release 2015.05.29

Subtitle conversion routine is removed, so the subtitles are TTML now. See
1c7e2e64f6

AUTHORS

@@ -124,3 +124,5 @@ Mohammad Teimori Pabandi
 Roman Le Négrate
 Matthias Küch
 Julian Richen
+Ping O.
+Mister Hat

README.md

@@ -17,12 +17,12 @@ youtube-dl - download videos from youtube.com or other video platforms
 To install it right away for all UNIX users (Linux, OS X, etc.), type:
 
     sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
-    sudo chmod a+x /usr/local/bin/youtube-dl
+    sudo chmod a+rx /usr/local/bin/youtube-dl
 
 If you do not have curl, you can alternatively use a recent wget:
 
     sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
-    sudo chmod a+x /usr/local/bin/youtube-dl
+    sudo chmod a+rx /usr/local/bin/youtube-dl
 
 Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29).
 
@@ -133,7 +133,7 @@ which means you can modify it, redistribute it or use it however you like.
     --no-mtime                       Do not use the Last-modified header to set the file modification time
     --write-description              Write video description to a .description file
     --write-info-json                Write video metadata to a .info.json file
-    --write-annotations              Write video annotations to a .annotation file
+    --write-annotations              Write video annotations to a .annotations.xml file
     --load-info FILE                 JSON file containing the video information (created with the "--write-info-json" option)
     --cookies FILE                   File to read cookies from and dump cookie jar in
     --cache-dir DIR                  Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
@@ -168,7 +168,7 @@ which means you can modify it, redistribute it or use it however you like.
     --no-progress                    Do not print progress bar
     --console-title                  Display progress in console titlebar
     -v, --verbose                    Print various debugging information
-    --dump-pages                     Print downloaded pages to debug problems (very verbose)
+    --dump-pages                     Print downloaded pages encoded using base64 to debug problems (very verbose)
     --write-pages                    Write downloaded intermediary pages to files in the current directory to debug problems
     --print-traffic                  Display sent and read HTTP traffic
     -C, --call-home                  Contact the youtube-dl server for debugging
@@ -216,11 +216,11 @@ which means you can modify it, redistribute it or use it however you like.
     --recode-video FORMAT            Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
     -k, --keep-video                 Keep the video file on disk after the post-processing; the video is erased by default
     --no-post-overwrites             Do not overwrite post-processed files; the post-processed files are overwritten by default
-    --embed-subs                     Embed subtitles in the video (only for mp4 videos)
+    --embed-subs                     Embed subtitles in the video (only for mkv and mp4 videos)
     --embed-thumbnail                Embed thumbnail in the audio as cover art
     --add-metadata                   Write metadata to the video file
     --metadata-from-title FORMAT     Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
-                                     parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s -
+                                     parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
                                      %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         Write metadata to the video file's xattrs (using dublin core and xdg standards)
     --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
@@ -269,7 +269,7 @@ The simplest case is requesting a specific format, for example `-f 22`. You can
 
 If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).  This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so  `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`.
 
-Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file.
+Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
 
 If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
 

docs/supportedsites.md

@@ -26,8 +26,7 @@
  - **anitube.se**
  - **AnySex**
  - **Aparat**
- - **AppleDailyAnimationNews**
- - **AppleDailyRealtimeNews**
+ - **AppleDaily**
  - **AppleTrailers**
  - **archive.org**: archive.org videos
  - **ARD**
@@ -44,6 +43,7 @@
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
+ - **BaiduVideo**
  - **bambuser**
  - **bambuser:channel**
  - **Bandcamp**
@@ -63,6 +63,8 @@
  - **BR**: Bayerischer Rundfunk Mediathek
  - **Break**
  - **Brightcove**
+ - **bt:article**: Bergens Tidende Articles
+ - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
  - **BuzzFeed**
  - **BYUtv**
  - **Camdemy**
@@ -139,6 +141,7 @@
  - **Eporner**
  - **EroProfile**
  - **Escapist**
+ - **ESPN** (Currently broken)
  - **EveryonesMixtape**
  - **exfm**: ex.fm
  - **ExpoTV**
@@ -148,13 +151,13 @@
  - **fc2**
  - **fernsehkritik.tv**
  - **fernsehkritik.tv:postecke**
- - **Firedrive**
  - **Firstpost**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
  - **Foxgay**
  - **FoxNews**
+ - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
  - **FranceInter**
@@ -184,7 +187,6 @@
  - **Golem**
  - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net
  - **Goshgay**
- - **Grooveshark**
  - **Groupon**
  - **Hark**
  - **HearThisAt**
@@ -226,6 +228,7 @@
  - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
+ - **KarriereVideos**
  - **keek**
  - **KeezMovies**
  - **KhanAcademy**
@@ -239,6 +242,7 @@
  - **LetvPlaylist**
  - **LetvTv**
  - **Libsyn**
+ - **life:embed**
  - **lifenews**: LIFE | NEWS
  - **LiveLeak**
  - **livestream**
@@ -287,6 +291,7 @@
  - **MySpass**
  - **myvideo**
  - **MyVidster**
+ - **N-JOY**
  - **n-tv.de**
  - **NationalGeographic**
  - **Naver**
@@ -316,6 +321,7 @@
  - **NosVideo**
  - **novamov**: NovaMov
  - **Nowness**
+ - **NowTV**
  - **nowvideo**: NowVideo
  - **npo.nl**
  - **npo.nl:live**
@@ -327,11 +333,13 @@
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
+ - **NYTimesArticle**
  - **ocw.mit.edu**
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
  - **Ooyala**
+ - **OoyalaExternal**
  - **OpenFilm**
  - **orf:fm4**: radio FM4
  - **orf:iptv**: iptv.ORF.at
@@ -363,9 +371,10 @@
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
  - **Pyvideo**
- - **QQMusic**
- - **QQMusicAlbum**
- - **QQMusicSinger**
+ - **qqmusic**
+ - **qqmusic:album**
+ - **qqmusic:singer**
+ - **qqmusic:toplist**
  - **QuickVid**
  - **R7**
  - **radio.de**
@@ -384,7 +393,6 @@
  - **Rte**
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **RTL2**
- - **RTLnow**
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
@@ -422,7 +430,6 @@
  - **smotri:community**: Smotri.com community videos
  - **smotri:user**: Smotri.com user videos
  - **Snotr**
- - **Sockshare**
  - **Sohu**
  - **soundcloud**
  - **soundcloud:playlist**
@@ -433,6 +440,8 @@
  - **southpark.cc.com**
  - **southpark.cc.com:español**
  - **southpark.de**
+ - **southpark.nl**
+ - **southparkstudios.dk**
  - **Space**
  - **SpankBang**
  - **Spankwire**
@@ -442,6 +451,7 @@
  - **Spike**
  - **Sport5**
  - **SportBox**
+ - **SportBoxEmbed**
  - **SportDeutschland**
  - **Srf**
  - **SRMediathek**: Saarländischer Rundfunk
@@ -452,6 +462,7 @@
  - **StreamCZ**
  - **StreetVoice**
  - **SunPorno**
+ - **SVT**
  - **SVTPlay**: SVT Play and Öppet arkiv
  - **SWRMediathek**
  - **Syfy**
@@ -485,6 +496,7 @@
  - **tlc.com**
  - **tlc.de**
  - **TMZ**
+ - **TMZArticle**
  - **TNAFlix**
  - **tou.tv**
  - **Toypics**: Toypics user profile
@@ -499,6 +511,8 @@
  - **Turbo**
  - **Tutv**
  - **tv.dfb.de**
+ - **TV2**
+ - **TV2Article**
  - **TV4**: tv4.se and tv4play.se
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvp.pl**
@@ -528,7 +542,7 @@
  - **Vessel**
  - **Vesti**: Вести.Ru
  - **Vevo**
- - **VGTV**
+ - **VGTV**: VGTV and BTTV
  - **vh1.com**
  - **Vice**
  - **Viddler**
@@ -548,6 +562,7 @@
  - **vier:videos**
  - **Viewster**
  - **viki**
+ - **viki:channel**
  - **vimeo**
  - **vimeo:album**
  - **vimeo:channel**
@@ -562,6 +577,7 @@
  - **vk.com**
  - **vk.com:user-videos**: vk.com:All of a user's videos
  - **Vodlocker**
+ - **VoiceRepublic**
  - **Vporn**
  - **VRT**
  - **vube**: Vube.com
@@ -586,6 +602,7 @@
  - **XHamster**
  - **XMinus**
  - **XNXX**
+ - **Xstream**
  - **XTube**
  - **XTubeUser**: XTube user profile
  - **Xuite**

test/test_YoutubeDL.py

@@ -12,6 +12,7 @@ import copy
 
 from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_str
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
 from youtube_dl.utils import match_filter_func
@@ -237,7 +238,7 @@ class TestFormatSelection(unittest.TestCase):
             f2['url'] = 'url:' + f2id
 
             info_dict = _make_result([f1, f2], extractor='youtube')
-            ydl = YDL()
+            ydl = YDL({'format': 'best/bestvideo'})
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
             ydl.process_ie_result(info_dict)
@@ -245,7 +246,7 @@ class TestFormatSelection(unittest.TestCase):
             self.assertEqual(downloaded['format_id'], f1id)
 
             info_dict = _make_result([f2, f1], extractor='youtube')
-            ydl = YDL()
+            ydl = YDL({'format': 'best/bestvideo'})
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
             ydl.process_ie_result(info_dict)
@@ -507,6 +508,51 @@ class TestYoutubeDL(unittest.TestCase):
         res = get_videos(f)
         self.assertEqual(res, ['1'])
 
+    def test_playlist_items_selection(self):
+        entries = [{
+            'id': compat_str(i),
+            'title': compat_str(i),
+            'url': TEST_URL,
+        } for i in range(1, 5)]
+        playlist = {
+            '_type': 'playlist',
+            'id': 'test',
+            'entries': entries,
+            'extractor': 'test:playlist',
+            'extractor_key': 'test:playlist',
+            'webpage_url': 'http://example.com',
+        }
+
+        def get_ids(params):
+            ydl = YDL(params)
+            # make a copy because the dictionary can be modified
+            ydl.process_ie_result(playlist.copy())
+            return [int(v['id']) for v in ydl.downloaded_info_dicts]
+
+        result = get_ids({})
+        self.assertEqual(result, [1, 2, 3, 4])
+
+        result = get_ids({'playlistend': 10})
+        self.assertEqual(result, [1, 2, 3, 4])
+
+        result = get_ids({'playlistend': 2})
+        self.assertEqual(result, [1, 2])
+
+        result = get_ids({'playliststart': 10})
+        self.assertEqual(result, [])
+
+        result = get_ids({'playliststart': 2})
+        self.assertEqual(result, [2, 3, 4])
+
+        result = get_ids({'playlist_items': '2-4'})
+        self.assertEqual(result, [2, 3, 4])
+
+        result = get_ids({'playlist_items': '2,4'})
+        self.assertEqual(result, [2, 4])
+
+        result = get_ids({'playlist_items': '10'})
+        self.assertEqual(result, [])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

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

test/test_utils.py

@@ -40,7 +40,8 @@ from youtube_dl.utils import (
     read_batch_urls,
     sanitize_filename,
     sanitize_path,
-    sanitize_url_path_consecutive_slashes,
+    prepend_extension,
+    replace_extension,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -51,6 +52,7 @@ from youtube_dl.utils import (
     unified_strdate,
     unsmuggle_url,
     uppercase_escape,
+    lowercase_escape,
     url_basename,
     urlencode_postdata,
     version_tuple,
@@ -173,25 +175,21 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_path('./abc'), 'abc')
         self.assertEqual(sanitize_path('./../abc'), '..\\abc')
 
-    def test_sanitize_url_path_consecutive_slashes(self):
-        self.assertEqual(
-            sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
-            'http://hostname/foo/bar/filename.html')
-        self.assertEqual(
-            sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
-            'http://hostname/foo/bar/filename.html')
-        self.assertEqual(
-            sanitize_url_path_consecutive_slashes('http://hostname//'),
-            'http://hostname/')
-        self.assertEqual(
-            sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
-            'http://hostname/foo/bar/filename.html')
-        self.assertEqual(
-            sanitize_url_path_consecutive_slashes('http://hostname/'),
-            'http://hostname/')
-        self.assertEqual(
-            sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
-            'http://hostname/abc/')
+    def test_prepend_extension(self):
+        self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
+        self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
+
+    def test_replace_extension(self):
+        self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
+        self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+        self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
+        self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
+        self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 
     def test_ordered_set(self):
         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
@@ -400,6 +398,10 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 
+    def test_lowercase_escape(self):
+        self.assertEqual(lowercase_escape('aä'), 'aä')
+        self.assertEqual(lowercase_escape('\\u0026'), '&')
+
     def test_limit_length(self):
         self.assertEqual(limit_length(None, 12), None)
         self.assertEqual(limit_length('foo', 12), 'foo')
@@ -598,7 +600,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
                 <div xml:lang="en">
                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
                     <p begin="1" end="2">第二行<br/>♪♪</p>
-                    <p begin="2" end="3"><span>Third<br/>Line</span></p>
+                    <p begin="2" dur="1"><span>Third<br/>Line</span></p>
                 </div>
             </body>
             </tt>'''
@@ -619,6 +621,21 @@ Line
 '''
         self.assertEqual(dfxp2srt(dfxp_data), srt_data)
 
+        dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
+            <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+            <body>
+                <div xml:lang="en">
+                    <p begin="0" end="1">The first line</p>
+                </div>
+            </body>
+            </tt>'''
+        srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The first line
+
+'''
+        self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
+
 
 if __name__ == '__main__':
     unittest.main()

tox.ini

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

youtube_dl/YoutubeDL.py

@@ -71,6 +71,7 @@ from .utils import (
     write_string,
     YoutubeDLHandler,
     prepend_extension,
+    replace_extension,
     args_to_str,
     age_restricted,
 )
@@ -259,7 +260,6 @@ class YoutubeDL(object):
     The following options are used by the post processors:
     prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
                        otherwise prefer avconv.
-    exec_cmd:          Arbitrary command to run after downloading
     """
 
     params = None
@@ -759,7 +759,9 @@ class YoutubeDL(object):
             if isinstance(ie_entries, list):
                 n_all_entries = len(ie_entries)
                 if playlistitems:
-                    entries = [ie_entries[i - 1] for i in playlistitems]
+                    entries = [
+                        ie_entries[i - 1] for i in playlistitems
+                        if -n_all_entries <= i - 1 < n_all_entries]
                 else:
                     entries = ie_entries[playliststart:playlistend]
                 n_entries = len(entries)
@@ -914,15 +916,16 @@ class YoutubeDL(object):
         if not available_formats:
             return None
 
-        if format_spec == 'best' or format_spec is None:
-            return available_formats[-1]
-        elif format_spec == 'worst':
+        if format_spec in ['best', 'worst', None]:
+            format_idx = 0 if format_spec == 'worst' else -1
             audiovideo_formats = [
                 f for f in available_formats
                 if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
             if audiovideo_formats:
-                return audiovideo_formats[0]
-            return available_formats[0]
+                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):
+                return available_formats[format_idx]
         elif format_spec == 'bestaudio':
             audio_formats = [
                 f for f in available_formats
@@ -1084,8 +1087,11 @@ class YoutubeDL(object):
         req_format = self.params.get('format')
         if req_format is None:
             req_format_list = []
-            if info_dict['extractor'] in ['youtube', 'ted'] and FFmpegMergerPP(self).available:
-                req_format_list.append('bestvideo+bestaudio')
+            if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
+                    info_dict['extractor'] in ['youtube', 'ted']):
+                merger = FFmpegMergerPP(self)
+                if merger.available and merger.can_merge():
+                    req_format_list.append('bestvideo+bestaudio')
             req_format_list.append('best')
             req_format = '/'.join(req_format_list)
         formats_to_download = []
@@ -1269,7 +1275,7 @@ class YoutubeDL(object):
             return
 
         if self.params.get('writedescription', False):
-            descfn = filename + '.description'
+            descfn = replace_extension(filename, 'description', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
             elif info_dict.get('description') is None:
@@ -1284,7 +1290,7 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeannotations', False):
-            annofn = filename + '.annotations.xml'
+            annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
                 self.to_screen('[info] Video annotations are already present')
             else:
@@ -1331,13 +1337,13 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeinfojson', False):
-            infofn = os.path.splitext(filename)[0] + '.info.json'
+            infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
                 self.to_screen('[info] Video description metadata is already present')
             else:
                 self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
                 try:
-                    write_json_file(info_dict, infofn)
+                    write_json_file(self.filter_requested_info(info_dict), infofn)
                 except (OSError, IOError):
                     self.report_error('Cannot write metadata to JSON file ' + infofn)
                     return
@@ -1362,7 +1368,7 @@ class YoutubeDL(object):
                         postprocessors = []
                         self.report_warning('You have requested multiple '
                                             'formats but ffmpeg or avconv are not installed.'
-                                            ' The formats won\'t be merged')
+                                            ' The formats won\'t be merged.')
                     else:
                         postprocessors = [merger]
 
@@ -1381,11 +1387,18 @@ class YoutubeDL(object):
                         # TODO: Check acodec/vcodec
                         return False
 
+                    filename_real_ext = os.path.splitext(filename)[1][1:]
+                    filename_wo_ext = (
+                        os.path.splitext(filename)[0]
+                        if filename_real_ext == info_dict['ext']
+                        else filename)
                     requested_formats = info_dict['requested_formats']
                     if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
-                        filename = os.path.splitext(filename)[0] + '.mkv'
-                        self.report_warning('You have requested formats uncompatible for merge. '
-                                            'The formats will be merged into mkv')
+                        info_dict['ext'] = 'mkv'
+                        self.report_warning(
+                            'Requested formats are incompatible for merge and will be merged into mkv.')
+                    # Ensure filename always has a correct extension for successful merge
+                    filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
                     if os.path.exists(encodeFilename(filename)):
                         self.to_screen(
                             '[download] %s has already been downloaded and '
@@ -1395,7 +1408,7 @@ class YoutubeDL(object):
                             new_info = dict(info_dict)
                             new_info.update(f)
                             fname = self.prepare_filename(new_info)
-                            fname = prepend_extension(fname, 'f%s' % f['format_id'])
+                            fname = prepend_extension(fname, 'f%s' % f['format_id'], new_info['ext'])
                             downloaded.append(fname)
                             partial_success = dl(fname, new_info)
                             success = success and partial_success
@@ -1487,7 +1500,7 @@ class YoutubeDL(object):
                 [info_filename], mode='r',
                 openhook=fileinput.hook_encoded('utf-8'))) as f:
             # FileInput doesn't have a read method, we can't call json.load
-            info = json.loads('\n'.join(f))
+            info = self.filter_requested_info(json.loads('\n'.join(f)))
         try:
             self.process_ie_result(info, download=True)
         except DownloadError:
@@ -1499,6 +1512,12 @@ class YoutubeDL(object):
                 raise
         return self._download_retcode
 
+    @staticmethod
+    def filter_requested_info(info_dict):
+        return dict(
+            (k, v) for k, v in info_dict.items()
+            if k not in ['requested_formats', 'requested_subtitles'])
+
     def post_process(self, filename, ie_info):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
@@ -1508,6 +1527,7 @@ class YoutubeDL(object):
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
+            files_to_delete = []
             try:
                 files_to_delete, info = pp.run(info)
             except PostProcessingError as e:
@@ -1832,7 +1852,7 @@ class YoutubeDL(object):
             thumb_ext = determine_ext(t['url'], 'jpg')
             suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
             thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
-            thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+            t['filename'] = thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
 
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
                 self.to_screen('[%s] %s: Thumbnail %sis already present' %

youtube_dl/__init__.py

@@ -240,13 +240,18 @@ def _real_main(argv=None):
     if opts.xattrs:
         postprocessors.append({'key': 'XAttrMetadata'})
     if opts.embedthumbnail:
-        postprocessors.append({'key': 'EmbedThumbnail'})
+        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+        postprocessors.append({
+            'key': 'EmbedThumbnail',
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',
-            'verboseOutput': opts.verbose,
             'exec_cmd': opts.exec_cmd,
         })
     if opts.xattr_set_filesize:
@@ -345,7 +350,6 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
-        'exec_cmd': opts.exec_cmd,
         'extract_flat': opts.extract_flat,
         'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,

youtube_dl/aes.py

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

youtube_dl/compat.py

@@ -46,11 +46,6 @@ try:
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
-try:
-    import html.parser as compat_html_parser
-except ImportError:  # Python 2
-    import HTMLParser as compat_html_parser
-
 try:
     import http.client as compat_http_client
 except ImportError:  # Python 2
@@ -404,7 +399,6 @@ __all__ = [
     'compat_getenv',
     'compat_getpass',
     'compat_html_entities',
-    'compat_html_parser',
     'compat_http_client',
     'compat_http_server',
     'compat_kwargs',

youtube_dl/downloader/http.py

@@ -28,13 +28,8 @@ class HttpFD(FileDownloader):
         add_headers = info_dict.get('http_headers')
         if add_headers:
             headers.update(add_headers)
-        data = info_dict.get('http_post_data')
-        http_method = info_dict.get('http_method')
-        basic_request = compat_urllib_request.Request(url, data, headers)
-        request = compat_urllib_request.Request(url, data, headers)
-        if http_method is not None:
-            basic_request.get_method = lambda: http_method
-            request.get_method = lambda: http_method
+        basic_request = compat_urllib_request.Request(url, None, headers)
+        request = compat_urllib_request.Request(url, None, headers)
 
         is_test = self.params.get('test', False)
 

youtube_dl/downloader/rtmp.py

@@ -131,7 +131,7 @@ class RtmpFD(FileDownloader):
         if play_path is not None:
             basic_args += ['--playpath', play_path]
         if tc_url is not None:
-            basic_args += ['--tcUrl', url]
+            basic_args += ['--tcUrl', tc_url]
         if test:
             basic_args += ['--stop', '1']
         if flash_version is not None:

youtube_dl/extractor/__init__.py

@@ -32,6 +32,7 @@ from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
+from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
@@ -140,6 +141,7 @@ from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
 from .escapist import EscapistIE
+from .espn import ESPNIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
 from .expotv import ExpoTVIE
@@ -147,7 +149,6 @@ from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
 from .fc2 import FC2IE
-from .firedrive import FiredriveIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
@@ -161,6 +162,7 @@ from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
+from .foxsports import FoxSportsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
@@ -198,7 +200,6 @@ from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
-from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .hearthisat import HearThisAtIE
@@ -242,6 +243,7 @@ from .kaltura import KalturaIE
 from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
+from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
@@ -257,7 +259,10 @@ from .letv import (
     LetvPlaylistIE
 )
 from .libsyn import LibsynIE
-from .lifenews import LifeNewsIE
+from .lifenews import (
+    LifeNewsIE,
+    LifeEmbedIE,
+)
 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,
@@ -320,7 +325,10 @@ from .nbc import (
     NBCSportsIE,
     NBCSportsVPlayerIE,
 )
-from .ndr import NDRIE
+from .ndr import (
+    NDRIE,
+    NJoyIE,
+)
 from .ndtv import NDTVIE
 from .netzkino import NetzkinoIE
 from .nerdcubed import NerdCubedFeedIE
@@ -330,8 +338,7 @@ from .newstube import NewstubeIE
 from .nextmedia import (
     NextMediaIE,
     NextMediaActionNewsIE,
-    AppleDailyRealtimeNewsIE,
-    AppleDailyAnimationNewsIE
+    AppleDailyIE,
 )
 from .nfb import NFBIE
 from .nfl import NFLIE
@@ -347,6 +354,7 @@ from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
+from .nowtv import NowTVIE
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
@@ -362,11 +370,17 @@ from .nrk import (
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
-from .nytimes import NYTimesIE
+from .nytimes import (
+    NYTimesIE,
+    NYTimesArticleIE,
+)
 from .nuvid import NuvidIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
-from .ooyala import OoyalaIE
+from .ooyala import (
+    OoyalaIE,
+    OoyalaExternalIE,
+)
 from .openfilm import OpenFilmIE
 from .orf import (
     ORFTVthekIE,
@@ -404,6 +418,7 @@ from .qqmusic import (
     QQMusicIE,
     QQMusicSingerIE,
     QQMusicAlbumIE,
+    QQMusicToplistIE,
 )
 from .quickvid import QuickVidIE
 from .r7 import R7IE
@@ -423,7 +438,6 @@ from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
 from .rte import RteIE
 from .rtlnl import RtlNlIE
-from .rtlnow import RTLnowIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
@@ -465,7 +479,6 @@ from .smotri import (
     SmotriBroadcastIE,
 )
 from .snotr import SnotrIE
-from .sockshare import SockshareIE
 from .sohu import SohuIE
 from .soundcloud import (
     SoundcloudIE,
@@ -479,8 +492,10 @@ from .soundgasm import (
 )
 from .southpark import (
     SouthParkIE,
+    SouthParkDeIE,
+    SouthParkDkIE,
     SouthParkEsIE,
-    SouthparkDeIE,
+    SouthParkNlIE
 )
 from .space import SpaceIE
 from .spankbang import SpankBangIE
@@ -489,7 +504,10 @@ from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .sport5 import Sport5IE
-from .sportbox import SportBoxIE
+from .sportbox import (
+    SportBoxIE,
+    SportBoxEmbedIE,
+)
 from .sportdeutschland import SportDeutschlandIE
 from .srf import SrfIE
 from .srmediathek import SRMediathekIE
@@ -500,7 +518,10 @@ from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
 from .streetvoice import StreetVoiceIE
 from .sunporno import SunPornoIE
-from .svtplay import SVTPlayIE
+from .svt import (
+    SVTIE,
+    SVTPlayIE,
+)
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
@@ -529,7 +550,10 @@ from .thesixtyone import TheSixtyOneIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
-from .tmz import TMZIE
+from .tmz import (
+    TMZIE,
+    TMZArticleIE,
+)
 from .tnaflix import TNAFlixIE
 from .thvideo import (
     THVideoIE,
@@ -546,6 +570,10 @@ from .tumblr import TumblrIE
 from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
+from .tv2 import (
+    TV2IE,
+    TV2ArticleIE,
+)
 from .tv4 import TV4IE
 from .tvigle import TvigleIE
 from .tvp import TvpIE, TvpSeriesIE
@@ -582,7 +610,11 @@ from .veoh import VeohIE
 from .vessel import VesselIE
 from .vesti import VestiIE
 from .vevo import VevoIE
-from .vgtv import VGTVIE
+from .vgtv import (
+    BTArticleIE,
+    BTVestlendingenIE,
+    VGTVIE,
+)
 from .vh1 import VH1IE
 from .vice import ViceIE
 from .viddler import ViddlerIE
@@ -613,12 +645,16 @@ from .vine import (
     VineIE,
     VineUserIE,
 )
-from .viki import VikiIE
+from .viki import (
+    VikiIE,
+    VikiChannelIE,
+)
 from .vk import (
     VKIE,
     VKUserVideosIE,
 )
 from .vodlocker import VodlockerIE
+from .voicerepublic import VoiceRepublicIE
 from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
@@ -645,9 +681,10 @@ from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
-from .xvideos import XVideosIE
+from .xstream import XstreamIE
 from .xtube import XTubeUserIE, XTubeIE
 from .xuite import XuiteIE
+from .xvideos import XVideosIE
 from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,

youtube_dl/extractor/aftenposten.py

@@ -1,21 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    parse_iso8601,
-    xpath_with_ns,
-    xpath_text,
-    find_xpath_attr,
-)
 
 
 class AftenpostenIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
-
     _TEST = {
         'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
         'md5': 'fd828cd29774a729bf4d4425fe192972',
@@ -30,69 +20,4 @@ class AftenpostenIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        data = self._download_xml(
-            'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)
-
-        NS_MAP = {
-            'atom': 'http://www.w3.org/2005/Atom',
-            'xt': 'http://xstream.dk/',
-            'media': 'http://search.yahoo.com/mrss/',
-        }
-
-        entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
-
-        title = xpath_text(
-            entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
-        description = xpath_text(
-            entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
-        timestamp = parse_iso8601(xpath_text(
-            entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
-
-        formats = []
-        media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
-        for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
-            media_url = media_content.get('url')
-            if not media_url:
-                continue
-            tbr = int_or_none(media_content.get('bitrate'))
-            mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
-            if mobj:
-                formats.append({
-                    'url': mobj.group('url'),
-                    'play_path': 'mp4:%s' % mobj.group('playpath'),
-                    'app': mobj.group('app'),
-                    'ext': 'flv',
-                    'tbr': tbr,
-                    'format_id': 'rtmp-%d' % tbr,
-                })
-            else:
-                formats.append({
-                    'url': media_url,
-                    'tbr': tbr,
-                })
-        self._sort_formats(formats)
-
-        link = find_xpath_attr(
-            entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
-        if link is not None:
-            formats.append({
-                'url': link.get('href'),
-                'format_id': link.get('rel'),
-            })
-
-        thumbnails = [{
-            'url': splash.get('url'),
-            'width': int_or_none(splash.get('width')),
-            'height': int_or_none(splash.get('height')),
-        } for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'formats': formats,
-            'thumbnails': thumbnails,
-        }
+        return self.url_result('xstream:ap:%s' % self._match_id(url), 'Xstream')

youtube_dl/extractor/archiveorg.py

@@ -33,7 +33,7 @@ class ArchiveOrgIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        json_url = url + ('?' if '?' in url else '&') + 'output=json'
+        json_url = url + ('&' if '?' in url else '?') + 'output=json'
         data = self._download_json(json_url, video_id)
 
         def get_optional(data_dict, field):

youtube_dl/extractor/arte.py

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

youtube_dl/extractor/baidu.py

@@ -0,0 +1,68 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+
+
+class BaiduVideoIE(InfoExtractor):
+    _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
+    _TESTS = [{
+        'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
+        'info_dict': {
+            'id': '1069',
+            'title': '中华小当家 TV版 (全52集)',
+            'description': 'md5:395a419e41215e531c857bb037bbaf80',
+        },
+        'playlist_count': 52,
+    }, {
+        'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
+        'info_dict': {
+            'id': '11595',
+            'title': 're:^奔跑吧兄弟',
+            'description': 'md5:1bf88bad6d850930f542d51547c089b8',
+        },
+        'playlist_mincount': 3,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        category = category2 = mobj.group('type')
+        if category == 'show':
+            category2 = 'tvshow'
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_title = self._html_search_regex(
+            r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage,
+            'playlist title', group='title')
+        playlist_description = self._html_search_regex(
+            r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage,
+            playlist_id, 'playlist description')
+
+        site = self._html_search_regex(
+            r'filterSite\s*:\s*["\']([^"]*)["\']', webpage,
+            'primary provider site')
+        api_result = self._download_json(
+            'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % (
+                category, category2, playlist_id, site),
+            playlist_id, 'Get playlist links')
+
+        entries = []
+        for episode in api_result[0]['episodes']:
+            episode_id = '%s_%s' % (playlist_id, episode['episode'])
+
+            redirect_page = self._download_webpage(
+                compat_urlparse.urljoin(url, episode['url']), episode_id,
+                note='Download Baidu redirect page')
+            real_url = self._html_search_regex(
+                r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL')
+
+            entries.append(self.url_result(
+                real_url, video_title=episode['single_title']))
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)

youtube_dl/extractor/bbccouk.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
 from ..compat import compat_HTTPError
 
 
@@ -112,6 +115,20 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             }
+        }, {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
+            'info_dict': {
+                'id': 'p02n76xf',
+                'ext': 'flv',
+                'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
+                'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
+                'duration': 3540,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'geolocation',
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
@@ -326,16 +343,27 @@ class BBCCoUkIE(InfoExtractor):
 
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
-        programme_id = self._search_regex(
-            r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+        programme_id = None
+
+        tviplayer = self._search_regex(
+            r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
+            webpage, 'player', default=None)
+
+        if tviplayer:
+            player = self._parse_json(tviplayer, group_id).get('player', {})
+            duration = int_or_none(player.get('duration'))
+            programme_id = player.get('vpid')
+
+        if not programme_id:
+            programme_id = self._search_regex(
+                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+
         if programme_id:
-            player = self._download_json(
-                'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,
-                group_id)['jsConf']['player']
-            title = player['title']
-            description = player['subtitle']
-            duration = player['duration']
             formats, subtitles = self._download_media_selector(programme_id)
+            title = self._og_search_title(webpage)
+            description = self._search_regex(
+                r'<p class="medium-description">([^<]+)</p>',
+                webpage, 'description', fatal=False)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
@@ -345,6 +373,7 @@ class BBCCoUkIE(InfoExtractor):
             'id': programme_id,
             'title': title,
             'description': description,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'duration': duration,
             'formats': formats,
             'subtitles': subtitles,

youtube_dl/extractor/bet.py

@@ -16,11 +16,11 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': '740ab250-bb94-4a8a-8787-fe0de7c74471',
+                'id': 'news/national/2014/a-conversation-with-president-obama',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
-                'title': 'BET News Presents: A Conversation With President Obama',
-                'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6',
+                'title': 'A Conversation With President Obama',
+                'description': 'md5:699d0652a350cf3e491cd15cc745b5da',
                 'duration': 1534,
                 'timestamp': 1418075340,
                 'upload_date': '20141208',
@@ -35,7 +35,7 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d',
+                'id': 'news/national/2014/justice-for-ferguson-a-community-reacts',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
@@ -61,6 +61,9 @@ class BetIE(InfoExtractor):
             [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
             webpage, 'media URL'))
 
+        video_id = self._search_regex(
+            r'/video/(.*)/_jcr_content/', media_url, 'video id')
+
         mrss = self._download_xml(media_url, display_id)
 
         item = mrss.find('./channel/item')
@@ -75,8 +78,6 @@ class BetIE(InfoExtractor):
         description = xpath_text(
             item, './description', 'description', fatal=False)
 
-        video_id = xpath_text(item, './guid', 'video id', fatal=False)
-
         timestamp = parse_iso8601(xpath_text(
             item, xpath_with_ns('./dc:date', NS_MAP),
             'upload date', fatal=False))

youtube_dl/extractor/bild.py

@@ -2,7 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    fix_xml_ampersands,
+)
 
 
 class BildIE(InfoExtractor):
@@ -15,7 +18,7 @@ class BildIE(InfoExtractor):
             'id': '38184146',
             'ext': 'mp4',
             'title': 'BILD hat sie getestet',
-            'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg',
+            'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 196,
             'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
         }
@@ -25,7 +28,7 @@ class BildIE(InfoExtractor):
         video_id = self._match_id(url)
 
         xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
-        doc = self._download_xml(xml_url, video_id)
+        doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
 
         duration = int_or_none(doc.attrib.get('duration'), scale=1000)
 

youtube_dl/extractor/bilibili.py

@@ -2,6 +2,9 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
+import json
+import xml.etree.ElementTree as ET
 
 from .common import InfoExtractor
 from ..utils import (
@@ -14,18 +17,25 @@ from ..utils import (
 class BiliBiliIE(InfoExtractor):
     _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '2c301e4dab317596e837c3e7633e7d86',
         'info_dict': {
-            'id': '1074402',
+            'id': '1074402_part1',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
             'duration': 308,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://www.bilibili.com/video/av1041170/',
+        'info_dict': {
+            'id': '1041170',
+            'title': '【BD1080P】刀语【诸神&异域】',
+        },
+        'playlist_count': 9,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -57,19 +67,22 @@ class BiliBiliIE(InfoExtractor):
 
         cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
 
-        lq_doc = self._download_xml(
+        entries = []
+
+        lq_page = self._download_webpage(
             'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
             video_id,
             note='Downloading LQ video info'
         )
-        lq_durl = lq_doc.find('./durl')
-        formats = [{
-            'format_id': 'lq',
-            'quality': 1,
-            'url': lq_durl.find('./url').text,
-            'filesize': int_or_none(
-                lq_durl.find('./size'), get_attr='text'),
-        }]
+        try:
+            err_info = json.loads(lq_page)
+            raise ExtractorError(
+                'BiliBili said: ' + err_info['error_text'], expected=True)
+        except ValueError:
+            pass
+
+        lq_doc = ET.fromstring(lq_page)
+        lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(
             'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
@@ -78,22 +91,45 @@ class BiliBiliIE(InfoExtractor):
             fatal=False,
         )
         if hq_doc is not False:
-            hq_durl = hq_doc.find('./durl')
-            formats.append({
-                'format_id': 'hq',
-                'quality': 2,
-                'ext': 'flv',
-                'url': hq_durl.find('./url').text,
+            hq_durls = hq_doc.findall('./durl')
+            assert len(lq_durls) == len(hq_durls)
+        else:
+            hq_durls = itertools.repeat(None)
+
+        i = 1
+        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
+            formats = [{
+                'format_id': 'lq',
+                'quality': 1,
+                'url': lq_durl.find('./url').text,
                 'filesize': int_or_none(
-                    hq_durl.find('./size'), get_attr='text'),
+                    lq_durl.find('./size'), get_attr='text'),
+            }]
+            if hq_durl:
+                formats.append({
+                    'format_id': 'hq',
+                    'quality': 2,
+                    'ext': 'flv',
+                    'url': hq_durl.find('./url').text,
+                    'filesize': int_or_none(
+                        hq_durl.find('./size'), get_attr='text'),
+                })
+            self._sort_formats(formats)
+
+            entries.append({
+                'id': '%s_part%d' % (video_id, i),
+                'title': title,
+                'formats': formats,
+                'duration': duration,
+                'upload_date': upload_date,
+                'thumbnail': thumbnail,
             })
 
-        self._sort_formats(formats)
+            i += 1
+
         return {
+            '_type': 'multi_video',
+            'entries': entries,
             'id': video_id,
-            'title': title,
-            'formats': formats,
-            'duration': duration,
-            'upload_date': upload_date,
-            'thumbnail': thumbnail,
+            'title': title
         }

youtube_dl/extractor/br.py

@@ -16,27 +16,38 @@ class BRIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
-            'md5': '93556dd2bcb2948d9259f8670c516d59',
+            'url': 'http://www.br.de/mediathek/video/sendungen/abendschau/betriebliche-altersvorsorge-104.html',
+            'md5': '83a0477cf0b8451027eb566d88b51106',
             'info_dict': {
-                'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
+                'id': '48f656ef-287e-486f-be86-459122db22cc',
                 'ext': 'mp4',
-                'title': 'Wenn das Traditions-Theater wackelt',
-                'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt',
-                'duration': 34,
-                'uploader': 'BR',
-                'upload_date': '20140802',
+                'title': 'Die böse Überraschung',
+                'description': 'Betriebliche Altersvorsorge: Die böse Überraschung',
+                'duration': 180,
+                'uploader': 'Reinhard Weber',
+                'upload_date': '20150422',
             }
         },
         {
-            'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html',
-            'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820',
+            'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
+            'md5': 'a44396d73ab6a68a69a568fae10705bb',
             'info_dict': {
-                'id': 'c6aae3de-2cf9-43f2-957f-f17fef9afaab',
+                'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05',
+                'ext': 'mp4',
+                'title': 'Manfred Schreiber ist tot',
+                'description': 'Abendschau kompakt: Manfred Schreiber ist tot',
+                'duration': 26,
+            }
+        },
+        {
+            'url': 'http://www.br.de/radio/br-klassik/sendungen/allegro/premiere-urauffuehrung-the-land-2015-dance-festival-muenchen-100.html',
+            'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d',
+            'info_dict': {
+                'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b',
                 'ext': 'aac',
-                'title': '"Keine neuen Schulden im nächsten Jahr"',
-                'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"',
-                'duration': 64,
+                'title': 'Kurzweilig und sehr bewegend',
+                'description': '"The Land" von Peeping Tom: Kurzweilig und sehr bewegend',
+                'duration': 296,
             }
         },
         {

youtube_dl/extractor/byutv.py

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

youtube_dl/extractor/canalplus.py

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

youtube_dl/extractor/cbsnews.py

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

youtube_dl/extractor/ccc.py

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

youtube_dl/extractor/chilloutzone.py

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

youtube_dl/extractor/cinemassacre.py

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

youtube_dl/extractor/cnn.py

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

youtube_dl/extractor/common.py

@@ -47,7 +47,7 @@ class InfoExtractor(object):
     information possibly downloading the video to the file system, among
     other possible outcomes.
 
-    The type field determines the the type of the result.
+    The type field determines the type of the result.
     By far the most common value (and the default if _type is missing) is
     "video", which indicates a single video.
 
@@ -111,11 +111,8 @@ class InfoExtractor(object):
                                   (quality takes higher priority)
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
-                    * http_method  HTTP method to use for the download.
                     * http_headers  A dictionary of additional HTTP headers
                                  to add to the request.
-                    * http_post_data  Additional data to send with a POST
-                                 request.
                     * stretched_ratio  If given and not 1, indicates that the
                                  video's pixels are not square.
                                  width : height ratio as float.
@@ -572,7 +569,7 @@ class InfoExtractor(object):
 
     def _get_login_info(self):
         """
-        Get the the login info as (username, password)
+        Get the login info as (username, password)
         It will look in the netrc file using the _NETRC_MACHINE value
         If there's no info available, return (None, None)
         """
@@ -767,7 +764,7 @@ class InfoExtractor(object):
                 f.get('fps') if f.get('fps') is not None else -1,
                 f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
                 f.get('source_preference') if f.get('source_preference') is not None else -1,
-                f.get('format_id'),
+                f.get('format_id') if f.get('format_id') is not None else '',
             )
         formats.sort(key=_formats_key)
 
@@ -789,8 +786,8 @@ class InfoExtractor(object):
             return True
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError):
-                self.report_warning(
-                    '%s URL is invalid, skipping' % item, video_id)
+                self.to_screen(
+                    '%s: %s URL is invalid, skipping' % (video_id, item))
                 return False
             raise
 
@@ -899,7 +896,7 @@ class InfoExtractor(object):
                 format_id = []
                 if m3u8_id:
                     format_id.append(m3u8_id)
-                last_media_name = last_media.get('NAME') if last_media else None
+                last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None
                 format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
                 f = {
                     'format_id': '-'.join(format_id),
@@ -1075,9 +1072,6 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
-    def _subtitles_timecode(self, seconds):
-        return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
-
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/dailymotion.py

@@ -52,6 +52,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'ext': 'mp4',
                 'uploader': 'IGN',
                 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
+                'upload_date': '20150306',
             }
         },
         # Vevo video
@@ -85,7 +86,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        url = 'http://www.dailymotion.com/video/%s' % video_id
+        url = 'https://www.dailymotion.com/video/%s' % video_id
 
         # Retrieve video webpage to extract further information
         request = self._build_request(url)
@@ -106,11 +107,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         age_limit = self._rta_search(webpage)
 
         video_upload_date = None
-        mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+        mobj = re.search(r'<meta property="video:release_date" content="([0-9]{4})-([0-9]{2})-([0-9]{2}).+?"/>', webpage)
         if mobj is not None:
-            video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
 
-        embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
+        embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id
         embed_request = self._build_request(embed_url)
         embed_page = self._download_webpage(
             embed_request, video_id, 'Downloading embed page')
@@ -224,7 +225,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:(?:old/)?user/)?(?P<user>[^/]+)$'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',
@@ -238,7 +239,8 @@ class DailymotionUserIE(DailymotionPlaylistIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
-        webpage = self._download_webpage(url, user)
+        webpage = self._download_webpage(
+            'https://www.dailymotion.com/user/%s' % user, user)
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
             webpage, 'user'))

youtube_dl/extractor/dreisat.py

@@ -11,19 +11,25 @@ from ..utils import (
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
-    _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
-    _TEST = {
-        'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
-        'md5': 'be37228896d30a88f315b638900a026e',
-        'info_dict': {
-            'id': '45918',
-            'ext': 'mp4',
-            'title': 'Waidmannsheil',
-            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
-            'uploader': '3sat',
-            'upload_date': '20140913'
-        }
-    }
+    _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+    _TESTS = [
+        {
+            'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
+            'md5': 'be37228896d30a88f315b638900a026e',
+            'info_dict': {
+                'id': '45918',
+                'ext': 'mp4',
+                'title': 'Waidmannsheil',
+                'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+                'uploader': '3sat',
+                'upload_date': '20140913'
+            }
+        },
+        {
+            'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
+            'only_matching': True,
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/drtv.py

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

youtube_dl/extractor/dumpert.py

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

youtube_dl/extractor/empflix.py

@@ -4,22 +4,28 @@ from .tnaflix import TNAFlixIE
 
 
 class EMPFlixIE(TNAFlixIE):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html'
+    _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\("([^"]+)"'
 
-    _TEST = {
-        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
-        'info_dict': {
-            'id': '33051',
-            'display_id': 'Amateur-Finger-Fuck',
-            'ext': 'mp4',
-            'title': 'Amateur Finger Fuck',
-            'description': 'Amateur solo finger fucking.',
-            'thumbnail': 're:https?://.*\.jpg$',
-            'age_limit': 18,
+    _TESTS = [
+        {
+            'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+            'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+            'info_dict': {
+                'id': '33051',
+                'display_id': 'Amateur-Finger-Fuck',
+                'ext': 'mp4',
+                'title': 'Amateur Finger Fuck',
+                'description': 'Amateur solo finger fucking.',
+                'thumbnail': 're:https?://.*\.jpg$',
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
+            'matching_only': True,
         }
-    }
+    ]

youtube_dl/extractor/eroprofile.py

@@ -4,7 +4,10 @@ import re
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    unescapeHTML
+)
 
 
 class EroProfileIE(InfoExtractor):
@@ -75,8 +78,8 @@ class EroProfileIE(InfoExtractor):
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)
 
-        video_url = self._search_regex(
-            r'<source src="([^"]+)', webpage, 'video url')
+        video_url = unescapeHTML(self._search_regex(
+            r'<source src="([^"]+)', webpage, 'video url'))
         title = self._html_search_regex(
             r'Title:</th><td>([^<]+)</td>', webpage, 'title')
         thumbnail = self._search_regex(

youtube_dl/extractor/escapist.py

@@ -8,7 +8,8 @@ from ..compat import compat_urllib_request
 from ..utils import (
     determine_ext,
     clean_html,
-    qualities,
+    int_or_none,
+    float_or_none,
 )
 
 
@@ -36,10 +37,10 @@ def _decrypt_config(key, string):
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
+    _VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
     _TESTS = [{
         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
-        'md5': 'c6793dbda81388f4264c1ba18684a74d',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
         'info_dict': {
             'id': '6618',
             'ext': 'mp4',
@@ -47,10 +48,11 @@ class EscapistIE(InfoExtractor):
             'title': "Breaking Down Baldur's Gate",
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 264,
+            'uploader': 'The Escapist',
         }
     }, {
         'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
-        'md5': 'cf8842a8a46444d241f9a9980d7874f2',
+        'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
         'info_dict': {
             'id': '10044',
             'ext': 'mp4',
@@ -58,6 +60,7 @@ class EscapistIE(InfoExtractor):
             'title': 'Evolve - One vs Multiplayer',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 304,
+            'uploader': 'The Escapist',
         }
     }]
 
@@ -65,35 +68,33 @@ class EscapistIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        imsVideo = self._parse_json(
+        ims_video = self._parse_json(
             self._search_regex(
                 r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
             video_id)
-        video_id = imsVideo['videoID']
-        key = imsVideo['hash']
+        video_id = ims_video['videoID']
+        key = ims_video['hash']
 
-        quality = qualities(['lq', 'hq', 'hd'])
+        config_req = compat_urllib_request.Request(
+            'http://www.escapistmagazine.com/videos/'
+            'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
+        config_req.add_header('Referer', url)
+        config = self._download_webpage(config_req, video_id, 'Downloading video config')
 
-        formats = []
-        for q in ['lq', 'hq', 'hd']:
-            config_req = compat_urllib_request.Request('http://www.escapistmagazine.com/videos/'
-                'vidconfig.php?videoID=%s&hash=%s&quality=%s' % (video_id, key, 'mp4_' + q))
-            config_req.add_header('Referer', url)
-            config = self._download_webpage(config_req, video_id, 'Downloading video config ' + q.upper())
+        data = json.loads(_decrypt_config(key, config))
 
-            data = json.loads(_decrypt_config(key, config))
+        video_data = data['videoData']
 
-            title = clean_html(data['videoData']['title'])
-            duration = data['videoData']['duration'] / 1000
-
-            for i, v in enumerate(data['files']['videos']):
-
-                formats.append({
-                    'url': v,
-                    'format_id': determine_ext(v) + '_' + q + str(i),
-                    'quality': quality(q),
-                    })
+        title = clean_html(video_data['title'])
+        duration = float_or_none(video_data.get('duration'), 1000)
+        uploader = video_data.get('publisher')
 
+        formats = [{
+            'url': video['src'],
+            'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
+            'height': int_or_none(video.get('res')),
+        } for video in data['files']['videos']]
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
@@ -102,4 +103,5 @@ class EscapistIE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
             'duration': duration,
+            'uploader': uploader,
         }

youtube_dl/extractor/espn.py

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

youtube_dl/extractor/facebook.py

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

youtube_dl/extractor/firedrive.py

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

youtube_dl/extractor/foxsports.py

@@ -0,0 +1,32 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import smuggle_url
+
+
+class FoxSportsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://www.foxsports.com/video?vid=432609859715',
+        'info_dict': {
+            'id': 'gA0bHB3Ladz3',
+            'ext': 'flv',
+            'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
+            'description': 'Courtney Lee talks about Memphis being focused.',
+        },
+        'add_ie': ['ThePlatform'],
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        config = self._parse_json(
+            self._search_regex(
+                r"data-player-config='([^']+)'", webpage, 'data player config'),
+            video_id)
+
+        return self.url_result(smuggle_url(
+            config['releaseURL'] + '&manifest=f4m', {'force_smil_url': True}))

youtube_dl/extractor/gamespot.py

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

youtube_dl/extractor/generic.py

@@ -32,11 +32,13 @@ from .brightcove import BrightcoveIE
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
+from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
 from .bliptv import BlipTVIE
+from .svt import SVTIE
 
 
 class GenericIE(InfoExtractor):
@@ -223,6 +225,37 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # SportBox embed
+        {
+            'url': 'http://www.vestifinance.ru/articles/25753',
+            'info_dict': {
+                'id': '25753',
+                'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '370908',
+                    'title': 'Госзаказ. День 3',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370905',
+                    'title': 'Госзаказ. День 2',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370902',
+                    'title': 'Госзаказ. День 1',
+                    'ext': 'mp4',
+                }
+            }],
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
@@ -645,6 +678,17 @@ class GenericIE(InfoExtractor):
                 'title': 'Facebook Creates "On This Day" | Crunch Report',
             },
         },
+        # SVT embed
+        {
+            'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
+            'info_dict': {
+                'id': '2900353',
+                'ext': 'flv',
+                'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+                'duration': 27,
+                'age_limit': 0,
+            },
+        },
         # RSS feed with enclosure
         {
             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
@@ -1078,6 +1122,11 @@ class GenericIE(InfoExtractor):
         if bliptv_url:
             return self.url_result(bliptv_url, 'BlipTV')
 
+        # Look for SVT player
+        svt_url = SVTIE._extract_url(webpage)
+        if svt_url:
+            return self.url_result(svt_url, 'SVT')
+
         # Look for embedded condenast player
         matches = re.findall(
             r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
@@ -1212,6 +1261,11 @@ class GenericIE(InfoExtractor):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
+        # 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 TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
@@ -1289,6 +1343,10 @@ class GenericIE(InfoExtractor):
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)
+        if not mobj:
+            mobj = re.search(
+                r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+                webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
 
@@ -1367,7 +1425,7 @@ class GenericIE(InfoExtractor):
         # Look for Senate ISVP iframe
         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
         if senate_isvp_url:
-            return self.url_result(surl, 'SenateISVP')
+            return self.url_result(senate_isvp_url, 'SenateISVP')
 
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
@@ -1436,7 +1494,7 @@ class GenericIE(InfoExtractor):
                 if refresh_header:
                     found = re.search(REDIRECT_REGEX, refresh_header)
             if found:
-                new_url = found.group(1)
+                new_url = compat_urlparse.urljoin(url, found.group(1))
                 self.report_following_redirect(new_url)
                 return {
                     '_type': 'url',

youtube_dl/extractor/giga.py

@@ -85,7 +85,8 @@ class GigaIE(InfoExtractor):
             r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False)
 
         view_count = str_to_int(self._search_regex(
-            r'<span class="views"><strong>([\d.]+)</strong>', webpage, 'view count', fatal=False))
+            r'<span class="views"><strong>([\d.,]+)</strong>',
+            webpage, 'view count', fatal=False))
 
         return {
             'id': video_id,

youtube_dl/extractor/gorillavid.py

@@ -35,13 +35,7 @@ class GorillaVidIE(InfoExtractor):
         },
     }, {
         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
-        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
-        'info_dict': {
-            'id': 'z08zf8le23c6',
-            'ext': 'mp4',
-            'title': 'Say something nice',
-            'thumbnail': 're:http://.*\.jpg',
-        },
+        'only_matching': True,
     }, {
         'url': 'http://daclips.in/3rso4kdn6f9m',
         'md5': '1ad8fd39bb976eeb66004d3a4895f106',

youtube_dl/extractor/grooveshark.py

@@ -1,191 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import time
-import math
-import os.path
-import re
-
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_html_parser,
-    compat_urllib_parse,
-    compat_urllib_request,
-    compat_urlparse,
-)
-from ..utils import ExtractorError
-
-
-class GroovesharkHtmlParser(compat_html_parser.HTMLParser):
-    def __init__(self):
-        self._current_object = None
-        self.objects = []
-        compat_html_parser.HTMLParser.__init__(self)
-
-    def handle_starttag(self, tag, attrs):
-        attrs = dict((k, v) for k, v in attrs)
-        if tag == 'object':
-            self._current_object = {'attrs': attrs, 'params': []}
-        elif tag == 'param':
-            self._current_object['params'].append(attrs)
-
-    def handle_endtag(self, tag):
-        if tag == 'object':
-            self.objects.append(self._current_object)
-            self._current_object = None
-
-    @classmethod
-    def extract_object_tags(cls, html):
-        p = cls()
-        p.feed(html)
-        p.close()
-        return p.objects
-
-
-class GroovesharkIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?grooveshark\.com/#!/s/([^/]+)/([^/]+)'
-    _TEST = {
-        'url': 'http://grooveshark.com/#!/s/Jolene+Tenth+Key+Remix+Ft+Will+Sessions/6SS1DW?src=5',
-        'md5': '7ecf8aefa59d6b2098517e1baa530023',
-        'info_dict': {
-            'id': '6SS1DW',
-            'title': 'Jolene (Tenth Key Remix ft. Will Sessions)',
-            'ext': 'mp3',
-            'duration': 227,
-        }
-    }
-
-    do_playerpage_request = True
-    do_bootstrap_request = True
-
-    def _parse_target(self, target):
-        uri = compat_urlparse.urlparse(target)
-        hash = uri.fragment[1:].split('?')[0]
-        token = os.path.basename(hash.rstrip('/'))
-        return (uri, hash, token)
-
-    def _build_bootstrap_url(self, target):
-        (uri, hash, token) = self._parse_target(target)
-        query = 'getCommunicationToken=1&hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
-        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
-
-    def _build_meta_url(self, target):
-        (uri, hash, token) = self._parse_target(target)
-        query = 'hash=%s&%d' % (compat_urllib_parse.quote(hash, safe=''), self.ts)
-        return (compat_urlparse.urlunparse((uri.scheme, uri.netloc, '/preload.php', None, query, None)), token)
-
-    def _build_stream_url(self, meta):
-        return compat_urlparse.urlunparse(('http', meta['streamKey']['ip'], '/stream.php', None, None, None))
-
-    def _build_swf_referer(self, target, obj):
-        (uri, _, _) = self._parse_target(target)
-        return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
-
-    def _transform_bootstrap(self, js):
-        return re.split('(?m)^\s*try\s*\{', js)[0] \
-                 .split(' = ', 1)[1].strip().rstrip(';')
-
-    def _transform_meta(self, js):
-        return js.split('\n')[0].split('=')[1].rstrip(';')
-
-    def _get_meta(self, target):
-        (meta_url, token) = self._build_meta_url(target)
-        self.to_screen('Metadata URL: %s' % meta_url)
-
-        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
-        req = compat_urllib_request.Request(meta_url, headers=headers)
-        res = self._download_json(req, token,
-                                  transform_source=self._transform_meta)
-
-        if 'getStreamKeyWithSong' not in res:
-            raise ExtractorError(
-                'Metadata not found. URL may be malformed, or Grooveshark API may have changed.')
-
-        if res['getStreamKeyWithSong'] is None:
-            raise ExtractorError(
-                'Metadata download failed, probably due to Grooveshark anti-abuse throttling. Wait at least an hour before retrying from this IP.',
-                expected=True)
-
-        return res['getStreamKeyWithSong']
-
-    def _get_bootstrap(self, target):
-        (bootstrap_url, token) = self._build_bootstrap_url(target)
-
-        headers = {'Referer': compat_urlparse.urldefrag(target)[0]}
-        req = compat_urllib_request.Request(bootstrap_url, headers=headers)
-        res = self._download_json(req, token, fatal=False,
-                                  note='Downloading player bootstrap data',
-                                  errnote='Unable to download player bootstrap data',
-                                  transform_source=self._transform_bootstrap)
-        return res
-
-    def _get_playerpage(self, target):
-        (_, _, token) = self._parse_target(target)
-
-        webpage = self._download_webpage(
-            target, token,
-            note='Downloading player page',
-            errnote='Unable to download player page',
-            fatal=False)
-
-        if webpage is not None:
-            # Search (for example German) error message
-            error_msg = self._html_search_regex(
-                r'<div id="content">\s*<h2>(.*?)</h2>', webpage,
-                'error message', default=None)
-            if error_msg is not None:
-                error_msg = error_msg.replace('\n', ' ')
-                raise ExtractorError('Grooveshark said: %s' % error_msg)
-
-        if webpage is not None:
-            o = GroovesharkHtmlParser.extract_object_tags(webpage)
-            return webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']
-
-        return webpage, None
-
-    def _real_initialize(self):
-        self.ts = int(time.time() * 1000)  # timestamp in millis
-
-    def _real_extract(self, url):
-        (target_uri, _, token) = self._parse_target(url)
-
-        # 1. Fill cookiejar by making a request to the player page
-        swf_referer = None
-        if self.do_playerpage_request:
-            (_, player_objs) = self._get_playerpage(url)
-            if player_objs:
-                swf_referer = self._build_swf_referer(url, player_objs[0])
-                self.to_screen('SWF Referer: %s' % swf_referer)
-
-        # 2. Ask preload.php for swf bootstrap data to better mimic webapp
-        if self.do_bootstrap_request:
-            bootstrap = self._get_bootstrap(url)
-            self.to_screen('CommunicationToken: %s' % bootstrap['getCommunicationToken'])
-
-        # 3. Ask preload.php for track metadata.
-        meta = self._get_meta(url)
-
-        # 4. Construct stream request for track.
-        stream_url = self._build_stream_url(meta)
-        duration = int(math.ceil(float(meta['streamKey']['uSecs']) / 1000000))
-        post_dict = {'streamKey': meta['streamKey']['streamKey']}
-        post_data = compat_urllib_parse.urlencode(post_dict).encode('utf-8')
-        headers = {
-            'Content-Length': len(post_data),
-            'Content-Type': 'application/x-www-form-urlencoded'
-        }
-        if swf_referer is not None:
-            headers['Referer'] = swf_referer
-
-        return {
-            'id': token,
-            'title': meta['song']['Name'],
-            'http_method': 'POST',
-            'url': stream_url,
-            'ext': 'mp3',
-            'format': 'mp3 audio',
-            'duration': duration,
-            'http_post_data': post_data,
-            'http_headers': headers,
-        }

youtube_dl/extractor/historicfilms.py

@@ -25,7 +25,8 @@ class HistoricFilmsIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         tape_id = self._search_regex(
-            r'class="tapeId">([^<]+)<', webpage, 'tape id')
+            [r'class="tapeId"[^>]*>([^<]+)<', r'tapeId\s*:\s*"([^"]+)"'],
+            webpage, 'tape id')
 
         title = self._og_search_title(webpage)
         description = self._og_search_description(webpage)

youtube_dl/extractor/iconosquare.py

@@ -1,36 +1,75 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class IconosquareIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://statigr.am/p/522207370455279102_24101272',
         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
         'info_dict': {
             'id': '522207370455279102_24101272',
             'ext': 'mp4',
-            'uploader_id': 'aguynamedpatrick',
-            'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+            'title': 'Instagram media by @aguynamedpatrick (Patrick Janelle)',
             'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
+            'timestamp': 1376471991,
+            'upload_date': '20130814',
+            'uploader': 'aguynamedpatrick',
+            'uploader_id': '24101272',
+            'comment_count': int,
+            'like_count': int,
         },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
+
+        media = self._parse_json(
+            self._search_regex(
+                r'window\.media\s*=\s*({.+?});\n', webpage, 'media'),
+            video_id)
+
+        formats = [{
+            'url': f['url'],
+            'format_id': format_id,
+            'width': int_or_none(f.get('width')),
+            'height': int_or_none(f.get('height'))
+        } for format_id, f in media['videos'].items()]
+        self._sort_formats(formats)
+
         title = self._html_search_regex(
             r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>',
             webpage, 'title')
-        uploader_id = self._html_search_regex(
-            r'@([^ ]+)', title, 'uploader name', fatal=False)
+
+        timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
+        description = media.get('caption', {}).get('text')
+
+        uploader = media.get('user', {}).get('username')
+        uploader_id = media.get('user', {}).get('id')
+
+        comment_count = int_or_none(media.get('comments', {}).get('count'))
+        like_count = int_or_none(media.get('likes', {}).get('count'))
+
+        thumbnails = [{
+            'url': t['url'],
+            'id': thumbnail_id,
+            'width': int_or_none(t.get('width')),
+            'height': int_or_none(t.get('height'))
+        } for thumbnail_id, t in media.get('images', {}).items()]
 
         return {
             'id': video_id,
-            'url': self._og_search_video_url(webpage),
             'title': title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id': uploader_id
+            'description': description,
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'comment_count': comment_count,
+            'like_count': like_count,
+            'formats': formats,
         }

youtube_dl/extractor/instagram.py

@@ -7,9 +7,9 @@ from ..utils import int_or_none
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
+    _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
     _TEST = {
-        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
         'info_dict': {
             'id': 'aye83DjauH',
@@ -41,11 +41,11 @@ class InstagramIE(InfoExtractor):
 
 
 class InstagramUserIE(InfoExtractor):
-    _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+    _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
     _TEST = {
-        'url': 'http://instagram.com/porsche',
+        'url': 'https://instagram.com/porsche',
         'info_dict': {
             'id': 'porsche',
             'title': 'porsche',

youtube_dl/extractor/kanalplay.py

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

youtube_dl/extractor/karrierevideos.py

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

youtube_dl/extractor/letv.py

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

youtube_dl/extractor/lifenews.py

@@ -4,7 +4,9 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
+    determine_ext,
     int_or_none,
     unified_strdate,
     ExtractorError,
@@ -14,9 +16,9 @@ from ..utils import (
 class LifeNewsIE(InfoExtractor):
     IE_NAME = 'lifenews'
     IE_DESC = 'LIFE | NEWS'
-    _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
+    _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://lifenews.ru/news/126342',
         'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
         'info_dict': {
@@ -27,16 +29,47 @@ class LifeNewsIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg',
             'upload_date': '20140130',
         }
-    }
+    }, {
+        # video in <iframe>
+        'url': 'http://lifenews.ru/news/152125',
+        'md5': '77d19a6f0886cd76bdbf44b4d971a273',
+        'info_dict': {
+            'id': '152125',
+            'ext': 'mp4',
+            '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',
+        'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795',
+        'info_dict': {
+            'id': '153461',
+            'ext': 'mp4',
+            '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',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        section = mobj.group('section')
 
-        webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
+        webpage = self._download_webpage(
+            'http://lifenews.ru/%s/%s' % (section, video_id),
+            video_id, 'Downloading page')
 
         videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
-        if not videos:
+        iframe_link = self._html_search_regex(
+            '<iframe[^>]+src=["\']([^"\']+)["\']', webpage, 'iframe link', default=None)
+        if not videos and not iframe_link:
             raise ExtractorError('No media links available for %s' % video_id)
 
         title = self._og_search_title(webpage)
@@ -47,28 +80,90 @@ class LifeNewsIE(InfoExtractor):
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
-            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
+            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\'>(\d+)</span>', webpage, 'comment count', fatal=False)
+            r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
             r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
         if upload_date is not None:
             upload_date = unified_strdate(upload_date)
 
+        common_info = {
+            'description': description,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'upload_date': upload_date,
+        }
+
         def make_entry(video_id, media, video_number=None):
-            return {
+            cur_info = dict(common_info)
+            cur_info.update({
                 'id': video_id,
                 'url': media[1],
                 'thumbnail': media[0],
                 'title': title if video_number is None else '%s-video%s' % (title, video_number),
-                'description': description,
-                'view_count': int_or_none(view_count),
-                'comment_count': int_or_none(comment_count),
-                'upload_date': upload_date,
-            }
+            })
+            return cur_info
+
+        if iframe_link:
+            iframe_link = self._proto_relative_url(iframe_link, 'http:')
+            cur_info = dict(common_info)
+            cur_info.update({
+                '_type': 'url_transparent',
+                'id': video_id,
+                'title': title,
+                'url': iframe_link,
+            })
+            return cur_info
 
         if len(videos) == 1:
             return make_entry(video_id, videos[0])
         else:
             return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)]
+
+
+class LifeEmbedIE(InfoExtractor):
+    IE_NAME = 'life:embed'
+    _VALID_URL = r'http://embed\.life\.ru/embed/(?P<id>[\da-f]{32})'
+
+    _TEST = {
+        'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
+        'md5': 'b889715c9e49cb1981281d0e5458fbbe',
+        'info_dict': {
+            'id': 'e50c2dec2867350528e2574c899b8291',
+            'ext': 'mp4',
+            'title': 'e50c2dec2867350528e2574c899b8291',
+            'thumbnail': 're:http://.*\.jpg',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = []
+        for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
+            video_url = compat_urlparse.urljoin(url, video_url)
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', m3u8_id='m3u8'))
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': ext,
+                    'preference': 1,
+                })
+        self._sort_formats(formats)
+
+        thumbnail = self._search_regex(
+            r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/livestream.py

@@ -194,23 +194,19 @@ class LivestreamIE(InfoExtractor):
 # The original version of Livestream uses a different system
 class LivestreamOriginalIE(InfoExtractor):
     IE_NAME = 'livestream:original'
-    _VALID_URL = r'''(?x)https?://www\.livestream\.com/
+    _VALID_URL = r'''(?x)https?://original\.livestream\.com/
         (?P<user>[^/]+)/(?P<type>video|folder)
         (?:\?.*?Id=|/)(?P<id>.*?)(&|$)
         '''
     _TESTS = [{
-        'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+        'url': 'http://original.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
         'info_dict': {
             'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
         },
-        'params': {
-            # rtmp
-            'skip_download': True,
-        },
     }, {
-        'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
+        'url': 'https://original.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
         'info_dict': {
             'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
         },
@@ -221,19 +217,17 @@ class LivestreamOriginalIE(InfoExtractor):
         api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
 
         info = self._download_xml(api_url, video_id)
+        # this url is used on mobile devices
+        stream_url = 'http://x{0}x.api.channel.livestream.com/3.0/getstream.json?id={1}'.format(user, video_id)
+        stream_info = self._download_json(stream_url, video_id)
         item = info.find('channel').find('item')
         ns = {'media': 'http://search.yahoo.com/mrss'}
         thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
-        # Remove the extension and number from the path (like 1.jpg)
-        path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')
 
         return {
             'id': video_id,
             'title': item.find('title').text,
-            'url': 'rtmp://extondemand.livestream.com/ondemand',
-            'play_path': 'trans/dv15/mogulus-{0}'.format(path),
-            'player_url': 'http://static.livestream.com/chromelessPlayer/v21/playerapi.swf?hash=5uetk&v=0803&classid=D27CDB6E-AE6D-11cf-96B8-444553540000&jsEnabled=false&wmode=opaque',
-            'ext': 'flv',
+            'url': stream_info['progressiveUrl'],
             'thumbnail': thumbnail_url,
         }
 

youtube_dl/extractor/mitele.py

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

youtube_dl/extractor/mlb.py

@@ -10,7 +10,21 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'https?://m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:[\da-z_-]+\.)*mlb\.com/
+                        (?:
+                            (?:
+                                (?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|
+                                (?:
+                                    shared/video/embed/(?:embed|m-internal-embed)\.html|
+                                    (?:[^/]+/)+(?:play|index)\.jsp|
+                                )\?.*?\bcontent_id=
+                            )
+                            (?P<id>n?\d+)|
+                            (?:[^/]+/)*(?P<path>[^/]+)
+                        )
+                    '''
     _TESTS = [
         {
             'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
@@ -68,6 +82,18 @@ class MLBIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
+        {
+            'url': 'http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer',
+            'md5': 'b190e70141fb9a1552a85426b4da1b5d',
+            'info_dict': {
+                'id': '75609783',
+                'ext': 'mp4',
+                'title': 'Must C: Pillar climbs for catch',
+                'description': '4/15/15: Blue Jays outfielder Kevin Pillar continues his defensive dominance by climbing the wall in left to rob Tim Beckham of a home run',
+                'timestamp': 1429124820,
+                'upload_date': '20150415',
+            }
+        },
         {
             'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb',
             'only_matching': True,
@@ -83,6 +109,15 @@ class MLBIE(InfoExtractor):
         {
             'url': 'http://m.cardinals.mlb.com/stl/video/v51175783/atlstl-piscotty-makes-great-sliding-catch-on-line/?partnerId=as_mlb_20150321_42500876&adbid=579409712979910656&adbpl=tw&adbpr=52847728',
             'only_matching': True,
+        },
+        {
+            # From http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer
+            'url': 'http://mlb.mlb.com/shared/video/embed/m-internal-embed.html?content_id=75609783&property=mlb&autoplay=true&hashmode=false&siteSection=mlb/multimedia/article_118550098/article_embed&club=mlb',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://washington.nationals.mlb.com/mlb/gameday/index.jsp?c_id=was&gid=2015_05_09_atlmlb_wasmlb_1&lang=en&content_id=108309983&mode=video#',
+            'only_matching': True,
         }
     ]
 
@@ -90,6 +125,12 @@ class MLBIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
+        if not video_id:
+            video_path = mobj.group('path')
+            webpage = self._download_webpage(url, video_path)
+            video_id = self._search_regex(
+                [r'data-video-?id="(\d+)"', r'content_id=(\d+)'], webpage, 'video id')
+
         detail = self._download_xml(
             'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'
             % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)

youtube_dl/extractor/naver.py

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

youtube_dl/extractor/nba.py

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

youtube_dl/extractor/nbc.py

@@ -10,6 +10,8 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     find_xpath_attr,
+    lowercase_escape,
+    unescapeHTML,
 )
 
 
@@ -37,14 +39,32 @@ class NBCIE(InfoExtractor):
             },
             'skip': 'Only works from US',
         },
+        {
+            'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
+            'info_dict': {
+                'id': '8iUuyzWDdYUZ',
+                'ext': 'flv',
+                'title': 'Star Wars Teaser',
+                'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
+            },
+            'skip': 'Only works from US',
+        },
+        {
+            # This video has expired but with an escaped embedURL
+            'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
+            'skip': 'Expired'
+        }
     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        theplatform_url = self._search_regex(
-            '(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
-            webpage, 'theplatform url').replace('_no_endcard', '')
+        theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
+            [
+                r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
+                r'"embedURL"\s*:\s*"([^"]+)"'
+            ],
+            webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
         if theplatform_url.startswith('//'):
             theplatform_url = 'http:' + theplatform_url
         return self.url_result(theplatform_url)

youtube_dl/extractor/ndr.py

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

youtube_dl/extractor/netzkino.py

@@ -49,7 +49,7 @@ class NetzkinoIE(InfoExtractor):
             'http://www.netzkino.de/beta/dist/production.min.js', video_id,
             note='Downloading player code')
         avo_js = self._search_regex(
-            r'window\.avoCore\s*=.*?urlTemplate:\s*(\{.*?"\})',
+            r'var urlTemplate=(\{.*?"\})',
             production_js, 'URL templates')
         templates = self._parse_json(
             avo_js, video_id, transform_source=js_to_json)

youtube_dl/extractor/nextmedia.py

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

youtube_dl/extractor/nhl.py

@@ -21,6 +21,9 @@ class NHLBaseInfoExtractor(InfoExtractor):
         return json_string.replace('\\\'', '\'')
 
     def _real_extract_video(self, video_id):
+        vid_parts = video_id.split(',')
+        if len(vid_parts) == 3:
+            video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0'))
         json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
         data = self._download_json(
             json_url, video_id, transform_source=self._fix_json)
@@ -47,7 +50,7 @@ class NHLBaseInfoExtractor(InfoExtractor):
             video_url = initial_video_url
 
         join = compat_urlparse.urljoin
-        return {
+        ret = {
             'id': video_id,
             'title': info['name'],
             'url': video_url,
@@ -56,11 +59,20 @@ class NHLBaseInfoExtractor(InfoExtractor):
             'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
             'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
         }
+        if video_url.startswith('rtmp:'):
+            mobj = re.match(r'(?P<tc_url>rtmp://[^/]+/(?P<app>[a-z0-9/]+))/(?P<play_path>mp4:.*)', video_url)
+            ret.update({
+                'tc_url': mobj.group('tc_url'),
+                'play_path': mobj.group('play_path'),
+                'app': mobj.group('app'),
+                'no_resume': True,
+            })
+        return ret
 
 
 class NHLIE(NHLBaseInfoExtractor):
     IE_NAME = 'nhl.com'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)(?:id|hlg)=(?P<id>[-0-9a-zA-Z,]+)'
 
     _TESTS = [{
         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
@@ -101,6 +113,29 @@ class NHLIE(NHLBaseInfoExtractor):
     }, {
         'url': 'http://video.nhl.com/videocenter/?id=736722',
         'only_matching': True,
+    }, {
+        'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en',
+        'md5': '076fcb88c255154aacbf0a7accc3f340',
+        'info_dict': {
+            'id': '2014020299-X-h',
+            'ext': 'mp4',
+            'title': 'Penguins at Islanders / Game Highlights',
+            'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014',
+            'duration': 268,
+            'upload_date': '20141122',
+        }
+    }, {
+        'url': 'http://video.oilers.nhl.com/videocenter/console?id=691469&catid=4',
+        'info_dict': {
+            'id': '691469',
+            'ext': 'mp4',
+            'title': 'RAW | Craig MacTavish Full Press Conference',
+            'description': 'Oilers GM Craig MacTavish addresses the media at Rexall Place on Friday.',
+            'upload_date': '20141205',
+        },
+        'params': {
+            'skip_download': True,  # Requires rtmpdump
+        }
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/niconico.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 import re
 import json
+import datetime
 
 from .common import InfoExtractor
 from ..compat import (
@@ -14,7 +15,9 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
-    unified_strdate,
+    parse_iso8601,
+    xpath_text,
+    determine_ext,
 )
 
 
@@ -32,30 +35,50 @@ class NiconicoIE(InfoExtractor):
             'uploader': 'takuya0301',
             'uploader_id': '2698420',
             'upload_date': '20131123',
+            'timestamp': 1385182762,
             'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
             'duration': 33,
         },
-        'params': {
-            'username': 'ydl.niconico@gmail.com',
-            'password': 'youtube-dl',
-        },
     }, {
+        # File downloaded with and without credentials are different, so omit
+        # the md5 field
         'url': 'http://www.nicovideo.jp/watch/nm14296458',
-        'md5': '8db08e0158457cf852a31519fceea5bc',
         'info_dict': {
             'id': 'nm14296458',
             'ext': 'swf',
             'title': '【鏡音リン】Dance on media【オリジナル】take2!',
-            'description': 'md5:',
+            'description': 'md5:689f066d74610b3b22e0f1739add0f58',
             'uploader': 'りょうた',
             'uploader_id': '18822557',
             'upload_date': '20110429',
+            'timestamp': 1304065916,
             'duration': 209,
         },
-        'params': {
-            'username': 'ydl.niconico@gmail.com',
-            'password': 'youtube-dl',
+    }, {
+        # 'video exists but is marked as "deleted"
+        # md5 is unstable
+        'url': 'http://www.nicovideo.jp/watch/sm10000',
+        'info_dict': {
+            'id': 'sm10000',
+            'ext': 'unknown_video',
+            'description': 'deleted',
+            'title': 'ドラえもんエターナル第3話「決戦第3新東京市」＜前編＞',
+            'upload_date': '20071224',
+            'timestamp': 1198527840,  # timestamp field has different value if logged in
+            'duration': 304,
         },
+    }, {
+        'url': 'http://www.nicovideo.jp/watch/so22543406',
+        'info_dict': {
+            'id': '1388129933',
+            'ext': 'mp4',
+            'title': '【第1回】RADIOアニメロミックス ラブライブ！～のぞえりRadio Garden～',
+            'description': 'md5:b27d224bb0ff53d3c8269e9f8b561cf1',
+            'timestamp': 1388851200,
+            'upload_date': '20140104',
+            'uploader': 'アニメロチャンネル',
+            'uploader_id': '312',
+        }
     }]
 
     _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
@@ -95,9 +118,13 @@ class NiconicoIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        # Get video webpage. We are not actually interested in it, but need
-        # the cookies in order to be able to download the info webpage
-        self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
+        # Get video webpage. We are not actually interested in it for normal
+        # cases, but need the cookies in order to be able to download the
+        # info webpage
+        webpage, handle = self._download_webpage_handle(
+            'http://www.nicovideo.jp/watch/' + video_id, video_id)
+        if video_id.startswith('so'):
+            video_id = self._match_id(handle.geturl())
 
         video_info = self._download_xml(
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
@@ -127,22 +154,78 @@ class NiconicoIE(InfoExtractor):
                 flv_info_request, video_id,
                 note='Downloading flv info', errnote='Unable to download flv info')
 
-        if 'deleted=' in flv_info_webpage:
-            raise ExtractorError('The video has been deleted.',
-                                 expected=True)
-        video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
+        flv_info = compat_urlparse.parse_qs(flv_info_webpage)
+        if 'url' not in flv_info:
+            if 'deleted' in flv_info:
+                raise ExtractorError('The video has been deleted.',
+                                     expected=True)
+            else:
+                raise ExtractorError('Unable to find video URL')
+
+        video_real_url = flv_info['url'][0]
 
         # Start extracting information
-        title = video_info.find('.//title').text
-        extension = video_info.find('.//movie_type').text
+        title = xpath_text(video_info, './/title')
+        if not title:
+            title = self._og_search_title(webpage, default=None)
+        if not title:
+            title = self._html_search_regex(
+                r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
+                webpage, 'video title')
+
+        watch_api_data_string = self._html_search_regex(
+            r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
+            webpage, 'watch api data', default=None)
+        watch_api_data = self._parse_json(watch_api_data_string, video_id) if watch_api_data_string else {}
+        video_detail = watch_api_data.get('videoDetail', {})
+
+        extension = xpath_text(video_info, './/movie_type')
+        if not extension:
+            extension = determine_ext(video_real_url)
         video_format = extension.upper()
-        thumbnail = video_info.find('.//thumbnail_url').text
-        description = video_info.find('.//description').text
-        upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
-        view_count = int_or_none(video_info.find('.//view_counter').text)
-        comment_count = int_or_none(video_info.find('.//comment_num').text)
-        duration = parse_duration(video_info.find('.//length').text)
-        webpage_url = video_info.find('.//watch_url').text
+
+        thumbnail = (
+            xpath_text(video_info, './/thumbnail_url') or
+            self._html_search_meta('image', webpage, 'thumbnail', default=None) or
+            video_detail.get('thumbnail'))
+
+        description = xpath_text(video_info, './/description')
+
+        timestamp = parse_iso8601(xpath_text(video_info, './/first_retrieve'))
+        if not timestamp:
+            match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
+            if match:
+                timestamp = parse_iso8601(match.replace('+', ':00+'))
+        if not timestamp and video_detail.get('postedAt'):
+            timestamp = parse_iso8601(
+                video_detail['postedAt'].replace('/', '-'),
+                delimiter=' ', timezone=datetime.timedelta(hours=9))
+
+        view_count = int_or_none(xpath_text(video_info, './/view_counter'))
+        if not view_count:
+            match = self._html_search_regex(
+                r'>Views: <strong[^>]*>([^<]+)</strong>',
+                webpage, 'view count', default=None)
+            if match:
+                view_count = int_or_none(match.replace(',', ''))
+        view_count = view_count or video_detail.get('viewCount')
+
+        comment_count = int_or_none(xpath_text(video_info, './/comment_num'))
+        if not comment_count:
+            match = self._html_search_regex(
+                r'>Comments: <strong[^>]*>([^<]+)</strong>',
+                webpage, 'comment count', default=None)
+            if match:
+                comment_count = int_or_none(match.replace(',', ''))
+        comment_count = comment_count or video_detail.get('commentCount')
+
+        duration = (parse_duration(
+            xpath_text(video_info, './/length') or
+            self._html_search_meta(
+                'video:duration', webpage, 'video duration', default=None)) or
+            video_detail.get('length'))
+
+        webpage_url = xpath_text(video_info, './/watch_url') or url
 
         if video_info.find('.//ch_id') is not None:
             uploader_id = video_info.find('.//ch_id').text
@@ -162,7 +245,7 @@ class NiconicoIE(InfoExtractor):
             'thumbnail': thumbnail,
             'description': description,
             'uploader': uploader,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'uploader_id': uploader_id,
             'view_count': view_count,
             'comment_count': comment_count,

youtube_dl/extractor/noco.py

@@ -14,7 +14,9 @@ from ..compat import (
 from ..utils import (
     clean_html,
     ExtractorError,
-    unified_strdate,
+    int_or_none,
+    float_or_none,
+    parse_iso8601,
 )
 
 
@@ -25,21 +27,38 @@ class NocoIE(InfoExtractor):
     _SUB_LANG_TEMPLATE = '&sub_lang=%s'
     _NETRC_MACHINE = 'noco'
 
-    _TEST = {
-        'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
-        'md5': '0a993f0058ddbcd902630b2047ef710e',
-        'info_dict': {
-            'id': '11538',
-            'ext': 'mp4',
-            'title': 'Ami Ami Idol - Hello! France',
-            'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86',
-            'upload_date': '20140412',
-            'uploader': 'Nolife',
-            'uploader_id': 'NOL',
-            'duration': 2851.2,
+    _TESTS = [
+        {
+            'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
+            'md5': '0a993f0058ddbcd902630b2047ef710e',
+            'info_dict': {
+                'id': '11538',
+                'ext': 'mp4',
+                'title': 'Ami Ami Idol - Hello! France',
+                'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86',
+                'upload_date': '20140412',
+                'uploader': 'Nolife',
+                'uploader_id': 'NOL',
+                'duration': 2851.2,
+            },
+            'skip': 'Requires noco account',
         },
-        'skip': 'Requires noco account',
-    }
+        {
+            'url': 'http://noco.tv/emission/12610/lbl42/the-guild/s01e01-wake-up-call',
+            'md5': 'c190f1f48e313c55838f1f412225934d',
+            'info_dict': {
+                'id': '12610',
+                'ext': 'mp4',
+                'title': 'The Guild #1 - Wake-Up Call',
+                'timestamp': 1403863200,
+                'upload_date': '20140627',
+                'uploader': 'LBL42',
+                'uploader_id': 'LBL',
+                'duration': 233.023,
+            },
+            'skip': 'Requires noco account',
+        }
+    ]
 
     def _real_initialize(self):
         self._login()
@@ -90,51 +109,66 @@ class NocoIE(InfoExtractor):
             'shows/%s/medias' % video_id,
             video_id, 'Downloading video JSON')
 
+        show = self._call_api(
+            'shows/by_id/%s' % video_id,
+            video_id, 'Downloading show JSON')[0]
+
+        options = self._call_api(
+            'users/init', video_id,
+            'Downloading user options JSON')['options']
+        audio_lang_pref = options.get('audio_language') or options.get('language', 'fr')
+
+        if audio_lang_pref == 'original':
+            audio_lang_pref = show['original_lang']
+        if len(medias) == 1:
+            audio_lang_pref = list(medias.keys())[0]
+        elif audio_lang_pref not in medias:
+            audio_lang_pref = 'fr'
+
         qualities = self._call_api(
             'qualities',
             video_id, 'Downloading qualities JSON')
 
         formats = []
 
-        for lang, lang_dict in medias['fr']['video_list'].items():
-            for format_id, fmt in lang_dict['quality_list'].items():
-                format_id_extended = '%s-%s' % (lang, format_id) if lang != 'none' else format_id
+        for audio_lang, audio_lang_dict in medias.items():
+            preference = 1 if audio_lang == audio_lang_pref else 0
+            for sub_lang, lang_dict in audio_lang_dict['video_list'].items():
+                for format_id, fmt in lang_dict['quality_list'].items():
+                    format_id_extended = 'audio-%s_sub-%s_%s' % (audio_lang, sub_lang, format_id)
 
-                video = self._call_api(
-                    'shows/%s/video/%s/fr' % (video_id, format_id.lower()),
-                    video_id, 'Downloading %s video JSON' % format_id_extended,
-                    lang if lang != 'none' else None)
+                    video = self._call_api(
+                        'shows/%s/video/%s/%s' % (video_id, format_id.lower(), audio_lang),
+                        video_id, 'Downloading %s video JSON' % format_id_extended,
+                        sub_lang if sub_lang != 'none' else None)
 
-                file_url = video['file']
-                if not file_url:
-                    continue
+                    file_url = video['file']
+                    if not file_url:
+                        continue
 
-                if file_url in ['forbidden', 'not found']:
-                    popmessage = video['popmessage']
-                    self._raise_error(popmessage['title'], popmessage['message'])
+                    if file_url in ['forbidden', 'not found']:
+                        popmessage = video['popmessage']
+                        self._raise_error(popmessage['title'], popmessage['message'])
 
-                formats.append({
-                    'url': file_url,
-                    'format_id': format_id_extended,
-                    'width': fmt['res_width'],
-                    'height': fmt['res_lines'],
-                    'abr': fmt['audiobitrate'],
-                    'vbr': fmt['videobitrate'],
-                    'filesize': fmt['filesize'],
-                    'format_note': qualities[format_id]['quality_name'],
-                    'preference': qualities[format_id]['priority'],
-                })
+                    formats.append({
+                        'url': file_url,
+                        'format_id': format_id_extended,
+                        'width': int_or_none(fmt.get('res_width')),
+                        'height': int_or_none(fmt.get('res_lines')),
+                        'abr': int_or_none(fmt.get('audiobitrate')),
+                        'vbr': int_or_none(fmt.get('videobitrate')),
+                        'filesize': int_or_none(fmt.get('filesize')),
+                        'format_note': qualities[format_id].get('quality_name'),
+                        'quality': qualities[format_id].get('priority'),
+                        'preference': preference,
+                    })
 
         self._sort_formats(formats)
 
-        show = self._call_api(
-            'shows/by_id/%s' % video_id,
-            video_id, 'Downloading show JSON')[0]
-
-        upload_date = unified_strdate(show['online_date_start_utc'])
-        uploader = show['partner_name']
-        uploader_id = show['partner_key']
-        duration = show['duration_ms'] / 1000.0
+        timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')
+        uploader = show.get('partner_name')
+        uploader_id = show.get('partner_key')
+        duration = float_or_none(show.get('duration_ms'), 1000)
 
         thumbnails = []
         for thumbnail_key, thumbnail_url in show.items():
@@ -166,7 +200,7 @@ class NocoIE(InfoExtractor):
             'title': title,
             'description': description,
             'thumbnails': thumbnails,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'uploader': uploader,
             'uploader_id': uploader_id,
             'duration': duration,

youtube_dl/extractor/nowtv.py

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

youtube_dl/extractor/nrk.py

@@ -4,7 +4,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     float_or_none,
@@ -200,20 +199,10 @@ class NRKTVIE(InfoExtractor):
         url = "%s%s" % (baseurl, subtitlesurl)
         self._debug_print('%s: Subtitle url: %s' % (video_id, url))
         captions = self._download_xml(
-            url, video_id, 'Downloading subtitles',
-            transform_source=lambda s: s.replace(r'<br />', '\r\n'))
+            url, video_id, 'Downloading subtitles')
         lang = captions.get('lang', 'no')
-        ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
-        srt = ''
-        for pos, p in enumerate(ps):
-            begin = parse_duration(p.get('begin'))
-            duration = parse_duration(p.get('dur'))
-            starttime = self._subtitles_timecode(begin)
-            endtime = self._subtitles_timecode(begin + duration)
-            srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
         return {lang: [
             {'ext': 'ttml', 'url': url},
-            {'ext': 'srt', 'data': srt},
         ]}
 
     def _extract_f4m(self, manifest_url, video_id):

youtube_dl/extractor/nytimes.py

@@ -8,30 +8,8 @@ from ..utils import (
 )
 
 
-class NYTimesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
-
-    _TESTS = [{
-        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
-        'md5': '18a525a510f942ada2720db5f31644c0',
-        'info_dict': {
-            'id': '100000002847155',
-            'ext': 'mov',
-            'title': 'Verbatim: What Is a Photocopier?',
-            'description': 'md5:93603dada88ddbda9395632fdc5da260',
-            'timestamp': 1398631707,
-            'upload_date': '20140427',
-            'uploader': 'Brett Weiner',
-            'duration': 419,
-        }
-    }, {
-        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
+class NYTimesBaseIE(InfoExtractor):
+    def _extract_video_from_id(self, video_id):
         video_data = self._download_json(
             'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
             video_id, 'Downloading video JSON')
@@ -81,3 +59,59 @@ class NYTimesIE(InfoExtractor):
             'formats': formats,
             'thumbnails': thumbnails,
         }
+
+
+class NYTimesIE(NYTimesBaseIE):
+    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
+        'md5': '18a525a510f942ada2720db5f31644c0',
+        'info_dict': {
+            'id': '100000002847155',
+            'ext': 'mov',
+            'title': 'Verbatim: What Is a Photocopier?',
+            'description': 'md5:93603dada88ddbda9395632fdc5da260',
+            'timestamp': 1398631707,
+            'upload_date': '20140427',
+            'uploader': 'Brett Weiner',
+            'duration': 419,
+        }
+    }, {
+        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        return self._extract_video_from_id(video_id)
+
+
+class NYTimesArticleIE(NYTimesBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
+    _TESTS = [{
+        'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
+        'md5': 'e2076d58b4da18e6a001d53fd56db3c9',
+        'info_dict': {
+            'id': '100000003628438',
+            'ext': 'mov',
+            'title': 'New Minimum Wage: $70,000 a Year',
+            'description': 'Dan Price, C.E.O. of Gravity Payments, surprised his 120-person staff by announcing that he planned over the next three years to raise the salary of every employee to $70,000 a year.',
+            'timestamp': 1429033037,
+            'upload_date': '20150414',
+            'uploader': 'Matthew Williams',
+        }
+    }, {
+        'url': 'http://www.nytimes.com/news/minute/2014/03/17/times-minute-whats-next-in-crimea/?_php=true&_type=blogs&_php=true&_type=blogs&_r=1',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._html_search_regex(r'data-videoid="(\d+)"', webpage, 'video id')
+
+        return self._extract_video_from_id(video_id)

youtube_dl/extractor/odnoklassniki.py

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

youtube_dl/extractor/ooyala.py

@@ -1,15 +1,111 @@
 from __future__ import unicode_literals
 import re
 import json
+import base64
 
 from .common import InfoExtractor
 from ..utils import (
     unescapeHTML,
     ExtractorError,
+    determine_ext,
+    int_or_none,
 )
 
 
-class OoyalaIE(InfoExtractor):
+class OoyalaBaseIE(InfoExtractor):
+
+    def _extract_result(self, info, more_info):
+        embedCode = info['embedCode']
+        video_url = info.get('ipad_url') or info['url']
+
+        if determine_ext(video_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
+        else:
+            formats = [{
+                'url': video_url,
+                'ext': 'mp4',
+            }]
+
+        return {
+            'id': embedCode,
+            'title': unescapeHTML(info['title']),
+            'formats': formats,
+            'description': unescapeHTML(more_info['description']),
+            'thumbnail': more_info['promo'],
+        }
+
+    def _extract(self, player_url, video_id):
+        player = self._download_webpage(player_url, video_id)
+        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
+                                        player, 'mobile player url')
+        # Looks like some videos are only available for particular devices
+        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
+        # is only available for ipad)
+        # Working around with fetching URLs for all the devices found starting with 'unknown'
+        # until we succeed or eventually fail for each device.
+        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
+        devices.remove('unknown')
+        devices.insert(0, 'unknown')
+        for device in devices:
+            mobile_player = self._download_webpage(
+                '%s&device=%s' % (mobile_url, device), video_id,
+                'Downloading mobile player JS for %s device' % device)
+            videos_info = self._search_regex(
+                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
+                mobile_player, 'info', fatal=False, default=None)
+            if videos_info:
+                break
+
+        if not videos_info:
+            formats = []
+            auth_data = self._download_json(
+                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
+                video_id)
+
+            cur_auth_data = auth_data['authorization_data'][video_id]
+
+            for stream in cur_auth_data['streams']:
+                formats.append({
+                    'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
+                    'ext': stream.get('delivery_type'),
+                    'format': stream.get('video_codec'),
+                    'format_id': stream.get('profile'),
+                    'width': int_or_none(stream.get('width')),
+                    'height': int_or_none(stream.get('height')),
+                    'abr': int_or_none(stream.get('audio_bitrate')),
+                    'vbr': int_or_none(stream.get('video_bitrate')),
+                })
+            if formats:
+                return {
+                    'id': video_id,
+                    'formats': formats,
+                    'title': 'Ooyala video',
+                }
+
+            if not cur_auth_data['authorized']:
+                raise ExtractorError(cur_auth_data['message'], expected=True)
+
+        if not videos_info:
+            raise ExtractorError('Unable to extract info')
+        videos_info = videos_info.replace('\\"', '"')
+        videos_more_info = self._search_regex(
+            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
+        videos_info = json.loads(videos_info)
+        videos_more_info = json.loads(videos_more_info)
+
+        if videos_more_info.get('lineup'):
+            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
+            return {
+                '_type': 'playlist',
+                'id': video_id,
+                'title': unescapeHTML(videos_more_info['title']),
+                'entries': videos,
+            }
+        else:
+            return self._extract_result(videos_info[0], videos_more_info)
+
+
+class OoyalaIE(OoyalaBaseIE):
     _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
 
     _TESTS = [
@@ -32,6 +128,17 @@ class OoyalaIE(InfoExtractor):
                 'description': '',
             },
         },
+        {
+            # Information available only through SAS api
+            # From http://community.plm.automation.siemens.com/t5/News-NX-Manufacturing/Tool-Path-Divide/ba-p/4187
+            'url': 'http://player.ooyala.com/player.js?embedCode=FiOG81ZTrvckcchQxmalf4aQj590qTEx',
+            'md5': 'a84001441b35ea492bc03736e59e7935',
+            'info_dict': {
+                'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
+                'ext': 'mp4',
+                'title': 'Ooyala video',
+            }
+        }
     ]
 
     @staticmethod
@@ -43,55 +150,47 @@ class OoyalaIE(InfoExtractor):
         return cls.url_result(cls._url_for_embed_code(embed_code),
                               ie=cls.ie_key())
 
-    def _extract_result(self, info, more_info):
-        return {
-            'id': info['embedCode'],
+    def _real_extract(self, url):
+        embed_code = self._match_id(url)
+        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+        return self._extract(player_url, embed_code)
+
+
+class OoyalaExternalIE(OoyalaBaseIE):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        ooyalaexternal:|
+                        https?://.+?\.ooyala\.com/.*?\bexternalId=
+                    )
+                    (?P<partner_id>[^:]+)
+                    :
+                    (?P<id>.+)
+                    (?:
+                        :|
+                        .*?&pcode=
+                    )
+                    (?P<pcode>.+?)
+                    (&|$)
+                    '''
+
+    _TEST = {
+        'url': 'https://player.ooyala.com/player.js?externalId=espn:10365079&pcode=1kNG061cgaoolOncv54OAO1ceO-I&adSetCode=91cDU6NuXTGKz3OdjOxFdAgJVtQcKJnI&callback=handleEvents&hasModuleParams=1&height=968&playerBrandingId=7af3bd04449c444c964f347f11873075&targetReplaceId=videoPlayer&width=1656&wmode=opaque&allowScriptAccess=always',
+        'info_dict': {
+            'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
             'ext': 'mp4',
-            'title': unescapeHTML(info['title']),
-            'url': info.get('ipad_url') or info['url'],
-            'description': unescapeHTML(more_info['description']),
-            'thumbnail': more_info['promo'],
-        }
+            'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
+            'description': '',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        embedCode = mobj.group('id')
-        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
-        player = self._download_webpage(player_url, embedCode)
-        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
-                                        player, 'mobile player url')
-        # Looks like some videos are only available for particular devices
-        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
-        # is only available for ipad)
-        # Working around with fetching URLs for all the devices found starting with 'unknown'
-        # until we succeed or eventually fail for each device.
-        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
-        devices.remove('unknown')
-        devices.insert(0, 'unknown')
-        for device in devices:
-            mobile_player = self._download_webpage(
-                '%s&device=%s' % (mobile_url, device), embedCode,
-                'Downloading mobile player JS for %s device' % device)
-            videos_info = self._search_regex(
-                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
-                mobile_player, 'info', fatal=False, default=None)
-            if videos_info:
-                break
-        if not videos_info:
-            raise ExtractorError('Unable to extract info')
-        videos_info = videos_info.replace('\\"', '"')
-        videos_more_info = self._search_regex(
-            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
-        videos_info = json.loads(videos_info)
-        videos_more_info = json.loads(videos_more_info)
-
-        if videos_more_info.get('lineup'):
-            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
-            return {
-                '_type': 'playlist',
-                'id': embedCode,
-                'title': unescapeHTML(videos_more_info['title']),
-                'entries': videos,
-            }
-        else:
-            return self._extract_result(videos_info[0], videos_more_info)
+        partner_id = mobj.group('partner_id')
+        video_id = mobj.group('id')
+        pcode = mobj.group('pcode')
+        player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
+        return self._extract(player_url, video_id)

youtube_dl/extractor/pbs.py

@@ -5,6 +5,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    determine_ext,
+    int_or_none,
     unified_strdate,
     US_RATINGS,
 )
@@ -149,21 +151,45 @@ class PBSIE(InfoExtractor):
                 for vid_id in video_id]
             return self.playlist_result(entries, display_id)
 
-        info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
-        info = self._download_json(info_url, display_id)
+        info = self._download_json(
+            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
+            display_id)
 
-        redirect_url = info['alternate_encoding']['url']
-        redirect_info = self._download_json(
-            redirect_url + '?format=json', display_id,
-            'Downloading video url info')
-        if redirect_info['status'] == 'error':
-            if redirect_info['http_code'] == 403:
-                message = (
-                    'The video is not available in your region due to '
-                    'right restrictions')
+        formats = []
+        for encoding_name in ('recommended_encoding', 'alternate_encoding'):
+            redirect = info.get(encoding_name)
+            if not redirect:
+                continue
+            redirect_url = redirect.get('url')
+            if not redirect_url:
+                continue
+
+            redirect_info = self._download_json(
+                redirect_url + '?format=json', display_id,
+                'Downloading %s video url info' % encoding_name)
+
+            if redirect_info['status'] == 'error':
+                if redirect_info['http_code'] == 403:
+                    message = (
+                        'The video is not available in your region due to '
+                        'right restrictions')
+                else:
+                    message = redirect_info['message']
+                raise ExtractorError(message, expected=True)
+
+            format_url = redirect_info.get('url')
+            if not format_url:
+                continue
+
+            if determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
             else:
-                message = redirect_info['message']
-            raise ExtractorError(message, expected=True)
+                formats.append({
+                    'url': format_url,
+                    'format_id': redirect.get('eeid'),
+                })
+        self._sort_formats(formats)
 
         rating_str = info.get('rating')
         if rating_str is not None:
@@ -174,11 +200,10 @@ class PBSIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': info['title'],
-            'url': redirect_info['url'],
-            'ext': 'mp4',
             'description': info['program'].get('description'),
             'thumbnail': info.get('image_url'),
-            'duration': info.get('duration'),
+            'duration': int_or_none(info.get('duration')),
             'age_limit': age_limit,
             'upload_date': upload_date,
+            'formats': formats,
         }

youtube_dl/extractor/pornhub.py

@@ -71,7 +71,8 @@ class PornHubIE(InfoExtractor):
 
         video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
         if webpage.find('"encrypted":true') != -1:
-            password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
+            password = compat_urllib_parse.unquote_plus(
+                self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
         formats = []

youtube_dl/extractor/prosiebensat1.py

@@ -17,7 +17,7 @@ from ..utils import (
 class ProSiebenSat1IE(InfoExtractor):
     IE_NAME = 'prosiebensat1'
     IE_DESC = 'ProSiebenSat.1 Digital'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)'
 
     _TESTS = [
         {

youtube_dl/extractor/qqmusic.py

@@ -9,11 +9,13 @@ from .common import InfoExtractor
 from ..utils import (
     strip_jsonp,
     unescapeHTML,
+    js_to_json,
 )
 from ..compat import compat_urllib_request
 
 
 class QQMusicIE(InfoExtractor):
+    IE_NAME = 'qqmusic'
     _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
@@ -24,7 +26,7 @@ class QQMusicIE(InfoExtractor):
             'title': '可惜没如果',
             'upload_date': '20141227',
             'creator': '林俊杰',
-            'description': 'md5:4348ff1dd24036906baa7b6f973f8d30',
+            'description': 'md5:d327722d0361576fde558f1ac68a7065',
         }
     }]
 
@@ -58,6 +60,8 @@ class QQMusicIE(InfoExtractor):
         lrc_content = self._html_search_regex(
             r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
             detail_info_page, 'LRC lyrics', default=None)
+        if lrc_content:
+            lrc_content = lrc_content.replace('\\n', '\n')
 
         guid = self.m_r_get_ruin()
 
@@ -96,6 +100,7 @@ class QQPlaylistBaseIE(InfoExtractor):
 
 
 class QQMusicSingerIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:singer'
     _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
@@ -139,6 +144,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
 
 
 class QQMusicAlbumIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:album'
     _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
 
     _TEST = {
@@ -168,3 +174,67 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
             album_page, 'album details', default=None)
 
         return self.playlist_result(entries, mid, album_name, album_detail)
+
+
+class QQMusicToplistIE(QQPlaylistBaseIE):
+    IE_NAME = 'qqmusic:toplist'
+    _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
+
+    _TESTS = [{
+        'url': 'http://y.qq.com/#type=toplist&p=global_12',
+        'info_dict': {
+            'id': 'global_12',
+            'title': 'itunes榜',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'http://y.qq.com/#type=toplist&p=top_6',
+        'info_dict': {
+            'id': 'top_6',
+            'title': 'QQ音乐巅峰榜·欧美',
+        },
+        'playlist_count': 100,
+    }, {
+        'url': 'http://y.qq.com/#type=toplist&p=global_5',
+        'info_dict': {
+            'id': 'global_5',
+            'title': '韩国mnet排行榜',
+        },
+        '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,
+            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
+
+        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)
+
+        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)
+
+        return self.playlist_result(entries, list_id, list_name)

youtube_dl/extractor/rtbf.py

@@ -1,10 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)
 
 
 class RTBFIE(InfoExtractor):
@@ -16,25 +17,24 @@ class RTBFIE(InfoExtractor):
             'id': '1921274',
             'ext': 'mp4',
             'title': 'Les Diables au coeur (épisode 2)',
-            'description': 'Football - Diables Rouges',
             'duration': 3099,
-            'timestamp': 1398456336,
-            'upload_date': '20140425',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
+        webpage = self._download_webpage(
+            'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
 
-        data = json.loads(self._html_search_regex(
-            r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data']
+        data = self._parse_json(
+            unescapeHTML(self._search_regex(
+                r'data-video="([^"]+)"', webpage, 'data video')),
+            video_id)
 
         video_url = data.get('downloadUrl') or data.get('url')
 
-        if data['provider'].lower() == 'youtube':
+        if data.get('provider').lower() == 'youtube':
             return self.url_result(video_url, 'Youtube')
 
         return {
@@ -42,8 +42,8 @@ class RTBFIE(InfoExtractor):
             'url': video_url,
             'title': data['title'],
             'description': data.get('description') or data.get('subtitle'),
-            'thumbnail': data['thumbnail']['large'],
+            'thumbnail': data.get('thumbnail'),
             'duration': data.get('duration') or data.get('realDuration'),
-            'timestamp': data['created'],
-            'view_count': data['viewCount'],
+            'timestamp': int_or_none(data.get('created')),
+            'view_count': int_or_none(data.get('viewCount')),
         }

youtube_dl/extractor/rtlnow.py

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

youtube_dl/extractor/rts.py

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

youtube_dl/extractor/rtve.py

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

youtube_dl/extractor/rutv.py

@@ -84,18 +84,27 @@ class RUTVIE(InfoExtractor):
                 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
                 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
             },
+            'skip': 'Translation has finished',
+        },
+        {
+            'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/',
+            'info_dict': {
+                'id': '21',
+                'ext': 'mp4',
+                'title': 're:^Россия 24. Прямой эфир [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'is_live': True,
+            },
             'params': {
-                # rtmp download
+                # m3u8 download
                 'skip_download': True,
             },
-            'skip': 'Translation has finished',
         },
     ]
 
     @classmethod
     def _extract_url(cls, webpage):
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
         if mobj:
             return mobj.group('url')
 
@@ -119,8 +128,10 @@ class RUTVIE(InfoExtractor):
         elif video_path.startswith('index/iframe/cast_id'):
             video_type = 'live'
 
+        is_live = video_type == 'live'
+
         json_data = self._download_json(
-            'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id),
+            'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if is_live else '', video_id),
             video_id, 'Downloading JSON')
 
         if json_data['errors']:
@@ -147,6 +158,7 @@ class RUTVIE(InfoExtractor):
 
         for transport, links in media['sources'].items():
             for quality, url in links.items():
+                preference = -1 if priority_transport == transport else -2
                 if transport == 'rtmp':
                     mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
                     if not mobj:
@@ -160,9 +172,11 @@ class RUTVIE(InfoExtractor):
                         'rtmp_live': True,
                         'ext': 'flv',
                         'vbr': int(quality),
+                        'preference': preference,
                     }
                 elif transport == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(url, video_id, 'mp4'))
+                    formats.extend(self._extract_m3u8_formats(
+                        url, video_id, 'mp4', preference=preference, m3u8_id='hls'))
                     continue
                 else:
                     fmt = {
@@ -172,21 +186,18 @@ class RUTVIE(InfoExtractor):
                     'width': width,
                     'height': height,
                     'format_id': '%s-%s' % (transport, quality),
-                    'preference': -1 if priority_transport == transport else -2,
                 })
                 formats.append(fmt)
 
-        if not formats:
-            raise ExtractorError('No media links available for %s' % video_id)
-
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,
             'duration': duration,
             'formats': formats,
+            'is_live': is_live,
         }

youtube_dl/extractor/sbs.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import json
 import re
 from .common import InfoExtractor
 from ..utils import (
@@ -33,16 +32,18 @@ class SBSIE(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)
 
-        release_urls_json = js_to_json(self._search_regex(
+        player = self._search_regex(
             r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
-            webpage, ''))
-        release_urls = json.loads(release_urls_json)
-        theplatform_url = (
-            release_urls.get('progressive') or release_urls.get('standard'))
+            webpage, 'player')
+        player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player)
+
+        release_urls = self._parse_json(js_to_json(player), video_id)
+
+        theplatform_url = release_urls.get('progressive') or release_urls['standard']
 
         title = remove_end(self._og_search_title(webpage), ' (The Feed)')
         description = self._html_search_meta('description', webpage)
@@ -52,7 +53,6 @@ class SBSIE(InfoExtractor):
             '_type': 'url_transparent',
             'id': video_id,
             'url': theplatform_url,
-
             'title': title,
             'description': description,
             'thumbnail': thumbnail,

youtube_dl/extractor/screenwavemedia.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class ScreenwaveMediaIE(InfoExtractor):
-    _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
+    _VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
 
     _TESTS = [{
         'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
@@ -20,7 +20,10 @@ class ScreenwaveMediaIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        playerdata = self._download_webpage(url, video_id, 'Downloading player webpage')
+
+        playerdata = self._download_webpage(
+            'http://player.screenwavemedia.com/play/player.php?id=%s' % video_id,
+            video_id, 'Downloading player webpage')
 
         vidtitle = self._search_regex(
             r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
@@ -99,7 +102,7 @@ class TeamFourIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         playerdata_url = self._search_regex(
-            r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+            r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
             webpage, 'player data URL')
 
         video_title = self._html_search_regex(

youtube_dl/extractor/senateisvp.py

@@ -48,7 +48,7 @@ class SenateISVPIE(InfoExtractor):
         ["arch", "", "http://ussenate-f.akamaihd.net/"]
     ]
     _IE_NAME = 'senate.gov'
-    _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
+    _VALID_URL = r'http://www\.senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
         'info_dict': {
@@ -72,12 +72,16 @@ class SenateISVPIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Integrated Senate Video Player'
         }
+    }, {
+        # From http://www.c-span.org/video/?96791-1
+        'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _search_iframe_url(webpage):
         mobj = re.search(
-            r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
+            r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
             webpage)
         if mobj:
             return mobj.group('url')

youtube_dl/extractor/shared.py

@@ -47,7 +47,7 @@ class SharedIE(InfoExtractor):
         video_url = self._html_search_regex(
             r'data-url="([^"]+)"', video_page, 'video URL')
         title = base64.b64decode(self._html_search_meta(
-            'full:title', webpage, 'title')).decode('utf-8')
+            'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
         filesize = int_or_none(self._html_search_meta(
             'full:size', webpage, 'file size', fatal=False))
         thumbnail = self._html_search_regex(

youtube_dl/extractor/sockshare.py

@@ -1,83 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-)
-
-from .common import InfoExtractor
-
-
-class SockshareIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
-    _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
-    _TEST = {
-        'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
-        'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
-        'info_dict': {
-            'id': '437BE28B89D799D7',
-            'title': 'big_buck_bunny_720p_surround.avi',
-            'ext': 'avi',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        url = 'http://sockshare.com/file/%s' % video_id
-        webpage = self._download_webpage(url, video_id)
-
-        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id,
-                                 expected=True)
-
-        confirm_hash = self._html_search_regex(r'''(?x)<input\s+
-            type="hidden"\s+
-            value="([^"]*)"\s+
-            name="hash"
-            ''', webpage, 'hash')
-
-        fields = {
-            "hash": confirm_hash.encode('utf-8'),
-            "confirm": "Continue as Free User"
-        }
-
-        post = compat_urllib_parse.urlencode(fields)
-        req = compat_urllib_request.Request(url, post)
-        # Apparently, this header is required for confirmation to work.
-        req.add_header('Host', 'www.sockshare.com')
-        req.add_header('Content-type', 'application/x-www-form-urlencoded')
-
-        webpage = self._download_webpage(
-            req, video_id, 'Downloading video page')
-
-        video_url = self._html_search_regex(
-            r'<a href="([^"]*)".+class="download_file_link"',
-            webpage, 'file url')
-        video_url = "http://www.sockshare.com" + video_url
-        title = self._html_search_regex((
-            r'<h1>(.+)<strong>',
-            r'var name = "([^"]+)";'),
-            webpage, 'title', default=None)
-        thumbnail = self._html_search_regex(
-            r'<img\s+src="([^"]*)".+?name="bg"',
-            webpage, 'thumbnail', default=None)
-
-        formats = [{
-            'format_id': 'sd',
-            'url': video_url,
-            'ext': determine_ext(title),
-        }]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }

youtube_dl/extractor/sohu.py

@@ -8,7 +8,7 @@ from ..compat import (
     compat_str,
     compat_urllib_request
 )
-from ..utils import sanitize_url_path_consecutive_slashes
+from ..utils import ExtractorError
 
 
 class SohuIE(InfoExtractor):
@@ -23,12 +23,10 @@ class SohuIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'MV：Far East Movement《The Illest》',
         },
-        'params': {
-            'cn_verification_proxy': 'proxy.uku.im:8888'
-        }
+        'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
-        'md5': '699060e75cf58858dd47fb9c03c42cfb',
+        'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a',
         'info_dict': {
             'id': '409385080',
             'ext': 'mp4',
@@ -36,7 +34,7 @@ class SohuIE(InfoExtractor):
         }
     }, {
         'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
-        'md5': '9bf34be48f2f4dadcb226c74127e203c',
+        'md5': '49308ff6dafde5ece51137d04aec311e',
         'info_dict': {
             'id': '78693464',
             'ext': 'mp4',
@@ -50,7 +48,7 @@ class SohuIE(InfoExtractor):
             'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{
-            'md5': 'bdbfb8f39924725e6589c146bc1883ad',
+            'md5': '492923eac023ba2f13ff69617c32754a',
             'info_dict': {
                 'id': '78910339_part1',
                 'ext': 'mp4',
@@ -58,7 +56,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
-            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
+            'md5': 'de604848c0e8e9c4a4dde7e1347c0637',
             'info_dict': {
                 'id': '78910339_part2',
                 'ext': 'mp4',
@@ -66,7 +64,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
-            'md5': '8407e634175fdac706766481b9443450',
+            'md5': '93584716ee0657c0b205b8aa3d27aa13',
             'info_dict': {
                 'id': '78910339_part3',
                 'ext': 'mp4',
@@ -117,6 +115,15 @@ class SohuIE(InfoExtractor):
             r'var vid ?= ?["\'](\d+)["\']',
             webpage, 'video path')
         vid_data = _fetch_data(vid, mytv)
+        if vid_data['play'] != 1:
+            if vid_data.get('status') == 12:
+                raise ExtractorError(
+                    'Sohu said: There\'s something wrong in the video.',
+                    expected=True)
+            else:
+                raise ExtractorError(
+                    'Sohu said: The video is only licensed to users in Mainland China.',
+                    expected=True)
 
         formats_json = {}
         for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
@@ -132,24 +139,21 @@ class SohuIE(InfoExtractor):
         for i in range(part_count):
             formats = []
             for format_id, format_data in formats_json.items():
-                allot = format_data['allot']
-                prot = format_data['prot']
-
                 data = format_data['data']
-                clips_url = data['clipsURL']
-                su = data['su']
 
-                part_str = self._download_webpage(
-                    'http://%s/?prot=%s&file=%s&new=%s' %
-                    (allot, prot, clips_url[i], su[i]),
-                    video_id,
-                    'Downloading %s video URL part %d of %d'
-                    % (format_id, i + 1, part_count))
-
-                part_info = part_str.split('|')
-
-                video_url = sanitize_url_path_consecutive_slashes(
-                    '%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
+                # URLs starts with http://newflv.sohu.ccgslb.net/ is not usable
+                # so retry until got a working URL
+                video_url = 'newflv.sohu.ccgslb.net'
+                retries = 0
+                while 'newflv.sohu.ccgslb.net' in video_url and retries < 5:
+                    download_note = 'Download information from CDN gateway for format ' + format_id
+                    if retries > 0:
+                        download_note += ' (retry #%d)' % retries
+                    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']
 
                 formats.append({
                     'url': video_url,

youtube_dl/extractor/soundcloud.py

@@ -336,7 +336,7 @@ class SoundcloudUserIE(SoundcloudIE):
             if len(new_entries) == 0:
                 self.to_screen('%s: End page received' % uploader)
                 break
-            entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries)
+            entries.extend(self.url_result(e['permalink_url'], 'Soundcloud') for e in new_entries)
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/southpark.py

@@ -32,7 +32,7 @@ class SouthParkEsIE(SouthParkIE):
     }]
 
 
-class SouthparkDeIE(SouthParkIE):
+class SouthParkDeIE(SouthParkIE):
     IE_NAME = 'southpark.de'
     _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
     _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
@@ -46,3 +46,25 @@ class SouthparkDeIE(SouthParkIE):
             'description': 'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
         },
     }]
+
+
+class SouthParkNlIE(SouthParkIE):
+    IE_NAME = 'southpark.nl'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _FEED_URL = 'http://www.southpark.nl/feeds/video-player/mrss/'
+
+    _TESTS = [{
+        'url': 'http://www.southpark.nl/full-episodes/s18e06-freemium-isnt-free',
+        'playlist_count': 4,
+    }]
+
+
+class SouthParkDkIE(SouthParkIE):
+    IE_NAME = 'southparkstudios.dk'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southparkstudios\.dk/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _FEED_URL = 'http://www.southparkstudios.dk/feeds/video-player/mrss/'
+
+    _TESTS = [{
+        'url': 'http://www.southparkstudios.dk/full-episodes/s18e07-grounded-vindaloop',
+        'playlist_count': 4,
+    }]

youtube_dl/extractor/spankwire.py

@@ -71,7 +71,7 @@ class SpankwireIE(InfoExtractor):
             compat_urllib_parse.unquote,
             re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))
         if webpage.find('flashvars\.encrypted = "true"') != -1:
-            password = self._html_search_regex(
+            password = self._search_regex(
                 r'flashvars\.video_title = "([^"]+)',
                 webpage, 'password').replace('+', ' ')
             video_urls = list(map(

youtube_dl/extractor/sportbox.py

@@ -4,37 +4,36 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
-    parse_duration,
-    parse_iso8601,
+    unified_strdate,
 )
 
 
 class SportBoxIE(InfoExtractor):
-    _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
-    _TESTS = [
-        {
-            'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
-            'md5': 'ff56a598c2cf411a9a38a69709e97079',
-            'info_dict': {
-                'id': '80822',
-                'ext': 'mp4',
-                'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
-                'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
-                'thumbnail': 're:^https?://.*\.jpg$',
-                'timestamp': 1411896237,
-                'upload_date': '20140928',
-                'duration': 4846,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-        }, {
-            'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
-            'only_matching': True,
-        }
-    ]
+    _VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
+    _TESTS = [{
+        'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
+        'md5': 'ff56a598c2cf411a9a38a69709e97079',
+        'info_dict': {
+            'id': '80822',
+            'ext': 'mp4',
+            'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
+            'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20140928',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
+        'only_matching': True,
+    }, {
+        'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -42,35 +41,75 @@ class SportBoxIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
-        video_id = self._search_regex(
-            r'src="/vdl/player/media/(\d+)"', webpage, 'video id')
-
-        player = self._download_webpage(
-            'http://news.sportbox.ru/vdl/player/media/%s' % video_id,
-            display_id, 'Downloading player webpage')
-
-        hls = self._search_regex(
-            r"var\s+original_hls_file\s*=\s*'([^']+)'", player, 'hls file')
-
-        formats = self._extract_m3u8_formats(hls, display_id, 'mp4')
+        player = self._search_regex(
+            r'src="/?(vdl/player/[^"]+)"', webpage, 'player')
 
         title = self._html_search_regex(
-            r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title')
-        description = self._html_search_regex(
-            r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False)
+            [r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'],
+            webpage, 'title')
+        description = self._og_search_description(webpage) or self._html_search_meta(
+            'description', webpage, 'description')
         thumbnail = self._og_search_thumbnail(webpage)
-        timestamp = parse_iso8601(self._search_regex(
-            r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False))
-        duration = parse_duration(self._html_search_regex(
-            r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False))
+        upload_date = unified_strdate(self._html_search_meta(
+            'dateCreated', webpage, 'upload date'))
 
         return {
-            'id': video_id,
+            '_type': 'url_transparent',
+            'url': compat_urlparse.urljoin(url, '/%s' % player),
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
+            'upload_date': upload_date,
+        }
+
+
+class SportBoxEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
+        'info_dict': {
+            'id': '211355',
+            'ext': 'mp4',
+            'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"',
+            webpage)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        hls = self._search_regex(
+            r"sportboxPlayer\.jwplayer_common_params\.file\s*=\s*['\"]([^'\"]+)['\"]",
+            webpage, 'hls file')
+
+        formats = self._extract_m3u8_formats(hls, video_id, 'mp4')
+
+        title = self._search_regex(
+            r'sportboxPlayer\.node_title\s*=\s*"([^"]+)"', webpage, 'title')
+
+        thumbnail = self._search_regex(
+            r'sportboxPlayer\.jwplayer_common_params\.image\s*=\s*"([^"]+)"',
+            webpage, 'thumbnail', default=None)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
             'formats': formats,
         }

youtube_dl/extractor/svt.py

@@ -9,41 +9,9 @@ from ..utils import (
 )
 
 
-class SVTPlayIE(InfoExtractor):
-    IE_DESC = 'SVT Play and Öppet arkiv'
-    _VALID_URL = r'https?://(?:www\.)?(?P<host>svtplay|oppetarkiv)\.se/video/(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final',
-        'md5': 'ade3def0643fa1c40587a422f98edfd9',
-        'info_dict': {
-            'id': '2609989',
-            'ext': 'flv',
-            'title': 'SM veckan vinter, Örebro - Rally, final',
-            'duration': 4500,
-            'thumbnail': 're:^https?://.*[\.-]jpg$',
-            'age_limit': 0,
-        },
-    }, {
-        'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318',
-        'md5': 'c3101a17ce9634f4c1f9800f0746c187',
-        'info_dict': {
-            'id': '1058509',
-            'ext': 'flv',
-            'title': 'Farlig kryssning',
-            'duration': 2566,
-            'thumbnail': 're:^https?://.*[\.-]jpg$',
-            'age_limit': 0,
-        },
-        'skip': 'Only works from Sweden',
-    }]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        host = mobj.group('host')
-
-        info = self._download_json(
-            'http://www.%s.se/video/%s?output=json' % (host, video_id), video_id)
+class SVTBaseIE(InfoExtractor):
+    def _extract_video(self, url, video_id):
+        info = self._download_json(url, video_id)
 
         title = info['context']['title']
         thumbnail = info['context'].get('thumbnailImage')
@@ -80,3 +48,70 @@ class SVTPlayIE(InfoExtractor):
             'duration': duration,
             'age_limit': age_limit,
         }
+
+
+class SVTIE(SVTBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
+        'md5': '9648197555fc1b49e3dc22db4af51d46',
+        'info_dict': {
+            'id': '2900353',
+            'ext': 'flv',
+            'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+            'duration': 27,
+            'age_limit': 0,
+        },
+    }
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        widget_id = mobj.group('widget_id')
+        article_id = mobj.group('id')
+        return self._extract_video(
+            'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
+            article_id)
+
+
+class SVTPlayIE(SVTBaseIE):
+    IE_DESC = 'SVT Play and Öppet arkiv'
+    _VALID_URL = r'https?://(?:www\.)?(?P<host>svtplay|oppetarkiv)\.se/video/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final',
+        'md5': 'ade3def0643fa1c40587a422f98edfd9',
+        'info_dict': {
+            'id': '2609989',
+            'ext': 'flv',
+            'title': 'SM veckan vinter, Örebro - Rally, final',
+            'duration': 4500,
+            'thumbnail': 're:^https?://.*[\.-]jpg$',
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318',
+        'md5': 'c3101a17ce9634f4c1f9800f0746c187',
+        'info_dict': {
+            'id': '1058509',
+            'ext': 'flv',
+            'title': 'Farlig kryssning',
+            'duration': 2566,
+            'thumbnail': 're:^https?://.*[\.-]jpg$',
+            'age_limit': 0,
+        },
+        'skip': 'Only works from Sweden',
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        host = mobj.group('host')
+        return self._extract_video(
+            'http://www.%s.se/video/%s?output=json' % (host, video_id),
+            video_id)

youtube_dl/extractor/teamcoco.py

@@ -2,13 +2,17 @@
 from __future__ import unicode_literals
 
 import base64
+import binascii
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     qualities,
+    determine_ext,
 )
+from ..compat import compat_ord
 
 
 class TeamcocoIE(InfoExtractor):
@@ -59,37 +63,53 @@ class TeamcocoIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         display_id = mobj.group('display_id')
-        webpage = self._download_webpage(url, display_id)
+        webpage, urlh = self._download_webpage_handle(url, display_id)
+        if 'src=expired' in urlh.geturl():
+            raise ExtractorError('This video is expired.', expected=True)
 
         video_id = mobj.group('video_id')
         if not video_id:
             video_id = self._html_search_regex(
                 self._VIDEO_ID_REGEXES, webpage, 'video id')
 
-        preload = None
-        preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
-        if preloads:
-            preload = max([(len(p), p) for p in preloads])[1]
+        data = None
 
-        if not preload:
-            preload = ''.join(re.findall(r'this\.push\("([^"]+)"\);', webpage))
+        preload_codes = self._html_search_regex(
+            r'(function.+)setTimeout\(function\(\)\{playlist',
+            webpage, 'preload codes')
+        base64_fragments = re.findall(r'"([a-zA-z0-9+/=]+)"', preload_codes)
+        base64_fragments.remove('init')
 
-        if not preload:
-            preload = self._html_search_regex([
-                r'player,\[?"([^"]+)"\]?', r'player.init\(\[?"([^"]+)"\]?\)'
-            ], webpage.replace('","', ''), 'preload data', default=None)
+        def _check_sequence(cur_fragments):
+            if not cur_fragments:
+                return
+            for i in range(len(cur_fragments)):
+                cur_sequence = (''.join(cur_fragments[i:] + cur_fragments[:i])).encode('ascii')
+                try:
+                    raw_data = base64.b64decode(cur_sequence)
+                    if compat_ord(raw_data[0]) == compat_ord('{'):
+                        return json.loads(raw_data.decode('utf-8'))
+                except (TypeError, binascii.Error, UnicodeDecodeError, ValueError):
+                    continue
 
-        if not preload:
+        def _check_data():
+            for i in range(len(base64_fragments) + 1):
+                for j in range(i, len(base64_fragments) + 1):
+                    data = _check_sequence(base64_fragments[:i] + base64_fragments[j:])
+                    if data:
+                        return data
+
+        self.to_screen('Try to compute possible data sequence. This may take some time.')
+        data = _check_data()
+
+        if not data:
             raise ExtractorError(
                 'Preload information could not be extracted', expected=True)
 
-        data = self._parse_json(
-            base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)
-
         formats = []
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
-            if filed['type'] == 'hls':
+            if determine_ext(filed['url']) == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     filed['url'], video_id, ext='mp4'))
             else:

youtube_dl/extractor/telecinco.py

@@ -16,6 +16,10 @@ class TelecincoIE(MiTeleIE):
             'title': 'Con Martín Berasategui, hacer un bacalao al ...',
             'duration': 662,
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
         'only_matching': True,

youtube_dl/extractor/tenplay.py

@@ -2,6 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+)
 
 
 class TenPlayIE(InfoExtractor):
@@ -49,18 +53,23 @@ class TenPlayIE(InfoExtractor):
             if protocol == 'rtmp':
                 url = url.replace('&mp4:', '')
 
+                tbr = int_or_none(rendition.get('encodingRate'), 1000)
+
             formats.append({
-                'format_id': '_'.join(['rtmp', rendition['videoContainer'].lower(), rendition['videoCodec'].lower()]),
-                'width': rendition['frameWidth'],
-                'height': rendition['frameHeight'],
-                'tbr': rendition['encodingRate'] / 1024,
-                'filesize': rendition['size'],
+                'format_id': '_'.join(
+                    ['rtmp', rendition['videoContainer'].lower(),
+                     rendition['videoCodec'].lower(), '%sk' % tbr]),
+                'width': int_or_none(rendition['frameWidth']),
+                'height': int_or_none(rendition['frameHeight']),
+                'tbr': tbr,
+                'filesize': int_or_none(rendition['size']),
                 'protocol': protocol,
                 'ext': ext,
                 'vcodec': rendition['videoCodec'].lower(),
                 'container': rendition['videoContainer'].lower(),
                 'url': url,
             })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
@@ -74,8 +83,8 @@ class TenPlayIE(InfoExtractor):
                 'url': json['thumbnailURL']
             }],
             'thumbnail': json['videoStillURL'],
-            'duration': json['length'] / 1000,
-            'timestamp': float(json['creationDate']) / 1000,
-            'uploader': json['customFields']['production_company_distributor'] if 'production_company_distributor' in json['customFields'] else 'TENplay',
-            'view_count': json['playsTotal']
+            'duration': float_or_none(json.get('length'), 1000),
+            'timestamp': float_or_none(json.get('creationDate'), 1000),
+            'uploader': json.get('customFields', {}).get('production_company_distributor') or 'TENplay',
+            'view_count': int_or_none(json.get('playsTotal')),
         }

youtube_dl/extractor/testtube.py

@@ -15,19 +15,37 @@ class TestTubeIE(InfoExtractor):
             'id': '60163',
             'display_id': '5-weird-ways-plants-can-eat-animals',
             'duration': 275,
-            'ext': 'mp4',
+            'ext': 'webm',
             'title': '5 Weird Ways Plants Can Eat Animals',
             'description': 'Why have some plants evolved to eat meat?',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'DNews',
             'uploader_id': 'dnews',
         },
+    }, {
+        'url': 'https://testtube.com/iflscience/insane-jet-ski-flipping',
+        'info_dict': {
+            'id': 'fAGfJ4YjVus',
+            'ext': 'mp4',
+            'title': 'Flipping Jet-Ski Skills | Outrageous Acts of Science',
+            'uploader': 'Science Channel',
+            'uploader_id': 'ScienceChannel',
+            'upload_date': '20150203',
+            'description': 'md5:e61374030015bae1d2e22f096d4769d6',
+        }
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
+
+        youtube_url = self._html_search_regex(
+            r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
+            webpage, 'youtube iframe', default=None)
+        if youtube_url:
+            return self.url_result(youtube_url, 'Youtube', video_id=display_id)
+
         video_id = self._search_regex(
             r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);",
             webpage, 'video ID')

youtube_dl/extractor/tf1.py

@@ -6,8 +6,8 @@ from .common import InfoExtractor
 
 class TF1IE(InfoExtractor):
     """TF1 uses the wat.tv player."""
-    _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
-    _TESTS = {
+    _VALID_URL = r'http://(?:videos\.tf1|www\.tfou|www\.tf1)\.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': {
             'id': '10635995',
@@ -32,7 +32,10 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/theplatform.py

@@ -129,7 +129,9 @@ class ThePlatformIE(InfoExtractor):
         head = meta.find(_x('smil:head'))
         body = meta.find(_x('smil:body'))
 
-        f4m_node = body.find(_x('smil:seq//smil:video')) or body.find(_x('smil:seq/smil:video'))
+        f4m_node = body.find(_x('smil:seq//smil:video'))
+        if f4m_node is None:
+            f4m_node = body.find(_x('smil:seq/smil:video'))
         if f4m_node is not None and '.f4m' in f4m_node.attrib['src']:
             f4m_url = f4m_node.attrib['src']
             if 'manifest.f4m?' not in f4m_url:
@@ -142,7 +144,9 @@ class ThePlatformIE(InfoExtractor):
             formats = []
             switch = body.find(_x('smil:switch'))
             if switch is None:
-                switch = body.find(_x('smil:par//smil:switch')) or body.find(_x('smil:par/smil:switch'))
+                switch = body.find(_x('smil:par//smil:switch'))
+            if switch is None:
+                switch = body.find(_x('smil:par/smil:switch'))
             if switch is None:
                 switch = body.find(_x('smil:par'))
             if switch is not None:
@@ -163,7 +167,9 @@ class ThePlatformIE(InfoExtractor):
                         'vbr': vbr,
                     })
             else:
-                switch = body.find(_x('smil:seq//smil:switch')) or body.find(_x('smil:seq/smil:switch'))
+                switch = body.find(_x('smil:seq//smil:switch'))
+                if switch is None:
+                    switch = body.find(_x('smil:seq/smil:switch'))
                 for f in switch.findall(_x('smil:video')):
                     attr = f.attrib
                     vbr = int_or_none(attr.get('system-bitrate'), 1000)

youtube_dl/extractor/tmz.py

@@ -30,3 +30,31 @@ class TMZIE(InfoExtractor):
             'description': self._og_search_description(webpage),
             'thumbnail': self._html_search_meta('ThumbURL', webpage),
         }
+
+
+class TMZArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
+    _TEST = {
+        'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
+        'md5': 'e482a414a38db73087450e3a6ce69d00',
+        'info_dict': {
+            'id': '0_6snoelag',
+            'ext': 'mp4',
+            'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
+            'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake.  She\'s watching me."',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        embedded_video_info_str = self._html_search_regex(
+            r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
+
+        embedded_video_info = self._parse_json(
+            embedded_video_info_str, video_id,
+            transform_source=lambda s: s.replace('\\', ''))
+
+        return self.url_result(
+            'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])

youtube_dl/extractor/tnaflix.py

@@ -10,26 +10,32 @@ from ..utils import (
 
 
 class TNAFlixIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)'
+    _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\("([^"]+)"'
 
-    _TEST = {
-        '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$',
-            'duration': 91,
-            'age_limit': 18,
+    _TESTS = [
+        {
+            'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+            'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+            'info_dict': {
+                'id': '553878',
+                'display_id': 'Carmella-Decesare-striptease',
+                'ext': 'mp4',
+                'title': 'Carmella Decesare - striptease',
+                'description': '',
+                'thumbnail': 're:https?://.*\.jpg$',
+                'duration': 91,
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
+            'matching_only': True,
         }
-    }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/tutv.py

@@ -26,7 +26,7 @@ class TutvIE(InfoExtractor):
 
         data_content = self._download_webpage(
             'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
-        video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8')
+        video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0].encode('utf-8')).decode('utf-8')
 
         return {
             'id': internal_id,