-dl - download videos from youtube.com or other video platforms
 To install it right away for all UNIX users (Linux, OS X, etc.), type:
 
     sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
-    sudo chmod a+x /usr/local/bin/youtube-dl
+    sudo chmod a+rx /usr/local/bin/youtube-dl
 
 If you do not have curl, you can alternatively use a recent wget:
 
     sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
-    sudo chmod a+x /usr/local/bin/youtube-dl
+    sudo chmod a+rx /usr/local/bin/youtube-dl
 
 Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
 
@@ -52,8 +52,9 @@ which means you can modify it, redistribute it or use it however you like.
     -i, --ignore-errors              Continue on download errors, for example to skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the playlist or the command line) if an error occurs
     --dump-user-agent                Display the current browser identification
-    --list-extractors                List all supported extractors and the URLs they would handle
+    --list-extractors                List all supported extractors
     --extractor-descriptions         Output descriptions of all supported extractors
+    --force-generic-extractor        Force extraction to use the generic extractor
     --default-search PREFIX          Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
                                      Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
                                      default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
@@ -107,7 +108,7 @@ which means you can modify it, redistribute it or use it however you like.
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with expected filesize (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of ffmpeg (experimental)
-    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,wget
+    --external-downloader COMMAND    Use the specified external downloader. Currently supports aria2c,curl,httpie,wget
     --external-downloader-args ARGS  Give these arguments to the external downloader
 
 ## Filesystem Options:
@@ -168,7 +169,7 @@ which means you can modify it, redistribute it or use it however you like.
     --no-progress                    Do not print progress bar
     --console-title                  Display progress in console titlebar
     -v, --verbose                    Print various debugging information
-    --dump-pages                     Print downloaded pages to debug problems (very verbose)
+    --dump-pages                     Print downloaded pages encoded using base64 to debug problems (very verbose)
     --write-pages                    Write downloaded intermediary pages to files in the current directory to debug problems
     --print-traffic                  Display sent and read HTTP traffic
     -C, --call-home                  Contact the youtube-dl server for debugging
@@ -189,8 +190,8 @@ which means you can modify it, redistribute it or use it however you like.
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific one is requested
     -F, --list-formats               List all available formats
-    --youtube-skip-dash-manifest     Do not download the DASH manifest on YouTube videos
-    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
+    --youtube-skip-dash-manifest     Do not download the DASH manifests and related data on YouTube videos
+    --merge-output-format FORMAT     If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no
                                      merge is required
 
 ## Subtitle Options:
@@ -220,10 +221,10 @@ which means you can modify it, redistribute it or use it however you like.
     --embed-thumbnail                Embed thumbnail in the audio as cover art
     --add-metadata                   Write metadata to the video file
     --metadata-from-title FORMAT     Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
-                                     parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s -
+                                     parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
                                      %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
-    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
+    --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default;
                                      fix file if we can, warn otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the postprocessors (default)
     --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the postprocessors
@@ -379,7 +380,7 @@ In February 2015, the new YouTube player contained a character sequence in a str
 
 ### HTTP Error 429: Too Many Requests or 402: Payment Required
 
-These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--network-address` options](#network-options) to select another IP address.
+These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
 
 ### SyntaxError: Non-ASCII character ###
 

docs/supportedsites.md

@@ -10,12 +10,14 @@
  - **56.com**
  - **5min**
  - **8tracks**
+ - **91porn**
  - **9gag**
  - **abc.net.au**
  - **Abc7News**
  - **AcademicEarth:Course**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVVideo**
  - **AdultSwim**
  - **Aftenposten**
  - **Aftonbladet**
@@ -26,8 +28,7 @@
  - **anitube.se**
  - **AnySex**
  - **Aparat**
- - **AppleDailyAnimationNews**
- - **AppleDailyRealtimeNews**
+ - **AppleDaily**
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -110,6 +111,7 @@
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
+ - **DailymotionCloud**
  - **daum.net**
  - **DBTV**
  - **DctpTv**
@@ -120,6 +122,8 @@
  - **divxstage**: DivxStage
  - **Dotsub**
  - **DouyuTV**
+ - **dramafever**
+ - **dramafever:series**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
@@ -142,6 +146,7 @@
  - **Eporner**
  - **EroProfile**
  - **Escapist**
+ - **ESPN** (Currently broken)
  - **EveryonesMixtape**
  - **exfm**: ex.fm
  - **ExpoTV**
@@ -151,8 +156,8 @@
  - **fc2**
  - **fernsehkritik.tv**
  - **fernsehkritik.tv:postecke**
- - **Firedrive**
  - **Firstpost**
+ - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
@@ -217,6 +222,7 @@
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
  - **IPrima**
+ - **iqiyi**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **Izlesene**
@@ -229,6 +235,7 @@
  - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
+ - **KarriereVideos**
  - **keek**
  - **KeezMovies**
  - **KhanAcademy**
@@ -276,6 +283,7 @@
  - **Motherless**
  - **Motorsport**: motorsport.com
  - **MovieClips**
+ - **MovieFap**
  - **Moviezine**
  - **movshare**: MovShare
  - **MPORA**
@@ -291,6 +299,7 @@
  - **MySpass**
  - **myvideo**
  - **MyVidster**
+ - **N-JOY**
  - **n-tv.de**
  - **NationalGeographic**
  - **Naver**
@@ -318,8 +327,10 @@
  - **Noco**
  - **Normalboots**
  - **NosVideo**
+ - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
  - **novamov**: NovaMov
  - **Nowness**
+ - **NowTV**
  - **nowvideo**: NowVideo
  - **npo.nl**
  - **npo.nl:live**
@@ -336,7 +347,9 @@
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnionStudios**
  - **Ooyala**
+ - **OoyalaExternal**
  - **OpenFilm**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
@@ -348,6 +361,7 @@
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
+ - **Pinkbike**
  - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
@@ -368,9 +382,11 @@
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
  - **Pyvideo**
- - **QQMusic**
- - **QQMusicAlbum**
- - **QQMusicSinger**
+ - **qqmusic**
+ - **qqmusic:album**
+ - **qqmusic:playlist**
+ - **qqmusic:singer**
+ - **qqmusic:toplist**
  - **QuickVid**
  - **R7**
  - **radio.de**
@@ -389,7 +405,6 @@
  - **Rte**
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **RTL2**
- - **RTLnow**
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
@@ -402,6 +417,7 @@
  - **rutube:movie**: Rutube movies
  - **rutube:person**: Rutube person videos
  - **RUTV**: RUTV.RU
+ - **Ruutu**
  - **safari**: safaribooksonline.com online video
  - **safari:course**: safaribooksonline.com online courses
  - **Sandia**: Sandia National Laboratories
@@ -426,9 +442,12 @@
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
+ - **SnagFilms**
+ - **SnagFilmsEmbed**
  - **Snotr**
- - **Sockshare**
  - **Sohu**
+ - **soompi**
+ - **soompi:show**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:set**
@@ -439,6 +458,7 @@
  - **southpark.cc.com:español**
  - **southpark.de**
  - **southpark.nl**
+ - **southparkstudios.dk**
  - **Space**
  - **SpankBang**
  - **Spankwire**
@@ -448,6 +468,7 @@
  - **Spike**
  - **Sport5**
  - **SportBox**
+ - **SportBoxEmbed**
  - **SportDeutschland**
  - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
@@ -485,6 +506,7 @@
  - **TheOnion**
  - **ThePlatform**
  - **TheSixtyOne**
+ - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
  - **THVideoPlaylist**
@@ -492,6 +514,7 @@
  - **tlc.com**
  - **tlc.de**
  - **TMZ**
+ - **TMZArticle**
  - **TNAFlix**
  - **tou.tv**
  - **Toypics**: Toypics user profile
@@ -500,13 +523,18 @@
  - **Trilulilu**
  - **TruTube**
  - **Tube8**
+ - **TubiTv**
  - **Tudou**
  - **Tumblr**
  - **TuneIn**
  - **Turbo**
  - **Tutv**
  - **tv.dfb.de**
+ - **TV2**
+ - **TV2Article**
  - **TV4**: tv4.se and tv4play.se
+ - **TVC**
+ - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
  - **tvp.pl:Series**
@@ -519,6 +547,7 @@
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
+ - **TwitterCard**
  - **Ubu**
  - **udemy**
  - **udemy:course**
@@ -555,6 +584,7 @@
  - **vier:videos**
  - **Viewster**
  - **viki**
+ - **viki:channel**
  - **vimeo**
  - **vimeo:album**
  - **vimeo:channel**
@@ -569,6 +599,7 @@
  - **vk.com**
  - **vk.com:user-videos**: vk.com:All of a user's videos
  - **Vodlocker**
+ - **VoiceRepublic**
  - **Vporn**
  - **VRT**
  - **vube**: Vube.com
@@ -591,6 +622,7 @@
  - **XBef**
  - **XboxClips**
  - **XHamster**
+ - **XHamsterEmbed**
  - **XMinus**
  - **XNXX**
  - **Xstream**
@@ -607,7 +639,7 @@
  - **YesJapan**
  - **Ynet**
  - **YouJizz**
- - **Youku**
+ - **youku**
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com

test/test_YoutubeDL.py

@@ -12,6 +12,7 @@ import copy
 
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_str
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
 from youtube_dl.utils import match_filter_func
@@ -507,6 +508,51 @@ class TestYoutubeDL(unittest.TestCase):
         res = get_videos(f)
         self.assertEqual(res, ['1'])
 
+    def test_playlist_items_selection(self):
+        entries = [{
+            'id': compat_str(i),
+            'title': compat_str(i),
+            'url': TEST_URL,
+        } for i in range(1, 5)]
+        playlist = {
+            '_type': 'playlist',
+            'id': 'test',
+            'entries': entries,
+            'extractor': 'test:playlist',
+            'extractor_key': 'test:playlist',
+            'webpage_url': 'http://example.com',
+        }
+
+        def get_ids(params):
+            ydl = YDL(params)
+            # make a copy because the dictionary can be modified
+            ydl.process_ie_result(playlist.copy())
+            return [int(v['id']) for v in ydl.downloaded_info_dicts]
+
+        result = get_ids({})
+        self.assertEqual(result, [1, 2, 3, 4])
+
+        result = get_ids({'playlistend': 10})
+        self.assertEqual(result, [1, 2, 3, 4])
+
+        result = get_ids({'playlistend': 2})
+        self.assertEqual(result, [1, 2])
+
+        result = get_ids({'playliststart': 10})
+        self.assertEqual(result, [])
+
+        result = get_ids({'playliststart': 2})
+        self.assertEqual(result, [2, 3, 4])
+
+        result = get_ids({'playlist_items': '2-4'})
+        self.assertEqual(result, [2, 3, 4])
+
+        result = get_ids({'playlist_items': '2,4'})
+        self.assertEqual(result, [2, 4])
+
+        result = get_ids({'playlist_items': '10'})
+        self.assertEqual(result, [])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -39,7 +39,7 @@ class TestAES(unittest.TestCase):
         encrypted = base64.b64encode(
             intlist_to_bytes(self.iv[:8]) +
             b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
-        )
+        ).decode('utf-8')
         decrypted = (aes_decrypt_text(encrypted, password, 16))
         self.assertEqual(decrypted, self.secret_msg)
 
@@ -47,7 +47,7 @@ class TestAES(unittest.TestCase):
         encrypted = base64.b64encode(
             intlist_to_bytes(self.iv[:8]) +
             b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
-        )
+        ).decode('utf-8')
         decrypted = (aes_decrypt_text(encrypted, password, 32))
         self.assertEqual(decrypted, self.secret_msg)
 

test/test_subtitles.py

@@ -266,7 +266,7 @@ class TestNRKSubtitles(BaseTestSubtitles):
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
         self.assertEqual(set(subtitles.keys()), set(['no']))
-        self.assertEqual(md5(subtitles['no']), '1d221e6458c95c5494dcd38e6a1f129a')
+        self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
 
 
 class TestRaiSubtitles(BaseTestSubtitles):

test/test_utils.py

@@ -600,7 +600,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
                 <div xml:lang="en">
                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
                     <p begin="1" end="2">第二行<br/>♪♪</p>
-                    <p begin="2" end="3"><span>Third<br/>Line</span></p>
+                    <p begin="2" dur="1"><span>Third<br/>Line</span></p>
                 </div>
             </body>
             </tt>'''
@@ -621,6 +621,21 @@ Line
 '''
         self.assertEqual(dfxp2srt(dfxp_data), srt_data)
 
+        dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
+            <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+            <body>
+                <div xml:lang="en">
+                    <p begin="0" end="1">The first line</p>
+                </div>
+            </body>
+            </tt>'''
+        srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The first line
+
+'''
+        self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
+
 
 if __name__ == '__main__':
     unittest.main()

tox.ini

@@ -4,6 +4,8 @@ envlist = py26,py27,py33,py34
 deps =
    nose
    coverage
+# We need a valid $HOME for test_compat_expanduser
+passenv = HOME
 defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
     --exclude test_subtitles.py --exclude test_write_annotations.py
     --exclude test_youtube_lists.py

youtube_dl/YoutubeDL.py

@@ -49,6 +49,7 @@ from .utils import (
     ExtractorError,
     format_bytes,
     formatSeconds,
+    HEADRequest,
     locked_file,
     make_HTTPS_handler,
     MaxDownloadsReached,
@@ -118,7 +119,7 @@ class YoutubeDL(object):
 
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
-    videopassword:     Password for acces a video.
+    videopassword:     Password for accessing a video.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
@@ -138,6 +139,7 @@ class YoutubeDL(object):
     outtmpl:           Template for output names.
     restrictfilenames: Do not allow "&" and spaces in file names
     ignoreerrors:      Do not stop on download errors.
+    force_generic_extractor: Force downloader to use the generic extractor
     nooverwrites:      Prevent overwriting files.
     playliststart:     Playlist item to start at.
     playlistend:       Playlist item to end at.
@@ -260,7 +262,6 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
-    exec_cmd:          Arbitrary command to run after downloading
     """
 
     params = None
@@ -626,13 +627,16 @@ class YoutubeDL(object):
             info_dict.setdefault(key, value)
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
-                     process=True):
+                     process=True, force_generic_extractor=False):
         '''
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
         '''
 
+        if not ie_key and force_generic_extractor:
+            ie_key = 'Generic'
+
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
         else:
@@ -760,7 +764,9 @@ class YoutubeDL(object):
             if isinstance(ie_entries, list):
                 n_all_entries = len(ie_entries)
                 if playlistitems:
-                    entries = [ie_entries[i - 1] for i in playlistitems]
+                    entries = [
+                        ie_entries[i - 1] for i in playlistitems
+                        if -n_all_entries <= i - 1 < n_all_entries]
                 else:
                     entries = ie_entries[playliststart:playlistend]
                 n_entries = len(entries)
@@ -922,8 +928,9 @@ class YoutubeDL(object):
                 if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
             if audiovideo_formats:
                 return audiovideo_formats[format_idx]
-            # for audio only urls, select the best/worst audio format
-            elif all(f.get('acodec') != 'none' for f in available_formats):
+            # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format
+            elif (all(f.get('acodec') != 'none' for f in available_formats) or
+                  all(f.get('vcodec') != 'none' for f in available_formats)):
                 return available_formats[format_idx]
         elif format_spec == 'bestaudio':
             audio_formats = [
@@ -1001,7 +1008,7 @@ class YoutubeDL(object):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
-                if 'width' in t and 'height' in t:
+                if t.get('width') and t.get('height'):
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i
@@ -1013,13 +1020,13 @@ class YoutubeDL(object):
             info_dict['display_id'] = info_dict['id']
 
         if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
-            # Working around negative timestamps in Windows
-            # (see http://bugs.python.org/issue1646728)
-            if info_dict['timestamp'] < 0 and os.name == 'nt':
-                info_dict['timestamp'] = 0
-            upload_date = datetime.datetime.utcfromtimestamp(
-                info_dict['timestamp'])
-            info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+            # Working around out-of-range timestamp values (e.g. negative ones on Windows,
+            # see http://bugs.python.org/issue1646728)
+            try:
+                upload_date = datetime.datetime.utcfromtimestamp(info_dict['timestamp'])
+                info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+            except (ValueError, OverflowError, OSError):
+                pass
 
         if self.params.get('listsubtitles', False):
             if 'automatic_captions' in info_dict:
@@ -1030,12 +1037,6 @@ class YoutubeDL(object):
             info_dict['id'], info_dict.get('subtitles'),
             info_dict.get('automatic_captions'))
 
-        # This extractors handle format selection themselves
-        if info_dict['extractor'] in ['Youku']:
-            if download:
-                self.process_info(info_dict)
-            return info_dict
-
         # We now pick which formats have to be downloaded
         if info_dict.get('formats') is None:
             # There's only one format available
@@ -1046,6 +1047,8 @@ class YoutubeDL(object):
         if not formats:
             raise ExtractorError('No video formats found!')
 
+        formats_dict = {}
+
         # We check that all the formats have the format and format_id fields
         for i, format in enumerate(formats):
             if 'url' not in format:
@@ -1053,6 +1056,18 @@ class YoutubeDL(object):
 
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
+            format_id = format['format_id']
+            if format_id not in formats_dict:
+                formats_dict[format_id] = []
+            formats_dict[format_id].append(format)
+
+        # Make sure all formats have unique format_id
+        for format_id, ambiguous_formats in formats_dict.items():
+            if len(ambiguous_formats) > 1:
+                for i, format in enumerate(ambiguous_formats):
+                    format['format_id'] = '%s-%d' % (format_id, i)
+
+        for i, format in enumerate(formats):
             if format.get('format') is None:
                 format['format'] = '{id} - {res}{note}'.format(
                     id=format['format_id'],
@@ -1086,10 +1101,11 @@ class YoutubeDL(object):
         req_format = self.params.get('format')
         if req_format is None:
             req_format_list = []
-            if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-'
-                    and info_dict['extractor'] in ['youtube', 'ted']
-                    and FFmpegMergerPP(self).available):
-                req_format_list.append('bestvideo+bestaudio')
+            if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
+                    info_dict['extractor'] in ['youtube', 'ted']):
+                merger = FFmpegMergerPP(self)
+                if merger.available and merger.can_merge():
+                    req_format_list.append('bestvideo+bestaudio')
             req_format_list.append('best')
             req_format = '/'.join(req_format_list)
         formats_to_download = []
@@ -1366,7 +1382,7 @@ class YoutubeDL(object):
                         postprocessors = []
                         self.report_warning('You have requested multiple '
                                             'formats but ffmpeg or avconv are not installed.'
-                                            ' The formats won\'t be merged')
+                                            ' The formats won\'t be merged.')
                     else:
                         postprocessors = [merger]
 
@@ -1393,8 +1409,8 @@ class YoutubeDL(object):
                     requested_formats = info_dict['requested_formats']
                     if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
                         info_dict['ext'] = 'mkv'
-                        self.report_warning('You have requested formats incompatible for merge. '
-                                            'The formats will be merged into mkv')
+                        self.report_warning(
+                            'Requested formats are incompatible for merge and will be merged into mkv.')
                     # Ensure filename always has a correct extension for successful merge
                     filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
                     if os.path.exists(encodeFilename(filename)):
@@ -1481,7 +1497,8 @@ class YoutubeDL(object):
         for url in url_list:
             try:
                 # It also downloads the videos
-                res = self.extract_info(url)
+                res = self.extract_info(
+                    url, force_generic_extractor=self.params.get('force_generic_extractor', False))
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
@@ -1525,6 +1542,7 @@ class YoutubeDL(object):
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
+            files_to_delete = []
             try:
                 files_to_delete, info = pp.run(info)
             except PostProcessingError as e:
@@ -1703,7 +1721,8 @@ class YoutubeDL(object):
             if req_is_string:
                 req = url_escaped
             else:
-                req = compat_urllib_request.Request(
+                req_type = HEADRequest if req.get_method() == 'HEAD' else compat_urllib_request.Request
+                req = req_type(
                     url_escaped, data=req.data, headers=req.headers,
                     origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
 
@@ -1849,7 +1868,7 @@ class YoutubeDL(object):
             thumb_ext = determine_ext(t['url'], 'jpg')
             suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
             thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
-            thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+            t['filename'] = thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
 
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
                 self.to_screen('[%s] %s: Thumbnail %sis already present' %

youtube_dl/__init__.py

@@ -240,13 +240,18 @@ def _real_main(argv=None):
     if opts.xattrs:
         postprocessors.append({'key': 'XAttrMetadata'})
     if opts.embedthumbnail:
-        postprocessors.append({'key': 'EmbedThumbnail'})
+        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+        postprocessors.append({
+            'key': 'EmbedThumbnail',
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',
-            'verboseOutput': opts.verbose,
             'exec_cmd': opts.exec_cmd,
         })
     if opts.xattr_set_filesize:
@@ -288,6 +293,7 @@ def _real_main(argv=None):
         'autonumber_size': opts.autonumber_size,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
+        'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts_retries,
@@ -345,7 +351,6 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
-        'exec_cmd': opts.exec_cmd,
         'extract_flat': opts.extract_flat,
         'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,

youtube_dl/aes.py

@@ -152,7 +152,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
     """
     NONCE_LENGTH_BYTES = 8
 
-    data = bytes_to_intlist(base64.b64decode(data))
+    data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
     password = bytes_to_intlist(password.encode('utf-8'))
 
     key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))

youtube_dl/downloader/external.py

@@ -109,6 +109,14 @@ class Aria2cFD(ExternalFD):
         cmd += ['--', info_dict['url']]
         return cmd
 
+
+class HttpieFD(ExternalFD):
+    def _make_cmd(self, tmpfilename, info_dict):
+        cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
+        for key, val in info_dict['http_headers'].items():
+            cmd += ['%s:%s' % (key, val)]
+        return cmd
+
 _BY_NAME = dict(
     (klass.get_basename(), klass)
     for name, klass in globals().items()
@@ -123,5 +131,6 @@ def list_external_downloaders():
 def get_external_downloader(external_downloader):
     """ Given the name of the executable, see whether we support the given
         downloader . """
-    bn = os.path.basename(external_downloader)
+    # Drop .exe extension on Windows
+    bn = os.path.splitext(os.path.basename(external_downloader))[0]
     return _BY_NAME[bn]

youtube_dl/extractor/__init__.py

@@ -4,7 +4,10 @@ from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
-from .adobetv import AdobeTVIE
+from .adobetv import (
+    AdobeTVIE,
+    AdobeTVVideoIE,
+)
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
@@ -103,6 +106,7 @@ from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
+    DailymotionCloudIE,
 )
 from .daum import DaumIE
 from .dbtv import DBTVIE
@@ -112,6 +116,10 @@ from .dfb import DFBIE
 from .dhm import DHMIE
 from .dotsub import DotsubIE
 from .douyutv import DouyuTVIE
+from .dramafever import (
+    DramaFeverIE,
+    DramaFeverSeriesIE,
+)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -136,11 +144,11 @@ from .ellentv import (
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
+from .espn import ESPNIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
@@ -148,10 +156,10 @@ from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
 from .fc2 import FC2IE
-from .firedrive import FiredriveIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
+from .fivetv import FiveTVIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
@@ -229,6 +237,7 @@ from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
+from .iqiyi import IqiyiIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -243,6 +252,7 @@ from .kaltura import KalturaIE
 from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
+from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
@@ -324,7 +334,10 @@ from .nbc import (
     NBCSportsIE,
     NBCSportsVPlayerIE,
 )
-from .ndr import NDRIE
+from .ndr import (
+    NDRIE,
+    NJoyIE,
+)
 from .ndtv import NDTVIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
@@ -334,8 +347,7 @@ from .newstube import NewstubeIE
 from .nextmedia import (
     NextMediaIE,
     NextMediaActionNewsIE,
-    AppleDailyRealtimeNewsIE,
-    AppleDailyAnimationNewsIE
+    AppleDailyIE,
 )
 from .nfb import NFBIE
 from .nfl import NFLIE
@@ -349,8 +361,10 @@ from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
+from .nova import NovaIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
+from .nowtv import NowTVIE
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
@@ -373,7 +387,11 @@ from .nytimes import (
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
-from .ooyala import OoyalaIE
+from .onionstudios import OnionStudiosIE
+from .ooyala import (
+    OoyalaIE,
+    OoyalaExternalIE,
+)
 from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,
@@ -387,6 +405,7 @@ from .pbs import PBSIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pinkbike import PinkbikeIE
 from .planetaplay import PlanetaPlayIE
 from .pladform import PladformIE
 from .played import PlayedIE
@@ -394,6 +413,7 @@ from .playfm import PlayFMIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
 from .podomatic import PodomaticIE
+from .porn91 import Porn91IE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
@@ -411,6 +431,8 @@ from .qqmusic import (
     QQMusicIE,
     QQMusicSingerIE,
     QQMusicAlbumIE,
+    QQMusicToplistIE,
+    QQMusicPlaylistIE,
 )
 from .quickvid import QuickVidIE
 from .r7 import R7IE
@@ -430,7 +452,6 @@ from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
 from .rte import RteIE
 from .rtlnl import RtlNlIE
-from .rtlnow import RTLnowIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
@@ -444,6 +465,7 @@ from .rutube import (
     RutubePersonIE,
 )
 from .rutv import RUTVIE
+from .ruutu import RuutuIE
 from .sandia import SandiaIE
 from .safari import (
     SafariIE,
@@ -471,9 +493,16 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snagfilms import (
+    SnagFilmsIE,
+    SnagFilmsEmbedIE,
+)
 from .snotr import SnotrIE
-from .sockshare import SockshareIE
 from .sohu import SohuIE
+from .soompi import (
+    SoompiIE,
+    SoompiShowIE,
+)
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
@@ -486,8 +515,9 @@ from .soundgasm import (
 )
 from .southpark import (
     SouthParkIE,
-    SouthParkEsIE,
     SouthParkDeIE,
+    SouthParkDkIE,
+    SouthParkEsIE,
     SouthParkNlIE
 )
 from .space import SpaceIE
@@ -497,7 +527,10 @@ from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .sport5 import Sport5IE
-from .sportbox import SportBoxIE
+from .sportbox import (
+    SportBoxIE,
+    SportBoxEmbedIE,
+)
 from .sportdeutschland import SportDeutschlandIE
 from .srf import SrfIE
 from .srmediathek import SRMediathekIE
@@ -537,11 +570,19 @@ from .tf1 import TF1IE
 from .theonion import TheOnionIE
 from .theplatform import ThePlatformIE
 from .thesixtyone import TheSixtyOneIE
+from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
-from .tmz import TMZIE
-from .tnaflix import TNAFlixIE
+from .tmz import (
+    TMZIE,
+    TMZArticleIE,
+)
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -552,12 +593,21 @@ from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
 from .tube8 import Tube8IE
+from .tubitv import TubiTvIE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
+from .tv2 import (
+    TV2IE,
+    TV2ArticleIE,
+)
 from .tv4 import TV4IE
+from .tvc import (
+    TVCIE,
+    TVCArticleIE,
+)
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
@@ -576,6 +626,7 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
+from .twitter import TwitterCardIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -628,12 +679,16 @@ from .vine import (
     VineIE,
     VineUserIE,
 )
-from .viki import VikiIE
+from .viki import (
+    VikiIE,
+    VikiChannelIE,
+)
 from .vk import (
     VKIE,
     VKUserVideosIE,
 )
 from .vodlocker import VodlockerIE
+from .voicerepublic import VoiceRepublicIE
 from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
@@ -657,7 +712,10 @@ from .wrzuta import WrzutaIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
-from .xhamster import XHamsterIE
+from .xhamster import (
+    XHamsterIE,
+    XHamsterEmbedIE,
+)
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xstream import XstreamIE

youtube_dl/extractor/adobetv.py

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

youtube_dl/extractor/aftonbladet.py

@@ -6,11 +6,11 @@ from ..utils import int_or_none
 
 
 class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'http://tv\.aftonbladet\.se/webbtv.+?(?P<id>article[0-9]+)\.ab(?:$|[?#])'
+    _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
+        'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
         'info_dict': {
-            'id': 'article36015',
+            'id': '36015',
             'ext': 'mp4',
             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
             'description': 'Jupiters måne mest aktiv av alla himlakroppar',
@@ -25,8 +25,9 @@ class AftonbladetIE(InfoExtractor):
 
         # find internal video meta data
         meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
-        internal_meta_id = self._html_search_regex(
-            r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
+        player_config = self._parse_json(self._html_search_regex(
+            r'data-player-config="([^"]+)"', webpage, 'player config'), video_id)
+        internal_meta_id = player_config['videoId']
         internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')

youtube_dl/extractor/arte.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
     unified_strdate,
-    get_element_by_id,
     get_element_by_attribute,
     int_or_none,
     qualities,
@@ -195,7 +194,9 @@ class ArteTVFutureIE(ArteTVPlus7IE):
     def _real_extract(self, url):
         anchor_id, lang = self._extract_url_info(url)
         webpage = self._download_webpage(url, anchor_id)
-        row = get_element_by_id(anchor_id, webpage)
+        row = self._search_regex(
+            r'(?s)id="%s"[^>]*>.+?(<div[^>]*arte_vp_url[^>]*>)' % anchor_id,
+            webpage, 'row')
         return self._extract_from_webpage(row, anchor_id, lang)
 
 

youtube_dl/extractor/bbccouk.py

@@ -129,6 +129,20 @@ class BBCCoUkIE(InfoExtractor):
                 'skip_download': True,
             },
             'skip': 'geolocation',
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
+            'info_dict': {
+                'id': 'b05zmgw1',
+                'ext': 'flv',
+                'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.',
+                'title': 'Royal Academy Summer Exhibition',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
@@ -237,26 +251,11 @@ class BBCCoUkIE(InfoExtractor):
         for connection in self._extract_connections(media):
             captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
-            ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
-            srt = ''
-
-            def _extract_text(p):
-                if p.text is not None:
-                    stripped_text = p.text.strip()
-                    if stripped_text:
-                        return stripped_text
-                return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span'))
-            for pos, p in enumerate(ps):
-                srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p))
             subtitles[lang] = [
                 {
                     'url': connection.get('href'),
                     'ext': 'ttml',
                 },
-                {
-                    'data': srt,
-                    'ext': 'srt',
-                },
             ]
         return subtitles
 
@@ -267,7 +266,7 @@ class BBCCoUkIE(InfoExtractor):
                 programme_id, 'Downloading media selection XML')
         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
-                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
+                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
             else:
                 raise
 
@@ -362,7 +361,7 @@ class BBCCoUkIE(InfoExtractor):
             formats, subtitles = self._download_media_selector(programme_id)
             title = self._og_search_title(webpage)
             description = self._search_regex(
-                r'<p class="medium-description">([^<]+)</p>',
+                r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
                 webpage, 'description', fatal=False)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)

youtube_dl/extractor/bilibili.py

@@ -3,6 +3,8 @@ from __future__ import unicode_literals
 
 import re
 import itertools
+import json
+import xml.etree.ElementTree as ET
 
 from .common import InfoExtractor
 from ..utils import (
@@ -67,11 +69,19 @@ class BiliBiliIE(InfoExtractor):
 
         entries = []
 
-        lq_doc = self._download_xml(
+        lq_page = self._download_webpage(
             'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
             video_id,
             note='Downloading LQ video info'
         )
+        try:
+            err_info = json.loads(lq_page)
+            raise ExtractorError(
+                'BiliBili said: ' + err_info['error_text'], expected=True)
+        except ValueError:
+            pass
+
+        lq_doc = ET.fromstring(lq_page)
         lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(
@@ -80,9 +90,11 @@ class BiliBiliIE(InfoExtractor):
             note='Downloading HQ video info',
             fatal=False,
         )
-        hq_durls = hq_doc.findall('./durl') if hq_doc is not False else itertools.repeat(None)
-
-        assert len(lq_durls) == len(hq_durls)
+        if hq_doc is not False:
+            hq_durls = hq_doc.findall('./durl')
+            assert len(lq_durls) == len(hq_durls)
+        else:
+            hq_durls = itertools.repeat(None)
 
         i = 1
         for lq_durl, hq_durl in zip(lq_durls, hq_durls):
@@ -93,7 +105,7 @@ class BiliBiliIE(InfoExtractor):
                 'filesize': int_or_none(
                     lq_durl.find('./size'), get_attr='text'),
             }]
-            if hq_durl:
+            if hq_durl is not None:
                 formats.append({
                     'format_id': 'hq',
                     'quality': 2,

youtube_dl/extractor/brightcove.py

@@ -13,6 +13,7 @@ from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 )
 from ..utils import (
     determine_ext,
@@ -119,7 +120,7 @@ class BrightcoveIE(InfoExtractor):
 
         try:
             object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
-        except xml.etree.ElementTree.ParseError:
+        except compat_xml_parse_error:
             return
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
@@ -156,6 +157,28 @@ class BrightcoveIE(InfoExtractor):
         linkBase = find_param('linkBaseURL')
         if linkBase is not None:
             params['linkBaseURL'] = linkBase
+        return cls._make_brightcove_url(params)
+
+    @classmethod
+    def _build_brighcove_url_from_js(cls, object_js):
+        # The layout of JS is as follows:
+        # customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) {
+        #   // build Brightcove <object /> XML
+        # }
+        m = re.search(
+            r'''(?x)customBC.\createVideo\(
+                .*?                                                  # skipping width and height
+                ["\'](?P<playerID>\d+)["\']\s*,\s*                   # playerID
+                ["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s*  # playerKey begins with AQ and is 50 characters
+                                                                     # in length, however it's appended to itself
+                                                                     # in places, so truncate
+                ["\'](?P<videoID>\d+)["\']                           # @videoPlayer
+            ''', object_js)
+        if m:
+            return cls._make_brightcove_url(m.groupdict())
+
+    @classmethod
+    def _make_brightcove_url(cls, params):
         data = compat_urllib_parse.urlencode(params)
         return cls._FEDERATED_URL_TEMPLATE % data
 
@@ -172,7 +195,7 @@ class BrightcoveIE(InfoExtractor):
         """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(
-            r'<meta\s+property="og:video"\s+content="(https?://(?:secure|c)\.brightcove.com/[^"]+)"',
+            r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
             webpage)
         if url_m:
             url = unescapeHTML(url_m.group(1))
@@ -188,7 +211,12 @@ class BrightcoveIE(InfoExtractor):
                 [^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
             ).+?>\s*</object>''',
             webpage)
-        return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+        if matches:
+            return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+
+        return list(filter(None, [
+            cls._build_brighcove_url_from_js(custom_bc)
+            for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})

youtube_dl/extractor/byutv.py

@@ -16,7 +16,7 @@ class BYUtvIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'md5:5438d33774b6bdc662f9485a340401cc',
             'title': 'Season 5 Episode 5',
-            'thumbnail': 're:^https?://.*promo.*'
+            'thumbnail': 're:^https?://.*\.jpg$'
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/canalplus.py

@@ -25,14 +25,14 @@ class CanalplusIE(InfoExtractor):
     }
 
     _TESTS = [{
-        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+        'md5': 'b3481d7ca972f61e37420798d0a9d934',
         'info_dict': {
-            'id': '922470',
+            'id': '1263092',
             'ext': 'flv',
-            'title': 'Zapping - 26/08/13',
-            'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
-            'upload_date': '20130826',
+            'title': 'Le Zapping - 13/05/15',
+            'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+            'upload_date': '20150513',
         },
     }, {
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
@@ -56,7 +56,7 @@ class CanalplusIE(InfoExtractor):
         'skip': 'videos get deleted after a while',
     }, {
         'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
-        'md5': '65aa83ad62fe107ce29e564bb8712580',
+        'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
         'info_dict': {
             'id': '1213714',
             'ext': 'flv',

youtube_dl/extractor/cbs.py

@@ -4,12 +4,13 @@ from .common import InfoExtractor
 
 
 class CBSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)/(?P<id>[^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '4JUVEwq3wUT7',
+            'display_id': 'connect-chat-feat-garth-brooks',
             'ext': 'flv',
             'title': 'Connect Chat feat. Garth Brooks',
             'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
@@ -24,6 +25,7 @@ class CBSIE(InfoExtractor):
         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
         'info_dict': {
             'id': 'WWF_5KqY3PK1',
+            'display_id': 'st-vincent',
             'ext': 'flv',
             'title': 'Live on Letterman - St. Vincent',
             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
@@ -34,12 +36,23 @@ class CBSIE(InfoExtractor):
             'skip_download': True,
         },
         '_skip': 'Blocked outside the US',
+    }, {
+        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
         real_id = self._search_regex(
-            r"video\.settings\.pid\s*=\s*'([^']+)';",
+            [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
             webpage, 'real video ID')
-        return self.url_result('theplatform:%s' % real_id)
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': 'theplatform:%s' % real_id,
+            'display_id': display_id,
+        }

youtube_dl/extractor/cbsnews.py

@@ -32,7 +32,7 @@ class CBSNewsIE(InfoExtractor):
                 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
                 'ext': 'flv',
                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
-                'thumbnail': 'http://cbsnews2.cbsistatic.com/hub/i/r/2014/04/04/0c9fbc66-576b-41ca-8069-02d122060dd2/thumbnail/140x90/6dad7a502f88875ceac38202984b6d58/en-0404-werner-replace-640x360.jpg',
+                'thumbnail': 're:^https?://.*\.jpg$',
                 'duration': 205,
             },
             'params': {

youtube_dl/extractor/ccc.py

@@ -16,7 +16,7 @@ class CCCIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video',
-        'md5': '205a365d0d57c0b1e43a12c9ffe8f9be',
+        'md5': '3a1eda8f3a29515d27f5adb967d7e740',
         'info_dict': {
             'id': '20131228183',
             'ext': 'mp4',
@@ -51,7 +51,7 @@ class CCCIE(InfoExtractor):
 
         matches = re.finditer(r'''(?xs)
             <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
-            <a\s+href='(?P<http_url>[^']+)'>\s*
+            <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
             (?:
                 .*?
                 <a\s+href='(?P<torrent_url>[^']+\.torrent)'

youtube_dl/extractor/chilloutzone.py

@@ -57,7 +57,7 @@ class ChilloutzoneIE(InfoExtractor):
 
         base64_video_info = self._html_search_regex(
             r'var cozVidData = "(.+?)";', webpage, 'video data')
-        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8')
         video_info_dict = json.loads(decoded_video_info)
 
         # get video information from dict

youtube_dl/extractor/cinemassacre.py

@@ -60,6 +60,17 @@ class CinemassacreIE(InfoExtractor):
                 'uploader_id': 'Cinemassacre',
                 'title': 'AVGN: McKids',
             }
+        },
+        {
+            'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/',
+            'md5': '1376908e49572389e7b06251a53cdd08',
+            'info_dict': {
+                'id': 'Cinemassacre-555779690c440',
+                'ext': 'mp4',
+                'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!',
+                'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays',
+                'upload_date': '20150525',
+            }
         }
     ]
 
@@ -72,7 +83,7 @@ class CinemassacreIE(InfoExtractor):
 
         playerdata_url = self._search_regex(
             [
-                r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+                r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
                 r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
             ],
             webpage, 'player data URL', default=None)

youtube_dl/extractor/cnet.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 class CNETIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
         'info_dict': {
             'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
@@ -25,7 +25,20 @@ class CNETIE(InfoExtractor):
         'params': {
             'skip_download': 'requires rtmpdump',
         }
-    }
+    }, {
+        'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
+        'info_dict': {
+            'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
+            'ext': 'flv',
+            'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
+            'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
+            'uploader': 'Ashley Esqueda',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -42,7 +55,7 @@ class CNETIE(InfoExtractor):
             raise ExtractorError('Cannot find video data')
 
         mpx_account = data['config']['players']['default']['mpx_account']
-        vid = vdata['files']['rtmp']
+        vid = vdata['files'].get('rtmp', vdata['files']['hds'])
         tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
 
         video_id = vdata['id']

youtube_dl/extractor/cnn.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class CNNIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))'''
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',

youtube_dl/extractor/common.py

@@ -22,6 +22,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    NO_DEFAULT,
     age_restricted,
     bug_reports_message,
     clean_html,
@@ -33,7 +34,6 @@ from ..utils import (
     sanitize_filename,
     unescapeHTML,
 )
-_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
@@ -523,7 +523,7 @@ class InfoExtractor(object):
             video_info['description'] = playlist_description
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -549,7 +549,7 @@ class InfoExtractor(object):
                 return next(g for g in mobj.groups() if g is not None)
             else:
                 return mobj.group(group)
-        elif default is not _NO_DEFAULT:
+        elif default is not NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
@@ -557,7 +557,7 @@ class InfoExtractor(object):
             self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
@@ -786,8 +786,8 @@ class InfoExtractor(object):
             return True
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
-                self.report_warning(
-                    '%s URL is invalid, skipping' % item, video_id)
+                self.to_screen(
+                    '%s: %s URL is invalid, skipping' % (video_id, item))
                 return False
             raise
 
@@ -846,7 +846,8 @@ class InfoExtractor(object):
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None,
-                              m3u8_id=None):
+                              m3u8_id=None, note=None, errnote=None,
+                              fatal=True):
 
         formats = [{
             'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
@@ -865,8 +866,11 @@ class InfoExtractor(object):
 
         m3u8_doc = self._download_webpage(
             m3u8_url, video_id,
-            note='Downloading m3u8 information',
-            errnote='Failed to download m3u8 information')
+            note=note or 'Downloading m3u8 information',
+            errnote=errnote or 'Failed to download m3u8 information',
+            fatal=fatal)
+        if m3u8_doc is False:
+            return m3u8_doc
         last_info = None
         last_media = None
         kv_rex = re.compile(
@@ -1072,9 +1076,6 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
-    def _subtitles_timecode(self, seconds):
-        return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
-
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/crunchyroll.py

@@ -27,7 +27,7 @@ from ..aes import (
 
 
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _NETRC_MACHINE = 'crunchyroll'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
@@ -45,6 +45,22 @@ class CrunchyrollIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
+        'info_dict': {
+            'id': '589804',
+            'ext': 'flv',
+            'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
+            'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Danny Choo Network',
+            'upload_date': '20120213',
+        },
+        'params': {
+            # rtmp
+            'skip_download': True,
+        },
+
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -76,8 +92,8 @@ class CrunchyrollIE(InfoExtractor):
         self._login()
 
     def _decrypt_subtitles(self, data, iv, id):
-        data = bytes_to_intlist(data)
-        iv = bytes_to_intlist(iv)
+        data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
+        iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
         id = int(id)
 
         def obfuscate_key_aux(count, modulo, start):
@@ -179,6 +195,16 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         return output
 
+    def _extract_subtitles(self, subtitle):
+        sub_root = xml.etree.ElementTree.fromstring(subtitle)
+        return [{
+            'ext': 'srt',
+            'data': self._convert_subtitles_to_srt(sub_root),
+        }, {
+            'ext': 'ass',
+            'data': self._convert_subtitles_to_ass(sub_root),
+        }]
+
     def _get_subtitles(self, video_id, webpage):
         subtitles = {}
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
@@ -190,25 +216,11 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             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('utf-8')
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
-            sub_root = xml.etree.ElementTree.fromstring(subtitle)
-            subtitles[lang_code] = [
-                {
-                    'ext': 'srt',
-                    'data': self._convert_subtitles_to_srt(sub_root),
-                },
-                {
-                    'ext': 'ass',
-                    'data': self._convert_subtitles_to_ass(sub_root),
-                },
-            ]
+            subtitles[lang_code] = self._extract_subtitles(subtitle)
         return subtitles
 
     def _real_extract(self, url):
@@ -255,16 +267,17 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
-            streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
-            # urlencode doesn't work!
-            streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
+            streamdata_req = compat_urllib_request.Request(
+                'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
+                % (stream_id, stream_format, stream_quality),
+                compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
             streamdata = self._download_xml(
                 streamdata_req, video_id,
                 note='Downloading media info for %s' % video_format)
-            video_url = streamdata.find('./host').text
-            video_play_path = streamdata.find('./file').text
+            stream_info = streamdata.find('./{default}preload/stream_info')
+            video_url = stream_info.find('./host').text
+            video_play_path = stream_info.find('./file').text
             formats.append({
                 'url': video_url,
                 'play_path': video_play_path,

youtube_dl/extractor/dailymotion.py

@@ -52,6 +52,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'ext': 'mp4',
                 'uploader': 'IGN',
                 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
+                'upload_date': '20150306',
             }
         },
         # Vevo video
@@ -106,9 +107,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         age_limit = self._rta_search(webpage)
 
         video_upload_date = None
-        mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+        mobj = re.search(r'<meta property="video:release_date" content="([0-9]{4})-([0-9]{2})-([0-9]{2}).+?"/>', webpage)
         if mobj is not None:
-            video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
 
         embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id
         embed_request = self._build_request(embed_url)
@@ -224,7 +225,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:(?:old/)?user/)?(?P<user>[^/]+)$'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',
@@ -238,7 +239,8 @@ class DailymotionUserIE(DailymotionPlaylistIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
-        webpage = self._download_webpage(url, user)
+        webpage = self._download_webpage(
+            'https://www.dailymotion.com/user/%s' % user, user)
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
             webpage, 'user'))
@@ -249,3 +251,53 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': full_user,
             'entries': self._extract_entries(user),
         }
+
+
+class DailymotionCloudIE(DailymotionBaseInfoExtractor):
+    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
+    _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
+
+    _TESTS = [{
+        # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
+        # Tested at FranceTvInfo_2
+        'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
+        'only_matching': True,
+    }, {
+        # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
+        'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_dmcloud_url(self, webpage):
+        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+        if mobj:
+            return mobj.group(1)
+
+        mobj = re.search(
+            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+            webpage)
+        if mobj:
+            return mobj.group(1)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        request = self._build_request(url)
+        webpage = self._download_webpage(request, video_id)
+
+        title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
+
+        video_info = self._parse_json(self._search_regex(
+            r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
+
+        # TODO: parse ios_url, which is in fact a manifest
+        video_url = video_info['mp4_url']
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': video_info.get('thumbnail_url'),
+        }

youtube_dl/extractor/discovery.py

@@ -2,19 +2,19 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    parse_duration,
     parse_iso8601,
-    int_or_none,
 )
+from ..compat import compat_str
 
 
 class DiscoveryIE(InfoExtractor):
     _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
-        'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
         'info_dict': {
-            'id': 'mission-impossible-outtakes',
-            'ext': 'flv',
+            'id': '20769',
+            'ext': 'mp4',
             'title': 'Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                             ' each other -- to the point of confusing Jamie\'s dog -- and '
@@ -24,22 +24,36 @@ class DiscoveryIE(InfoExtractor):
             'timestamp': 1303099200,
             'upload_date': '20110418',
         },
-    }
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        }
+    }, {
+        'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons',
+        'info_dict': {
+            'id': 'mythbusters-the-simpsons',
+            'title': 'MythBusters: The Simpsons',
+        },
+        'playlist_count': 9,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        info = self._download_json(url + '?flat=1', video_id)
 
-        info = self._parse_json(self._search_regex(
-            r'(?s)<script type="application/ld\+json">(.*?)</script>',
-            webpage, 'video info'), video_id)
+        video_title = info.get('playlist_title') or info.get('video_title')
 
-        return {
-            'id': video_id,
-            'title': info['name'],
-            'url': info['contentURL'],
-            'description': info.get('description'),
-            'thumbnail': info.get('thumbnailUrl'),
-            'timestamp': parse_iso8601(info.get('uploadDate')),
-            'duration': int_or_none(info.get('duration')),
-        }
+        entries = [{
+            'id': compat_str(video_info['id']),
+            'formats': self._extract_m3u8_formats(
+                video_info['src'], video_id, ext='mp4',
+                note='Download m3u8 information for video %d' % (idx + 1)),
+            'title': video_info['title'],
+            'description': video_info.get('description'),
+            'duration': parse_duration(video_info.get('video_length')),
+            'webpage_url': video_info.get('href'),
+            'thumbnail': video_info.get('thumbnailURL'),
+            'alt_title': video_info.get('secondary_title'),
+            'timestamp': parse_iso8601(video_info.get('publishedDate')),
+        } for idx, video_info in enumerate(info['playlist'])]
+
+        return self.playlist_result(entries, video_id, video_title)

youtube_dl/extractor/dramafever.py

@@ -0,0 +1,197 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_HTTPError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class DramaFeverBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
+    _NETRC_MACHINE = 'dramafever'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'username': username,
+            'password': password,
+        }
+
+        request = compat_urllib_request.Request(
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        response = self._download_webpage(
+            request, None, 'Logging in as %s' % username)
+
+        if all(logout_pattern not in response
+               for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
+            error = self._html_search_regex(
+                r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
+                response, 'error message', default=None)
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+
+class DramaFeverIE(DramaFeverBaseIE):
+    IE_NAME = 'dramafever'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
+    _TEST = {
+        'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
+        'info_dict': {
+            'id': '4512.1',
+            'ext': 'flv',
+            'title': 'Cooking with Shin 4512.1',
+            'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'timestamp': 1404336058,
+            'upload_date': '20140702',
+            'duration': 343,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url).replace('/', '.')
+
+        try:
+            feed = self._download_json(
+                'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
+                video_id, 'Downloading episode JSON')['channel']['item']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                raise ExtractorError(
+                    'Currently unavailable in your country.', expected=True)
+            raise
+
+        media_group = feed.get('media-group', {})
+
+        formats = []
+        for media_content in media_group['media-content']:
+            src = media_content.get('@attributes', {}).get('url')
+            if not src:
+                continue
+            ext = determine_ext(src)
+            if ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    src, video_id, f4m_id='hds'))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        title = media_group.get('media-title')
+        description = media_group.get('media-description')
+        duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
+        thumbnail = self._proto_relative_url(
+            media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
+        timestamp = parse_iso8601(feed.get('pubDate'), ' ')
+
+        subtitles = {}
+        for media_subtitle in media_group.get('media-subTitle', []):
+            lang = media_subtitle.get('@attributes', {}).get('lang')
+            href = media_subtitle.get('@attributes', {}).get('href')
+            if not lang or not href:
+                continue
+            subtitles[lang] = [{
+                'ext': 'ttml',
+                'url': href,
+            }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class DramaFeverSeriesIE(DramaFeverBaseIE):
+    IE_NAME = 'dramafever:series'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
+    _TESTS = [{
+        'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
+        'info_dict': {
+            'id': '4512',
+            'title': 'Cooking with Shin',
+            'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
+        },
+        'playlist_count': 4,
+    }, {
+        'url': 'http://www.dramafever.com/drama/124/IRIS/',
+        'info_dict': {
+            'id': '124',
+            'title': 'IRIS',
+            'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
+        },
+        'playlist_count': 20,
+    }]
+
+    _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
+    _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
+
+    def _get_consumer_secret(self, video_id):
+        mainjs = self._download_webpage(
+            'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
+            video_id, 'Downloading main.js', fatal=False)
+        if not mainjs:
+            return self._CONSUMER_SECRET
+        return self._search_regex(
+            r"var\s+cs\s*=\s*'([^']+)'", mainjs,
+            'consumer secret', default=self._CONSUMER_SECRET)
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+
+        consumer_secret = self._get_consumer_secret(series_id)
+
+        series = self._download_json(
+            'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
+            % (consumer_secret, series_id),
+            series_id, 'Downloading series JSON')['series'][series_id]
+
+        title = clean_html(series['name'])
+        description = clean_html(series.get('description') or series.get('description_short'))
+
+        entries = []
+        for page_num in itertools.count(1):
+            episodes = self._download_json(
+                'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
+                % (consumer_secret, series_id, self._PAGE_SIZE, page_num),
+                series_id, 'Downloading episodes JSON page #%d' % page_num)
+            for episode in episodes.get('value', []):
+                episode_url = episode.get('episode_url')
+                if not episode_url:
+                    continue
+                entries.append(self.url_result(
+                    compat_urlparse.urljoin(url, episode_url),
+                    'DramaFever', episode.get('guid')))
+            if page_num == episodes['num_pages']:
+                break
+
+        return self.playlist_result(entries, series_id, title, description)

youtube_dl/extractor/drbonanza.py

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

youtube_dl/extractor/drtuber.py

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

youtube_dl/extractor/drtv.py

@@ -1,8 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor, ExtractorError
-from ..utils import parse_iso8601
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_iso8601,
+)
 
 
 class DRTVIE(InfoExtractor):
@@ -60,19 +63,31 @@ class DRTVIE(InfoExtractor):
                 restricted_to_denmark = asset['RestrictedToDenmark']
                 spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
                 for link in asset['Links']:
-                    target = link['Target']
                     uri = link['Uri']
+                    target = link['Target']
                     format_id = target
-                    preference = -1 if target == 'HDS' else -2
+                    preference = None
                     if spoken_subtitles:
-                        preference -= 2
+                        preference = -1
                         format_id += '-spoken-subtitles'
-                    formats.append({
-                        'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
-                        'format_id': format_id,
-                        'ext': link['FileFormat'],
-                        'preference': preference,
-                    })
+                    if target == 'HDS':
+                        formats.extend(self._extract_f4m_formats(
+                            uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
+                            video_id, preference, f4m_id=format_id))
+                    elif target == 'HLS':
+                        formats.extend(self._extract_m3u8_formats(
+                            uri, video_id, 'mp4', preference=preference,
+                            m3u8_id=format_id))
+                    else:
+                        bitrate = link.get('Bitrate')
+                        if bitrate:
+                            format_id += '-%s' % bitrate
+                        formats.append({
+                            'url': uri,
+                            'format_id': format_id,
+                            'tbr': bitrate,
+                            'ext': link.get('FileFormat'),
+                        })
                 subtitles_list = asset.get('SubtitlesList')
                 if isinstance(subtitles_list, list):
                     LANGS = {

youtube_dl/extractor/dumpert.py

@@ -26,7 +26,7 @@ class DumpertIE(InfoExtractor):
         video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
-        req.add_header('Cookie', 'nsfw=1')
+        req.add_header('Cookie', 'nsfw=1; cpc=10')
         webpage = self._download_webpage(req, video_id)
 
         files_base64 = self._search_regex(

youtube_dl/extractor/empflix.py

@@ -1,25 +0,0 @@
-from __future__ import unicode_literals
-
-from .tnaflix import TNAFlixIE
-
-
-class EMPFlixIE(TNAFlixIE):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html'
-
-    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
-    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TEST = {
-        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
-        'info_dict': {
-            'id': '33051',
-            'display_id': 'Amateur-Finger-Fuck',
-            'ext': 'mp4',
-            'title': 'Amateur Finger Fuck',
-            'description': 'Amateur solo finger fucking.',
-            'thumbnail': 're:https?://.*\.jpg$',
-            'age_limit': 18,
-        }
-    }

youtube_dl/extractor/espn.py

@@ -0,0 +1,55 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ESPNIE(InfoExtractor):
+    _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _WORKING = False
+    _TESTS = [{
+        'url': 'http://espn.go.com/video/clip?id=10365079',
+        'info_dict': {
+            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
+            'ext': 'mp4',
+            'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
+            'description': '',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/nba/recap?gameId=400793786',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/blog/golden-state-warriors/post/_/id/593/how-warriors-rapidly-regained-a-winning-edge',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/sports/endurance/story/_/id/12893522/dzhokhar-tsarnaev-sentenced-role-boston-marathon-bombings',
+        'only_matching': True,
+    }, {
+        'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            r'class="video-play-button"[^>]+data-id="(\d+)',
+            webpage, 'video id')
+
+        player = self._download_webpage(
+            'https://espn.go.com/video/iframe/twitter/?id=%s' % video_id, video_id)
+
+        pcode = self._search_regex(
+            r'["\']pcode=([^"\']+)["\']', player, 'pcode')
+
+        return self.url_result(
+            'ooyalaexternal:espn:%s:%s' % (video_id, pcode),
+            'OoyalaExternal')

youtube_dl/extractor/facebook.py

@@ -50,7 +50,10 @@ class FacebookIE(InfoExtractor):
             'id': '274175099429670',
             'ext': 'mp4',
             'title': 'Facebook video #274175099429670',
-        }
+        },
+        'expected_warnings': [
+            'title'
+        ]
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -149,12 +152,12 @@ class FacebookIE(InfoExtractor):
             raise ExtractorError('Cannot find video formats')
 
         video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
-            fatal=False)
+            r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
+            default=None)
         if not video_title:
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
-                webpage, 'alternative title', default=None)
+                webpage, 'alternative title', fatal=False)
             video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id

youtube_dl/extractor/faz.py

@@ -6,9 +6,9 @@ from .common import InfoExtractor
 
 class FazIE(InfoExtractor):
     IE_NAME = 'faz.net'
-    _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
         'info_dict': {
             'id': '12610585',
@@ -16,7 +16,22 @@ class FazIE(InfoExtractor):
             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
-    }
+    }, {
+        'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.faz.net/foobarblafasel-13659345.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/firedrive.py

@@ -1,80 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
-from ..utils import (
-    ExtractorError,
-)
-
-
-class FiredriveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \
-                 '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)'
-    _FILE_DELETED_REGEX = r'<div class="removed_file_image">'
-
-    _TESTS = [{
-        'url': 'https://www.firedrive.com/file/FEB892FA160EBD01',
-        'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970',
-        'info_dict': {
-            'id': 'FEB892FA160EBD01',
-            'ext': 'flv',
-            'title': 'bbb_theora_486kbit.flv',
-            'thumbnail': 're:^http://.*\.jpg$',
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        url = 'http://firedrive.com/file/%s' % video_id
-        webpage = self._download_webpage(url, video_id)
-
-        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id,
-                                 expected=True)
-
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            value="([^"]*)"
-            ''', webpage))
-
-        post = compat_urllib_parse.urlencode(fields)
-        req = compat_urllib_request.Request(url, post)
-        req.add_header('Content-type', 'application/x-www-form-urlencoded')
-
-        # Apparently, this header is required for confirmation to work.
-        req.add_header('Host', 'www.firedrive.com')
-
-        webpage = self._download_webpage(req, video_id,
-                                         'Downloading video page')
-
-        title = self._search_regex(r'class="external_title_left">(.+)</div>',
-                                   webpage, 'title')
-        thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage,
-                                       'thumbnail', fatal=False)
-        if thumbnail is not None:
-            thumbnail = 'http:' + thumbnail
-
-        ext = self._search_regex(r'type:\s?\'([^\']+)\',',
-                                 webpage, 'extension', fatal=False)
-        video_url = self._search_regex(
-            r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url')
-
-        formats = [{
-            'format_id': 'sd',
-            'url': video_url,
-            'ext': ext,
-        }]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }

youtube_dl/extractor/fivetv.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class FiveTVIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    http://
+                        (?:www\.)?5-tv\.ru/
+                        (?:
+                            (?:[^/]+/)+(?P<id>\d+)|
+                            (?P<path>[^/?#]+)(?:[/?#])?
+                        )
+                    '''
+
+    _TESTS = [{
+        'url': 'http://5-tv.ru/news/96814/',
+        'md5': 'bbff554ad415ecf5416a2f48c22d9283',
+        'info_dict': {
+            'id': '96814',
+            'ext': 'mp4',
+            'title': 'Россияне выбрали имя для общенациональной платежной системы',
+            'description': 'md5:a8aa13e2b7ad36789e9f77a74b6de660',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 180,
+        },
+    }, {
+        'url': 'http://5-tv.ru/video/1021729/',
+        'info_dict': {
+            'id': '1021729',
+            'ext': 'mp4',
+            'title': '3D принтер',
+            'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 180,
+        },
+    }, {
+        'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
+        'info_dict': {
+            'id': 'glavnoe',
+            'ext': 'mp4',
+            'title': 'Итоги недели с 8 по 14 июня 2015 года',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',
+        'only_matching': True,
+    }, {
+        'url': 'http://5-tv.ru/films/1507502/',
+        'only_matching': True,
+    }, {
+        'url': 'http://5-tv.ru/programs/broadcast/508713/',
+        'only_matching': True,
+    }, {
+        'url': 'http://5-tv.ru/angel/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.5-tv.ru/schedule/?iframe=true&width=900&height=450',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id') or mobj.group('path')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"',
+            webpage, 'video url')
+
+        title = self._og_search_title(webpage, default=None) or self._search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        duration = int_or_none(self._og_search_property(
+            'video:duration', webpage, 'duration', default=None))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'duration': duration,
+        }

youtube_dl/extractor/francetv.py

@@ -18,6 +18,7 @@ from ..utils import (
     parse_duration,
     determine_ext,
 )
+from .dailymotion import DailymotionCloudIE
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -60,7 +61,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                     continue
                 video_url_parsed = compat_urllib_parse_urlparse(video_url)
                 f4m_url = self._download_webpage(
-                    'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
+                    'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url_parsed.path,
                     video_id, 'Downloading f4m manifest token', fatal=False)
                 if f4m_url:
                     formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
@@ -131,12 +132,26 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
             'skip_download': 'HLS (reqires ffmpeg)'
         },
         'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
+    }, {
+        'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
+        'md5': 'f485bda6e185e7d15dbc69b72bae993e',
+        'info_dict': {
+            'id': '556e03339473995ee145930c',
+            'ext': 'mp4',
+            'title': 'Les entreprises familiales : le secret de la réussite',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
+        }
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
+
+        dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+        if dmcloud_url:
+            return self.url_result(dmcloud_url, 'DailymotionCloud')
+
         video_id, catalogue = self._search_regex(
             r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
         return self._extract_video(video_id, catalogue)

youtube_dl/extractor/gamespot.py

@@ -14,8 +14,8 @@ from ..utils import (
 
 
 class GameSpotIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
-    _TEST = {
+    _VALID_URL = r'http://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
+    _TESTS = [{
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
         'info_dict': {
@@ -23,8 +23,16 @@ class GameSpotIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Arma 3 - Community Guide: SITREP I',
             'description': 'Check out this video where some of the basics of Arma 3 is explained.',
-        }
-    }
+        },
+    }, {
+        'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
+        'info_dict': {
+            'id': 'gs-2300-6424837',
+            'ext': 'flv',
+            'title': 'The Witcher 3: Wild Hunt [Xbox ONE]  - Now Playing',
+            'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
+        },
+    }]
 
     def _real_extract(self, url):
         page_id = self._match_id(url)
@@ -32,25 +40,37 @@ class GameSpotIE(InfoExtractor):
         data_video_json = self._search_regex(
             r'data-video=["\'](.*?)["\']', webpage, 'data video')
         data_video = json.loads(unescapeHTML(data_video_json))
+        streams = data_video['videoStreams']
 
-        # Transform the manifest url to a link to the mp4 files
-        # they are used in mobile devices.
-        f4m_url = data_video['videoStreams']['f4m_stream']
-        f4m_path = compat_urlparse.urlparse(f4m_url).path
-        QUALITIES_RE = r'((,\d+)+,?)'
-        qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',')
-        http_path = f4m_path[1:].split('/', 1)[1]
-        http_template = re.sub(QUALITIES_RE, r'%s', http_path)
-        http_template = http_template.replace('.csmil/manifest.f4m', '')
-        http_template = compat_urlparse.urljoin(
-            'http://video.gamespotcdn.com/', http_template)
         formats = []
-        for q in qualities:
-            formats.append({
-                'url': http_template % q,
-                'ext': 'mp4',
-                'format_id': q,
-            })
+        f4m_url = streams.get('f4m_stream')
+        if f4m_url is not None:
+            # Transform the manifest url to a link to the mp4 files
+            # they are used in mobile devices.
+            f4m_path = compat_urlparse.urlparse(f4m_url).path
+            QUALITIES_RE = r'((,\d+)+,?)'
+            qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',')
+            http_path = f4m_path[1:].split('/', 1)[1]
+            http_template = re.sub(QUALITIES_RE, r'%s', http_path)
+            http_template = http_template.replace('.csmil/manifest.f4m', '')
+            http_template = compat_urlparse.urljoin(
+                'http://video.gamespotcdn.com/', http_template)
+            for q in qualities:
+                formats.append({
+                    'url': http_template % q,
+                    'ext': 'mp4',
+                    'format_id': q,
+                })
+        else:
+            for quality in ['sd', 'hd']:
+                # It's actually a link to a flv file
+                flv_url = streams.get('f4m_{0}'.format(quality))
+                if flv_url is not None:
+                    formats.append({
+                        'url': flv_url,
+                        'ext': 'flv',
+                        'format_id': quality,
+                    })
 
         return {
             'id': data_video['guid'],

youtube_dl/extractor/generic.py

@@ -9,6 +9,8 @@ from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..compat import (
     compat_urllib_parse,
+    compat_urllib_parse_unquote,
+    compat_urllib_request,
     compat_urlparse,
     compat_xml_parse_error,
 )
@@ -32,12 +34,20 @@ from .brightcove import BrightcoveIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
+from .tvc import TVCIE
+from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
 from .svt import SVTIE
+from .pornhub import PornHubIE
+from .xhamster import XHamsterEmbedIE
+from .vimeo import VimeoIE
+from .dailymotion import DailymotionCloudIE
+from .onionstudios import OnionStudiosIE
+from .snagfilms import SnagFilmsEmbedIE
 
 
 class GenericIE(InfoExtractor):
@@ -45,6 +55,97 @@ class GenericIE(InfoExtractor):
     _VALID_URL = r'.*'
     IE_NAME = 'generic'
     _TESTS = [
+        # Direct link to a video
+        {
+            'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
+            'md5': '67d406c2bcb6af27fa886f31aa934bbe',
+            'info_dict': {
+                'id': 'trailer',
+                'ext': 'mp4',
+                'title': 'trailer',
+                'upload_date': '20100513',
+            }
+        },
+        # Direct link to media delivered compressed (until Accept-Encoding is *)
+        {
+            'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
+            'md5': '128c42e68b13950268b648275386fc74',
+            'info_dict': {
+                'id': 'FictionJunction-Parallel_Hearts',
+                'ext': 'flac',
+                'title': 'FictionJunction-Parallel_Hearts',
+                'upload_date': '20140522',
+            },
+            'expected_warnings': [
+                'URL could be a direct video link, returning it as such.'
+            ]
+        },
+        # Direct download with broken HEAD
+        {
+            'url': 'http://ai-radio.org:8000/radio.opus',
+            'info_dict': {
+                'id': 'radio',
+                'ext': 'opus',
+                'title': 'radio',
+            },
+            'params': {
+                'skip_download': True,  # infinite live stream
+            },
+            'expected_warnings': [
+                r'501.*Not Implemented'
+            ],
+        },
+        # Direct link with incorrect MIME type
+        {
+            'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+            'md5': '4ccbebe5f36706d85221f204d7eb5913',
+            'info_dict': {
+                'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+                'id': '5_Lennart_Poettering_-_Systemd',
+                'ext': 'webm',
+                'title': '5_Lennart_Poettering_-_Systemd',
+                'upload_date': '20141120',
+            },
+            'expected_warnings': [
+                'URL could be a direct video link, returning it as such.'
+            ]
+        },
+        # RSS feed
+        {
+            'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+            'info_dict': {
+                'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+                'title': 'Zero Punctuation',
+                'description': 're:.*groundbreaking video review series.*'
+            },
+            'playlist_mincount': 11,
+        },
+        # RSS feed with enclosure
+        {
+            'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
+            'info_dict': {
+                'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+                'ext': 'm4v',
+                'upload_date': '20150228',
+                'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+            }
+        },
+        # google redirect
+        {
+            'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
+            'info_dict': {
+                'id': 'cmQHVoWB5FY',
+                'ext': 'mp4',
+                'upload_date': '20130224',
+                'uploader_id': 'TheVerge',
+                'description': 're:^Chris Ziegler takes a look at the\.*',
+                'uploader': 'The Verge',
+                'title': 'First Firefox OS phones side-by-side',
+            },
+            'params': {
+                'skip_download': False,
+            }
+        },
         {
             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
@@ -124,17 +225,6 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,  # m3u8 download
             },
         },
-        # Direct link to a video
-        {
-            'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
-            'md5': '67d406c2bcb6af27fa886f31aa934bbe',
-            'info_dict': {
-                'id': 'trailer',
-                'ext': 'mp4',
-                'title': 'trailer',
-                'upload_date': '20100513',
-            }
-        },
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
@@ -159,22 +249,6 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Ooyala'],
         },
-        # google redirect
-        {
-            'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
-            'info_dict': {
-                'id': 'cmQHVoWB5FY',
-                'ext': 'mp4',
-                'upload_date': '20130224',
-                'uploader_id': 'TheVerge',
-                'description': 're:^Chris Ziegler takes a look at the\.*',
-                'uploader': 'The Verge',
-                'title': 'First Firefox OS phones side-by-side',
-            },
-            'params': {
-                'skip_download': False,
-            }
-        },
         # embed.ly video
         {
             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
@@ -224,6 +298,55 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # TVC embed
+        {
+            'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
+            'info_dict': {
+                'id': '55304',
+                'ext': 'mp4',
+                'title': 'Дошкольное воспитание',
+            },
+        },
+        # SportBox embed
+        {
+            'url': 'http://www.vestifinance.ru/articles/25753',
+            'info_dict': {
+                'id': '25753',
+                'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '370908',
+                    'title': 'Госзаказ. День 3',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370905',
+                    'title': 'Госзаказ. День 2',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370902',
+                    'title': 'Госзаказ. День 1',
+                    'ext': 'mp4',
+                }
+            }],
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        # XHamster embed
+        {
+            'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
+            'info_dict': {
+                'id': 'showthread',
+                'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
+            },
+            'playlist_mincount': 7,
+        },
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
@@ -375,16 +498,6 @@ class GenericIE(InfoExtractor):
                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
             }
         },
-        # RSS feed
-        {
-            'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
-            'info_dict': {
-                'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
-                'title': 'Zero Punctuation',
-                'description': 're:.*groundbreaking video review series.*'
-            },
-            'playlist_mincount': 11,
-        },
         # Multiple brightcove videos
         # https://github.com/rg3/youtube-dl/issues/2283
         {
@@ -438,21 +551,6 @@ class GenericIE(InfoExtractor):
                 'uploader': 'thoughtworks.wistia.com',
             },
         },
-        # Direct download with broken HEAD
-        {
-            'url': 'http://ai-radio.org:8000/radio.opus',
-            'info_dict': {
-                'id': 'radio',
-                'ext': 'opus',
-                'title': 'radio',
-            },
-            'params': {
-                'skip_download': True,  # infinite live stream
-            },
-            'expected_warnings': [
-                r'501.*Not Implemented'
-            ],
-        },
         # Soundcloud embed
         {
             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
@@ -484,21 +582,6 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 2,
         },
-        # Direct link with incorrect MIME type
-        {
-            'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
-            'md5': '4ccbebe5f36706d85221f204d7eb5913',
-            'info_dict': {
-                'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
-                'id': '5_Lennart_Poettering_-_Systemd',
-                'ext': 'webm',
-                'title': '5_Lennart_Poettering_-_Systemd',
-                'upload_date': '20141120',
-            },
-            'expected_warnings': [
-                'URL could be a direct video link, returning it as such.'
-            ]
-        },
         # Cinchcast embed
         {
             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
@@ -586,6 +669,18 @@ class GenericIE(InfoExtractor):
                 'title': 'John Carlson Postgame 2/25/15',
             },
         },
+        # Kaltura embed (different embed code)
+        {
+            'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
+            'info_dict': {
+                'id': '1_a52wc67y',
+                'ext': 'flv',
+                'upload_date': '20150127',
+                'uploader_id': 'PremierMedia',
+                'timestamp': int,
+                'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
+            },
+        },
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -657,16 +752,6 @@ class GenericIE(InfoExtractor):
                 'age_limit': 0,
             },
         },
-        # RSS feed with enclosure
-        {
-            'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
-            'info_dict': {
-                'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
-                'ext': 'm4v',
-                'upload_date': '20150228',
-                'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
-            }
-        },
         # Crooks and Liars embed
         {
             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
@@ -741,6 +826,62 @@ class GenericIE(InfoExtractor):
                 # rtmpe downloads
                 'skip_download': True,
             }
+        },
+        # Brightcove URL in single quotes
+        {
+            'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
+            'md5': '4ae374f1f8b91c889c4b9203c8c752af',
+            'info_dict': {
+                'id': '4255764656001',
+                'ext': 'mp4',
+                'title': 'SN Presents: Russell Martin, World Citizen',
+                'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
+                'uploader': 'Rogers Sportsnet',
+            },
+        },
+        # Dailymotion Cloud video
+        {
+            'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
+            'md5': '49444254273501a64675a7e68c502681',
+            'info_dict': {
+                'id': '5585de919473990de4bee11b',
+                'ext': 'mp4',
+                'title': 'Le débat',
+                'thumbnail': 're:^https?://.*\.jpe?g$',
+            }
+        },
+        # OnionStudios embed
+        {
+            'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
+            'info_dict': {
+                'id': '2855',
+                'ext': 'mp4',
+                'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+                'thumbnail': 're:^https?://.*\.jpe?g$',
+                'uploader': 'ClickHole',
+                'uploader_id': 'clickhole',
+            }
+        },
+        # SnagFilms embed
+        {
+            'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
+            'info_dict': {
+                'id': '74849a00-85a9-11e1-9660-123139220831',
+                'ext': 'mp4',
+                'title': '#whilewewatch',
+            }
+        },
+        # AdobeTVVideo embed
+        {
+            'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
+            'md5': '43662b577c018ad707a63766462b1e87',
+            'info_dict': {
+                'id': '2456',
+                'ext': 'mp4',
+                'title': 'New experience with Acrobat DC',
+                'description': 'New experience with Acrobat DC',
+                'duration': 248.667,
+            },
         }
     ]
 
@@ -862,7 +1003,7 @@ class GenericIE(InfoExtractor):
             force_videoid = smuggled_data['force_videoid']
             video_id = force_videoid
         else:
-            video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
+            video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
 
         self.to_screen('%s: Requesting header' % video_id)
 
@@ -884,7 +1025,9 @@ class GenericIE(InfoExtractor):
 
         full_response = None
         if head_response is False:
-            full_response = self._request_webpage(url, video_id)
+            request = compat_urllib_request.Request(url)
+            request.add_header('Accept-Encoding', '*')
+            full_response = self._request_webpage(request, video_id)
             head_response = full_response
 
         # Check for direct link to a video
@@ -895,7 +1038,7 @@ class GenericIE(InfoExtractor):
                 head_response.headers.get('Last-Modified'))
             return {
                 'id': video_id,
-                'title': os.path.splitext(url_basename(url))[0],
+                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
                 'direct': True,
                 'formats': [{
                     'format_id': m.group('format_id'),
@@ -906,10 +1049,22 @@ class GenericIE(InfoExtractor):
             }
 
         if not self._downloader.params.get('test', False) and not is_intentional:
-            self._downloader.report_warning('Falling back on generic information extractor.')
+            force = self._downloader.params.get('force_generic_extractor', False)
+            self._downloader.report_warning(
+                '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
 
         if not full_response:
-            full_response = self._request_webpage(url, video_id)
+            request = compat_urllib_request.Request(url)
+            # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
+            # making it impossible to download only chunk of the file (yet we need only 512kB to
+            # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
+            # that will always result in downloading the whole file that is not desirable.
+            # Therefore for extraction pass we have to override Accept-Encoding to any in order
+            # to accept raw bytes and being able to download only a chunk.
+            # It may probably better to solve this by checking Content-Type for application/octet-stream
+            # after HEAD request finishes, but not sure if we can rely on this.
+            request.add_header('Accept-Encoding', '*')
+            full_response = self._request_webpage(request, video_id)
 
         # Maybe it's a direct link to a video?
         # Be careful not to download the whole thing!
@@ -921,7 +1076,7 @@ class GenericIE(InfoExtractor):
                 head_response.headers.get('Last-Modified'))
             return {
                 'id': video_id,
-                'title': os.path.splitext(url_basename(url))[0],
+                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
                 'direct': True,
                 'url': url,
                 'upload_date': upload_date,
@@ -1001,23 +1156,14 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded rtl.nl player
         matches = re.findall(
-            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+            r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
             webpage)
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 
-        # Look for embedded (iframe) Vimeo player
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
-        if mobj:
-            player_url = unescapeHTML(mobj.group('url'))
-            surl = smuggle_url(player_url, {'Referer': url})
-            return self.url_result(surl)
-        # Look for embedded (swf embed) Vimeo player
-        mobj = re.search(
-            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
-        if mobj:
-            return self.url_result(mobj.group(1))
+        vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+        if vimeo_url is not None:
+            return self.url_result(vimeo_url)
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
@@ -1229,6 +1375,32 @@ class GenericIE(InfoExtractor):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
+        # Look for embedded TVC player
+        tvc_url = TVCIE._extract_url(webpage)
+        if tvc_url:
+            return self.url_result(tvc_url, 'TVC')
+
+        # Look for embedded SportBox player
+        sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+        if sportbox_urls:
+            return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
+
+        # Look for embedded PornHub player
+        pornhub_url = PornHubIE._extract_url(webpage)
+        if pornhub_url:
+            return self.url_result(pornhub_url, 'PornHub')
+
+        # Look for embedded XHamster player
+        xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
+        if xhamster_urls:
+            return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
+
+        # Look for embedded Tvigle player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Tvigle')
+
         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
@@ -1332,8 +1504,8 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds
-        mobj = re.search(
-            r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+        mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
+                re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
         if mobj is not None:
             return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
 
@@ -1388,7 +1560,31 @@ class GenericIE(InfoExtractor):
         # Look for Senate ISVP iframe
         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
         if senate_isvp_url:
-            return self.url_result(surl, 'SenateISVP')
+            return self.url_result(senate_isvp_url, 'SenateISVP')
+
+        # Look for Dailymotion Cloud videos
+        dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+        if dmcloud_url:
+            return self.url_result(dmcloud_url, 'DailymotionCloud')
+
+        # Look for OnionStudios embeds
+        onionstudios_url = OnionStudiosIE._extract_url(webpage)
+        if onionstudios_url:
+            return self.url_result(onionstudios_url)
+
+        # Look for SnagFilms embeds
+        snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
+        if snagfilms_url:
+            return self.url_result(snagfilms_url)
+
+        # Look for AdobeTVVideo embeds
+        mobj = re.search(
+            r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
+            webpage)
+        if mobj is not None:
+            return self.url_result(
+                self._proto_relative_url(unescapeHTML(mobj.group(1))),
+                'AdobeTVVideo')
 
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):

youtube_dl/extractor/gfycat.py

@@ -6,12 +6,13 @@ from ..utils import (
     int_or_none,
     float_or_none,
     qualities,
+    ExtractorError,
 )
 
 
 class GfycatIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?P<id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/)?(?P<id>[^/?#]+)'
+    _TESTS = [{
         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
         'info_dict': {
             'id': 'DeadlyDecisiveGermanpinscher',
@@ -27,14 +28,33 @@ class GfycatIE(InfoExtractor):
             'categories': list,
             'age_limit': 0,
         }
-    }
+    }, {
+        'url': 'http://gfycat.com/ifr/JauntyTimelyAmazontreeboa',
+        'info_dict': {
+            'id': 'JauntyTimelyAmazontreeboa',
+            'ext': 'mp4',
+            'title': 'JauntyTimelyAmazontreeboa',
+            'timestamp': 1411720126,
+            'upload_date': '20140926',
+            'uploader': 'anonymous',
+            'duration': 3.52,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'categories': list,
+            'age_limit': 0,
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         gfy = self._download_json(
             'http://gfycat.com/cajax/get/%s' % video_id,
-            video_id, 'Downloading video info')['gfyItem']
+            video_id, 'Downloading video info')
+        if 'error' in gfy:
+            raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
+        gfy = gfy['gfyItem']
 
         title = gfy.get('title') or gfy['gfyName']
         description = gfy.get('description')

youtube_dl/extractor/hentaistigma.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -19,20 +17,19 @@ class HentaiStigmaIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
-            r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
+            r'<h2[^>]+class="posttitle"[^>]*><a[^>]*>([^<]+)</a>',
             webpage, 'title')
         wrap_url = self._html_search_regex(
-            r'<iframe src="([^"]+mp4)"', webpage, 'wrapper url')
+            r'<iframe[^>]+src="([^"]+mp4)"', webpage, 'wrapper url')
         wrap_webpage = self._download_webpage(wrap_url, video_id)
 
         video_url = self._html_search_regex(
-            r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url')
+            r'file\s*:\s*"([^"]+)"', wrap_webpage, 'video url')
 
         return {
             'id': video_id,

youtube_dl/extractor/howcast.py

@@ -1,8 +1,7 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import parse_iso8601
 
 
 class HowcastIE(InfoExtractor):
@@ -13,29 +12,31 @@ class HowcastIE(InfoExtractor):
         'info_dict': {
             'id': '390161',
             'ext': 'mp4',
-            'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.',
             'title': 'How to Tie a Square Knot Properly',
-        }
+            'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
+            'timestamp': 1276081287,
+            'upload_date': '20100609',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
 
-        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
-
-        video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
-                                       webpage, 'video URL')
-
-        video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
-                                                    webpage, 'description', fatal=False)
+        embed_code = self._search_regex(
+            r'<iframe[^>]+src="[^"]+\bembed_code=([^\b]+)\b',
+            webpage, 'ooyala embed code')
 
         return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % embed_code,
             'id': video_id,
-            'url': video_url,
-            'title': self._og_search_title(webpage),
-            'description': video_description,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'timestamp': parse_iso8601(self._html_search_meta(
+                'article:published_time', webpage, 'timestamp')),
         }

youtube_dl/extractor/imdb.py

@@ -46,7 +46,7 @@ class ImdbIE(InfoExtractor):
             format_info = info['videoPlayerObject']['video']
             formats.append({
                 'format_id': f_id,
-                'url': format_info['url'],
+                'url': format_info['videoInfoList'][0]['videoUrl'],
             })
 
         return {

youtube_dl/extractor/imgur.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     int_or_none,
     js_to_json,
@@ -12,7 +13,7 @@ from ..utils import (
 
 
 class ImgurIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)(?:\.mp4|\.gifv)?'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)'
 
     _TESTS = [{
         'url': 'https://i.imgur.com/A61SaA1.gifv',
@@ -34,7 +35,8 @@ class ImgurIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            compat_urlparse.urljoin(url, video_id), video_id)
 
         width = int_or_none(self._search_regex(
             r'<param name="width" value="([0-9]+)"',

youtube_dl/extractor/ina.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class InaIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
     _TEST = {
         'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
         'md5': 'a667021bf2b41f8dc6049479d9bb38a3',

youtube_dl/extractor/infoq.py

@@ -5,13 +5,14 @@ import base64
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urlparse,
 )
 
 
 class InfoQIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
         'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
         'info_dict': {
@@ -20,7 +21,10 @@ class InfoQIE(InfoExtractor):
             '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',
         },
-    }
+    }, {
+        'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -42,7 +46,7 @@ class InfoQIE(InfoExtractor):
         video_id, extension = video_filename.split('.')
 
         http_base = self._search_regex(
-            r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
+            r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage,
             'HTTP base URL')
 
         formats = [{
@@ -52,7 +56,7 @@ class InfoQIE(InfoExtractor):
             'play_path': playpath,
         }, {
             'format_id': 'http',
-            'url': http_base + real_id,
+            'url': compat_urlparse.urljoin(url, http_base) + real_id,
         }]
         self._sort_formats(formats)
 

youtube_dl/extractor/instagram.py

@@ -3,13 +3,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    limit_length,
+)
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
+    _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
     _TEST = {
-        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
         'info_dict': {
             'id': 'aye83DjauH',
@@ -41,11 +44,11 @@ class InstagramIE(InfoExtractor):
 
 
 class InstagramUserIE(InfoExtractor):
-    _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+    _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
     _TEST = {
-        'url': 'http://instagram.com/porsche',
+        'url': 'https://instagram.com/porsche',
         'info_dict': {
             'id': 'porsche',
             'title': 'porsche',
@@ -100,11 +103,13 @@ class InstagramUserIE(InfoExtractor):
                 thumbnails_el = it.get('images', {})
                 thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
 
-                title = it.get('caption', {}).get('text', it['id'])
+                # In some cases caption is null, which corresponds to None
+                # in python. As a result, it.get('caption', {}) gives None
+                title = (it.get('caption') or {}).get('text', it['id'])
 
                 entries.append({
                     'id': it['id'],
-                    'title': title,
+                    'title': limit_length(title, 80),
                     'formats': formats,
                     'thumbnail': thumbnail,
                     'webpage_url': it.get('link'),

youtube_dl/extractor/iprima.py

@@ -11,11 +11,12 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    remove_end,
 )
 
 
 class IPrimaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
 
     _TESTS = [{
         'url': 'http://play.iprima.cz/particka/particka-92',
@@ -23,7 +24,7 @@ class IPrimaIE(InfoExtractor):
             'id': '39152',
             'ext': 'flv',
             'title': 'Partička (92)',
-            'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+            'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
         },
         'params': {
@@ -35,13 +36,14 @@ class IPrimaIE(InfoExtractor):
             'id': '9718337',
             'ext': 'flv',
             'title': 'Tchibo Partička - Jarní móda',
-            'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
             'thumbnail': 're:^http:.*\.jpg$',
         },
         'params': {
             'skip_download': True,  # requires rtmpdump
         },
-        'skip': 'Do not have permission to access this page',
+    }, {
+        'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -102,8 +104,10 @@ class IPrimaIE(InfoExtractor):
 
         return {
             'id': real_id,
-            'title': self._og_search_title(webpage),
+            'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
-            'description': self._og_search_description(webpage),
+            'description': self._search_regex(
+                r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
+                webpage, 'description', default=None),
         }

youtube_dl/extractor/iqiyi.py

@@ -0,0 +1,296 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import math
+import os.path
+import random
+import re
+import time
+import uuid
+import zlib
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse
+from ..utils import (
+    ExtractorError,
+    url_basename,
+)
+
+
+class IqiyiIE(InfoExtractor):
+    IE_NAME = 'iqiyi'
+
+    _VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html'
+
+    _TESTS = [{
+        'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
+        'md5': '2cb594dc2781e6c941a110d8f358118b',
+        'info_dict': {
+            'id': '9c1fb1b99d192b21c559e5a1a2cb3c73',
+            'title': '美国德州空中惊现奇异云团 酷似UFO',
+            'ext': 'f4v',
+        }
+    }, {
+        'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
+        'info_dict': {
+            'id': 'e3f585b550a280af23c98b6cb2be19fb',
+            'title': '名侦探柯南第752集',
+        },
+        'playlist': [{
+            'md5': '7e49376fecaffa115d951634917fe105',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part1',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': '41b75ba13bb7ac0e411131f92bc4f6ca',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part2',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': '0cee1dd0a3d46a83e71e2badeae2aab0',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part3',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': '4f8ad72373b0c491b582e7c196b0b1f9',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part4',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': 'd89ad028bcfad282918e8098e811711d',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part5',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': '9cb1e5c95da25dff0660c32ae50903b7',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part6',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': '155116e0ff1867bbc9b98df294faabc9',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part7',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }, {
+            'md5': '53f5db77622ae14fa493ed2a278a082b',
+            'info_dict': {
+                'id': 'e3f585b550a280af23c98b6cb2be19fb_part8',
+                'ext': 'f4v',
+                'title': '名侦探柯南第752集',
+            },
+        }],
+    }]
+
+    _FORMATS_MAP = [
+        ('1', 'h6'),
+        ('2', 'h5'),
+        ('3', 'h4'),
+        ('4', 'h3'),
+        ('5', 'h2'),
+        ('10', 'h1'),
+    ]
+
+    def construct_video_urls(self, data, video_id, _uuid):
+        def do_xor(x, y):
+            a = y % 3
+            if a == 1:
+                return x ^ 121
+            if a == 2:
+                return x ^ 72
+            return x ^ 103
+
+        def get_encode_code(l):
+            a = 0
+            b = l.split('-')
+            c = len(b)
+            s = ''
+            for i in range(c - 1, -1, -1):
+                a = do_xor(int(b[c - i - 1], 16), i)
+                s += chr(a)
+            return s[::-1]
+
+        def get_path_key(x, format_id, segment_index):
+            mg = ')(*&^flash@#$%a'
+            tm = self._download_json(
+                'http://data.video.qiyi.com/t?tn=' + str(random.random()), video_id,
+                note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
+            )['t']
+            t = str(int(math.floor(int(tm) / (600.0))))
+            return hashlib.md5((t + mg + x).encode('utf8')).hexdigest()
+
+        video_urls_dict = {}
+        for format_item in data['vp']['tkl'][0]['vs']:
+            if 0 < int(format_item['bid']) <= 10:
+                format_id = self.get_format(format_item['bid'])
+            else:
+                continue
+
+            video_urls = []
+
+            video_urls_info = format_item['fs']
+            if not format_item['fs'][0]['l'].startswith('/'):
+                t = get_encode_code(format_item['fs'][0]['l'])
+                if t.endswith('mp4'):
+                    video_urls_info = format_item['flvs']
+
+            for segment_index, segment in enumerate(video_urls_info):
+                vl = segment['l']
+                if not vl.startswith('/'):
+                    vl = get_encode_code(vl)
+                key = get_path_key(
+                    vl.split('/')[-1].split('.')[0], format_id, segment_index)
+                filesize = segment['b']
+                base_url = data['vp']['du'].split('/')
+                base_url.insert(-1, key)
+                base_url = '/'.join(base_url)
+                param = {
+                    'su': _uuid,
+                    'qyid': uuid.uuid4().hex,
+                    'client': '',
+                    'z': '',
+                    'bt': '',
+                    'ct': '',
+                    'tn': str(int(time.time()))
+                }
+                api_video_url = base_url + vl + '?' + \
+                    compat_urllib_parse.urlencode(param)
+                js = self._download_json(
+                    api_video_url, video_id,
+                    note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
+                video_url = js['l']
+                video_urls.append(
+                    (video_url, filesize))
+
+            video_urls_dict[format_id] = video_urls
+        return video_urls_dict
+
+    def get_format(self, bid):
+        matched_format_ids = [_format_id for _bid, _format_id in self._FORMATS_MAP if _bid == str(bid)]
+        return matched_format_ids[0] if len(matched_format_ids) else None
+
+    def get_bid(self, format_id):
+        matched_bids = [_bid for _bid, _format_id in self._FORMATS_MAP if _format_id == format_id]
+        return matched_bids[0] if len(matched_bids) else None
+
+    def get_raw_data(self, tvid, video_id, enc_key, _uuid):
+        tm = str(int(time.time()))
+        param = {
+            'key': 'fvip',
+            'src': hashlib.md5(b'youtube-dl').hexdigest(),
+            'tvId': tvid,
+            'vid': video_id,
+            'vinfo': 1,
+            'tm': tm,
+            'enc': hashlib.md5(
+                (enc_key + tm + tvid).encode('utf8')).hexdigest(),
+            'qyid': _uuid,
+            'tn': random.random(),
+            'um': 0,
+            'authkey': hashlib.md5(
+                (tm + tvid).encode('utf8')).hexdigest()
+        }
+
+        api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
+            compat_urllib_parse.urlencode(param)
+        raw_data = self._download_json(api_url, video_id)
+        return raw_data
+
+    def get_enc_key(self, swf_url, video_id):
+        filename, _ = os.path.splitext(url_basename(swf_url))
+        enc_key_json = self._downloader.cache.load('iqiyi-enc-key', filename)
+        if enc_key_json is not None:
+            return enc_key_json[0]
+
+        req = self._request_webpage(
+            swf_url, video_id, note='download swf content')
+        cn = req.read()
+        cn = zlib.decompress(cn[8:])
+        pt = re.compile(b'MixerRemote\x08(?P<enc_key>.+?)\$&vv')
+        enc_key = self._search_regex(pt, cn, 'enc_key').decode('utf8')
+
+        self._downloader.cache.store('iqiyi-enc-key', filename, [enc_key])
+
+        return enc_key
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(
+            url, 'temp_id', note='download video page')
+        tvid = self._search_regex(
+            r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
+        video_id = self._search_regex(
+            r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
+        swf_url = self._search_regex(
+            r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
+        _uuid = uuid.uuid4().hex
+
+        enc_key = self.get_enc_key(swf_url, video_id)
+
+        raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)
+
+        if raw_data['code'] != 'A000000':
+            raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
+
+        if not raw_data['data']['vp']['tkl']:
+            raise ExtractorError('No support iQiqy VIP video')
+
+        data = raw_data['data']
+
+        title = data['vi']['vn']
+
+        # generate video_urls_dict
+        video_urls_dict = self.construct_video_urls(
+            data, video_id, _uuid)
+
+        # construct info
+        entries = []
+        for format_id in video_urls_dict:
+            video_urls = video_urls_dict[format_id]
+            for i, video_url_info in enumerate(video_urls):
+                if len(entries) < i + 1:
+                    entries.append({'formats': []})
+                entries[i]['formats'].append(
+                    {
+                        'url': video_url_info[0],
+                        'filesize': video_url_info[-1],
+                        'format_id': format_id,
+                        'preference': int(self.get_bid(format_id))
+                    }
+                )
+
+        for i in range(len(entries)):
+            self._sort_formats(entries[i]['formats'])
+            entries[i].update(
+                {
+                    'id': '%s_part%d' % (video_id, i + 1),
+                    'title': title,
+                }
+            )
+
+        if len(entries) > 1:
+            info = {
+                '_type': 'multi_video',
+                'id': video_id,
+                'title': title,
+                'entries': entries,
+            }
+        else:
+            info = entries[0]
+            info['id'] = video_id
+            info['title'] = title
+
+        return info

youtube_dl/extractor/izlesene.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     determine_ext,
     float_or_none,
@@ -30,7 +31,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'pelikzzle',
-                'timestamp': 1404302298,
+                'timestamp': int,
                 'upload_date': '20140702',
                 'duration': 95.395,
                 'age_limit': 0,
@@ -46,7 +47,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'Tarkan Dortmund 2006 Konseri',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'parlayankiz',
-                'timestamp': 1163322193,
+                'timestamp': int,
                 'upload_date': '20061112',
                 'duration': 253.666,
                 'age_limit': 0,
@@ -67,9 +68,9 @@ class IzleseneIE(InfoExtractor):
 
         uploader = self._html_search_regex(
             r"adduserUsername\s*=\s*'([^']+)';",
-            webpage, 'uploader', fatal=False, default='')
+            webpage, 'uploader', fatal=False)
         timestamp = parse_iso8601(self._html_search_meta(
-            'uploadDate', webpage, 'upload date', fatal=False))
+            'uploadDate', webpage, 'upload date'))
 
         duration = float_or_none(self._html_search_regex(
             r'"videoduration"\s*:\s*"([^"]+)"',
@@ -86,8 +87,7 @@ class IzleseneIE(InfoExtractor):
 
         # Might be empty for some videos.
         streams = self._html_search_regex(
-            r'"qualitylevel"\s*:\s*"([^"]+)"',
-            webpage, 'streams', fatal=False, default='')
+            r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='')
 
         formats = []
         if streams:
@@ -95,15 +95,15 @@ class IzleseneIE(InfoExtractor):
                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
                 formats.append({
                     'format_id': '%sp' % quality if quality else 'sd',
-                    'url': url,
+                    'url': compat_urllib_parse_unquote(url),
                     'ext': ext,
                 })
         else:
             stream_url = self._search_regex(
-                r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
+                r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL')
             formats.append({
                 'format_id': 'sd',
-                'url': stream_url,
+                'url': compat_urllib_parse_unquote(stream_url),
                 'ext': ext,
             })
 

youtube_dl/extractor/kanalplay.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     float_or_none,
+    srt_subtitles_timecode,
 )
 
 
@@ -39,8 +40,8 @@ class KanalPlayIE(InfoExtractor):
             '%s\r\n%s --> %s\r\n%s'
             % (
                 num,
-                self._subtitles_timecode(item['startMillis'] / 1000.0),
-                self._subtitles_timecode(item['endMillis'] / 1000.0),
+                srt_subtitles_timecode(item['startMillis'] / 1000.0),
+                srt_subtitles_timecode(item['endMillis'] / 1000.0),
                 item['text'],
             ) for num, item in enumerate(subs, 1))
 

youtube_dl/extractor/karrierevideos.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    fix_xml_ampersands,
+    float_or_none,
+    xpath_with_ns,
+    xpath_text,
+)
+
+
+class KarriereVideosIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin',
+        'info_dict': {
+            'id': '32c91',
+            'ext': 'flv',
+            'title': 'AltenpflegerIn',
+            'description': 'md5:dbadd1259fde2159a9b28667cb664ae2',
+            'thumbnail': 're:^http://.*\.png',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        # broken ampersands
+        'url': 'http://www.karrierevideos.at/orientierung/vaeterkarenz-und-neue-chancen-fuer-muetter-baby-was-nun',
+        'info_dict': {
+            'id': '5sniu',
+            'ext': 'flv',
+            'title': 'Väterkarenz und neue Chancen für Mütter - "Baby - was nun?"',
+            'description': 'md5:97092c6ad1fd7d38e9d6a5fdeb2bcc33',
+            'thumbnail': 're:^http://.*\.png',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = (self._html_search_meta('title', webpage, default=None) or
+                 self._search_regex(r'<h1 class="title">([^<]+)</h1>'))
+
+        video_id = self._search_regex(
+            r'/config/video/(.+?)\.xml', webpage, 'video id')
+        playlist = self._download_xml(
+            'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id,
+            video_id, transform_source=fix_xml_ampersands)
+
+        NS_MAP = {
+            'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'
+        }
+
+        def ns(path):
+            return xpath_with_ns(path, NS_MAP)
+
+        item = playlist.find('./tracklist/item')
+        video_file = xpath_text(
+            item, ns('./jwplayer:file'), 'video url', fatal=True)
+        streamer = xpath_text(
+            item, ns('./jwplayer:streamer'), 'streamer', fatal=True)
+
+        uploader = xpath_text(
+            item, ns('./jwplayer:author'), 'uploader')
+        duration = float_or_none(
+            xpath_text(item, ns('./jwplayer:duration'), 'duration'))
+
+        description = self._html_search_regex(
+            r'(?s)<div class="leadtext">(.+?)</div>',
+            webpage, 'description')
+
+        thumbnail = self._html_search_meta(
+            'thumbnail', webpage, 'thumbnail')
+        if thumbnail:
+            thumbnail = compat_urlparse.urljoin(url, thumbnail)
+
+        return {
+            'id': video_id,
+            'url': streamer.replace('rtmpt', 'rtmp'),
+            'play_path': 'mp4:%s' % video_file,
+            'ext': 'flv',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'duration': duration,
+        }

youtube_dl/extractor/kickstarter.py

@@ -28,6 +28,14 @@ class KickStarterIE(InfoExtractor):
             'uploader': 'Pebble Technology',
             'title': 'Pebble iOS Notifications',
         }
+    }, {
+        'url': 'https://www.kickstarter.com/projects/1420158244/power-drive-2000/widget/video.html',
+        'info_dict': {
+            'id': '1420158244',
+            'ext': 'mp4',
+            'title': 'Power Drive 2000',
+        },
+        'expected_warnings': ['OpenGraph description'],
     }]
 
     def _real_extract(self, url):
@@ -48,10 +56,15 @@ class KickStarterIE(InfoExtractor):
                 'title': title,
             }
 
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+        if thumbnail is None:
+            thumbnail = self._html_search_regex(
+                r'<img[^>]+class="[^"]+\s*poster\s*[^"]+"[^>]+src="([^"]+)"',
+                webpage, 'thumbnail image', fatal=False)
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
             'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/letv.py

@@ -50,9 +50,7 @@ class LetvIE(InfoExtractor):
             'title': '与龙共舞 完整版',
             'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
         },
-        'params': {
-            'cn_verification_proxy': 'http://proxy.uku.im:8888'
-        },
+        'skip': 'Only available in China',
     }]
 
     @staticmethod

youtube_dl/extractor/lifenews.py

@@ -8,6 +8,7 @@ from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
     int_or_none,
+    remove_end,
     unified_strdate,
     ExtractorError,
 )
@@ -39,7 +40,6 @@ class LifeNewsIE(InfoExtractor):
             'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
             'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
             'upload_date': '20150402',
-            'uploader': 'embed.life.ru',
         }
     }, {
         'url': 'http://lifenews.ru/news/153461',
@@ -50,7 +50,6 @@ class LifeNewsIE(InfoExtractor):
             'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве',
             'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
             'upload_date': '20150505',
-            'uploader': 'embed.life.ru',
         }
     }, {
         'url': 'http://lifenews.ru/video/13035',
@@ -72,20 +71,20 @@ class LifeNewsIE(InfoExtractor):
         if not videos and not iframe_link:
             raise ExtractorError('No media links available for %s' % video_id)
 
-        title = self._og_search_title(webpage)
-        TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
-        if title.endswith(TITLE_SUFFIX):
-            title = title[:-len(TITLE_SUFFIX)]
+        title = remove_end(
+            self._og_search_title(webpage),
+            ' - Первый по срочным новостям — LIFE | NEWS')
 
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
             r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
-            r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
+            r'=\'commentCount\'[^>]*>\s*(\d+)\s*<',
+            webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
-            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
+            r'<time[^>]*datetime=\'([^\']+)\'', webpage, 'upload date', fatal=False)
         if upload_date is not None:
             upload_date = unified_strdate(upload_date)
 
@@ -156,6 +155,7 @@ class LifeEmbedIE(InfoExtractor):
                     'format_id': ext,
                     'preference': 1,
                 })
+        self._sort_formats(formats)
 
         thumbnail = self._search_regex(
             r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)

youtube_dl/extractor/liveleak.py

@@ -40,6 +40,17 @@ class LiveLeakIE(InfoExtractor):
             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
             'age_limit': 18,
         }
+    }, {
+        # Covers https://github.com/rg3/youtube-dl/pull/5983
+        'url': 'http://www.liveleak.com/view?i=801_1409392012',
+        'md5': '0b3bec2d888c20728ca2ad3642f0ef15',
+        'info_dict': {
+            'id': '801_1409392012',
+            'ext': 'mp4',
+            'description': "Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.",
+            'uploader': 'bony333',
+            'title': 'Crazy Hungarian tourist films close call waterspout in Croatia'
+        }
     }]
 
     def _real_extract(self, url):
@@ -85,7 +96,10 @@ class LiveLeakIE(InfoExtractor):
             'url': s['file'],
         } for i, s in enumerate(sources)]
         for i, s in enumerate(sources):
-            orig_url = s['file'].replace('.h264_base.mp4', '')
+            # Removing '.h264_*.mp4' gives the raw video, which is essentially
+            # the same video without the LiveLeak logo at the top (see
+            # https://github.com/rg3/youtube-dl/pull/4768)
+            orig_url = re.sub(r'\.h264_.+?\.mp4', '', s['file'])
             if s['file'] != orig_url:
                 formats.append({
                     'format_id': 'original-%s' % i,

youtube_dl/extractor/lynda.py

@@ -30,13 +30,13 @@ class LyndaBaseIE(InfoExtractor):
             return
 
         login_form = {
-            'username': username,
-            'password': password,
+            'username': username.encode('utf-8'),
+            'password': password.encode('utf-8'),
             'remember': 'false',
             'stayPut': 'false'
         }
         request = compat_urllib_request.Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 
@@ -65,7 +65,7 @@ class LyndaBaseIE(InfoExtractor):
                     'stayPut': 'false',
                 }
                 request = compat_urllib_request.Request(
-                    self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form))
+                    self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form).encode('utf-8'))
                 login_page = self._download_webpage(
                     request, None,
                     'Confirming log in and log out from another device')

youtube_dl/extractor/mitele.py

@@ -20,7 +20,6 @@ class MiTeleIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
-        'md5': '6a75fe9d0d3275bead0cb683c616fddb',
         'info_dict': {
             'id': '0fce117d',
             'ext': 'mp4',
@@ -29,6 +28,10 @@ class MiTeleIE(InfoExtractor):
             'display_id': 'programa-144',
             'duration': 2913,
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
@@ -56,12 +59,14 @@ class MiTeleIE(InfoExtractor):
             episode,
             transform_source=strip_jsonp
         )
+        formats = self._extract_m3u8_formats(
+            token_info['tokenizedUrl'], episode, ext='mp4')
 
         return {
             'id': embed_data['videoId'],
             'display_id': episode,
             'title': info_el.find('title').text,
-            'url': token_info['tokenizedUrl'],
+            'formats': formats,
             'description': get_element_by_attribute('class', 'text', webpage),
             'thumbnail': info_el.find('thumb').text,
             'duration': parse_duration(info_el.find('duration').text),

youtube_dl/extractor/mlb.py

@@ -12,13 +12,13 @@ from ..utils import (
 class MLBIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
-                        m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/
+                        (?:[\da-z_-]+\.)*mlb\.com/
                         (?:
                             (?:
                                 (?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|
                                 (?:
                                     shared/video/embed/(?:embed|m-internal-embed)\.html|
-                                    [^/]+/video/play\.jsp
+                                    (?:[^/]+/)+(?:play|index)\.jsp|
                                 )\?.*?\bcontent_id=
                             )
                             (?P<id>n?\d+)|
@@ -114,6 +114,10 @@ class MLBIE(InfoExtractor):
             # From http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer
             'url': 'http://mlb.mlb.com/shared/video/embed/m-internal-embed.html?content_id=75609783&property=mlb&autoplay=true&hashmode=false&siteSection=mlb/multimedia/article_118550098/article_embed&club=mlb',
             'only_matching': True,
+        },
+        {
+            'url': 'http://washington.nationals.mlb.com/mlb/gameday/index.jsp?c_id=was&gid=2015_05_09_atlmlb_wasmlb_1&lang=en&content_id=108309983&mode=video#',
+            'only_matching': True,
         }
     ]
 
@@ -125,7 +129,7 @@ class MLBIE(InfoExtractor):
             video_path = mobj.group('path')
             webpage = self._download_webpage(url, video_path)
             video_id = self._search_regex(
-                r'data-video-?id="(\d+)"', webpage, 'video id')
+                [r'data-video-?id="(\d+)"', r'content_id=(\d+)'], webpage, 'video id')
 
         detail = self._download_xml(
             'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'

youtube_dl/extractor/naver.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
@@ -16,7 +17,7 @@ from ..utils import (
 class NaverIE(InfoExtractor):
     _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://tvcast.naver.com/v/81652',
         'info_dict': {
             'id': '81652',
@@ -25,7 +26,18 @@ class NaverIE(InfoExtractor):
             'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
             'upload_date': '20130903',
         },
-    }
+    }, {
+        'url': 'http://tvcast.naver.com/v/395837',
+        'md5': '638ed4c12012c458fefcddfd01f173cd',
+        'info_dict': {
+            'id': '395837',
+            'ext': 'mp4',
+            'title': '9년이 지나도 아픈 기억, 전효성의 아버지',
+            'description': 'md5:5bf200dcbf4b66eb1b350d1eb9c753f7',
+            'upload_date': '20150519',
+        },
+        'skip': 'Georestricted',
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -35,7 +47,7 @@ class NaverIE(InfoExtractor):
                          webpage)
         if m_id is None:
             m_error = re.search(
-                r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
+                r'(?s)<div class="(?:nation_error|nation_box)">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
                 webpage)
             if m_error:
                 raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
@@ -58,14 +70,18 @@ class NaverIE(InfoExtractor):
         formats = []
         for format_el in urls.findall('EncodingOptions/EncodingOption'):
             domain = format_el.find('Domain').text
+            uri = format_el.find('uri').text
             f = {
-                'url': domain + format_el.find('uri').text,
+                'url': compat_urlparse.urljoin(domain, uri),
                 'ext': 'mp4',
                 'width': int(format_el.find('width').text),
                 'height': int(format_el.find('height').text),
             }
             if domain.startswith('rtmp'):
+                # urlparse does not support custom schemes
+                # https://bugs.python.org/issue18828
                 f.update({
+                    'url': domain + uri,
                     'ext': 'flv',
                     'rtmp_protocol': '1',  # rtmpt
                 })

youtube_dl/extractor/nba.py

@@ -22,6 +22,18 @@ class NBAIE(InfoExtractor):
     }, {
         'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
         'only_matching': True,
+    }, {
+        'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
+        'info_dict': {
+            'id': '0041400301-cle-atl-recap.nba',
+            'ext': 'mp4',
+            'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1',
+            'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
+            'duration': 228,
+        },
+        'params': {
+            'skip_download': True,
+        }
     }]
 
     def _real_extract(self, url):
@@ -35,8 +47,12 @@ class NBAIE(InfoExtractor):
             self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
 
         description = self._og_search_description(webpage)
-        duration = parse_duration(
-            self._html_search_meta('duration', webpage, 'duration'))
+        duration_str = self._html_search_meta(
+            'duration', webpage, 'duration', default=None)
+        if not duration_str:
+            duration_str = self._html_search_regex(
+                r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False)
+        duration = parse_duration(duration_str)
 
         return {
             'id': shortened_video_id,

youtube_dl/extractor/ndr.py

@@ -8,41 +8,11 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     qualities,
+    parse_duration,
 )
 
 
-class NDRIE(InfoExtractor):
-    IE_NAME = 'ndr'
-    IE_DESC = 'NDR.de - Mediathek'
-    _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
-
-    _TESTS = [
-        {
-            'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
-            'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
-            'note': 'Video file',
-            'info_dict': {
-                'id': '25866',
-                'ext': 'mp4',
-                'title': 'Kartoffeltage in der Lewitz',
-                'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8',
-                'duration': 166,
-            }
-        },
-        {
-            'url': 'http://www.ndr.de/info/audio51535.html',
-            'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
-            'note': 'Audio file',
-            'info_dict': {
-                'id': '51535',
-                'ext': 'mp3',
-                'title': 'La Valette entgeht der Hinrichtung',
-                'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
-                'duration': 884,
-            }
-        }
-    ]
-
+class NDRBaseIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
@@ -54,7 +24,11 @@ class NDRIE(InfoExtractor):
         if description:
             description = description.strip()
 
-        duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
+        duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', default=None))
+        if not duration:
+            duration = parse_duration(self._html_search_regex(
+                r'(<span class="min">\d+</span>:<span class="sec">\d+</span>)',
+                page, 'duration', default=None))
 
         formats = []
 
@@ -92,3 +66,65 @@ class NDRIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
         }
+
+
+class NDRIE(NDRBaseIE):
+    IE_NAME = 'ndr'
+    IE_DESC = 'NDR.de - Mediathek'
+    _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+
+    _TESTS = [
+        {
+            'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
+            'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
+            'note': 'Video file',
+            'info_dict': {
+                'id': '25866',
+                'ext': 'mp4',
+                'title': 'Kartoffeltage in der Lewitz',
+                'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8',
+                'duration': 166,
+            },
+            'skip': '404 Not found',
+        },
+        {
+            'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
+            'md5': 'dadc003c55ae12a5d2f6bd436cd73f59',
+            'info_dict': {
+                'id': '988',
+                'ext': 'mp4',
+                'title': 'Party, Pötte und Parade',
+                'description': 'Hunderttausende feiern zwischen Speicherstadt und St. Pauli den 826. Hafengeburtstag. Die NDR Sondersendung zeigt die schönsten und spektakulärsten Bilder vom Auftakt.',
+                'duration': 3498,
+            },
+        },
+        {
+            'url': 'http://www.ndr.de/info/audio51535.html',
+            'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
+            'note': 'Audio file',
+            'info_dict': {
+                'id': '51535',
+                'ext': 'mp3',
+                'title': 'La Valette entgeht der Hinrichtung',
+                'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
+                'duration': 884,
+            }
+        }
+    ]
+
+
+class NJoyIE(NDRBaseIE):
+    IE_NAME = 'N-JOY'
+    _VALID_URL = r'https?://www\.n-joy\.de/.+?(?P<id>\d+)\.html'
+
+    _TEST = {
+        'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
+        'md5': 'cb63be60cd6f9dd75218803146d8dc67',
+        'info_dict': {
+            'id': '2480',
+            'ext': 'mp4',
+            'title': 'Benaissa beim NDR Comedy Contest',
+            'description': 'Von seinem sehr "behaarten" Leben lässt sich Benaissa trotz aller Schwierigkeiten nicht unterkriegen.',
+            'duration': 654,
+        }
+    }

youtube_dl/extractor/newstube.py

@@ -31,7 +31,7 @@ class NewstubeIE(InfoExtractor):
         page = self._download_webpage(url, video_id, 'Downloading page')
 
         video_guid = self._html_search_regex(
-            r'<meta property="og:video" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+            r'<meta property="og:video:url" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
             page, 'video GUID')
 
         player = self._download_xml(

youtube_dl/extractor/nextmedia.py

@@ -89,8 +89,8 @@ class NextMediaActionNewsIE(NextMediaIE):
         return self._extract_from_nextmedia_page(news_id, url, article_page)
 
 
-class AppleDailyRealtimeNewsIE(NextMediaIE):
-    _VALID_URL = r'http://(www|ent).appledaily.com.tw/(realtimenews|enews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+class AppleDailyIE(NextMediaIE):
+    _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -99,7 +99,7 @@ class AppleDailyRealtimeNewsIE(NextMediaIE):
             'ext': 'mp4',
             'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:b23787119933404ce515c6356a8c355c',
+            'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4',
             'upload_date': '20150128',
         }
     }, {
@@ -110,26 +110,10 @@ class AppleDailyRealtimeNewsIE(NextMediaIE):
             'ext': 'mp4',
             'title': '不滿被踩腳　山東兩大媽一路打下車',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:2648aaf6fc4f401f6de35a91d111aa1d',
+            'description': 'md5:175b4260c1d7c085993474217e4ab1b4',
             'upload_date': '20150128',
         }
-    }]
-
-    _URL_PATTERN = r'\{url: \'(.+)\'\}'
-
-    def _fetch_title(self, page):
-        return self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title')
-
-    def _fetch_thumbnail(self, page):
-        return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
-
-    def _fetch_timestamp(self, page):
-        return None
-
-
-class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
-    _VALID_URL = 'http://www.appledaily.com.tw/animation/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
-    _TESTS = [{
+    }, {
         'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671',
         'md5': '03df296d95dedc2d5886debbb80cb43f',
         'info_dict': {
@@ -154,10 +138,22 @@ class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
         'expected_warnings': [
             'video thumbnail',
         ]
+    }, {
+        'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/',
+        'only_matching': True,
     }]
 
+    _URL_PATTERN = r'\{url: \'(.+)\'\}'
+
     def _fetch_title(self, page):
-        return self._html_search_meta('description', page, 'news title')
+        return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or
+                self._html_search_meta('description', page, 'news title'))
+
+    def _fetch_thumbnail(self, page):
+        return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
+
+    def _fetch_timestamp(self, page):
+        return None
 
     def _fetch_description(self, page):
         return self._html_search_meta('description', page, 'news description')

youtube_dl/extractor/nfl.py

@@ -19,7 +19,7 @@ class NFLIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/
         (?:.+?/)*
-        (?P<id>(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
+        (?P<id>(?:[a-z0-9]{16}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
     _TESTS = [
         {
             'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
@@ -58,6 +58,10 @@ class NFLIE(InfoExtractor):
                 'upload_date': '20150202',
             },
         },
+        {
+            'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood',
+            'only_matching': True,
+        }
     ]
 
     @staticmethod

youtube_dl/extractor/niconico.py

@@ -182,7 +182,6 @@ class NiconicoIE(InfoExtractor):
         extension = xpath_text(video_info, './/movie_type')
         if not extension:
             extension = determine_ext(video_real_url)
-        video_format = extension.upper()
 
         thumbnail = (
             xpath_text(video_info, './/thumbnail_url') or
@@ -241,7 +240,7 @@ class NiconicoIE(InfoExtractor):
             'url': video_real_url,
             'title': title,
             'ext': extension,
-            'format': video_format,
+            'format_id': 'economy' if video_real_url.endswith('low') else 'normal',
             'thumbnail': thumbnail,
             'description': description,
             'uploader': uploader,

youtube_dl/extractor/noco.py

@@ -166,6 +166,10 @@ class NocoIE(InfoExtractor):
         self._sort_formats(formats)
 
         timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')
+
+        if timestamp is not None and timestamp < 0:
+            timestamp = None
+
         uploader = show.get('partner_name')
         uploader_id = show.get('partner_key')
         duration = float_or_none(show.get('duration_ms'), 1000)
@@ -191,7 +195,7 @@ class NocoIE(InfoExtractor):
         if episode_number:
             title += ' #' + compat_str(episode_number)
         if episode:
-            title += ' - ' + episode
+            title += ' - ' + compat_str(episode)
 
         description = show.get('show_resume') or show.get('family_resume')
 

youtube_dl/extractor/nova.py

@@ -0,0 +1,179 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    unified_strdate,
+)
+
+
+class NovaIE(InfoExtractor):
+    IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz'
+    _VALID_URL = 'http://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
+    _TESTS = [{
+        'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html?utm_source=tvnoviny&utm_medium=cpfooter&utm_campaign=novaplus',
+        'info_dict': {
+            'id': '1608920',
+            'display_id': 'co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou',
+            'ext': 'flv',
+            'title': 'Duel: Michal Hrdlička a Petr Suchoň',
+            'description': 'md5:d0cc509858eee1b1374111c588c6f5d5',
+            'thumbnail': 're:^https?://.*\.(?:jpg)',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
+        'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
+        'info_dict': {
+            'id': '1757139',
+            'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
+            'ext': 'mp4',
+            'title': 'Podzemní nemocnice v pražské Krči',
+            'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53',
+            'thumbnail': 're:^https?://.*\.(?:jpg)',
+        }
+    }, {
+        'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove',
+        'info_dict': {
+            'id': '1756825',
+            'display_id': '5591-policie-modrava-15-dil-blondynka-na-hrbitove',
+            'ext': 'flv',
+            'title': 'Policie Modrava - 15. díl - Blondýnka na hřbitově',
+            'description': 'md5:dc24e50be5908df83348e50d1431295e',  # Make sure this description is clean of html tags
+            'thumbnail': 're:^https?://.*\.(?:jpg)',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://novaplus.nova.cz/porad/televizni-noviny/video/5585-televizni-noviny-30-5-2015/',
+        'info_dict': {
+            'id': '1756858',
+            'ext': 'flv',
+            'title': 'Televizní noviny - 30. 5. 2015',
+            'thumbnail': 're:^https?://.*\.(?:jpg)',
+            'upload_date': '20150530',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html',
+        'info_dict': {
+            'id': '1753621',
+            'ext': 'mp4',
+            'title': 'Zaklínač 3: Divoký hon',
+            'description': 're:.*Pokud se stejně jako my nemůžete.*',
+            'thumbnail': 're:https?://.*\.jpg(\?.*)?',
+            'upload_date': '20150521',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://doma.nova.cz/clanek/zdravi/prijdte-se-zapsat-do-registru-kostni-drene-jiz-ve-stredu-3-cervna.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://prask.nova.cz/clanek/novinky/co-si-na-sobe-nase-hvezdy-nechaly-pojistit.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.nova.cz/clanek/novinky/zivot-je-zivot-bondovsky-trailer.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        site = mobj.group('site')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            [r"(?:media|video_id)\s*:\s*'(\d+)'",
+             r'media=(\d+)',
+             r'id="article_video_(\d+)"',
+             r'id="player_(\d+)"'],
+            webpage, 'video id')
+
+        config_url = self._search_regex(
+            r'src="(http://tn\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"',
+            webpage, 'config url', default=None)
+
+        if not config_url:
+            DEFAULT_SITE_ID = '23000'
+            SITES = {
+                'tvnoviny': DEFAULT_SITE_ID,
+                'novaplus': DEFAULT_SITE_ID,
+                'vymena': DEFAULT_SITE_ID,
+                'krasna': DEFAULT_SITE_ID,
+                'fanda': '30',
+                'tn': '30',
+                'doma': '30',
+            }
+
+            site_id = self._search_regex(
+                r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(site, DEFAULT_SITE_ID)
+
+            config_url = ('http://tn.nova.cz/bin/player/videojs/config.php?site=%s&media=%s&jsVar=vjsconfig'
+                          % (site_id, video_id))
+
+        config = self._download_json(
+            config_url, display_id,
+            'Downloading config JSON',
+            transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
+
+        mediafile = config['mediafile']
+        video_url = mediafile['src']
+
+        m = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+?))/&*(?P<playpath>.+)$', video_url)
+        if m:
+            formats = [{
+                'url': m.group('url'),
+                'app': m.group('app'),
+                'play_path': m.group('playpath'),
+                'player_path': 'http://tvnoviny.nova.cz/static/shared/app/videojs/video-js.swf',
+                'ext': 'flv',
+            }]
+        else:
+            formats = [{
+                'url': video_url,
+            }]
+        self._sort_formats(formats)
+
+        title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
+        description = clean_html(self._og_search_description(webpage, default=None))
+        thumbnail = config.get('poster')
+
+        if site == 'novaplus':
+            upload_date = unified_strdate(self._search_regex(
+                r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
+        elif site == 'fanda':
+            upload_date = unified_strdate(self._search_regex(
+                r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
+        else:
+            upload_date = None
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/nowtv.py

@@ -0,0 +1,192 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    parse_duration,
+    remove_start,
+)
+
+
+class NowTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nowtv\.de/(?P<station>rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<id>.+?)/player'
+
+    _TESTS = [{
+        # rtl
+        'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player',
+        'info_dict': {
+            'id': '203519',
+            'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
+            'ext': 'mp4',
+            'title': 'Die neuen Bauern und eine Hochzeit',
+            'description': 'md5:e234e1ed6d63cf06be5c070442612e7e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432580700,
+            'upload_date': '20150525',
+            'duration': 2786,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # rtl2
+        'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player',
+        'info_dict': {
+            'id': '203481',
+            'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934',
+            'ext': 'mp4',
+            'title': 'Berlin - Tag & Nacht (Folge 934)',
+            'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432666800,
+            'upload_date': '20150526',
+            'duration': 2641,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # rtlnitro
+        'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player',
+        'info_dict': {
+            'id': '165780',
+            'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00',
+            'ext': 'mp4',
+            'title': 'Hals- und Beinbruch',
+            'description': 'md5:b50d248efffe244e6f56737f0911ca57',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432415400,
+            'upload_date': '20150523',
+            'duration': 2742,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # superrtl
+        'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player',
+        'info_dict': {
+            'id': '99205',
+            'display_id': 'medicopter-117/angst',
+            'ext': 'mp4',
+            'title': 'Angst!',
+            'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1222632900,
+            'upload_date': '20080928',
+            'duration': 3025,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # ntv
+        'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player',
+        'info_dict': {
+            'id': '203521',
+            'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch',
+            'ext': 'mp4',
+            'title': 'Thema u.a.: Der erste Blick: Die Apple Watch',
+            'description': 'md5:4312b6c9d839ffe7d8caf03865a531af',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432751700,
+            'upload_date': '20150527',
+            'duration': 1083,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # vox
+        'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player',
+        'info_dict': {
+            'id': '128953',
+            'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel',
+            'ext': 'mp4',
+            'title': "Büro-Fall / Chihuahua 'Joel'",
+            'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432408200,
+            'upload_date': '20150523',
+            'duration': 3092,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        station = mobj.group('station')
+
+        info = self._download_json(
+            'https://api.nowtv.de/v3/movies/%s?fields=*,format,files' % display_id,
+            display_id)
+
+        video_id = compat_str(info['id'])
+
+        files = info['files']
+        if not files:
+            if info.get('geoblocked', False):
+                raise ExtractorError(
+                    'Video %s is not available from your location due to geo restriction' % video_id,
+                    expected=True)
+            if not info.get('free', True):
+                raise ExtractorError(
+                    'Video %s is not available for free' % video_id, expected=True)
+
+        f = info.get('format', {})
+        station = f.get('station') or station
+
+        STATIONS = {
+            'rtl': 'rtlnow',
+            'rtl2': 'rtl2now',
+            'vox': 'voxnow',
+            'nitro': 'rtlnitronow',
+            'ntv': 'n-tvnow',
+            'superrtl': 'superrtlnow'
+        }
+
+        formats = []
+        for item in files['items']:
+            item_path = remove_start(item['path'], '/')
+            tbr = int_or_none(item['bitrate'])
+            m3u8_url = 'http://hls.fra.%s.de/hls-vod-enc/%s.m3u8' % (STATIONS[station], item_path)
+            m3u8_url = m3u8_url.replace('now/', 'now/videos/')
+            formats.append({
+                'url': m3u8_url,
+                'format_id': '%s-%sk' % (item['id'], tbr),
+                'ext': 'mp4',
+                'tbr': tbr,
+            })
+        self._sort_formats(formats)
+
+        title = info['title']
+        description = info.get('articleLong') or info.get('articleShort')
+        timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ')
+        duration = parse_duration(info.get('duration'))
+        thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/npo.py

@@ -16,8 +16,24 @@ class NPOBaseIE(InfoExtractor):
         token_page = self._download_webpage(
             'http://ida.omroep.nl/npoplayer/i.js',
             video_id, note='Downloading token')
-        return self._search_regex(
+        token = self._search_regex(
             r'npoplayer\.token = "(.+?)"', token_page, 'token')
+        # Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
+        token_l = list(token)
+        first = second = None
+        for i in range(5, len(token_l) - 4):
+            if token_l[i].isdigit():
+                if first is None:
+                    first = i
+                elif second is None:
+                    second = i
+        if first is None or second is None:
+            first = 12
+            second = 13
+
+        token_l[first], token_l[second] = token_l[second], token_l[first]
+
+        return ''.join(token_l)
 
 
 class NPOIE(NPOBaseIE):
@@ -92,7 +108,7 @@ class NPOIE(NPOBaseIE):
 
     def _get_info(self, video_id):
         metadata = self._download_json(
-            'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
+            'http://e.omroep.nl/metadata/%s' % video_id,
             video_id,
             # We have to remove the javascript callback
             transform_source=strip_jsonp,

youtube_dl/extractor/nrk.py

@@ -4,7 +4,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     float_or_none,
@@ -14,7 +13,7 @@ from ..utils import (
 
 
 class NRKIE(InfoExtractor):
-    _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
+    _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
 
     _TESTS = [
         {
@@ -77,7 +76,7 @@ class NRKIE(InfoExtractor):
 
 
 class NRKPlaylistIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
@@ -117,11 +116,11 @@ class NRKPlaylistIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):
-    _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
+    _VALID_URL = r'(?P<baseurl>https?://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 
     _TESTS = [
         {
-            'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
+            'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',
@@ -133,7 +132,7 @@ class NRKTVIE(InfoExtractor):
             },
         },
         {
-            'url': 'http://tv.nrk.no/program/mdfp15000514',
+            'url': 'https://tv.nrk.no/program/mdfp15000514',
             'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',
@@ -146,7 +145,7 @@ class NRKTVIE(InfoExtractor):
         },
         {
             # single playlist video
-            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
             'md5': 'adbd1dbd813edaf532b0a253780719c2',
             'info_dict': {
                 'id': 'MSPO40010515-part2',
@@ -158,7 +157,7 @@ class NRKTVIE(InfoExtractor):
             'skip': 'Only works from Norway',
         },
         {
-            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
             'playlist': [
                 {
                     'md5': '9480285eff92d64f06e02a5367970a7a',
@@ -200,20 +199,10 @@ class NRKTVIE(InfoExtractor):
         url = "%s%s" % (baseurl, subtitlesurl)
         self._debug_print('%s: Subtitle url: %s' % (video_id, url))
         captions = self._download_xml(
-            url, video_id, 'Downloading subtitles',
-            transform_source=lambda s: s.replace(r'<br />', '\r\n'))
+            url, video_id, 'Downloading subtitles')
         lang = captions.get('lang', 'no')
-        ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
-        srt = ''
-        for pos, p in enumerate(ps):
-            begin = parse_duration(p.get('begin'))
-            duration = parse_duration(p.get('dur'))
-            starttime = self._subtitles_timecode(begin)
-            endtime = self._subtitles_timecode(begin + duration)
-            srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
         return {lang: [
             {'ext': 'ttml', 'url': url},
-            {'ext': 'srt', 'data': srt},
         ]}
 
     def _extract_f4m(self, manifest_url, video_id):

youtube_dl/extractor/nytimes.py

@@ -89,7 +89,7 @@ class NYTimesIE(NYTimesBaseIE):
 
 
 class NYTimesArticleIE(NYTimesBaseIE):
-    _VALID_URL = r'https?://(?:www)?\.nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
     _TESTS = [{
         'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
         'md5': 'e2076d58b4da18e6a001d53fd56db3c9',

youtube_dl/extractor/odnoklassniki.py

@@ -2,16 +2,19 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse
 from ..utils import (
     unified_strdate,
     int_or_none,
     qualities,
+    unescapeHTML,
 )
 
 
 class OdnoklassnikiIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
     _TESTS = [{
+        # metadata in JSON
         'url': 'http://ok.ru/video/20079905452',
         'md5': '8e24ad2da6f387948e7a7d44eb8668fe',
         'info_dict': {
@@ -19,11 +22,22 @@ class OdnoklassnikiIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Культура меняет нас (прекрасный ролик!))',
             'duration': 100,
-            'upload_date': '20141207',
             'uploader_id': '330537914540',
             'uploader': 'Виталий Добровольский',
             'like_count': int,
-            'age_limit': 0,
+        },
+    }, {
+        # metadataUrl
+        'url': 'http://ok.ru/video/63567059965189-0',
+        'md5': '9676cf86eff5391d35dea675d224e131',
+        'info_dict': {
+            'id': '63567059965189-0',
+            'ext': 'mp4',
+            'title': 'Девушка без комплексов ...',
+            'duration': 191,
+            'uploader_id': '534380003155',
+            'uploader': 'Андрей Мещанинов',
+            'like_count': int,
         },
     }, {
         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
@@ -33,14 +47,23 @@ class OdnoklassnikiIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://ok.ru/video/%s' % video_id, video_id)
 
         player = self._parse_json(
-            self._search_regex(
-                r"OKVideo\.start\(({.+?})\s*,\s*'VideoAutoplay_player'", webpage, 'player'),
+            unescapeHTML(self._search_regex(
+                r'data-attributes="([^"]+)"', webpage, 'player')),
             video_id)
 
-        metadata = self._parse_json(player['flashvars']['metadata'], video_id)
+        flashvars = player['flashvars']
+
+        metadata = flashvars.get('metadata')
+        if metadata:
+            metadata = self._parse_json(metadata, video_id)
+        else:
+            metadata = self._download_json(
+                compat_urllib_parse.unquote(flashvars['metadataUrl']),
+                video_id, 'Downloading metadata JSON')
 
         movie = metadata['movie']
         title = movie['title']
@@ -52,11 +75,11 @@ class OdnoklassnikiIE(InfoExtractor):
         uploader = author.get('name')
 
         upload_date = unified_strdate(self._html_search_meta(
-            'ya:ovs:upload_date', webpage, 'upload date'))
+            'ya:ovs:upload_date', webpage, 'upload date', default=None))
 
         age_limit = None
         adult = self._html_search_meta(
-            'ya:ovs:adult', webpage, 'age limit')
+            'ya:ovs:adult', webpage, 'age limit', default=None)
         if adult:
             age_limit = 18 if adult == 'true' else 0
 

youtube_dl/extractor/onionstudios.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class OnionStudiosIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
+
+    _TESTS = [{
+        'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
+        'md5': 'd4851405d31adfadf71cd7a487b765bb',
+        'info_dict': {
+            'id': '2937',
+            'ext': 'mp4',
+            'title': 'Hannibal charges forward, stops for a cocktail',
+            'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'The A.V. Club',
+            'uploader_id': 'TheAVClub',
+        },
+    }, {
+        'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/embed.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
+
+        formats = []
+        for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
+            if determine_ext(src) != 'm3u8':  # m3u8 always results in 403
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        title = self._search_regex(
+            r'share_title\s*=\s*"([^"]+)"', webpage, 'title')
+        description = self._search_regex(
+            r'share_description\s*=\s*"([^"]+)"', webpage,
+            'description', default=None)
+        thumbnail = self._search_regex(
+            r'poster="([^"]+)"', webpage, 'thumbnail', default=False)
+
+        uploader_id = self._search_regex(
+            r'twitter_handle\s*=\s*"([^"]+)"',
+            webpage, 'uploader id', fatal=False)
+        uploader = self._search_regex(
+            r'window\.channelName\s*=\s*"Embedded:([^"]+)"',
+            webpage, 'uploader', default=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/ooyala.py

@@ -12,7 +12,100 @@ from ..utils import (
 )
 
 
-class OoyalaIE(InfoExtractor):
+class OoyalaBaseIE(InfoExtractor):
+
+    def _extract_result(self, info, more_info):
+        embedCode = info['embedCode']
+        video_url = info.get('ipad_url') or info['url']
+
+        if determine_ext(video_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
+        else:
+            formats = [{
+                'url': video_url,
+                'ext': 'mp4',
+            }]
+
+        return {
+            'id': embedCode,
+            'title': unescapeHTML(info['title']),
+            'formats': formats,
+            'description': unescapeHTML(more_info['description']),
+            'thumbnail': more_info['promo'],
+        }
+
+    def _extract(self, player_url, video_id):
+        player = self._download_webpage(player_url, video_id)
+        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
+                                        player, 'mobile player url')
+        # Looks like some videos are only available for particular devices
+        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
+        # is only available for ipad)
+        # Working around with fetching URLs for all the devices found starting with 'unknown'
+        # until we succeed or eventually fail for each device.
+        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
+        devices.remove('unknown')
+        devices.insert(0, 'unknown')
+        for device in devices:
+            mobile_player = self._download_webpage(
+                '%s&device=%s' % (mobile_url, device), video_id,
+                'Downloading mobile player JS for %s device' % device)
+            videos_info = self._search_regex(
+                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
+                mobile_player, 'info', fatal=False, default=None)
+            if videos_info:
+                break
+
+        if not videos_info:
+            formats = []
+            auth_data = self._download_json(
+                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
+                video_id)
+
+            cur_auth_data = auth_data['authorization_data'][video_id]
+
+            for stream in cur_auth_data['streams']:
+                formats.append({
+                    'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
+                    'ext': stream.get('delivery_type'),
+                    'format': stream.get('video_codec'),
+                    'format_id': stream.get('profile'),
+                    'width': int_or_none(stream.get('width')),
+                    'height': int_or_none(stream.get('height')),
+                    'abr': int_or_none(stream.get('audio_bitrate')),
+                    'vbr': int_or_none(stream.get('video_bitrate')),
+                })
+            if formats:
+                return {
+                    'id': video_id,
+                    'formats': formats,
+                    'title': 'Ooyala video',
+                }
+
+            if not cur_auth_data['authorized']:
+                raise ExtractorError(cur_auth_data['message'], expected=True)
+
+        if not videos_info:
+            raise ExtractorError('Unable to extract info')
+        videos_info = videos_info.replace('\\"', '"')
+        videos_more_info = self._search_regex(
+            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
+        videos_info = json.loads(videos_info)
+        videos_more_info = json.loads(videos_more_info)
+
+        if videos_more_info.get('lineup'):
+            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
+            return {
+                '_type': 'playlist',
+                'id': video_id,
+                'title': unescapeHTML(videos_more_info['title']),
+                'entries': videos,
+            }
+        else:
+            return self._extract_result(videos_info[0], videos_more_info)
+
+
+class OoyalaIE(OoyalaBaseIE):
     _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
 
     _TESTS = [
@@ -57,95 +150,47 @@ class OoyalaIE(InfoExtractor):
         return cls.url_result(cls._url_for_embed_code(embed_code),
                               ie=cls.ie_key())
 
-    def _extract_result(self, info, more_info):
-        embedCode = info['embedCode']
-        video_url = info.get('ipad_url') or info['url']
+    def _real_extract(self, url):
+        embed_code = self._match_id(url)
+        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+        return self._extract(player_url, embed_code)
 
-        if determine_ext(video_url) == 'm3u8':
-            formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
-        else:
-            formats = [{
-                'url': video_url,
-                'ext': 'mp4',
-            }]
 
-        return {
-            'id': embedCode,
-            'title': unescapeHTML(info['title']),
-            'formats': formats,
-            'description': unescapeHTML(more_info['description']),
-            'thumbnail': more_info['promo'],
-        }
+class OoyalaExternalIE(OoyalaBaseIE):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        ooyalaexternal:|
+                        https?://.+?\.ooyala\.com/.*?\bexternalId=
+                    )
+                    (?P<partner_id>[^:]+)
+                    :
+                    (?P<id>.+)
+                    (?:
+                        :|
+                        .*?&pcode=
+                    )
+                    (?P<pcode>.+?)
+                    (&|$)
+                    '''
+
+    _TEST = {
+        'url': 'https://player.ooyala.com/player.js?externalId=espn:10365079&pcode=1kNG061cgaoolOncv54OAO1ceO-I&adSetCode=91cDU6NuXTGKz3OdjOxFdAgJVtQcKJnI&callback=handleEvents&hasModuleParams=1&height=968&playerBrandingId=7af3bd04449c444c964f347f11873075&targetReplaceId=videoPlayer&width=1656&wmode=opaque&allowScriptAccess=always',
+        'info_dict': {
+            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
+            'ext': 'mp4',
+            'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
+            'description': '',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        embedCode = mobj.group('id')
-        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
-        player = self._download_webpage(player_url, embedCode)
-        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
-                                        player, 'mobile player url')
-        # Looks like some videos are only available for particular devices
-        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
-        # is only available for ipad)
-        # Working around with fetching URLs for all the devices found starting with 'unknown'
-        # until we succeed or eventually fail for each device.
-        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
-        devices.remove('unknown')
-        devices.insert(0, 'unknown')
-        for device in devices:
-            mobile_player = self._download_webpage(
-                '%s&device=%s' % (mobile_url, device), embedCode,
-                'Downloading mobile player JS for %s device' % device)
-            videos_info = self._search_regex(
-                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
-                mobile_player, 'info', fatal=False, default=None)
-            if videos_info:
-                break
-
-        if not videos_info:
-            formats = []
-            auth_data = self._download_json(
-                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (embedCode, embedCode),
-                embedCode)
-
-            cur_auth_data = auth_data['authorization_data'][embedCode]
-
-            for stream in cur_auth_data['streams']:
-                formats.append({
-                    'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
-                    'ext': stream.get('delivery_type'),
-                    'format': stream.get('video_codec'),
-                    'format_id': stream.get('profile'),
-                    'width': int_or_none(stream.get('width')),
-                    'height': int_or_none(stream.get('height')),
-                    'abr': int_or_none(stream.get('audio_bitrate')),
-                    'vbr': int_or_none(stream.get('video_bitrate')),
-                })
-            if formats:
-                return {
-                    'id': embedCode,
-                    'formats': formats,
-                    'title': 'Ooyala video',
-                }
-
-            if not cur_auth_data['authorized']:
-                raise ExtractorError(cur_auth_data['message'], expected=True)
-
-        if not videos_info:
-            raise ExtractorError('Unable to extract info')
-        videos_info = videos_info.replace('\\"', '"')
-        videos_more_info = self._search_regex(
-            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
-        videos_info = json.loads(videos_info)
-        videos_more_info = json.loads(videos_more_info)
-
-        if videos_more_info.get('lineup'):
-            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
-            return {
-                '_type': 'playlist',
-                'id': embedCode,
-                'title': unescapeHTML(videos_more_info['title']),
-                'entries': videos,
-            }
-        else:
-            return self._extract_result(videos_info[0], videos_more_info)
+        partner_id = mobj.group('partner_id')
+        video_id = mobj.group('id')
+        pcode = mobj.group('pcode')
+        player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
+        return self._extract(player_url, video_id)

youtube_dl/extractor/patreon.py

@@ -87,7 +87,7 @@ class PatreonIE(InfoExtractor):
             r'<div class="attach"><a target="_blank" href="([^"]+)">',
             webpage, 'attachment URL', default=None)
         embed = self._html_search_regex(
-            r'<div id="watchCreation">\s*<iframe class="embedly-embed" src="([^"]+)"',
+            r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"',
             webpage, 'embedded URL', default=None)
 
         if attach_fn is not None:

youtube_dl/extractor/pbs.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -35,6 +36,9 @@ class PBSIE(InfoExtractor):
                 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
                 'duration': 3190,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
@@ -46,6 +50,9 @@ class PBSIE(InfoExtractor):
                 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
                 'duration': 5050,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            }
         },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
@@ -68,7 +75,10 @@ class PBSIE(InfoExtractor):
                 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
                 'duration': 6559,
                 'thumbnail': 're:^https?://.*\.jpg$',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
@@ -82,7 +92,10 @@ class PBSIE(InfoExtractor):
                 'duration': 3172,
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'upload_date': '20140122',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
@@ -90,6 +103,21 @@ class PBSIE(InfoExtractor):
                 'id': 'united-states-of-secrets',
             },
             'playlist_count': 2,
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
+            'info_dict': {
+                'id': '2280706814',
+                'display_id': 'player',
+                'ext': 'mp4',
+                'title': 'Death and the Civil War',
+                'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
+                'duration': 6705,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         }
     ]
 
@@ -123,7 +151,7 @@ class PBSIE(InfoExtractor):
                 return media_id, presumptive_id, upload_date
 
             url = self._search_regex(
-                r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 

youtube_dl/extractor/pinkbike.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    remove_end,
+    remove_start,
+    str_to_int,
+    unified_strdate,
+)
+
+
+class PinkbikeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?pinkbike\.com/video/|es\.pinkbike\.org/i/kvid/kvid-y5\.swf\?id=)(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.pinkbike.com/video/402811/',
+        'md5': '4814b8ca7651034cd87e3361d5c2155a',
+        'info_dict': {
+            'id': '402811',
+            'ext': 'mp4',
+            'title': 'Brandon Semenuk - RAW 100',
+            'description': 'Official release: www.redbull.ca/rupertwalker',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 100,
+            'upload_date': '20150406',
+            'uploader': 'revelco',
+            'location': 'Victoria, British Columbia, Canada',
+            'view_count': int,
+            'comment_count': int,
+        }
+    }, {
+        'url': 'http://es.pinkbike.org/i/kvid/kvid-y5.swf?id=406629',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.pinkbike.com/video/%s' % video_id, video_id)
+
+        formats = []
+        for _, format_id, src in re.findall(
+                r'data-quality=((?:\\)?["\'])(.+?)\1[^>]+src=\1(.+?)\1', webpage):
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]$', format_id, 'height', default=None))
+            formats.append({
+                'url': src,
+                'format_id': format_id,
+                'height': height,
+            })
+        self._sort_formats(formats)
+
+        title = remove_end(self._og_search_title(webpage), ' Video - Pinkbike')
+        description = self._html_search_regex(
+            r'(?s)id="media-description"[^>]*>(.+?)<',
+            webpage, 'description', default=None) or remove_start(
+            self._og_search_description(webpage), title + '. ')
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'duration'))
+
+        uploader = self._search_regex(
+            r'un:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
+        upload_date = unified_strdate(self._search_regex(
+            r'class="fullTime"[^>]+title="([^"]+)"',
+            webpage, 'upload date', fatal=False))
+
+        location = self._html_search_regex(
+            r'(?s)<dt>Location</dt>\s*<dd>(.+?)<',
+            webpage, 'location', fatal=False)
+
+        def extract_count(webpage, label):
+            return str_to_int(self._search_regex(
+                r'<span[^>]+class="stat-num"[^>]*>([\d,.]+)</span>\s*<span[^>]+class="stat-label"[^>]*>%s' % label,
+                webpage, label, fatal=False))
+
+        view_count = extract_count(webpage, 'Views')
+        comment_count = extract_count(webpage, 'Comments')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'upload_date': upload_date,
+            'uploader': uploader,
+            'location': location,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'formats': formats
+        }

youtube_dl/extractor/planetaplay.py

@@ -18,7 +18,8 @@ class PlanetaPlayIE(InfoExtractor):
             'id': '3586',
             'ext': 'flv',
             'title': 'md5:e829428ee28b1deed00de90de49d1da1',
-        }
+        },
+        'skip': 'Not accessible from Travis CI server',
     }
 
     _SONG_FORMATS = {

youtube_dl/extractor/porn91.py

@@ -0,0 +1,71 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from ..compat import compat_urllib_parse
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    ExtractorError,
+)
+
+
+class Porn91IE(InfoExtractor):
+    IE_NAME = '91porn'
+    _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
+
+    _TEST = {
+        'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
+        'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
+        'info_dict': {
+            'id': '7e42283b4f5ab36da134',
+            'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
+            'ext': 'mp4',
+            'duration': 431,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
+        self._set_cookie('91porn.com', 'language', 'cn_CN')
+        webpage = self._download_webpage(url, video_id, 'get HTML content')
+
+        if '作为游客，你每天只可观看10个视频' in webpage:
+            raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True)
+
+        title = self._search_regex(
+            r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
+        title = title.replace('\n', '')
+
+        # get real url
+        file_id = self._search_regex(
+            r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
+        sec_code = self._search_regex(
+            r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
+        max_vid = self._search_regex(
+            r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
+        url_params = compat_urllib_parse.urlencode({
+            'VID': file_id,
+            'mp4': '1',
+            'seccode': sec_code,
+            'max_vid': max_vid,
+        })
+        info_cn = self._download_webpage(
+            'http://91porn.com/getfile.php?' + url_params, video_id,
+            'get real video url')
+        video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url')
+
+        duration = parse_duration(self._search_regex(
+            r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
+
+        comment_count = int_or_none(self._search_regex(
+            r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'duration': duration,
+            'comment_count': comment_count,
+        }

youtube_dl/extractor/pornhub.py

@@ -19,8 +19,8 @@ from ..aes import (
 
 
 class PornHubIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
+    _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {
@@ -30,7 +30,17 @@ class PornHubIE(InfoExtractor):
             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }
-    }
+    }, {
+        'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_url(cls, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
 
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(
@@ -39,7 +49,8 @@ class PornHubIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        req = compat_urllib_request.Request(url)
+        req = compat_urllib_request.Request(
+            'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
@@ -71,7 +82,8 @@ class PornHubIE(InfoExtractor):
 
         video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
         if webpage.find('"encrypted":true') != -1:
-            password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
+            password = compat_urllib_parse.unquote_plus(
+                self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
         formats = []

youtube_dl/extractor/pornovoisines.py

@@ -34,7 +34,7 @@ class PornoVoisinesIE(InfoExtractor):
             'duration': 120,
             'view_count': int,
             'average_rating': float,
-            'categories': ['Débutante', 'Scénario', 'Sodomie'],
+            'categories': ['Débutantes', 'Scénario', 'Sodomie'],
             'age_limit': 18,
         }
     }
@@ -71,7 +71,7 @@ class PornoVoisinesIE(InfoExtractor):
         view_count = int_or_none(self._search_regex(
             r'(\d+) vues', webpage, 'view count', fatal=False))
         average_rating = self._search_regex(
-            r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
+            r'Note\s*:\s*(\d+(?:,\d+)?)', webpage, 'average rating', fatal=False)
         if average_rating:
             average_rating = float_or_none(average_rating.replace(',', '.'))
 

youtube_dl/extractor/prosiebensat1.py

@@ -17,7 +17,7 @@ from ..utils import (
 class ProSiebenSat1IE(InfoExtractor):
     IE_NAME = 'prosiebensat1'
     IE_DESC = 'ProSiebenSat.1 Digital'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)'
 
     _TESTS = [
         {
@@ -177,6 +177,7 @@ class ProSiebenSat1IE(InfoExtractor):
         r'<header class="clearfix">\s*<h3>(.+?)</h3>',
         r'<!-- start video -->\s*<h1>(.+?)</h1>',
         r'<h1 class="att-name">\s*(.+?)</h1>',
+        r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
     ]
     _DESCRIPTION_REGEXES = [
         r'<p itemprop="description">\s*(.+?)</p>',
@@ -206,8 +207,8 @@ class ProSiebenSat1IE(InfoExtractor):
     def _extract_clip(self, url, webpage):
         clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
 
-        access_token = 'testclient'
-        client_name = 'kolibri-1.2.5'
+        access_token = 'prosieben'
+        client_name = 'kolibri-1.12.6'
         client_location = url
 
         videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({
@@ -275,13 +276,17 @@ class ProSiebenSat1IE(InfoExtractor):
         for source in urls_sources:
             protocol = source['protocol']
             if protocol == 'rtmp' or protocol == 'rtmpe':
-                mobj = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', source['url'])
+                mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source['url'])
                 if not mobj:
                     continue
+                path = mobj.group('path')
+                mp4colon_index = path.rfind('mp4:')
+                app = path[:mp4colon_index]
+                play_path = path[mp4colon_index:]
                 formats.append({
-                    'url': mobj.group('url'),
-                    'app': mobj.group('app'),
-                    'play_path': mobj.group('playpath'),
+                    'url': '%s/%s' % (mobj.group('url'), app),
+                    'app': app,
+                    'play_path': play_path,
                     'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
                     'page_url': 'http://www.prosieben.de',
                     'vbr': fix_bitrate(source['bitrate']),

youtube_dl/extractor/qqmusic.py

@@ -9,25 +9,47 @@ from .common import InfoExtractor
 from ..utils import (
     strip_jsonp,
     unescapeHTML,
+    clean_html,
 )
 from ..compat import compat_urllib_request
 
 
 class QQMusicIE(InfoExtractor):
+    IE_NAME = 'qqmusic'
     _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
-        'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
+        'md5': '9ce1c1c8445f561506d2e3cfb0255705',
         'info_dict': {
             'id': '004295Et37taLD',
-            'ext': 'm4a',
+            'ext': 'mp3',
             'title': '可惜没如果',
             'upload_date': '20141227',
             'creator': '林俊杰',
-            'description': 'md5:4348ff1dd24036906baa7b6f973f8d30',
+            'description': 'md5:d327722d0361576fde558f1ac68a7065',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'note': 'There is no mp3-320 version of this song.',
+        'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
+        'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
+        'info_dict': {
+            'id': '004MsGEo3DdNxV',
+            'ext': 'mp3',
+            'title': '如果',
+            'upload_date': '20050626',
+            'creator': '李季美',
+            'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }]
 
+    _FORMATS = {
+        'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
+        'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
+        'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10}
+    }
+
     # Reference: m_r_GetRUin() in top_player.js
     # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
     @staticmethod
@@ -58,6 +80,16 @@ class QQMusicIE(InfoExtractor):
         lrc_content = self._html_search_regex(
             r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
             detail_info_page, 'LRC lyrics', default=None)
+        if lrc_content:
+            lrc_content = lrc_content.replace('\\n', '\n')
+
+        thumbnail_url = None
+        albummid = self._search_regex(
+            [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
+            detail_info_page, 'album mid', default=None)
+        if albummid:
+            thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \
+                            % (albummid[-2:-1], albummid[-1], albummid)
 
         guid = self.m_r_get_ruin()
 
@@ -65,15 +97,28 @@ class QQMusicIE(InfoExtractor):
             'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
             mid, note='Retrieve vkey', errnote='Unable to get vkey',
             transform_source=strip_jsonp)['key']
-        song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
+
+        formats = []
+        for format_id, details in self._FORMATS.items():
+            formats.append({
+                'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
+                       % (details['prefix'], mid, details['ext'], vkey, guid),
+                'format': format_id,
+                'format_id': format_id,
+                'preference': details['preference'],
+                'abr': details.get('abr'),
+            })
+        self._check_formats(formats, mid)
+        self._sort_formats(formats)
 
         return {
             'id': mid,
-            'url': song_url,
+            'formats': formats,
             'title': song_name,
             'upload_date': publish_time,
             'creator': singer,
             'description': lrc_content,
+            'thumbnail': thumbnail_url,
         }
 
 
@@ -96,6 +141,7 @@ class QQPlaylistBaseIE(InfoExtractor):
 
 
 class QQMusicSingerIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:singer'
     _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
@@ -139,32 +185,128 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
 
 
 class QQMusicAlbumIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:album'
     _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
 
-    _TEST = {
-        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
+    _TESTS = [{
+        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
         'info_dict': {
             'id': '000gXCTb2AhRR1',
             'title': '我们都是这样长大的',
-            'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
+            'description': 'md5:179c5dce203a5931970d306aa9607ea6',
         },
         'playlist_count': 4,
-    }
+    }, {
+        'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
+        'info_dict': {
+            'id': '002Y5a3b3AlCu3',
+            'title': '그리고...',
+            'description': 'md5:a48823755615508a95080e81b51ba729',
+        },
+        'playlist_count': 8,
+    }]
 
     def _real_extract(self, url):
         mid = self._match_id(url)
 
-        album_page = self._download_webpage(
-            self.qq_static_url('album', mid), mid, 'Download album page')
+        album = self._download_json(
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
+            mid, 'Download album page')['data']
 
-        entries = self.get_entries_from_page(album_page)
-
-        album_name = self._html_search_regex(
-            r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
-            default=None)
-
-        album_detail = self._html_search_regex(
-            r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
-            album_page, 'album details', default=None)
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            ) for song in album['list']
+        ]
+        album_name = album.get('name')
+        album_detail = album.get('desc')
+        if album_detail is not None:
+            album_detail = album_detail.strip()
 
         return self.playlist_result(entries, mid, album_name, album_detail)
+
+
+class QQMusicToplistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:toplist'
+    _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
+
+    _TESTS = [{
+        'url': 'http://y.qq.com/#type=toplist&p=global_123',
+        'info_dict': {
+            'id': 'global_123',
+            'title': '美国iTunes榜',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'http://y.qq.com/#type=toplist&p=top_3',
+        'info_dict': {
+            'id': 'top_3',
+            'title': 'QQ音乐巅峰榜·欧美',
+            'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成，集结当下最流行的欧美新歌！:更新时间：每周四22点|统'
+                           '计周期：一周（上周四至本周三）|统计对象：三个月内发行的欧美歌曲|统计数量：100首|统计算法：根据'
+                           '歌曲在一周内的有效播放次数，由高到低取前100名（同一歌手最多允许5首歌曲同时上榜）|有效播放次数：'
+                           '登录用户完整播放一首歌曲，记为一次有效播放；同一用户收听同一首歌曲，每天记录为1次有效播放'
+        },
+        'playlist_count': 100,
+    }, {
+        'url': 'http://y.qq.com/#type=toplist&p=global_106',
+        'info_dict': {
+            'id': 'global_106',
+            'title': '韩国Mnet榜',
+        },
+        'playlist_count': 50,
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        list_type, num_id = list_id.split("_")
+
+        toplist_json = self._download_json(
+            'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json'
+            % (list_type, num_id),
+            list_id, 'Download toplist page')
+
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
+            ) for song in toplist_json['songlist']
+        ]
+
+        topinfo = toplist_json.get('topinfo', {})
+        list_name = topinfo.get('ListName')
+        list_description = topinfo.get('info')
+        return self.playlist_result(entries, list_id, list_name, list_description)
+
+
+class QQMusicPlaylistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:playlist'
+    _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://y.qq.com/#type=taoge&id=3462654915',
+        'info_dict': {
+            'id': '3462654915',
+            'title': '韩国5月新歌精选下旬',
+            'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
+        },
+        'playlist_count': 40,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        list_json = self._download_json(
+            'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
+            % list_id, list_id, 'Download list page',
+            transform_source=strip_jsonp)['cdlist'][0]
+
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+            ) for song in list_json['songlist']
+        ]
+
+        list_name = list_json.get('dissname')
+        list_description = clean_html(unescapeHTML(list_json.get('desc')))
+        return self.playlist_result(entries, list_id, list_name, list_description)

youtube_dl/extractor/quickvid.py

@@ -24,6 +24,7 @@ class QuickVidIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
             'view_count': int,
         },
+        'skip': 'Not accessible from Travis CI server',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/rtbf.py

@@ -1,10 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)
 
 
 class RTBFIE(InfoExtractor):
@@ -16,34 +17,47 @@ class RTBFIE(InfoExtractor):
             'id': '1921274',
             'ext': 'mp4',
             'title': 'Les Diables au coeur (épisode 2)',
-            'description': 'Football - Diables Rouges',
             'duration': 3099,
-            'timestamp': 1398456336,
-            'upload_date': '20140425',
         }
     }
 
+    _QUALITIES = [
+        ('mobile', 'mobile'),
+        ('web', 'SD'),
+        ('url', 'MD'),
+        ('high', 'HD'),
+    ]
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
+        webpage = self._download_webpage(
+            'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
 
-        data = json.loads(self._html_search_regex(
-            r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data']
+        data = self._parse_json(
+            unescapeHTML(self._search_regex(
+                r'data-video="([^"]+)"', webpage, 'data video')),
+            video_id)
 
-        video_url = data.get('downloadUrl') or data.get('url')
-
-        if data['provider'].lower() == 'youtube':
+        if data.get('provider').lower() == 'youtube':
+            video_url = data.get('downloadUrl') or data.get('url')
             return self.url_result(video_url, 'Youtube')
+        formats = []
+        for key, format_id in self._QUALITIES:
+            format_url = data['sources'].get(key)
+            if format_url:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                })
 
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': data['title'],
             'description': data.get('description') or data.get('subtitle'),
-            'thumbnail': data['thumbnail']['large'],
+            'thumbnail': data.get('thumbnail'),
             'duration': data.get('duration') or data.get('realDuration'),
-            'timestamp': data['created'],
-            'view_count': data['viewCount'],
+            'timestamp': int_or_none(data.get('created')),
+            'view_count': int_or_none(data.get('viewCount')),
         }

youtube_dl/extractor/rtlnl.py

@@ -12,10 +12,10 @@ class RtlNlIE(InfoExtractor):
     IE_NAME = 'rtl.nl'
     IE_DESC = 'rtl.nl and rtlxl.nl'
     _VALID_URL = r'''(?x)
-        https?://(www\.)?
+        https?://(?:www\.)?
         (?:
             rtlxl\.nl/\#!/[^/]+/|
-            rtl\.nl/system/videoplayer/[^?#]+?/video_embed\.html\#uuid=
+            rtl\.nl/system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html\b.+?\buuid=
         )
         (?P<id>[0-9a-f-]+)'''
 
@@ -43,12 +43,19 @@ class RtlNlIE(InfoExtractor):
             'upload_date': '20150215',
             'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
         }
+    }, {
+        # encrypted m3u8 streams, georestricted
+        'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         uuid = self._match_id(url)
         info = self._download_json(
-            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
+            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
             uuid)
 
         material = info['material'][0]
@@ -56,9 +63,14 @@ class RtlNlIE(InfoExtractor):
         subtitle = material['title'] or info['episodes'][0]['name']
         description = material.get('synopsis') or info['episodes'][0]['synopsis']
 
+        meta = info.get('meta', {})
+
         # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
-        videopath = material['videopath'].replace('.f4m', '.m3u8')
-        m3u8_url = 'http://manifest.us.rtl.nl' + videopath
+        # NB: nowadays, recent ffmpeg and avconv can handle these encrypted streams, so
+        # this adaptive -> flash workaround is not required in general, but it also
+        # allows bypassing georestriction therefore is retained for now.
+        videopath = material['videopath'].replace('/adaptive/', '/flash/')
+        m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
 
         formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
 
@@ -79,7 +91,7 @@ class RtlNlIE(InfoExtractor):
         self._sort_formats(formats)
 
         thumbnails = []
-        meta = info.get('meta', {})
+
         for p in ('poster_base_url', '"thumb_base_url"'):
             if not meta.get(p):
                 continue

youtube_dl/extractor/rtlnow.py

@@ -1,174 +0,0 @@
-# encoding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    clean_html,
-    unified_strdate,
-    int_or_none,
-)
-
-
-class RTLnowIE(InfoExtractor):
-    """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
-    _VALID_URL = r'''(?x)
-                        (?:https?://)?
-                        (?P<url>
-                            (?P<domain>
-                                rtl-now\.rtl\.de|
-                                rtl2now\.rtl2\.de|
-                                (?:www\.)?voxnow\.de|
-                                (?:www\.)?rtlnitronow\.de|
-                                (?:www\.)?superrtlnow\.de|
-                                (?:www\.)?n-tvnow\.de)
-                            /+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?
-                            (?:container_id|film_id)=(?P<video_id>[0-9]+)&
-                            player=1(?:&season=[0-9]+)?(?:&.*)?
-                        )'''
-
-    _TESTS = [
-        {
-            'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
-            'info_dict': {
-                'id': '90419',
-                'ext': 'flv',
-                'title': 'Ahornallee - Folge 1 - Der Einzug',
-                'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de',
-                'upload_date': '20070416',
-                'duration': 1685,
-            },
-            'params': {
-                'skip_download': True,
-            },
-            'skip': 'Only works from Germany',
-        },
-        {
-            'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
-            'info_dict': {
-                'id': '69756',
-                'ext': 'flv',
-                'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
-                'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0',
-                'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
-                'upload_date': '20120519',
-                'duration': 1245,
-            },
-            'params': {
-                'skip_download': True,
-            },
-            'skip': 'Only works from Germany',
-        },
-        {
-            'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
-            'info_dict': {
-                'id': '13883',
-                'ext': 'flv',
-                'title': 'Voxtours - Südafrika-Reporter II',
-                'description': 'md5:de7f8d56be6fd4fed10f10f57786db00',
-                'upload_date': '20090627',
-                'duration': 1800,
-            },
-            'params': {
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
-            'info_dict': {
-                'id': '99205',
-                'ext': 'flv',
-                'title': 'Medicopter 117 - Angst!',
-                'description': 're:^Im Therapiezentrum \'Sonnalm\' kommen durch eine Unachtsamkeit die für die B.handlung mit Phobikern gehaltenen Voglespinnen frei\. Eine Ausreißerin',
-                'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg',
-                'upload_date': '20080928',
-                'duration': 2691,
-            },
-            'params': {
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://rtl-now.rtl.de/der-bachelor/folge-4.php?film_id=188729&player=1&season=5',
-            'info_dict': {
-                'id': '188729',
-                'ext': 'flv',
-                'upload_date': '20150204',
-                'description': 'md5:5e1ce23095e61a79c166d134b683cecc',
-                'title': 'Der Bachelor - Folge 4',
-            }
-        }, {
-            'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0',
-            'only_matching': True,
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_page_url = 'http://%s/' % mobj.group('domain')
-        video_id = mobj.group('video_id')
-
-        webpage = self._download_webpage('http://' + mobj.group('url'), video_id)
-
-        mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage)
-        if mobj:
-            raise ExtractorError(clean_html(mobj.group(1)), expected=True)
-
-        title = self._og_search_title(webpage)
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(webpage, default=None)
-
-        upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date'))
-
-        mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage)
-        duration = int(mobj.group('seconds')) if mobj else None
-
-        playerdata_url = self._html_search_regex(
-            r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url')
-
-        playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML')
-
-        videoinfo = playerdata.find('./playlist/videoinfo')
-
-        formats = []
-        for filename in videoinfo.findall('filename'):
-            mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text)
-            if mobj:
-                fmt = {
-                    'url': mobj.group('url'),
-                    'play_path': 'mp4:' + mobj.group('play_path'),
-                    'page_url': video_page_url,
-                    'player_url': video_page_url + 'includes/vodplayer.swf',
-                }
-            else:
-                mobj = re.search(r'.*/(?P<hoster>[^/]+)/videos/(?P<play_path>.+)\.f4m', filename.text)
-                if mobj:
-                    fmt = {
-                        'url': 'rtmpe://fms.rtl.de/' + mobj.group('hoster'),
-                        'play_path': 'mp4:' + mobj.group('play_path'),
-                        'page_url': url,
-                        'player_url': video_page_url + 'includes/vodplayer.swf',
-                    }
-                else:
-                    fmt = {
-                        'url': filename.text,
-                    }
-            fmt.update({
-                'width': int_or_none(filename.get('width')),
-                'height': int_or_none(filename.get('height')),
-                'vbr': int_or_none(filename.get('bitrate')),
-                'ext': 'flv',
-            })
-            formats.append(fmt)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-            'duration': duration,
-            'formats': formats,
-        }

youtube_dl/extractor/rts.py

@@ -190,6 +190,7 @@ class RTSIE(InfoExtractor):
                 'tbr': media['rate'] or extract_bitrate(media['url']),
             } for media in info['media'] if media.get('rate')])
 
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/rtve.py

@@ -17,7 +17,7 @@ from ..utils import (
 
 
 def _decrypt_url(png):
-    encrypted_data = base64.b64decode(png)
+    encrypted_data = base64.b64decode(png.encode('utf-8'))
     text_index = encrypted_data.find(b'tEXt')
     text_chunk = encrypted_data[text_index - 4:]
     length = struct_unpack('!I', text_chunk[:4])[0]

youtube_dl/extractor/rutv.py

@@ -104,7 +104,7 @@ class RUTVIE(InfoExtractor):
     @classmethod
     def _extract_url(cls, webpage):
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
         if mobj:
             return mobj.group('url')
 

youtube_dl/extractor/ruutu.py

@@ -0,0 +1,119 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    xpath_text,
+)
+
+
+class RuutuIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
+    _TESTS = [
+        {
+            'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
+            'md5': 'ab2093f39be1ca8581963451b3c0234f',
+            'info_dict': {
+                'id': '2058907',
+                'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
+                'ext': 'mp4',
+                'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
+                'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 114,
+                'age_limit': 0,
+            },
+        },
+        {
+            'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa',
+            'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
+            'info_dict': {
+                'id': '2057306',
+                'display_id': 'superpesis-katso-koko-kausi-ruudussa',
+                'ext': 'mp4',
+                'title': 'Superpesis: katso koko kausi Ruudussa',
+                'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'duration': 40,
+                'age_limit': 0,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'data-media-id="(\d+)"', webpage, 'media id')
+
+        video_xml_url = None
+
+        media_data = self._search_regex(
+            r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage,
+            'media data', default=None)
+        if media_data:
+            media_json = self._parse_json(media_data, display_id, fatal=False)
+            if media_json:
+                xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl')
+                if xml_url:
+                    video_xml_url = xml_url.replace('{ID}', video_id)
+
+        if not video_xml_url:
+            video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id
+
+        video_xml = self._download_xml(video_xml_url, video_id)
+
+        formats = []
+        processed_urls = []
+
+        def extract_formats(node):
+            for child in node:
+                if child.tag.endswith('Files'):
+                    extract_formats(child)
+                elif child.tag.endswith('File'):
+                    video_url = child.text
+                    if not video_url or video_url in processed_urls or 'NOT_USED' in video_url:
+                        return
+                    processed_urls.append(video_url)
+                    ext = determine_ext(video_url)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4', m3u8_id='hls'))
+                    elif ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            video_url, video_id, f4m_id='hds'))
+                    else:
+                        proto = compat_urllib_parse_urlparse(video_url).scheme
+                        if not child.tag.startswith('HTTP') and proto != 'rtmp':
+                            continue
+                        preference = -1 if proto == 'rtmp' else 1
+                        label = child.get('label')
+                        tbr = int_or_none(child.get('bitrate'))
+                        width, height = [int_or_none(x) for x in child.get('resolution', '').split('x')]
+                        formats.append({
+                            'format_id': '%s-%s' % (proto, label if label else tbr),
+                            'url': video_url,
+                            'width': width,
+                            'height': height,
+                            'tbr': tbr,
+                            'preference': preference,
+                        })
+
+        extract_formats(video_xml.find('./Clip'))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
+            'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
+            'formats': formats,
+        }

youtube_dl/extractor/safari.py

@@ -83,7 +83,7 @@ class SafariIE(SafariBaseIE):
                                     library/view/[^/]+|
                                     api/v1/book
                                 )/
-                                (?P<course_id>\d+)/
+                                (?P<course_id>[^/]+)/
                                     (?:chapter(?:-content)?/)?
                                 (?P<part>part\d+)\.html
     '''
@@ -100,6 +100,10 @@ class SafariIE(SafariBaseIE):
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
         'only_matching': True,
+    }, {
+        # non-digits in course id
+        'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -122,7 +126,7 @@ class SafariCourseIE(SafariBaseIE):
     IE_NAME = 'safari:course'
     IE_DESC = 'safaribooksonline.com online courses'
 
-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',