release 2015.07.07

Python 2.x does not work without it.

AUTHORS

@@ -126,3 +126,7 @@ Matthias Küch
 Julian Richen
 Ping O.
 Mister Hat
+Peter Ding
+jackyzy823
+George Brighton
+Remita Amine

README.md

@@ -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:
@@ -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:
@@ -223,7 +224,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      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**
@@ -109,6 +111,7 @@
  - **dailymotion**
  - **dailymotion:playlist**
  - **dailymotion:user**
+ - **DailymotionCloud**
  - **daum.net**
  - **DBTV**
  - **DctpTv**
@@ -119,6 +122,8 @@
  - **divxstage**: DivxStage
  - **Dotsub**
  - **DouyuTV**
+ - **dramafever**
+ - **dramafever:series**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
@@ -152,6 +157,7 @@
  - **fernsehkritik.tv**
  - **fernsehkritik.tv:postecke**
  - **Firstpost**
+ - **FiveTV**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
@@ -216,6 +222,7 @@
  - **instagram:user**: Instagram user profile
  - **InternetVideoArchive**
  - **IPrima**
+ - **iqiyi**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **Izlesene**
@@ -276,6 +283,7 @@
  - **Motherless**
  - **Motorsport**: motorsport.com
  - **MovieClips**
+ - **MovieFap**
  - **Moviezine**
  - **movshare**: MovShare
  - **MPORA**
@@ -319,6 +327,7 @@
  - **Noco**
  - **Normalboots**
  - **NosVideo**
+ - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
  - **novamov**: NovaMov
  - **Nowness**
  - **NowTV**
@@ -338,6 +347,7 @@
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
+ - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
  - **OpenFilm**
@@ -351,6 +361,7 @@
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
  - **Photobucket**
+ - **Pinkbike**
  - **Pladform**
  - **PlanetaPlay**
  - **play.fm**
@@ -373,6 +384,7 @@
  - **Pyvideo**
  - **qqmusic**
  - **qqmusic:album**
+ - **qqmusic:playlist**
  - **qqmusic:singer**
  - **qqmusic:toplist**
  - **QuickVid**
@@ -405,6 +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
@@ -429,8 +442,12 @@
  - **smotri:broadcast**: Smotri.com broadcasts
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
+ - **SnagFilms**
+ - **SnagFilmsEmbed**
  - **Snotr**
  - **Sohu**
+ - **soompi**
+ - **soompi:show**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:set**
@@ -489,6 +506,7 @@
  - **TheOnion**
  - **ThePlatform**
  - **TheSixtyOne**
+ - **ThisAmericanLife**
  - **ThisAV**
  - **THVideo**
  - **THVideoPlaylist**
@@ -505,6 +523,7 @@
  - **Trilulilu**
  - **TruTube**
  - **Tube8**
+ - **TubiTv**
  - **Tudou**
  - **Tumblr**
  - **TuneIn**
@@ -514,6 +533,8 @@
  - **TV2**
  - **TV2Article**
  - **TV4**: tv4.se and tv4play.se
+ - **TVC**
+ - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
  - **tvp.pl:Series**
@@ -526,6 +547,7 @@
  - **twitch:stream**
  - **twitch:video**
  - **twitch:vod**
+ - **TwitterCard**
  - **Ubu**
  - **udemy**
  - **udemy:course**
@@ -600,6 +622,7 @@
  - **XBef**
  - **XboxClips**
  - **XHamster**
+ - **XHamsterEmbed**
  - **XMinus**
  - **XNXX**
  - **Xstream**
@@ -616,7 +639,7 @@
  - **YesJapan**
  - **Ynet**
  - **YouJizz**
- - **Youku**
+ - **youku**
  - **YouPorn**
  - **YourUpload**
  - **youtube**: YouTube.com

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)
 

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.
@@ -625,13 +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:
@@ -923,8 +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 = [
@@ -1002,7 +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
@@ -1014,13 +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:
@@ -1031,12 +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
@@ -1047,6 +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:
@@ -1054,6 +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'],
@@ -1483,7 +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:
@@ -1706,7 +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)
 

youtube_dl/__init__.py

@@ -293,6 +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,

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
@@ -136,7 +144,6 @@ 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
@@ -152,6 +159,7 @@ from .fc2 import FC2IE
 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
@@ -352,6 +361,7 @@ 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
@@ -377,6 +387,7 @@ from .nytimes import (
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
+from .onionstudios import OnionStudiosIE
 from .ooyala import (
     OoyalaIE,
     OoyalaExternalIE,
@@ -394,6 +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
@@ -401,6 +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,
@@ -419,6 +432,7 @@ from .qqmusic import (
     QQMusicSingerIE,
     QQMusicAlbumIE,
     QQMusicToplistIE,
+    QQMusicPlaylistIE,
 )
 from .quickvid import QuickVidIE
 from .r7 import R7IE
@@ -451,6 +465,7 @@ from .rutube import (
     RutubePersonIE,
 )
 from .rutv import RUTVIE
+from .ruutu import RuutuIE
 from .sandia import SandiaIE
 from .safari import (
     SafariIE,
@@ -478,8 +493,16 @@ from .smotri import (
     SmotriUserIE,
     SmotriBroadcastIE,
 )
+from .snagfilms import (
+    SnagFilmsIE,
+    SnagFilmsEmbedIE,
+)
 from .snotr import SnotrIE
 from .sohu import SohuIE
+from .soompi import (
+    SoompiIE,
+    SoompiShowIE,
+)
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
@@ -547,6 +570,7 @@ 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
@@ -554,7 +578,11 @@ from .tmz import (
     TMZIE,
     TMZArticleIE,
 )
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE
@@ -565,6 +593,7 @@ 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
@@ -575,6 +604,10 @@ from .tv2 import (
     TV2ArticleIE,
 )
 from .tv4 import TV4IE
+from .tvc import (
+    TVCIE,
+    TVCArticleIE,
+)
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
 from .tvplay import TVPlayIE
@@ -593,6 +626,7 @@ from .twitch import (
     TwitchBookmarksIE,
     TwitchStreamIE,
 )
+from .twitter import TwitterCardIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -678,7 +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/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

@@ -105,7 +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/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/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/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.
         """
@@ -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(

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

@@ -251,3 +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/empflix.py

@@ -1,31 +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>.+?)-(?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\("([^"]+)"'
-
-    _TESTS = [
-        {
-            '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,
-            }
-        },
-        {
-            'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
-            'matching_only': True,
-        }
-    ]

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/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/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,
 )
@@ -32,6 +34,7 @@ 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
@@ -39,6 +42,12 @@ 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):
@@ -46,6 +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',
@@ -125,17 +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',
@@ -160,22 +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/',
@@ -225,6 +298,15 @@ 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',
@@ -256,6 +338,15 @@ class GenericIE(InfoExtractor):
                 '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/',
@@ -407,16 +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
         {
@@ -470,21 +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/',
@@ -516,21 +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/',
@@ -618,6 +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/',
@@ -689,16 +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',
@@ -773,6 +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,
+            },
         }
     ]
 
@@ -894,7 +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)
 
@@ -916,7 +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
@@ -927,7 +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'),
@@ -938,10 +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!
@@ -953,7 +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,
@@ -1033,23 +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)
@@ -1261,11 +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)
@@ -1369,8 +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')
 
@@ -1427,6 +1562,30 @@ class GenericIE(InfoExtractor):
         if senate_isvp_url:
             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):
                 return True

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

@@ -3,7 +3,10 @@ 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):
@@ -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/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/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)
 

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/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/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/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

@@ -13,7 +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 = [
         {
@@ -76,7 +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',
@@ -116,11 +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',
@@ -132,7 +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',
@@ -145,7 +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',
@@ -157,7 +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',

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/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)
 

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

@@ -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

@@ -9,7 +9,7 @@ from .common import InfoExtractor
 from ..utils import (
     strip_jsonp,
     unescapeHTML,
-    js_to_json,
+    clean_html,
 )
 from ..compat import compat_urllib_request
 
@@ -19,17 +19,37 @@ class QQMusicIE(InfoExtractor):
     _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: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
@@ -63,21 +83,42 @@ class QQMusicIE(InfoExtractor):
         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()
 
         vkey = self._download_json(
             '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,
         }
 
 
@@ -147,31 +188,40 @@ 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)
 
@@ -181,60 +231,82 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
     _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_12',
+        'url': 'http://y.qq.com/#type=toplist&p=global_123',
         'info_dict': {
-            'id': 'global_12',
-            'title': 'itunes榜',
+            'id': 'global_123',
+            'title': '美国iTunes榜',
         },
         'playlist_count': 10,
     }, {
-        'url': 'http://y.qq.com/#type=toplist&p=top_6',
+        'url': 'http://y.qq.com/#type=toplist&p=top_3',
         'info_dict': {
-            'id': 'top_6',
+            '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_5',
+        'url': 'http://y.qq.com/#type=toplist&p=global_106',
         'info_dict': {
-            'id': 'global_5',
-            'title': '韩国mnet排行榜',
+            'id': 'global_106',
+            'title': '韩国Mnet榜',
         },
         'playlist_count': 50,
     }]
 
-    @staticmethod
-    def strip_qq_jsonp(code):
-        return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code))
-
     def _real_extract(self, url):
         list_id = self._match_id(url)
 
         list_type, num_id = list_id.split("_")
 
-        list_page = self._download_webpage(
-            "http://y.qq.com/y/static/toplist/index/%s.html" % list_id,
+        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 = []
-        if list_type == 'top':
-            jsonp_url = "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id
-        else:
-            jsonp_url = "http://y.qq.com/y/static/toplist/json/global/%s/1_1.js" % num_id
+        entries = [
+            self.url_result(
+                'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
+            ) for song in toplist_json['songlist']
+        ]
 
-        toplist_json = self._download_json(
-            jsonp_url, list_id, note='Retrieve toplist json',
-            errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp)
+        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)
 
-        for song in toplist_json['l']:
-            s = song['s']
-            song_mid = s.split("|")[20]
-            entries.append(self.url_result(
-                'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
-                song_mid))
 
-        list_name = self._html_search_regex(
-            r'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name',
-            default=None)
+class QQMusicPlaylistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:playlist'
+    _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
 
-        return self.playlist_result(entries, list_id, list_name)
+    _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

@@ -21,6 +21,13 @@ class RTBFIE(InfoExtractor):
         }
     }
 
+    _QUALITIES = [
+        ('mobile', 'mobile'),
+        ('web', 'SD'),
+        ('url', 'MD'),
+        ('high', 'HD'),
+    ]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
@@ -32,14 +39,21 @@ class RTBFIE(InfoExtractor):
                 r'data-video="([^"]+)"', webpage, 'data video')),
             video_id)
 
-        video_url = data.get('downloadUrl') or data.get('url')
-
         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.get('thumbnail'),

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/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/',

youtube_dl/extractor/smotri.py

@@ -53,7 +53,7 @@ class SmotriIE(InfoExtractor):
                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },
-        # video-password
+        # video-password, not approved by moderator
         {
             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
             'md5': 'f6331cef33cad65a0815ee482a54440b',
@@ -71,7 +71,24 @@ class SmotriIE(InfoExtractor):
             },
             'skip': 'Video is not approved by moderator',
         },
-        # age limit + video-password
+        # video-password
+        {
+            'url': 'http://smotri.com/video/view/?id=v6984858774#',
+            'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
+            'info_dict': {
+                'id': 'v6984858774',
+                'ext': 'mp4',
+                'title': 'Дача Солженицина ПАРОЛЬ 223322',
+                'uploader': 'psavari1',
+                'uploader_id': 'psavari1',
+                'upload_date': '20081103',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'videopassword': '223322',
+            },
+        },
+        # age limit + video-password, not approved by moderator
         {
             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
             'md5': '91e909c9f0521adf5ee86fbe073aad70',
@@ -90,19 +107,22 @@ class SmotriIE(InfoExtractor):
             },
             'skip': 'Video is not approved by moderator',
         },
-        # not approved by moderator, but available
+        # age limit + video-password
         {
-            'url': 'http://smotri.com/video/view/?id=v28888533b73',
-            'md5': 'f44bc7adac90af518ef1ecf04893bb34',
+            'url': 'http://smotri.com/video/view/?id=v7780025814',
+            'md5': 'b4599b068422559374a59300c5337d72',
             'info_dict': {
-                'id': 'v28888533b73',
+                'id': 'v7780025814',
                 'ext': 'mp4',
-                'title': 'Russian Spies Killed By ISIL Child Soldier',
-                'uploader': 'Mopeder',
-                'uploader_id': 'mopeder',
-                'duration': 71,
-                'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg',
-                'upload_date': '20150114',
+                'title': 'Sexy Beach (пароль 123)',
+                'uploader': 'вАся',
+                'uploader_id': 'asya_prosto',
+                'upload_date': '20081218',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'age_limit': 18,
+            },
+            'params': {
+                'videopassword': '123'
             },
         },
         # swf player
@@ -152,6 +172,10 @@ class SmotriIE(InfoExtractor):
             'getvideoinfo': '1',
         }
 
+        video_password = self._downloader.params.get('videopassword', None)
+        if video_password:
+            video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
+
         request = compat_urllib_request.Request(
             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
@@ -161,13 +185,18 @@ class SmotriIE(InfoExtractor):
         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 
         if not video_url:
-            if video.get('_moderate_no') or not video.get('moderated'):
+            if video.get('_moderate_no'):
                 raise ExtractorError(
                     'Video %s has not been approved by moderator' % video_id, expected=True)
 
             if video.get('error'):
                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
+            if video.get('_pass_protected') == 1:
+                msg = ('Invalid video password' if video_password
+                       else 'This video is protected by a password, use the --video-password option')
+                raise ExtractorError(msg, expected=True)
+
         title = video['title']
         thumbnail = video['_imgURL']
         upload_date = unified_strdate(video['added'])

youtube_dl/extractor/snagfilms.py

@@ -0,0 +1,171 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    parse_duration,
+)
+
+
+class SnagFilmsEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
+    _TESTS = [{
+        'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
+        'md5': '2924e9215c6eff7a55ed35b72276bd93',
+        'info_dict': {
+            'id': '74849a00-85a9-11e1-9660-123139220831',
+            'ext': 'mp4',
+            'title': '#whilewewatch',
+        }
+    }, {
+        'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        if '>This film is not playable in your area.<' in webpage:
+            raise ExtractorError(
+                'Film %s is not playable in your area.' % video_id, expected=True)
+
+        formats = []
+        for source in self._parse_json(js_to_json(self._search_regex(
+                r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
+            file_ = source.get('file')
+            if not file_:
+                continue
+            type_ = source.get('type')
+            format_id = source.get('label')
+            ext = determine_ext(file_)
+            if any(_ == 'm3u8' for _ in (type_, ext)):
+                formats.extend(self._extract_m3u8_formats(
+                    file_, video_id, 'mp4', m3u8_id='hls'))
+            else:
+                bitrate = int_or_none(self._search_regex(
+                    r'(\d+)kbps', file_, 'bitrate', default=None))
+                height = int_or_none(self._search_regex(
+                    r'^(\d+)[pP]$', format_id, 'height', default=None))
+                formats.append({
+                    'url': file_,
+                    'format_id': format_id,
+                    'tbr': bitrate,
+                    'height': height,
+                })
+        self._sort_formats(formats)
+
+        title = self._search_regex(
+            [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
+            webpage, 'title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }
+
+
+class SnagFilmsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'http://www.snagfilms.com/films/title/lost_for_life',
+        'md5': '19844f897b35af219773fd63bdec2942',
+        'info_dict': {
+            'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
+            'display_id': 'lost_for_life',
+            'ext': 'mp4',
+            'title': 'Lost for Life',
+            'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 4489,
+            'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
+        }
+    }, {
+        'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
+        'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
+        'info_dict': {
+            'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
+            'display_id': 'the_world_cut_project/india',
+            'ext': 'mp4',
+            'title': 'India',
+            'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 979,
+            'categories': ['Documentary', 'Sports', 'Politics']
+        }
+    }, {
+        # Film is not playable in your area.
+        'url': 'http://www.snagfilms.com/films/title/inside_mecca',
+        'only_matching': True,
+    }, {
+        # Film is not available.
+        'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        if ">Sorry, the Film you're looking for is not available.<" in webpage:
+            raise ExtractorError(
+                'Film %s is not available.' % display_id, expected=True)
+
+        film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
+
+        snag = self._parse_json(
+            self._search_regex(
+                'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
+            display_id)
+
+        for item in snag:
+            if item.get('data', {}).get('film', {}).get('id') == film_id:
+                data = item['data']['film']
+                title = data['title']
+                description = clean_html(data.get('synopsis'))
+                thumbnail = data.get('image')
+                duration = int_or_none(data.get('duration') or data.get('runtime'))
+                categories = [
+                    category['title'] for category in data.get('categories', [])
+                    if category.get('title')]
+                break
+        else:
+            title = self._search_regex(
+                r'itemprop="title">([^<]+)<', webpage, 'title')
+            description = self._html_search_regex(
+                r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
+                webpage, 'description', default=None) or self._og_search_description(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
+            duration = parse_duration(self._search_regex(
+                r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
+                webpage, 'duration', fatal=False))
+            categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
+            'id': film_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'categories': categories,
+        }

youtube_dl/extractor/sohu.py

@@ -6,9 +6,12 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
-    compat_urllib_request
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+from ..utils import (
+    ExtractorError,
 )
-from ..utils import ExtractorError
 
 
 class SohuIE(InfoExtractor):
@@ -26,7 +29,7 @@ class SohuIE(InfoExtractor):
         'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
-        'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a',
+        'md5': '699060e75cf58858dd47fb9c03c42cfb',
         'info_dict': {
             'id': '409385080',
             'ext': 'mp4',
@@ -34,7 +37,7 @@ class SohuIE(InfoExtractor):
         }
     }, {
         'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
-        'md5': '49308ff6dafde5ece51137d04aec311e',
+        'md5': '9bf34be48f2f4dadcb226c74127e203c',
         'info_dict': {
             'id': '78693464',
             'ext': 'mp4',
@@ -48,7 +51,7 @@ class SohuIE(InfoExtractor):
             'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{
-            'md5': '492923eac023ba2f13ff69617c32754a',
+            'md5': 'bdbfb8f39924725e6589c146bc1883ad',
             'info_dict': {
                 'id': '78910339_part1',
                 'ext': 'mp4',
@@ -56,7 +59,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
-            'md5': 'de604848c0e8e9c4a4dde7e1347c0637',
+            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
             'info_dict': {
                 'id': '78910339_part2',
                 'ext': 'mp4',
@@ -64,7 +67,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
-            'md5': '93584716ee0657c0b205b8aa3d27aa13',
+            'md5': '8407e634175fdac706766481b9443450',
             'info_dict': {
                 'id': '78910339_part3',
                 'ext': 'mp4',
@@ -139,21 +142,42 @@ class SohuIE(InfoExtractor):
         for i in range(part_count):
             formats = []
             for format_id, format_data in formats_json.items():
-                data = format_data['data']
+                allot = format_data['allot']
+
+                data = format_data['data']
+                clips_url = data['clipsURL']
+                su = data['su']
 
-                # URLs starts with http://newflv.sohu.ccgslb.net/ is not usable
-                # so retry until got a working URL
                 video_url = 'newflv.sohu.ccgslb.net'
+                cdnId = None
                 retries = 0
-                while 'newflv.sohu.ccgslb.net' in video_url and retries < 5:
-                    download_note = 'Download information from CDN gateway for format ' + format_id
+
+                while 'newflv.sohu.ccgslb.net' in video_url:
+                    params = {
+                        'prot': 9,
+                        'file': clips_url[i],
+                        'new': su[i],
+                        'prod': 'flash',
+                    }
+
+                    if cdnId is not None:
+                        params['idc'] = cdnId
+
+                    download_note = 'Downloading %s video URL part %d of %d' % (
+                        format_id, i + 1, part_count)
+
                     if retries > 0:
                         download_note += ' (retry #%d)' % retries
+                    part_info = self._parse_json(self._download_webpage(
+                        'http://%s/?%s' % (allot, compat_urllib_parse.urlencode(params)),
+                        video_id, download_note), video_id)
+
+                    video_url = part_info['url']
+                    cdnId = part_info.get('nid')
+
                     retries += 1
-                    cdn_info = self._download_json(
-                        'http://data.vod.itc.cn/cdnList?new=' + data['su'][i],
-                        video_id, download_note)
-                    video_url = cdn_info['url']
+                    if retries > 5:
+                        raise ExtractorError('Failed to get video URL')
 
                 formats.append({
                     'url': video_url,

youtube_dl/extractor/soompi.py

@@ -0,0 +1,146 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .crunchyroll import CrunchyrollIE
+
+from .common import InfoExtractor
+from ..compat import compat_HTTPError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    remove_start,
+    xpath_text,
+)
+
+
+class SoompiBaseIE(InfoExtractor):
+    def _get_episodes(self, webpage, episode_filter=None):
+        episodes = self._parse_json(
+            self._search_regex(
+                r'VIDEOS\s*=\s*(\[.+?\]);', webpage, 'episodes JSON'),
+            None)
+        return list(filter(episode_filter, episodes))
+
+
+class SoompiIE(SoompiBaseIE, CrunchyrollIE):
+    IE_NAME = 'soompi'
+    _VALID_URL = r'https?://tv\.soompi\.com/(?:en/)?watch/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://tv.soompi.com/en/watch/29235',
+        'info_dict': {
+            'id': '29235',
+            'ext': 'mp4',
+            'title': 'Episode 1096',
+            'description': '2015-05-20'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _get_episode(self, webpage, video_id):
+        return self._get_episodes(webpage, lambda x: x['id'] == video_id)[0]
+
+    def _get_subtitles(self, config, video_id):
+        sub_langs = {}
+        for subtitle in config.findall('./{default}preload/subtitles/subtitle'):
+            sub_langs[subtitle.attrib['id']] = subtitle.attrib['title']
+
+        subtitles = {}
+        for s in config.findall('./{default}preload/subtitle'):
+            lang_code = sub_langs.get(s.attrib['id'])
+            if not lang_code:
+                continue
+            sub_id = s.get('id')
+            data = xpath_text(s, './data', 'data')
+            iv = xpath_text(s, './iv', 'iv')
+            if not id or not iv or not data:
+                continue
+            subtitle = self._decrypt_subtitles(data, iv, sub_id).decode('utf-8')
+            subtitles[lang_code] = self._extract_subtitles(subtitle)
+        return subtitles
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        try:
+            webpage = self._download_webpage(
+                url, video_id, 'Downloading episode page')
+        except ExtractorError as ee:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
+                webpage = ee.cause.read()
+                block_message = self._html_search_regex(
+                    r'(?s)<div class="block-message">(.+?)</div>', webpage,
+                    'block message', default=None)
+                if block_message:
+                    raise ExtractorError(block_message, expected=True)
+            raise
+
+        formats = []
+        config = None
+        for format_id in re.findall(r'\?quality=([0-9a-zA-Z]+)', webpage):
+            config = self._download_xml(
+                'http://tv.soompi.com/en/show/_/%s-config.xml?mode=hls&quality=%s' % (video_id, format_id),
+                video_id, 'Downloading %s XML' % format_id)
+            m3u8_url = xpath_text(
+                config, './{default}preload/stream_info/file',
+                '%s m3u8 URL' % format_id)
+            if not m3u8_url:
+                continue
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', m3u8_id=format_id))
+        self._sort_formats(formats)
+
+        episode = self._get_episode(webpage, video_id)
+
+        title = episode['name']
+        description = episode.get('description')
+        duration = int_or_none(episode.get('duration'))
+
+        thumbnails = [{
+            'id': thumbnail_id,
+            'url': thumbnail_url,
+        } for thumbnail_id, thumbnail_url in episode.get('img_url', {}).items()]
+
+        subtitles = self.extract_subtitles(config, video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnails': thumbnails,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles
+        }
+
+
+class SoompiShowIE(SoompiBaseIE):
+    IE_NAME = 'soompi:show'
+    _VALID_URL = r'https?://tv\.soompi\.com/en/shows/(?P<id>[0-9a-zA-Z\-_]+)'
+    _TESTS = [{
+        'url': 'http://tv.soompi.com/en/shows/liar-game',
+        'info_dict': {
+            'id': 'liar-game',
+            'title': 'Liar Game',
+            'description': 'md5:52c02bce0c1a622a95823591d0589b66',
+        },
+        'playlist_count': 14,
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, show_id, 'Downloading show page')
+
+        title = remove_start(self._og_search_title(webpage), 'SoompiTV | ')
+        description = self._og_search_description(webpage)
+
+        entries = [
+            self.url_result('http://tv.soompi.com/en/watch/%s' % episode['id'], 'Soompi')
+            for episode in self._get_episodes(webpage)]
+
+        return self.playlist_result(entries, show_id, title, description)

youtube_dl/extractor/soundcloud.py

@@ -29,7 +29,7 @@ class SoundcloudIE(InfoExtractor):
     _VALID_URL = r'''(?x)^(?:https?://)?
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?P<uploader>[\w\d-]+)/
-                            (?!sets/|likes/?(?:$|[?#]))
+                            (?!sets/|(?:likes|tracks)/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
@@ -307,6 +307,9 @@ class SoundcloudUserIE(SoundcloudIE):
             'title': 'The Royal Concept',
         },
         'playlist_mincount': 1,
+    }, {
+        'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/spankwire.py

@@ -27,7 +27,7 @@ class SpankwireIE(InfoExtractor):
             'description': 'Crazy Bitch X rated music video.',
             'uploader': 'oreusz',
             'uploader_id': '124697',
-            'upload_date': '20070508',
+            'upload_date': '20070507',
             'age_limit': 18,
         }
     }
@@ -44,7 +44,7 @@ class SpankwireIE(InfoExtractor):
         title = self._html_search_regex(
             r'<h1>([^<]+)', webpage, 'title')
         description = self._html_search_regex(
-            r'<div\s+id="descriptionContent">([^<]+)<',
+            r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
             webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
@@ -64,12 +64,12 @@ class SpankwireIE(InfoExtractor):
             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
             webpage, 'view count', fatal=False))
         comment_count = str_to_int(self._html_search_regex(
-            r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>',
+            r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
             webpage, 'comment count', fatal=False))
 
         video_urls = list(map(
             compat_urllib_parse.unquote,
-            re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))
+            re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)))
         if webpage.find('flashvars\.encrypted = "true"') != -1:
             password = self._search_regex(
                 r'flashvars\.video_title = "([^"]+)',

youtube_dl/extractor/spiegeltv.py

@@ -2,7 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import (
+    determine_ext,
+    float_or_none,
+)
 
 
 class SpiegeltvIE(InfoExtractor):
@@ -17,7 +21,7 @@ class SpiegeltvIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg$',
         },
         'params': {
-            # rtmp download
+            # m3u8 download
             'skip_download': True,
         }
     }, {
@@ -51,9 +55,39 @@ class SpiegeltvIE(InfoExtractor):
         is_wide = media_json['is_wide']
 
         server_json = self._download_json(
-            'http://www.spiegel.tv/streaming_servers/', video_id,
-            note='Downloading server information')
-        server = server_json[0]['endpoint']
+            'http://spiegeltv-prod-static.s3.amazonaws.com/projectConfigs/projectConfig.json',
+            video_id, note='Downloading server information')
+
+        format = '16x9' if is_wide else '4x3'
+
+        formats = []
+        for streamingserver in server_json['streamingserver']:
+            endpoint = streamingserver.get('endpoint')
+            if not endpoint:
+                continue
+            play_path = 'mp4:%s_spiegeltv_0500_%s.m4v' % (uuid, format)
+            if endpoint.startswith('rtmp'):
+                formats.append({
+                    'url': endpoint,
+                    'format_id': 'rtmp',
+                    'app': compat_urllib_parse_urlparse(endpoint).path[1:],
+                    'play_path': play_path,
+                    'player_path': 'http://prod-static.spiegel.tv/frontend-076.swf',
+                    'ext': 'flv',
+                    'rtmp_live': True,
+                })
+            elif determine_ext(endpoint) == 'm3u8':
+                m3u8_formats = self._extract_m3u8_formats(
+                    endpoint.replace('[video]', play_path),
+                    video_id, 'm4v',
+                    preference=1,  # Prefer hls since it allows to workaround georestriction
+                    m3u8_id='hls', fatal=False)
+                if m3u8_formats is not False:
+                    formats.extend(m3u8_formats)
+            else:
+                formats.append({
+                    'url': endpoint,
+                })
 
         thumbnails = []
         for image in media_json['images']:
@@ -65,16 +99,12 @@ class SpiegeltvIE(InfoExtractor):
 
         description = media_json['subtitle']
         duration = float_or_none(media_json.get('duration_in_ms'), scale=1000)
-        format = '16x9' if is_wide else '4x3'
-
-        url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
 
         return {
             'id': video_id,
             'title': title,
-            'url': url,
-            'ext': 'm4v',
             'description': description,
             'duration': duration,
-            'thumbnails': thumbnails
+            'thumbnails': thumbnails,
+            'formats': formats,
         }

youtube_dl/extractor/sunporno.py

@@ -44,7 +44,7 @@ class SunPornoIE(InfoExtractor):
             webpage, 'duration', fatal=False))
 
         view_count = int_or_none(self._html_search_regex(
-            r'class="views">\s*(\d+)\s*<',
+            r'class="views">(?:<noscript>)?\s*(\d+)\s*<',
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'(\d+)</b> Comments?',

youtube_dl/extractor/teamcoco.py

@@ -51,6 +51,17 @@ class TeamcocoIE(InfoExtractor):
             'params': {
                 'skip_download': True,  # m3u8 downloads
             }
+        }, {
+            'url': 'http://teamcoco.com/video/full-episode-mon-6-1-joel-mchale-jake-tapper-and-musical-guest-courtney-barnett?playlist=x;eyJ0eXBlIjoidGFnIiwiaWQiOjl9',
+            'info_dict': {
+                'id': '89341',
+                'ext': 'mp4',
+                'title': 'Full Episode - Mon. 6/1 - Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+                'description': 'Guests: Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett',
+            },
+            'params': {
+                'skip_download': True,  # m3u8 downloads
+            }
         }
     ]
     _VIDEO_ID_REGEXES = (
@@ -110,9 +121,23 @@ class TeamcocoIE(InfoExtractor):
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
             if determine_ext(filed['url']) == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    filed['url'], video_id, ext='mp4'))
+                # compat_urllib_parse.urljoin does not work here
+                if filed['url'].startswith('/'):
+                    m3u8_url = 'http://ht.cdn.turner.com/tbs/big/teamcoco' + filed['url']
+                else:
+                    m3u8_url = filed['url']
+                m3u8_formats = self._extract_m3u8_formats(
+                    m3u8_url, video_id, ext='mp4')
+                for m3u8_format in m3u8_formats:
+                    if m3u8_format not in formats:
+                        formats.append(m3u8_format)
+            elif determine_ext(filed['url']) == 'f4m':
+                # TODO Correct f4m extraction
+                continue
             else:
+                if filed['url'].startswith('/mp4:protected/'):
+                    # TODO Correct extraction for these files
+                    continue
                 m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
                 if m_format is not None:
                     format_id = m_format.group(1)

youtube_dl/extractor/tf1.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'http://(?:videos\.tf1|www\.tfou|www\.tf1)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
+    _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
     _TESTS = [{
         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
         'info_dict': {
@@ -35,6 +35,9 @@ class TF1IE(InfoExtractor):
     }, {
         'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
         'only_matching': True,
+    }, {
+        'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/theplatform.py

@@ -26,7 +26,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language
 class ThePlatformIE(InfoExtractor):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
-           (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
+           (?:(?P<media>(?:[^/]+/)+select/media/)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
          |theplatform:)(?P<id>[^/\?&]+)'''
 
     _TESTS = [{
@@ -56,6 +56,17 @@ class ThePlatformIE(InfoExtractor):
             # rtmp download
             'skip_download': True,
         }
+    }, {
+        'url': 'https://player.theplatform.com/p/D6x-PC/pulse_preview/embed/select/media/yMBg9E8KFxZD',
+        'info_dict': {
+            'id': 'yMBg9E8KFxZD',
+            'ext': 'mp4',
+            'description': 'md5:644ad9188d655b742f942bf2e06b002d',
+            'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
+        }
+    }, {
+        'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -85,6 +96,11 @@ class ThePlatformIE(InfoExtractor):
         if not provider_id:
             provider_id = 'dJ5BDC'
 
+        path = provider_id
+        if mobj.group('media'):
+            path += '/media'
+        path += '/' + video_id
+
         if smuggled_data.get('force_smil_url', False):
             smil_url = url
         elif mobj.group('config'):
@@ -94,8 +110,7 @@ class ThePlatformIE(InfoExtractor):
             config = self._download_json(config_url, video_id, 'Downloading config')
             smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
         else:
-            smil_url = ('http://link.theplatform.com/s/{0}/{1}/meta.smil?'
-                        'format=smil&mbr=true'.format(provider_id, video_id))
+            smil_url = 'http://link.theplatform.com/s/%s/meta.smil?format=smil&mbr=true' % path
 
         sig = smuggled_data.get('sig')
         if sig:
@@ -112,7 +127,7 @@ class ThePlatformIE(InfoExtractor):
         else:
             raise ExtractorError(error_msg, expected=True)
 
-        info_url = 'http://link.theplatform.com/s/{0}/{1}?format=preview'.format(provider_id, video_id)
+        info_url = 'http://link.theplatform.com/s/%s?format=preview' % path
         info_json = self._download_webpage(info_url, video_id)
         info = json.loads(info_json)
 

youtube_dl/extractor/thesixtyone.py

@@ -1,9 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..utils import unified_strdate
 
@@ -17,7 +14,7 @@ class TheSixtyOneIE(InfoExtractor):
             song
         )/(?P<id>[A-Za-z0-9]+)/?$'''
     _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
-    _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}.thesixtyone.com/thesixtyone_production/audio/{0:}_stream'
+    _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream'
     _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
     _TESTS = [
         {
@@ -70,14 +67,19 @@ class TheSixtyOneIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group('id')
+        song_id = self._match_id(url)
 
         webpage = self._download_webpage(
             self._SONG_URL_TEMPLATE.format(song_id), song_id)
 
-        song_data = json.loads(self._search_regex(
-            r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'))
+        song_data = self._parse_json(self._search_regex(
+            r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'), song_id)
+
+        if self._search_regex(r'(t61\.s3_audio_load\s*=\s*1\.0;)', webpage, 's3_audio_load marker', default=None):
+            song_data['audio_server'] = 's3.amazonaws.com'
+        else:
+            song_data['audio_server'] = song_data['audio_server'] + '.thesixtyone.com'
+
         keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']]
         url = self._SONG_FILE_URL_TEMPLATE.format(
             "".join(reversed(keys)), **song_data)

youtube_dl/extractor/thisamericanlife.py

@@ -0,0 +1,40 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ThisAmericanLifeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/(?:radio-archives/episode/|play_full\.php\?play=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one',
+        'md5': '8f7d2da8926298fdfca2ee37764c11ce',
+        'info_dict': {
+            'id': '487',
+            'ext': 'm4a',
+            'title': '487: Harper High School, Part One',
+            'description': 'md5:ee40bdf3fb96174a9027f76dbecea655',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.thisamericanlife.org/play_full.php?play=487',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.thisamericanlife.org/radio-archives/episode/%s' % video_id, video_id)
+
+        return {
+            'id': video_id,
+            'url': 'http://stream.thisamericanlife.org/{0}/stream/{0}_64k.m3u8'.format(video_id),
+            'protocol': 'm3u8_native',
+            'ext': 'm4a',
+            'acodec': 'aac',
+            'vcodec': 'none',
+            'abr': 64,
+            'title': self._html_search_meta(r'twitter:title', webpage, 'title', fatal=True),
+            'description': self._html_search_meta(r'description', webpage, 'description'),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/tlc.py

@@ -12,17 +12,22 @@ class TlcIE(DiscoveryIE):
     IE_NAME = 'tlc.com'
     _VALID_URL = r'http://www\.tlc\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
 
-    _TEST = {
+    # DiscoveryIE has _TESTS
+    _TESTS = [{
         'url': 'http://www.tlc.com/tv-shows/cake-boss/videos/too-big-to-fly.htm',
-        'md5': 'c4038f4a9b44d0b5d74caaa64ed2a01a',
         'info_dict': {
-            'id': '853232',
+            'id': '104493',
             'ext': 'mp4',
-            'title': 'Cake Boss: Too Big to Fly',
+            'title': 'Too Big to Fly',
             'description': 'Buddy has taken on a high flying task.',
             'duration': 119,
+            'timestamp': 1393365060,
+            'upload_date': '20140225',
         },
-    }
+        'params': {
+            'skip_download': True,  # requires ffmpef
+        },
+    }]
 
 
 class TlcDeIE(InfoExtractor):

youtube_dl/extractor/tnaflix.py

@@ -3,39 +3,70 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    parse_duration,
     fix_xml_ampersands,
+    float_or_none,
+    int_or_none,
+    parse_duration,
+    str_to_int,
+    xpath_text,
 )
 
 
-class TNAFlixIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
-
-    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
-    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TESTS = [
-        {
-            'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
-            'md5': 'ecf3498417d09216374fc5907f9c6ec0',
-            'info_dict': {
-                'id': '553878',
-                'display_id': 'Carmella-Decesare-striptease',
-                'ext': 'mp4',
-                'title': 'Carmella Decesare - striptease',
-                'description': '',
-                'thumbnail': 're:https?://.*\.jpg$',
-                'duration': 91,
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
-            'matching_only': True,
-        }
+class TNAFlixNetworkBaseIE(InfoExtractor):
+    # May be overridden in descendants if necessary
+    _CONFIG_REGEX = [
+        r'flashvars\.config\s*=\s*escape\("([^"]+)"',
+        r'<input[^>]+name="config\d?" value="([^"]+)"',
     ]
+    _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
+    _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
+    _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
+    _VIEW_COUNT_REGEX = None
+    _COMMENT_COUNT_REGEX = None
+    _AVERAGE_RATING_REGEX = None
+    _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
+
+    def _extract_thumbnails(self, flix_xml):
+
+        def get_child(elem, names):
+            for name in names:
+                child = elem.find(name)
+                if child is not None:
+                    return child
+
+        timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
+        if timeline is None:
+            return
+
+        pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
+        if pattern_el is None or not pattern_el.text:
+            return
+
+        first_el = get_child(timeline, ['imageFirst', 'first'])
+        last_el = get_child(timeline, ['imageLast', 'last'])
+        if first_el is None or last_el is None:
+            return
+
+        first_text = first_el.text
+        last_text = last_el.text
+        if not first_text.isdigit() or not last_text.isdigit():
+            return
+
+        first = int(first_text)
+        last = int(last_text)
+        if first > last:
+            return
+
+        width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
+        height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
+
+        return [{
+            'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
+            'width': width,
+            'height': height,
+        } for i in range(first, last + 1)]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -44,47 +75,195 @@ class TNAFlixIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._html_search_regex(
-            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
-        description = self._html_search_regex(
-            self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
-
-        age_limit = self._rta_search(webpage)
-
-        duration = self._html_search_meta('duration', webpage, 'duration', default=None)
-        if duration:
-            duration = parse_duration(duration[1:])
-
         cfg_url = self._proto_relative_url(self._html_search_regex(
             self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
 
         cfg_xml = self._download_xml(
-            cfg_url, display_id, note='Downloading metadata',
+            cfg_url, display_id, 'Downloading metadata',
             transform_source=fix_xml_ampersands)
 
-        thumbnail = cfg_xml.find('./startThumb').text
-
         formats = []
+
+        def extract_video_url(vl):
+            return re.sub('speed=\d+', 'speed=', vl.text)
+
+        video_link = cfg_xml.find('./videoLink')
+        if video_link is not None:
+            formats.append({
+                'url': extract_video_url(video_link),
+                'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
+            })
+
         for item in cfg_xml.findall('./quality/item'):
-            video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
-            format_id = item.find('res').text
-            fmt = {
-                'url': video_url,
+            video_link = item.find('./videoLink')
+            if video_link is None:
+                continue
+            res = item.find('res')
+            format_id = None if res is None else res.text
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]', format_id, 'height', default=None))
+            formats.append({
+                'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
                 'format_id': format_id,
-            }
-            m = re.search(r'^(\d+)', format_id)
-            if m:
-                fmt['height'] = int(m.group(1))
-            formats.append(fmt)
+                'height': height,
+            })
+
         self._sort_formats(formats)
 
+        thumbnail = self._proto_relative_url(
+            xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
+        thumbnails = self._extract_thumbnails(cfg_xml)
+
+        title = self._html_search_regex(
+            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
+
+        age_limit = self._rta_search(webpage)
+
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration', default=None))
+
+        def extract_field(pattern, name):
+            return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
+
+        description = extract_field(self._DESCRIPTION_REGEX, 'description')
+        uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
+        view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
+        comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
+        average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
+
+        categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
+        categories = categories_str.split(', ') if categories_str is not None else []
+
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'duration': duration,
             'age_limit': age_limit,
+            'uploader': uploader,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'average_rating': average_rating,
+            'categories': categories,
             'formats': formats,
         }
+
+
+class TNAFlixIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
+
+    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
+    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+    _UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
+
+    _TESTS = [{
+        # anonymous uploader, no categories
+        'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'info_dict': {
+            'id': '553878',
+            'display_id': 'Carmella-Decesare-striptease',
+            'ext': 'mp4',
+            'title': 'Carmella Decesare - striptease',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 91,
+            'age_limit': 18,
+            'uploader': 'Anonymous',
+            'categories': [],
+        }
+    }, {
+        # non-anonymous uploader, categories
+        'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
+        'md5': '0f5d4d490dbfd117b8607054248a07c0',
+        'info_dict': {
+            'id': '6538',
+            'display_id': 'Educational-xxx-video',
+            'ext': 'mp4',
+            'title': 'Educational xxx video',
+            'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 164,
+            'age_limit': 18,
+            'uploader': 'bobwhite39',
+            'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
+        }
+    }, {
+        'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
+        'only_matching': True,
+    }]
+
+
+class EMPFlixIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
+
+    _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
+
+    _TESTS = [{
+        '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$',
+            'duration': 83,
+            'age_limit': 18,
+            'uploader': 'cwbike',
+            'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
+        }
+    }, {
+        'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
+        'only_matching': True,
+    }]
+
+
+class MovieFapIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
+
+    _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
+    _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
+    _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
+    _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
+
+    _TESTS = [{
+        # normal, multi-format video
+        'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
+        'md5': '26624b4e2523051b550067d547615906',
+        'info_dict': {
+            'id': 'be9867c9416c19f54a4a',
+            'display_id': 'experienced-milf-amazing-handjob',
+            'ext': 'mp4',
+            'title': 'Experienced MILF Amazing Handjob',
+            'description': 'Experienced MILF giving an Amazing Handjob',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+            'uploader': 'darvinfred06',
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
+        }
+    }, {
+        # quirky single-format case where the extension is given as fid, but the video is really an flv
+        'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
+        'md5': 'fa56683e291fc80635907168a743c9ad',
+        'info_dict': {
+            'id': 'e5da0d3edce5404418f5',
+            'display_id': 'jeune-couple-russe',
+            'ext': 'flv',
+            'title': 'Jeune Couple Russe',
+            'description': 'Amateur',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+            'uploader': 'whiskeyjar',
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Amateur', 'Teen'],
+        }
+    }]

youtube_dl/extractor/tube8.py

@@ -47,7 +47,7 @@ class Tube8IE(InfoExtractor):
         webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
-            r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
+            r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'))
 
         video_url = flashvars['video_url']
         if flashvars.get('encrypted') is True:
@@ -58,19 +58,19 @@ class Tube8IE(InfoExtractor):
         thumbnail = flashvars.get('image_url')
 
         title = self._html_search_regex(
-            r'videotitle\s*=\s*"([^"]+)', webpage, 'title')
+            r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
         description = self._html_search_regex(
-            r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
+            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
         uploader = self._html_search_regex(
-            r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>',
+            r'<span class="username">\s*(.+?)\s*<',
             webpage, 'uploader', fatal=False)
 
         like_count = int_or_none(self._html_search_regex(
-            r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False))
+            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
         dislike_count = int_or_none(self._html_search_regex(
-            r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False))
+            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
         view_count = self._html_search_regex(
-            r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False)
+            r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False)
         if view_count:
             view_count = str_to_int(view_count)
         comment_count = self._html_search_regex(

youtube_dl/extractor/tubitv.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import codecs
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class TubiTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video\?id=(?P<id>[0-9]+)'
+    _LOGIN_URL = 'http://tubitv.com/login'
+    _NETRC_MACHINE = 'tubitv'
+    _TEST = {
+        'url': 'http://tubitv.com/video?id=54411&title=The_Kitchen_Musical_-_EP01',
+        'info_dict': {
+            'id': '54411',
+            'ext': 'mp4',
+            'title': 'The Kitchen Musical - EP01',
+            'thumbnail': 're:^https?://.*\.png$',
+            'description': 'md5:37532716166069b353e8866e71fefae7',
+            'duration': 2407,
+        },
+        'params': {
+            'skip_download': 'HLS download',
+        },
+    }
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+        self.report_login()
+        form_data = {
+            'username': username,
+            'password': password,
+        }
+        payload = compat_urllib_parse.urlencode(form_data).encode('utf-8')
+        request = compat_urllib_request.Request(self._LOGIN_URL, payload)
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        login_page = self._download_webpage(
+            request, None, False, 'Wrong login info')
+        if not re.search(r'id="tubi-logout"', login_page):
+            raise ExtractorError(
+                'Login failed (invalid username/password)', expected=True)
+
+    def _real_initialize(self):
+        self._login()
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        if re.search(r"<(?:DIV|div) class='login-required-screen'>", webpage):
+            raise ExtractorError(
+                'This video requires login, use --username and --password '
+                'options to provide account credentials.', expected=True)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'duration'))
+
+        apu = self._search_regex(r"apu='([^']+)'", webpage, 'apu')
+        m3u8_url = codecs.decode(apu, 'rot_13')[::-1]
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+        }

youtube_dl/extractor/tumblr.py

@@ -4,6 +4,8 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .pornhub import PornHubIE
+from .vimeo import VimeoIE
 
 
 class TumblrIE(InfoExtractor):
@@ -28,6 +30,28 @@ class TumblrIE(InfoExtractor):
             'description': 'md5:dba62ac8639482759c8eb10ce474586a',
             'thumbnail': 're:http://.*\.jpg',
         }
+    }, {
+        'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching',
+        'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab',
+        'info_dict': {
+            'id': 'Wmur',
+            'ext': 'mp4',
+            'title': 'naked smoking & stretching',
+            'upload_date': '20150506',
+            'timestamp': 1430931613,
+        },
+        'add_ie': ['Vidme'],
+    }, {
+        'url': 'http://camdamage.tumblr.com/post/98846056295/',
+        'md5': 'a9e0c8371ea1ca306d6554e3fecf50b6',
+        'info_dict': {
+            'id': '105463834',
+            'ext': 'mp4',
+            'title': 'Cam Damage-HD 720p',
+            'uploader': 'John Moyer',
+            'uploader_id': 'user32021558',
+        },
+        'add_ie': ['Vimeo'],
     }]
 
     def _real_extract(self, url):
@@ -38,6 +62,20 @@ class TumblrIE(InfoExtractor):
         url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
         webpage = self._download_webpage(url, video_id)
 
+        vid_me_embed_url = self._search_regex(
+            r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
+            webpage, 'vid.me embed', default=None)
+        if vid_me_embed_url is not None:
+            return self.url_result(vid_me_embed_url, 'Vidme')
+
+        pornhub_url = PornHubIE._extract_url(webpage)
+        if pornhub_url:
+            return self.url_result(pornhub_url, 'PornHub')
+
+        vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+        if vimeo_url:
+            return self.url_result(vimeo_url, 'Vimeo')
+
         iframe_url = self._search_regex(
             r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
             webpage, 'iframe url')

youtube_dl/extractor/turbo.py

@@ -23,7 +23,7 @@ class TurboIE(InfoExtractor):
             'ext': 'mp4',
             'duration': 3715,
             'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
-            'description': 'Retrouvez dans cette rubrique toutes les vidéos de l\'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
+            'description': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia...',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
@@ -42,7 +42,7 @@ class TurboIE(InfoExtractor):
         title = xpath_text(item, './title', 'title')
         duration = int_or_none(xpath_text(item, './durate', 'duration'))
         thumbnail = xpath_text(item, './visuel_clip', 'thumbnail')
-        description = self._og_search_description(webpage)
+        description = self._html_search_meta('description', webpage)
 
         formats = []
         get_quality = qualities(['3g', 'sd', 'hq'])

youtube_dl/extractor/tvc.py

@@ -0,0 +1,109 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+)
+
+
+class TVCIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.tvc.ru/video/iframe/id/74622/isPlay/false/id_stat/channel/?acc_video_id=/channel/brand/id/17/show/episodes/episode_id/39702',
+        'md5': 'bbc5ff531d1e90e856f60fc4b3afd708',
+        'info_dict': {
+            'id': '74622',
+            'ext': 'mp4',
+            'title': 'События. "События". Эфир от 22.05.2015 14:30',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1122,
+        },
+    }
+
+    @classmethod
+    def _extract_url(cls, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:http:)?//(?:www\.)?tvc\.ru/video/iframe/id/[^"]+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://www.tvc.ru/video/json/id/%s' % video_id, video_id)
+
+        formats = []
+        for info in video.get('path', {}).get('quality', []):
+            video_url = info.get('url')
+            if not video_url:
+                continue
+            format_id = self._search_regex(
+                r'cdnvideo/([^/]+?)(?:-[^/]+?)?/', video_url,
+                'format id', default=None)
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+                'width': int_or_none(info.get('width')),
+                'height': int_or_none(info.get('height')),
+                'tbr': int_or_none(info.get('bitrate')),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video['title'],
+            'thumbnail': video.get('picture'),
+            'duration': int_or_none(video.get('duration')),
+            'formats': formats,
+        }
+
+
+class TVCArticleIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'http://www.tvc.ru/channel/brand/id/29/show/episodes/episode_id/39702/',
+        'info_dict': {
+            'id': '74622',
+            'ext': 'mp4',
+            'title': 'События. "События". Эфир от 22.05.2015 14:30',
+            'description': 'md5:ad7aa7db22903f983e687b8a3e98c6dd',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1122,
+        },
+    }, {
+        'url': 'http://www.tvc.ru/news/show/id/69944',
+        'info_dict': {
+            'id': '75399',
+            'ext': 'mp4',
+            'title': 'Эксперты: в столице встал вопрос о максимально безопасных остановках',
+            'description': 'md5:f2098f71e21f309e89f69b525fd9846e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 278,
+        },
+    }, {
+        'url': 'http://www.tvc.ru/channel/brand/id/47/show/episodes#',
+        'info_dict': {
+            'id': '2185',
+            'ext': 'mp4',
+            'title': 'Ещё не поздно. Эфир от 03.08.2013',
+            'description': 'md5:51fae9f3f8cfe67abce014e428e5b027',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 3316,
+        },
+    }]
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, self._match_id(url))
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'TVC',
+            'url': self._og_search_video_url(webpage),
+            'title': clean_html(self._og_search_title(webpage)),
+            'description': clean_html(self._og_search_description(webpage)),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/tvigle.py

@@ -5,7 +5,9 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     float_or_none,
+    int_or_none,
     parse_age_limit,
 )
 
@@ -24,22 +26,24 @@ class TvigleIE(InfoExtractor):
                 'display_id': 'sokrat',
                 'ext': 'flv',
                 'title': 'Сократ',
-                'description': 'md5:a05bd01be310074d5833efc6743be95e',
+                'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
                 'duration': 6586,
-                'age_limit': 0,
+                'age_limit': 12,
             },
+            'skip': 'georestricted',
         },
         {
             'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
-            'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574',
+            'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
             'info_dict': {
                 'id': '5142516',
-                'ext': 'mp4',
+                'ext': 'flv',
                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
                 'duration': 186.080,
                 'age_limit': 0,
             },
+            'skip': 'georestricted',
         }, {
             'url': 'https://cloud.tvigle.ru/video/5267604/',
             'only_matching': True,
@@ -54,7 +58,7 @@ class TvigleIE(InfoExtractor):
         if not video_id:
             webpage = self._download_webpage(url, display_id)
             video_id = self._html_search_regex(
-                r'<li class="video-preview current_playing" id="(\d+)">',
+                r'class="video-preview current_playing" id="(\d+)">',
                 webpage, 'video id')
 
         video_data = self._download_json(
@@ -62,21 +66,34 @@ class TvigleIE(InfoExtractor):
 
         item = video_data['playlist']['items'][0]
 
+        videos = item.get('videos')
+
+        error_message = item.get('errorMessage')
+        if not videos and error_message:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+
         title = item['title']
-        description = item['description']
-        thumbnail = item['thumbnail']
+        description = item.get('description')
+        thumbnail = item.get('thumbnail')
         duration = float_or_none(item.get('durationMilliseconds'), 1000)
         age_limit = parse_age_limit(item.get('ageRestrictions'))
 
         formats = []
         for vcodec, fmts in item['videos'].items():
-            for quality, video_url in fmts.items():
+            for format_id, video_url in fmts.items():
+                if format_id == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', m3u8_id=vcodec))
+                    continue
+                height = self._search_regex(
+                    r'^(\d+)[pP]$', format_id, 'height', default=None)
                 formats.append({
                     'url': video_url,
-                    'format_id': '%s-%s' % (vcodec, quality),
+                    'format_id': '%s-%s' % (vcodec, format_id),
                     'vcodec': vcodec,
-                    'height': int(quality[:-1]),
-                    'filesize': item['video_files_size'][vcodec][quality],
+                    'height': int_or_none(height),
+                    'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)),
                 })
         self._sort_formats(formats)
 

youtube_dl/extractor/tvplay.py

@@ -26,6 +26,7 @@ class TVPlayIE(InfoExtractor):
            viasat4play\.no/programmer|
            tv6play\.no/programmer|
            tv3play\.dk/programmer|
+           play\.novatv\.bg/programi
         )/[^/]+/(?P<id>\d+)
         '''
     _TESTS = [
@@ -173,6 +174,22 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
+            'info_dict': {
+                'id': '624952',
+                'ext': 'flv',
+                'title': 'Здравей, България (12.06.2015 г.) ',
+                'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
+                'duration': 8838,
+                'timestamp': 1434100372,
+                'upload_date': '20150612',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/twentyfourvideo.py

@@ -15,7 +15,7 @@ class TwentyFourVideoIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://www.24video.net/video/view/1044982',
-            'md5': '48dd7646775690a80447a8dca6a2df76',
+            'md5': 'd041af8b5b4246ea466226a0d6693345',
             'info_dict': {
                 'id': '1044982',
                 'ext': 'mp4',
@@ -54,7 +54,7 @@ class TwentyFourVideoIE(InfoExtractor):
             webpage, 'upload date'))
 
         uploader = self._html_search_regex(
-            r'Загрузил\s*<a href="/jsecUser/movies/[^"]+" class="link">([^<]+)</a>',
+            r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
             webpage, 'uploader', fatal=False)
 
         view_count = int_or_none(self._html_search_regex(

youtube_dl/extractor/twitch.py

@@ -189,17 +189,17 @@ class TwitchVodIE(TwitchItemBaseIE):
     _ITEM_SHORTCUT = 'v'
 
     _TEST = {
-        'url': 'http://www.twitch.tv/ksptv/v/3622000',
+        'url': 'http://www.twitch.tv/riotgames/v/6528877',
         'info_dict': {
-            'id': 'v3622000',
+            'id': 'v6528877',
             'ext': 'mp4',
-            'title': '''KSPTV: Squadcast: "Everyone's on vacation so here's Dahud" Edition!''',
+            'title': 'LCK Summer Split - Week 6 Day 1',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'duration': 6951,
-            'timestamp': 1419028564,
-            'upload_date': '20141219',
-            'uploader': 'KSPTV',
-            'uploader_id': 'ksptv',
+            'duration': 17208,
+            'timestamp': 1435131709,
+            'upload_date': '20150624',
+            'uploader': 'Riot Games',
+            'uploader_id': 'riotgames',
             'view_count': int,
         },
         'params': {
@@ -215,7 +215,7 @@ class TwitchVodIE(TwitchItemBaseIE):
             '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
             'Downloading %s access token' % self._ITEM_TYPE)
         formats = self._extract_m3u8_formats(
-            '%s/vod/%s?nauth=%s&nauthsig=%s'
+            '%s/vod/%s?nauth=%s&nauthsig=%s&allow_source=true'
             % (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
             item_id, 'mp4')
         self._prefer_source(formats)

youtube_dl/extractor/twitter.py

@@ -0,0 +1,72 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import (
+    float_or_none,
+    unescapeHTML,
+)
+
+
+class TwitterCardIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
+        'md5': 'a74f50b310c83170319ba16de6955192',
+        'info_dict': {
+            'id': '560070183650213889',
+            'ext': 'mp4',
+            'title': 'TwitterCard',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 30.033,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        # Different formats served for different User-Agents
+        USER_AGENTS = [
+            'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)',  # mp4
+            'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0',  # webm
+        ]
+
+        config = None
+        formats = []
+        for user_agent in USER_AGENTS:
+            request = compat_urllib_request.Request(url)
+            request.add_header('User-Agent', user_agent)
+            webpage = self._download_webpage(request, video_id)
+
+            config = self._parse_json(
+                unescapeHTML(self._search_regex(
+                    r'data-player-config="([^"]+)"', webpage, 'data player config')),
+                video_id)
+
+            video_url = config['playlist'][0]['source']
+
+            f = {
+                'url': video_url,
+            }
+
+            m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
+            if m:
+                f.update({
+                    'width': int(m.group('width')),
+                    'height': int(m.group('height')),
+                })
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = config.get('posterImageUrl')
+        duration = float_or_none(config.get('duration'))
+
+        return {
+            'id': video_id,
+            'title': 'TwitterCard',
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/vbox7.py

@@ -5,6 +5,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
@@ -26,11 +27,21 @@ class Vbox7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';',
-                                          redirect_page, 'redirect location')
-        redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id,
+        # need to get the page 3 times for the correct jsSecretToken cookie
+        # which is necessary for the correct title
+        def get_session_id():
+            redirect_page = self._download_webpage(url, video_id)
+            session_id_url = self._search_regex(
+                r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
+                'session id url')
+            self._download_webpage(
+                compat_urlparse.urljoin(url, session_id_url), video_id,
+                'Getting session id')
+
+        get_session_id()
+        get_session_id()
+
+        webpage = self._download_webpage(url, video_id,
                                          'Downloading redirect page')
 
         title = self._html_search_regex(r'<title>(.*)</title>',

youtube_dl/extractor/vgtv.py

@@ -4,7 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+)
 
 
 class VGTVIE(InfoExtractor):
@@ -59,16 +62,16 @@ class VGTVIE(InfoExtractor):
         },
         {
             # streamType: live
-            'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
+            'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
             'info_dict': {
-                'id': '100015',
+                'id': '113063',
                 'ext': 'flv',
-                'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
-                'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
+                'title': 're:^DIREKTE: V75 fra Solvalla [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'description': 'md5:b3743425765355855f88e096acc93231',
                 'thumbnail': 're:^https?://.*\.jpg',
                 'duration': 0,
-                'timestamp': 1407423348,
-                'upload_date': '20140807',
+                'timestamp': 1432975582,
+                'upload_date': '20150530',
                 'view_count': int,
             },
             'params': {
@@ -97,7 +100,12 @@ class VGTVIE(InfoExtractor):
             % (host, video_id, HOST_WEBSITES[host]),
             video_id, 'Downloading media JSON')
 
+        if data.get('status') == 'inactive':
+            raise ExtractorError(
+                'Video %s is no longer available' % video_id, expected=True)
+
         streams = data['streamUrls']
+        stream_type = data.get('streamType')
 
         formats = []
 
@@ -107,7 +115,8 @@ class VGTVIE(InfoExtractor):
                 hls_url, video_id, 'mp4', m3u8_id='hls'))
 
         hds_url = streams.get('hds')
-        if hds_url:
+        # wasLive hds are always 404
+        if hds_url and stream_type != 'wasLive':
             formats.extend(self._extract_f4m_formats(
                 hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
                 video_id, f4m_id='hds'))
@@ -135,13 +144,14 @@ class VGTVIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': data['title'],
+            'title': self._live_title(data['title']),
             'description': data['description'],
             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
             'timestamp': data['published'],
             'duration': float_or_none(data['duration'], 1000),
             'view_count': data['displays'],
             'formats': formats,
+            'is_live': True if stream_type == 'live' else False,
         }
 
 

youtube_dl/extractor/vidme.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class VidmeIE(InfoExtractor):
     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://vid.me/QNB',
         'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
         'info_dict': {
@@ -23,9 +23,14 @@ class VidmeIE(InfoExtractor):
             'upload_date': '20140725',
             'thumbnail': 're:^https?://.*\.jpg',
         },
-    }
+    }, {
+        # From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
+        'url': 'https://vid.me/e/Wmur',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
+        url = url.replace('vid.me/e/', 'vid.me/')
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

youtube_dl/extractor/viki.py

@@ -1,5 +1,7 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import time
 import hmac
 import hashlib
@@ -11,6 +13,7 @@ from ..utils import (
     parse_age_limit,
     parse_iso8601,
 )
+from ..compat import compat_urllib_request
 from .common import InfoExtractor
 
 
@@ -23,27 +26,35 @@ class VikiBaseIE(InfoExtractor):
     _APP_VERSION = '2.2.5.1428709186'
     _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'
 
-    def _prepare_call(self, path, timestamp=None):
+    _NETRC_MACHINE = 'viki'
+
+    _token = None
+
+    def _prepare_call(self, path, timestamp=None, post_data=None):
         path += '?' if '?' not in path else '&'
         if not timestamp:
             timestamp = int(time.time())
         query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
+        if self._token:
+            query += '&token=%s' % self._token
         sig = hmac.new(
             self._APP_SECRET.encode('ascii'),
             query.encode('ascii'),
             hashlib.sha1
         ).hexdigest()
-        return self._API_URL_TEMPLATE % (query, sig)
+        url = self._API_URL_TEMPLATE % (query, sig)
+        return compat_urllib_request.Request(
+            url, json.dumps(post_data).encode('utf-8')) if post_data else url
 
-    def _call_api(self, path, video_id, note, timestamp=None):
+    def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
         resp = self._download_json(
-            self._prepare_call(path, timestamp), video_id, note)
+            self._prepare_call(path, timestamp, post_data), video_id, note)
 
         error = resp.get('error')
         if error:
             if error == 'invalid timestamp':
                 resp = self._download_json(
-                    self._prepare_call(path, int(resp['current_timestamp'])),
+                    self._prepare_call(path, int(resp['current_timestamp']), post_data),
                     video_id, '%s (retry)' % note)
                 error = resp.get('error')
             if error:
@@ -56,6 +67,27 @@ class VikiBaseIE(InfoExtractor):
             '%s returned error: %s' % (self.IE_NAME, error),
             expected=True)
 
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'login_id': username,
+            'password': password,
+        }
+
+        login = self._call_api(
+            'sessions.json', None,
+            'Logging in as %s' % username, post_data=login_form)
+
+        self._token = login.get('token')
+        if not self._token:
+            self.report_warning('Unable to get session token, login has probably failed')
+
 
 class VikiIE(VikiBaseIE):
     IE_NAME = 'viki'

youtube_dl/extractor/vimeo.py

@@ -22,6 +22,7 @@ from ..utils import (
     unified_strdate,
     unsmuggle_url,
     urlencode_postdata,
+    unescapeHTML,
 )
 
 
@@ -173,6 +174,21 @@ class VimeoIE(VimeoBaseInfoExtractor):
         },
     ]
 
+    @staticmethod
+    def _extract_vimeo_url(url, webpage):
+        # 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 surl
+        # Look for embedded (swf embed) Vimeo player
+        mobj = re.search(
+            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
+        if mobj:
+            return mobj.group(1)
+
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword', None)
         if password is None:

youtube_dl/extractor/vk.py

@@ -13,6 +13,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     orderedSet,
+    str_to_int,
     unescapeHTML,
     unified_strdate,
 )
@@ -34,6 +35,7 @@ class VKIE(InfoExtractor):
                 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
                 'duration': 195,
                 'upload_date': '20120212',
+                'view_count': int,
             },
         },
         {
@@ -45,7 +47,8 @@ class VKIE(InfoExtractor):
                 'uploader': 'Tom Cruise',
                 'title': 'No name',
                 'duration': 9,
-                'upload_date': '20130721'
+                'upload_date': '20130721',
+                'view_count': int,
             }
         },
         {
@@ -59,6 +62,7 @@ class VKIE(InfoExtractor):
                 'title': 'Lin Dan',
                 'duration': 101,
                 'upload_date': '20120730',
+                'view_count': int,
             }
         },
         {
@@ -73,7 +77,8 @@ class VKIE(InfoExtractor):
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'duration': 8352,
-                'upload_date': '20121218'
+                'upload_date': '20121218',
+                'view_count': int,
             },
             'skip': 'Requires vk account credentials',
         },
@@ -100,6 +105,7 @@ class VKIE(InfoExtractor):
                 'title': 'Книга Илая',
                 'duration': 6771,
                 'upload_date': '20140626',
+                'view_count': int,
             },
             'skip': 'Only works from Russia',
         },
@@ -115,20 +121,27 @@ class VKIE(InfoExtractor):
         if username is None:
             return
 
-        login_form = {
-            'act': 'login',
-            'role': 'al_frame',
-            'expire': '1',
-            'email': username,
-            'pass': password,
-        }
+        login_page = self._download_webpage(
+            'https://vk.com', None, 'Downloading login page')
 
-        request = compat_urllib_request.Request('https://login.vk.com/?act=login',
-                                                compat_urllib_parse.urlencode(login_form).encode('utf-8'))
-        login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+        login_form = dict(re.findall(
+            r'<input\s+type="hidden"\s+name="([^"]+)"\s+(?:id="[^"]+"\s+)?value="([^"]*)"',
+            login_page))
+
+        login_form.update({
+            'email': username.encode('cp1251'),
+            'pass': password.encode('cp1251'),
+        })
+
+        request = compat_urllib_request.Request(
+            'https://login.vk.com/?act=login',
+            compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        login_page = self._download_webpage(
+            request, None, note='Logging in as %s' % username)
 
         if re.search(r'onLoginFailed', login_page):
-            raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
+            raise ExtractorError(
+                'Unable to login, incorrect username and/or password', expected=True)
 
     def _real_initialize(self):
         self._login()
@@ -140,9 +153,14 @@ class VKIE(InfoExtractor):
         if not video_id:
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 
-        info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+        info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
         info_page = self._download_webpage(info_url, video_id)
 
+        if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
+            raise ExtractorError(
+                'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
+                expected=True)
+
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
             'Video %s has been removed from public access due to rightholder complaint.',
@@ -175,25 +193,29 @@ class VKIE(InfoExtractor):
                 m_rutube.group(1).replace('\\', ''))
             return self.url_result(rutube_url)
 
-        m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
+        m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
         if m_opts:
-            m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
+            m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
             if m_opts_url:
                 opts_url = m_opts_url.group(1)
                 if opts_url.startswith('//'):
                     opts_url = 'http:' + opts_url
                 return self.url_result(opts_url)
 
-        data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
+        data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
         data = json.loads(data_json)
 
         # Extract upload date
         upload_date = None
-        mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
+        mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
         if mobj is not None:
             mobj.group(1) + ' ' + mobj.group(2)
             upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
 
+        view_count = str_to_int(self._search_regex(
+            r'"mv_views_count_number"[^>]*>([\d,.]+) views<',
+            info_page, 'view count', fatal=False))
+
         formats = [{
             'format_id': k,
             'url': v,
@@ -210,6 +232,7 @@ class VKIE(InfoExtractor):
             'uploader': data.get('md_author'),
             'duration': data.get('duration'),
             'upload_date': upload_date,
+            'view_count': view_count,
         }
 
 

youtube_dl/extractor/vube.py

@@ -36,6 +36,7 @@ class VubeIE(InfoExtractor):
                 'comment_count': int,
                 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
             },
+            'skip': 'Not accessible from Travis CI server',
         }, {
             'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
             'md5': 'db7aba89d4603dadd627e9d1973946fe',

youtube_dl/extractor/xhamster.py

@@ -13,7 +13,6 @@ from ..utils import (
 
 
 class XHamsterIE(InfoExtractor):
-    """Information Extractor for xHamster"""
     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
     _TESTS = [
         {
@@ -133,3 +132,36 @@ class XHamsterIE(InfoExtractor):
             'age_limit': age_limit,
             'formats': formats,
         }
+
+
+class XHamsterEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://xhamster.com/xembed.php?video=3328539',
+        'info_dict': {
+            'id': '3328539',
+            'ext': 'mp4',
+            'title': 'Pen Masturbation',
+            'upload_date': '20140728',
+            'uploader_id': 'anonymous',
+            'duration': 5,
+            'age_limit': 18,
+        }
+    }
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
+            webpage, 'xhamster url')
+
+        return self.url_result(video_url, 'XHamster')

youtube_dl/extractor/xvideos.py

@@ -5,10 +5,12 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urllib_request,
 )
 from ..utils import (
     clean_html,
     ExtractorError,
+    determine_ext,
 )
 
 
@@ -25,6 +27,8 @@ class XVideosIE(InfoExtractor):
         }
     }
 
+    _ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
@@ -40,9 +44,30 @@ class XVideosIE(InfoExtractor):
         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
 
+        formats = [{
+            'url': video_url,
+        }]
+
+        android_req = compat_urllib_request.Request(url)
+        android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
+        android_webpage = self._download_webpage(android_req, video_id, fatal=False)
+
+        if android_webpage is not None:
+            player_params_str = self._search_regex(
+                'mobileReplacePlayerDivTwoQual\(([^)]+)\)',
+                android_webpage, 'player parameters', default='')
+            player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(',')))
+            if player_params:
+                formats.extend([{
+                    'url': param,
+                    'preference': -10,
+                } for param in player_params if determine_ext(param) == 'mp4'])
+
+        self._sort_formats(formats)
+
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'title': video_title,
             'ext': 'flv',
             'thumbnail': video_thumbnail,

youtube_dl/extractor/youku.py

@@ -1,123 +1,235 @@
 # coding: utf-8
-
 from __future__ import unicode_literals
 
-import math
-import random
-import re
-import time
+import base64
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..utils import ExtractorError
+
+from ..compat import (
+    compat_urllib_parse,
+    compat_ord,
+    compat_urllib_request,
 )
 
 
 class YoukuIE(InfoExtractor):
+    IE_NAME = 'youku'
     _VALID_URL = r'''(?x)
         (?:
             http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
             youku:)
         (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
     '''
-    _TEST = {
-        'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html',
-        'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b',
-        'params': {
-            'test': False
-        },
+
+    _TESTS = [{
+        'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
+        'md5': '5f3af4192eabacc4501508d54a8cabd7',
         'info_dict': {
-            'id': 'XNDgyMDQ2NTQw_part00',
-            'ext': 'flv',
-            'title': 'youtube-dl test video "\'/\\ä↭𝕐'
+            'id': 'XMTc1ODE5Njcy_part1',
+            'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
+            'ext': 'flv'
         }
-    }
+    }, {
+        'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
+        'only_matching': True,
+    }, {
+        'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
+        'info_dict': {
+            'id': 'XODgxNjg1Mzk2',
+            'title': '武媚娘传奇 85',
+        },
+        'playlist_count': 11,
+    }, {
+        'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
+        'info_dict': {
+            'id': 'XMTI1OTczNDM5Mg',
+            'title': '花千骨 04',
+        },
+        'playlist_count': 13,
+        'skip': 'Available in China only',
+    }]
 
-    def _gen_sid(self):
-        nowTime = int(time.time() * 1000)
-        random1 = random.randint(1000, 1998)
-        random2 = random.randint(1000, 9999)
+    def construct_video_urls(self, data1, data2):
+        # get sid, token
+        def yk_t(s1, s2):
+            ls = list(range(256))
+            t = 0
+            for i in range(256):
+                t = (t + ls[i] + compat_ord(s1[i % len(s1)])) % 256
+                ls[i], ls[t] = ls[t], ls[i]
+            s = bytearray()
+            x, y = 0, 0
+            for i in range(len(s2)):
+                y = (y + 1) % 256
+                x = (x + ls[y]) % 256
+                ls[x], ls[y] = ls[y], ls[x]
+                s.append(compat_ord(s2[i]) ^ ls[(ls[x] + ls[y]) % 256])
+            return bytes(s)
 
-        return "%d%d%d" % (nowTime, random1, random2)
+        sid, token = yk_t(
+            b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
+        ).decode('ascii').split('_')
 
-    def _get_file_ID_mix_string(self, seed):
-        mixed = []
-        source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
-        seed = float(seed)
-        for i in range(len(source)):
-            seed = (seed * 211 + 30031) % 65536
-            index = math.floor(seed / 65536 * len(source))
-            mixed.append(source[int(index)])
-            source.remove(source[int(index)])
-        # return ''.join(mixed)
-        return mixed
+        # get oip
+        oip = data2['ip']
 
-    def _get_file_id(self, fileId, seed):
-        mixed = self._get_file_ID_mix_string(seed)
-        ids = fileId.split('*')
-        realId = []
-        for ch in ids:
-            if ch:
-                realId.append(mixed[int(ch)])
-        return ''.join(realId)
+        # get fileid
+        string_ls = list(
+            'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
+        shuffled_string_ls = []
+        seed = data1['seed']
+        N = len(string_ls)
+        for ii in range(N):
+            seed = (seed * 0xd3 + 0x754f) % 0x10000
+            idx = seed * len(string_ls) // 0x10000
+            shuffled_string_ls.append(string_ls[idx])
+            del string_ls[idx]
+
+        fileid_dict = {}
+        for format in data1['streamtypes']:
+            streamfileid = [
+                int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
+            fileid = ''.join(
+                [shuffled_string_ls[i] for i in streamfileid])
+            fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
+
+        def get_fileid(format, n):
+            fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
+            return fileid
+
+        # get ep
+        def generate_ep(format, n):
+            fileid = get_fileid(format, n)
+            ep_t = yk_t(
+                b'bf7e5f01',
+                ('%s_%s_%s' % (sid, fileid, token)).encode('ascii')
+            )
+            ep = base64.b64encode(ep_t).decode('ascii')
+            return ep
+
+        # generate video_urls
+        video_urls_dict = {}
+        for format in data1['streamtypes']:
+            video_urls = []
+            for dt in data1['segs'][format]:
+                n = str(int(dt['no']))
+                param = {
+                    'K': dt['k'],
+                    'hd': self.get_hd(format),
+                    'myp': 0,
+                    'ts': dt['seconds'],
+                    'ypp': 0,
+                    'ctype': 12,
+                    'ev': 1,
+                    'token': token,
+                    'oip': oip,
+                    'ep': generate_ep(format, n)
+                }
+                video_url = \
+                    'http://k.youku.com/player/getFlvPath/' + \
+                    'sid/' + sid + \
+                    '_' + str(int(n) + 1).zfill(2) + \
+                    '/st/' + self.parse_ext_l(format) + \
+                    '/fileid/' + get_fileid(format, n) + '?' + \
+                    compat_urllib_parse.urlencode(param)
+                video_urls.append(video_url)
+            video_urls_dict[format] = video_urls
+
+        return video_urls_dict
+
+    def get_hd(self, fm):
+        hd_id_dict = {
+            'flv': '0',
+            'mp4': '1',
+            'hd2': '2',
+            'hd3': '3',
+            '3gp': '0',
+            '3gphd': '1'
+        }
+        return hd_id_dict[fm]
+
+    def parse_ext_l(self, fm):
+        ext_dict = {
+            'flv': 'flv',
+            'mp4': 'mp4',
+            'hd2': 'flv',
+            'hd3': 'flv',
+            '3gp': 'flv',
+            '3gphd': 'mp4'
+        }
+        return ext_dict[fm]
+
+    def get_format_name(self, fm):
+        _dict = {
+            '3gp': 'h6',
+            '3gphd': 'h5',
+            'flv': 'h4',
+            'mp4': 'h3',
+            'hd2': 'h2',
+            'hd3': 'h1'
+        }
+        return _dict[fm]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
+        def retrieve_data(req_url, note):
+            req = compat_urllib_request.Request(req_url)
 
-        config = self._download_json(info_url, video_id)
+            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+            if cn_verification_proxy:
+                req.add_header('Ytdl-request-proxy', cn_verification_proxy)
 
-        error_code = config['data'][0].get('error_code')
+            raw_data = self._download_json(req, video_id, note=note)
+            return raw_data['data'][0]
+
+        # request basic data
+        data1 = retrieve_data(
+            'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id,
+            'Downloading JSON metadata 1')
+        data2 = retrieve_data(
+            'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
+            'Downloading JSON metadata 2')
+
+        error_code = data1.get('error_code')
         if error_code:
-            # -8 means blocked outside China.
-            error = config['data'][0].get('error')  # Chinese and English, separated by newline.
-            raise ExtractorError(error or 'Server reported error %i' % error_code,
-                                 expected=True)
-
-        video_title = config['data'][0]['title']
-        seed = config['data'][0]['seed']
-
-        format = self._downloader.params.get('format', None)
-        supported_format = list(config['data'][0]['streamfileids'].keys())
-
-        # TODO proper format selection
-        if format is None or format == 'best':
-            if 'hd2' in supported_format:
-                format = 'hd2'
+            error = data1.get('error')
+            if error is not None and '因版权原因无法观看此视频' in error:
+                raise ExtractorError(
+                    'Youku said: Sorry, this video is available in China only', expected=True)
             else:
-                format = 'flv'
-            ext = 'flv'
-        elif format == 'worst':
-            format = 'mp4'
-            ext = 'mp4'
-        else:
-            format = 'flv'
-            ext = 'flv'
+                msg = 'Youku server reported error %i' % error_code
+                if error is not None:
+                    msg += ': ' + error
+                raise ExtractorError(msg)
 
-        fileid = config['data'][0]['streamfileids'][format]
-        keys = [s['k'] for s in config['data'][0]['segs'][format]]
-        # segs is usually a dictionary, but an empty *list* if an error occured.
+        title = data1['title']
 
-        files_info = []
-        sid = self._gen_sid()
-        fileid = self._get_file_id(fileid, seed)
+        # generate video_urls_dict
+        video_urls_dict = self.construct_video_urls(data1, data2)
 
-        # column 8,9 of fileid represent the segment number
-        # fileid[7:9] should be changed
-        for index, key in enumerate(keys):
-            temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
-            download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
+        # construct info
+        entries = [{
+            'id': '%s_part%d' % (video_id, i + 1),
+            'title': title,
+            'formats': [],
+            # some formats are not available for all parts, we have to detect
+            # which one has all
+        } for i in range(max(len(v) for v in data1['segs'].values()))]
+        for fm in data1['streamtypes']:
+            video_urls = video_urls_dict[fm]
+            for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries):
+                entry['formats'].append({
+                    'url': video_url,
+                    'format_id': self.get_format_name(fm),
+                    'ext': self.parse_ext_l(fm),
+                    'filesize': int(seg['size']),
+                })
 
-            info = {
-                'id': '%s_part%02d' % (video_id, index),
-                'url': download_url,
-                'uploader': None,
-                'upload_date': None,
-                'title': video_title,
-                'ext': ext,
-            }
-            files_info.append(info)
-
-        return files_info
+        return {
+            '_type': 'multi_video',
+            'id': video_id,
+            'title': title,
+            'entries': entries,
+        }

youtube_dl/extractor/youtube.py

@@ -29,9 +29,11 @@ from ..utils import (
     get_element_by_id,
     int_or_none,
     orderedSet,
+    str_to_int,
     unescapeHTML,
     unified_strdate,
     uppercase_escape,
+    ISO3166Utils,
 )
 
 
@@ -234,6 +236,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '44': {'ext': 'webm', 'width': 854, 'height': 480},
         '45': {'ext': 'webm', 'width': 1280, 'height': 720},
         '46': {'ext': 'webm', 'width': 1920, 'height': 1080},
+        '59': {'ext': 'mp4', 'width': 854, 'height': 480},
+        '78': {'ext': 'mp4', 'width': 854, 'height': 480},
 
 
         # 3d videos
@@ -516,6 +520,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'skip_download': 'requires avconv',
             }
         },
+        # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
+        {
+            'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
+            'info_dict': {
+                'id': 'FIl7x6_3R5Y',
+                'ext': 'mp4',
+                'title': 'md5:7b81415841e02ecd4313668cde88737a',
+                'description': 'md5:116377fd2963b81ec4ce64b542173306',
+                'upload_date': '20150625',
+                'uploader_id': 'dorappi2000',
+                'uploader': 'dorappi2000',
+                'formats': 'mincount:33',
+            },
+        }
     ]
 
     def __init__(self, *args, **kwargs):
@@ -785,7 +803,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             s = mobj.group(1)
             dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
             return '/signature/%s' % dec_s
-        dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
+        dash_manifest_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, dash_manifest_url)
         dash_doc = self._download_xml(
             dash_manifest_url, video_id,
             note='Downloading DASH manifest',
@@ -822,6 +840,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     except StopIteration:
                         full_info = self._formats.get(format_id, {}).copy()
                         full_info.update(f)
+                        codecs = r.attrib.get('codecs')
+                        if codecs:
+                            if full_info.get('acodec') == 'none' and 'vcodec' not in full_info:
+                                full_info['vcodec'] = codecs
+                            elif full_info.get('vcodec') == 'none' and 'acodec' not in full_info:
+                                full_info['acodec'] = codecs
                         formats.append(full_info)
                     else:
                         existing_format.update(f)
@@ -851,6 +875,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             player_url = None
 
+        dash_mpds = []
+
+        def add_dash_mpd(video_info):
+            dash_mpd = video_info.get('dashmpd')
+            if dash_mpd and dash_mpd[0] not in dash_mpds:
+                dash_mpds.append(dash_mpd[0])
+
         # Get video info
         embed_webpage = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
@@ -871,24 +902,29 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 note='Refetching age-gated info webpage',
                 errnote='unable to download video info webpage')
             video_info = compat_parse_qs(video_info_webpage)
+            add_dash_mpd(video_info)
         else:
             age_gate = False
-            try:
-                # Try looking directly into the video webpage
-                mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
-                if not mobj:
-                    raise ValueError('Could not find ytplayer.config')  # caught below
+            video_info = None
+            # Try looking directly into the video webpage
+            mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
+            if mobj:
                 json_code = uppercase_escape(mobj.group(1))
                 ytplayer_config = json.loads(json_code)
                 args = ytplayer_config['args']
-                # Convert to the same format returned by compat_parse_qs
-                video_info = dict((k, [v]) for k, v in args.items())
-                if not args.get('url_encoded_fmt_stream_map'):
-                    raise ValueError('No stream_map present')  # caught below
-            except ValueError:
-                # We fallback to the get_video_info pages (used by the embed page)
+                if args.get('url_encoded_fmt_stream_map'):
+                    # Convert to the same format returned by compat_parse_qs
+                    video_info = dict((k, [v]) for k, v in args.items())
+                    add_dash_mpd(video_info)
+            if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
+                # We also try looking in get_video_info since it may contain different dashmpd
+                # URL that points to a DASH manifest with possibly different itag set (some itags
+                # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
+                # manifest pointed by get_video_info's dashmpd).
+                # The general idea is to take a union of itags of both DASH manifests (for example
+                # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
                 self.report_video_info_webpage_download(video_id)
-                for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+                for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
                     video_info_url = (
                         '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
                         % (proto, video_id, el_type))
@@ -896,11 +932,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         video_info_url,
                         video_id, note=False,
                         errnote='unable to download video info webpage')
-                    video_info = compat_parse_qs(video_info_webpage)
-                    if 'token' in video_info:
+                    get_video_info = compat_parse_qs(video_info_webpage)
+                    add_dash_mpd(get_video_info)
+                    if not video_info:
+                        video_info = get_video_info
+                    if 'token' in get_video_info:
                         break
         if 'token' not in video_info:
             if 'reason' in video_info:
+                if 'The uploader has not made this video available in your country.' in video_info['reason']:
+                    regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
+                    if regions_allowed is not None:
+                        raise ExtractorError('YouTube said: This video is available in %s only' % (
+                            ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
+                            expected=True)
                 raise ExtractorError(
                     'YouTube said: %s' % video_info['reason'][0],
                     expected=True, video_id=video_id)
@@ -954,15 +999,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
 
         # upload date
-        upload_date = None
-        mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage)
-        if mobj is None:
-            mobj = re.search(
-                r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>',
-                video_webpage)
-        if mobj is not None:
-            upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
-            upload_date = unified_strdate(upload_date)
+        upload_date = self._html_search_meta(
+            'datePublished', video_webpage, 'upload date', default=None)
+        if not upload_date:
+            upload_date = self._search_regex(
+                [r'(?s)id="eow-date.*?>(.*?)</span>',
+                 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+                video_webpage, 'upload date', default=None)
+            if upload_date:
+                upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
+        upload_date = unified_strdate(upload_date)
 
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
@@ -996,12 +1042,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 video_description = ''
 
         def _extract_count(count_name):
-            count = self._search_regex(
-                r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name),
-                video_webpage, count_name, default=None)
-            if count is not None:
-                return int(count.replace(',', ''))
-            return None
+            return str_to_int(self._search_regex(
+                r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
+                % re.escape(count_name),
+                video_webpage, count_name, default=None))
+
         like_count = _extract_count('like')
         dislike_count = _extract_count('dislike')
 
@@ -1116,24 +1161,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         # Look for the DASH manifest
         if self._downloader.params.get('youtube_include_dash_manifest', True):
-            dash_mpd = video_info.get('dashmpd')
-            if dash_mpd:
-                dash_manifest_url = dash_mpd[0]
+            for dash_manifest_url in dash_mpds:
+                dash_formats = {}
                 try:
-                    dash_formats = self._parse_dash_manifest(
-                        video_id, dash_manifest_url, player_url, age_gate)
+                    for df in self._parse_dash_manifest(
+                            video_id, dash_manifest_url, player_url, age_gate):
+                        # Do not overwrite DASH format found in some previous DASH manifest
+                        if df['format_id'] not in dash_formats:
+                            dash_formats[df['format_id']] = df
                 except (ExtractorError, KeyError) as e:
                     self.report_warning(
                         'Skipping DASH manifest: %r' % e, video_id)
-                else:
+                if dash_formats:
                     # Remove the formats we found through non-DASH, they
                     # contain less info and it can be wrong, because we use
                     # fixed values (for example the resolution). See
                     # https://github.com/rg3/youtube-dl/issues/5774 for an
                     # example.
-                    dash_keys = set(df['format_id'] for df in dash_formats)
-                    formats = [f for f in formats if f['format_id'] not in dash_keys]
-                    formats.extend(dash_formats)
+                    formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
+                    formats.extend(dash_formats.values())
 
         # Check for malformed aspect ratio
         stretched_m = re.search(
@@ -1290,7 +1336,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     def _extract_playlist(self, playlist_id):
         url = self._TEMPLATE_URL % playlist_id
         page = self._download_webpage(url, playlist_id)
-        more_widget_html = content_html = page
 
         for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
             match = match.strip()
@@ -1310,36 +1355,36 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                 self.report_warning('Youtube gives an alert message: ' + match)
 
         # Extract the video ids from the playlist pages
-        ids = []
+        def _entries():
+            more_widget_html = content_html = page
+            for page_num in itertools.count(1):
+                matches = re.finditer(self._VIDEO_RE, content_html)
+                # We remove the duplicates and the link with index 0
+                # (it's not the first video of the playlist)
+                new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
+                for vid_id in new_ids:
+                    yield self.url_result(vid_id, 'Youtube', video_id=vid_id)
 
-        for page_num in itertools.count(1):
-            matches = re.finditer(self._VIDEO_RE, content_html)
-            # We remove the duplicates and the link with index 0
-            # (it's not the first video of the playlist)
-            new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
-            ids.extend(new_ids)
+                mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+                if not mobj:
+                    break
 
-            mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
-            if not mobj:
-                break
-
-            more = self._download_json(
-                'https://youtube.com/%s' % mobj.group('more'), playlist_id,
-                'Downloading page #%s' % page_num,
-                transform_source=uppercase_escape)
-            content_html = more['content_html']
-            if not content_html.strip():
-                # Some webpages show a "Load more" button but they don't
-                # have more videos
-                break
-            more_widget_html = more['load_more_widget_html']
+                more = self._download_json(
+                    'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+                    'Downloading page #%s' % page_num,
+                    transform_source=uppercase_escape)
+                content_html = more['content_html']
+                if not content_html.strip():
+                    # Some webpages show a "Load more" button but they don't
+                    # have more videos
+                    break
+                more_widget_html = more['load_more_widget_html']
 
         playlist_title = self._html_search_regex(
             r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
             page, 'title')
 
-        url_results = self._ids_to_results(ids)
-        return self.playlist_result(url_results, playlist_id, playlist_title)
+        return self.playlist_result(_entries(), playlist_id, playlist_title)
 
     def _real_extract(self, url):
         # Extract playlist id
@@ -1399,6 +1444,24 @@ class YoutubeChannelIE(InfoExtractor):
         channel_id = self._match_id(url)
 
         url = self._TEMPLATE_URL % channel_id
+
+        # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
+        # Workaround by extracting as a playlist if managed to obtain channel playlist URL
+        # otherwise fallback on channel by page extraction
+        channel_page = self._download_webpage(
+            url + '?view=57', channel_id,
+            'Downloading channel page', fatal=False)
+        channel_playlist_id = self._html_search_meta(
+            'channelId', channel_page, 'channel id', default=None)
+        if not channel_playlist_id:
+            channel_playlist_id = self._search_regex(
+                r'data-channel-external-id="([^"]+)"',
+                channel_page, 'channel id', default=None)
+        if channel_playlist_id and channel_playlist_id.startswith('UC'):
+            playlist_id = 'UU' + channel_playlist_id[2:]
+            return self.url_result(
+                compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
+
         channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
         autogenerated = re.search(r'''(?x)
                 class="[^"]*?(?:
@@ -1487,7 +1550,7 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
 
         for pagenum in itertools.count(1):
             url_query = {
-                'search_query': query,
+                'search_query': query.encode('utf-8'),
                 'page': pagenum,
                 'spf': 'navigate',
             }