release 2017.02.01

* Added new Regex for prosiebensat1 Extractor Description. Fixes #11810

* Using _og_search_description() as a Fallback for Description-Regex

* Using _og_search_description() as a Fallback for Description-Regex - Second try

* Also added fallback regex

* Using _og_search_description() as a Fallback for Description-Regex - Third try

* removed fatal=False from search for description regex. default=None should be preferred only

* Using fatal=false for _og_search_description

* Revert "Using fatal=false for _og_search_description"

This reverts commit 2b7e123f9d0f2bd6ada54fa8e4e6035fece5dbf4.

* Deleted default=None Parameter for _og_search_property

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.08*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.01.08**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.01*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.01**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2017.01.08
+[debug] youtube-dl version 2017.02.01
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

AUTHORS

@@ -191,3 +191,13 @@ Rich Leeper
 Zhong Jianxin
 Thor77
 Mattias Wadman
+Arjan Verwer
+Costy Petrisor
+Logan B
+Alex Seiler
+Vijay Singh
+Paul Hartmann
+Stephen Chen
+Fabian Stahl
+Bagira
+Odd Stråbø

ChangeLog

@@ -1,3 +1,169 @@
+version 2017.02.01
+
+Extractors
++ [facebook] Add another fallback extraction scenario (#11926)
+* [prosiebensat1] Fix extraction of descriptions (#11810, #11929)
+- [crunchyroll] Remove ScaledBorderAndShadow settings (#9028)
++ [vimeo] Extract upload timestamp
++ [vimeo] Extract license (#8726, #11880)
++ [nrk:series] Add support for series (#11571, #11711)
+
+
+version 2017.01.31
+
+Core
++ [compat] Add compat_etree_register_namespace
+
+Extractors
+* [youtube] Fix extraction for domainless player URLs (#11890, #11891, #11892,
+  #11894, #11895, #11897, #11900, #11903, #11904, #11906, #11907, #11909,
+  #11913, #11914, #11915, #11916, #11917, #11918, #11919)
++ [vimeo] Extract both mixed and separated DASH formats
++ [ruutu] Extract DASH formats
+* [itv] Fix extraction for python 2.6
+
+
+version 2017.01.29
+
+Core
+* [extractor/common] Fix initialization template (#11605, #11825)
++ [extractor/common] Document fragment_base_url and fragment's path fields
+* [extractor/common] Fix duration per DASH segment (#11868)
++ Introduce --autonumber-start option for initial value of %(autonumber)s
+  template (#727, #2702, #9362, #10457, #10529, #11862)
+
+Extractors
++ [azmedien:playlist] Add support for topic and themen playlists (#11817)
+* [npo] Fix subtitles extraction
++ [itv] Extract subtitles
++ [itv] Add support for itv.com (#9240)
++ [mtv81] Add support for mtv81.com (#7619)
++ [vlive] Add support for channels (#11826)
++ [kaltura] Add fallback for fileExt
++ [kaltura] Improve uploader_id extraction
++ [konserthusetplay] Add support for rspoplay.se (#11828)
+
+
+version 2017.01.28
+
+Core
+* [utils] Improve parse_duration
+
+Extractors
+* [crunchyroll] Improve series and season metadata extraction (#11832)
+* [soundcloud] Improve formats extraction and extract audio bitrate
++ [soundcloud] Extract HLS formats
+* [soundcloud] Fix track URL extraction (#11852)
++ [twitch:vod] Expand URL regular expressions (#11846)
+* [aenetworks] Fix season episodes extraction (#11669)
++ [tva] Add support for videos.tva.ca (#11842)
+* [jamendo] Improve and extract more metadata (#11836)
++ [disney] Add support for Disney sites (#7409, #11801, #4975, #11000)
+* [vevo] Remove request to old API and catch API v2 errors
++ [cmt,mtv,southpark] Add support for episode URLs (#11837)
++ [youtube] Add fallback for duration extraction (#11841)
+
+
+version 2017.01.25
+
+Extractors
++ [openload] Fallback video extension to mp4
++ [extractor/generic] Add support for Openload embeds (#11536, #11812)
+* [srgssr] Fix rts video extraction (#11831)
++ [afreecatv:global] Add support for afreeca.tv (#11807)
++ [crackle] Extract vtt subtitles
++ [crackle] Extract multiple resolutions for thumbnails
++ [crackle] Add support for mobile URLs
++ [konserthusetplay] Extract subtitles (#11823)
++ [konserthusetplay] Add support for HLS videos (#11823)
+* [vimeo:review] Fix config URL extraction (#11821)
+
+
+version 2017.01.24
+
+Extractors
+* [pluralsight] Fix extraction (#11820)
++ [nextmedia] Add support for NextTV (壹電視)
+* [24video] Fix extraction (#11811)
+* [youtube:playlist] Fix nonexistent and private playlist detection (#11604)
++ [chirbit] Extract uploader (#11809)
+
+
+version 2017.01.22
+
+Extractors
++ [pornflip] Add support for pornflip.com (#11556, #11795)
+* [chaturbate] Fix extraction (#11797, #11802)
++ [azmedien] Add support for AZ Medien sites (#11784, #11785)
++ [nextmedia] Support redirected URLs
++ [vimeo:channel] Extract videos' titles for playlist entries (#11796)
++ [youtube] Extract episode metadata (#9695, #11774)
++ [cspan] Support Ustream embedded videos (#11547)
++ [1tv] Add support for HLS videos (#11786)
+* [uol] Fix extraction (#11770)
+* [mtv] Relax triforce feed regular expression (#11766)
+
+
+version 2017.01.18
+
+Extractors
+* [bilibili] Fix extraction (#11077)
++ [canalplus] Add fallback for video id (#11764)
+* [20min] Fix extraction (#11683, #11751)
+* [imdb] Extend URL regular expression (#11744)
++ [naver] Add support for tv.naver.com links (#11743)
+
+
+version 2017.01.16
+
+Core
+* [options] Apply custom config to final composite configuration (#11741)
+* [YoutubeDL] Improve protocol auto determining (#11720)
+
+Extractors
+* [xiami] Relax URL regular expressions
+* [xiami] Improve track metadata extraction (#11699)
++ [limelight] Check hand-make direct HTTP links
++ [limelight] Add support for direct HTTP links at video.llnw.net (#11737)
++ [brightcove] Recognize another player ID pattern (#11688)
++ [niconico] Support login via cookies (#7968)
+* [yourupload] Fix extraction (#11601)
++ [beam:live] Add support for beam.pro live streams (#10702, #11596)
+* [vevo] Improve geo restriction detection
++ [dramafever] Add support for URLs with language code (#11714)
+* [cbc] Improve playlist support (#11704)
+
+
+version 2017.01.14
+
+Core
++ [common] Add ability to customize akamai manifest host
++ [utils] Add more date formats
+
+Extractors
+- [mtv] Eliminate _transform_rtmp_url
+* [mtv] Generalize triforce mgid extraction
++ [cmt] Add support for full episodes and video clips (#11623)
++ [mitele] Extract DASH formats
++ [ooyala] Add support for videos with embedToken (#11684)
+* [mixcloud] Fix extraction (#11674)
+* [openload] Fix extraction (#10408)
+* [tv4] Improve extraction (#11698)
+* [freesound] Fix and improve extraction (#11602)
++ [nick] Add support for beta.nick.com (#11655)
+* [mtv,cc] Use HLS by default with native HLS downloader (#11641)
+* [mtv] Fix non-HLS extraction
+
+
+version 2017.01.10
+
+Extractors
+* [youtube] Fix extraction (#11663, #11664)
++ [inc] Add support for inc.com (#11277, #11647)
++ [youtube] Add itag 212 (#11575)
++ [egghead:course] Add support for egghead.io courses
+
+
 version 2017.01.08
 
 Core

README.md

@@ -88,8 +88,6 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     --mark-watched                   Mark videos watched (YouTube only)
     --no-mark-watched                Do not mark videos watched (YouTube only)
     --no-color                       Do not emit color codes in output
-    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
-                                     available
 
 ## Network Options:
     --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -99,16 +97,13 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      string (--proxy "") for direct connection
     --socket-timeout SECONDS         Time to wait before giving up, in seconds
     --source-address IP              Client-side IP address to bind to
-                                     (experimental)
     -4, --force-ipv4                 Make all connections via IPv4
-                                     (experimental)
     -6, --force-ipv6                 Make all connections via IPv6
-                                     (experimental)
     --geo-verification-proxy URL     Use this proxy to verify the IP address for
                                      some geo-restricted sites. The default
                                      proxy specified by --proxy (or none, if the
                                      options is not present) is used for the
-                                     actual downloading. (experimental)
+                                     actual downloading.
 
 ## Video Selection:
     --playlist-start NUMBER          Playlist video to start at (default is 1)
@@ -139,23 +134,23 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      COUNT views
     --max-views COUNT                Do not download any videos with more than
                                      COUNT views
-    --match-filter FILTER            Generic video filter (experimental).
-                                     Specify any key (see help for -o for a list
-                                     of available keys) to match if the key is
-                                     present, !key to check if the key is not
-                                     present,key > NUMBER (like "comment_count >
-                                     12", also works with >=, <, <=, !=, =) to
-                                     compare against a number, and & to require
-                                     multiple matches. Values which are not
-                                     known are excluded unless you put a
-                                     question mark (?) after the operator.For
-                                     example, to only match videos that have
-                                     been liked more than 100 times and disliked
-                                     less than 50 times (or the dislike
-                                     functionality is not available at the given
-                                     service), but who also have a description,
-                                     use --match-filter "like_count > 100 &
-                                     dislike_count <? 50 & description" .
+    --match-filter FILTER            Generic video filter. Specify any key (see
+                                     help for -o for a list of available keys)
+                                     to match if the key is present, !key to
+                                     check if the key is not present,key >
+                                     NUMBER (like "comment_count > 12", also
+                                     works with >=, <, <=, !=, =) to compare
+                                     against a number, and & to require multiple
+                                     matches. Values which are not known are
+                                     excluded unless you put a question mark (?)
+                                     after the operator.For example, to only
+                                     match videos that have been liked more than
+                                     100 times and disliked less than 50 times
+                                     (or the dislike functionality is not
+                                     available at the given service), but who
+                                     also have a description, use --match-filter
+                                     "like_count > 100 & dislike_count <? 50 &
+                                     description" .
     --no-playlist                    Download only the video, if the URL refers
                                      to a video and a playlist.
     --yes-playlist                   Download the playlist, if the URL refers to
@@ -178,6 +173,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      only)
     --skip-unavailable-fragments     Skip unavailable fragments (DASH and
                                      hlsnative only)
+    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
+                                     available
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -210,7 +207,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     --autonumber-size NUMBER         Specify the number of digits in
                                      %(autonumber)s when it is present in output
                                      filename template or --auto-number option
-                                     is given
+                                     is given (default is 5)
+    --autonumber-start NUMBER        Specify the start value for %(autonumber)s
+                                     (default is 1)
     --restrict-filenames             Restrict filenames to only ASCII
                                      characters, and avoid "&" and spaces in
                                      filenames
@@ -374,7 +373,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      avprobe)
     --audio-format FORMAT            Specify audio format: "best", "aac",
                                      "vorbis", "mp3", "m4a", "opus", or "wav";
-                                     "best" by default
+                                     "best" by default; No effect without -x
     --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert
                                      a value between 0 (better) and 9 (worse)
                                      for VBR or a specific bitrate like 128K
@@ -841,7 +840,7 @@ Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
 
 In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
 
-Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
+Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
 
 Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
 

docs/supportedsites.md

@@ -33,7 +33,8 @@
  - **AdobeTVVideo**
  - **AdultSwim**
  - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
- - **AfreecaTV**: afreecatv.com
+ - **afreecatv**: afreecatv.com
+ - **afreecatv:global**: afreecatv.com
  - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
@@ -74,6 +75,8 @@
  - **awaan:live**
  - **awaan:season**
  - **awaan:video**
+ - **AZMedien**: AZ Medien videos
+ - **AZMedienPlaylist**: AZ Medien playlists
  - **Azubu**
  - **AzubuLive**
  - **BaiduVideo**: 百度视频
@@ -86,6 +89,7 @@
  - **bbc.co.uk:article**: BBC articles
  - **bbc.co.uk:iplayer:playlist**
  - **bbc.co.uk:playlist**
+ - **Beam:live**
  - **Beatport**
  - **Beeg**
  - **BehindKink**
@@ -198,6 +202,7 @@
  - **Digiteka**
  - **Discovery**
  - **DiscoveryGo**
+ - **Disney**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
  - **DPlay**
@@ -214,6 +219,7 @@
  - **EaglePlatform**
  - **EbaumsWorld**
  - **EchoMsk**
+ - **egghead:course**: egghead.io course
  - **eHow**
  - **Einthusan**
  - **eitb.tv**
@@ -321,6 +327,7 @@
  - **Imgur**
  - **ImgurAlbum**
  - **Ina**
+ - **Inc**
  - **Indavideo**
  - **IndavideoEmbed**
  - **InfoQ**
@@ -330,6 +337,7 @@
  - **IPrima**
  - **iqiyi**: 爱奇艺
  - **Ir90Tv**
+ - **ITV**
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
@@ -438,6 +446,7 @@
  - **mtg**: MTG services
  - **mtv**
  - **mtv.de**
+ - **mtv81**
  - **mtv:video**
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
@@ -480,6 +489,7 @@
  - **Newstube**
  - **NextMedia**: 蘋果日報
  - **NextMediaActionNews**: 蘋果日報 - 動新聞
+ - **NextTV**: 壹電視
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **NhkVod**
@@ -518,6 +528,7 @@
  - **NRKTV**: NRK TV and NRK Radio
  - **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
  - **NRKTVEpisodes**
+ - **NRKTVSeries**
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
@@ -569,6 +580,7 @@
  - **PolskieRadio**
  - **PolskieRadioCategory**
  - **PornCom**
+ - **PornFlip**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
  - **PornHubPlaylist**
@@ -777,6 +789,7 @@
  - **TV2Article**
  - **TV3**
  - **TV4**: tv4.se and tv4play.se
+ - **TVA**
  - **TVANouvelles**
  - **TVANouvellesArticle**
  - **TVC**
@@ -877,6 +890,7 @@
  - **vk:uservideos**: VK - User's Videos
  - **vk:wallpost**
  - **vlive**
+ - **vlive:channel**
  - **Vodlocker**
  - **VODPlatform**
  - **VoiceRepublic**

test/test_utils.py

@@ -295,6 +295,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
         self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
         self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
+        self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
+        self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
+        self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
 
     def test_unified_timestamps(self):
         self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
@@ -507,6 +510,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
         self.assertEqual(parse_duration('87 Min.'), 5220)
         self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
+        self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(

youtube_dl/YoutubeDL.py

@@ -584,7 +584,7 @@ class YoutubeDL(object):
             if autonumber_size is None:
                 autonumber_size = 5
             autonumber_templ = '%0' + str(autonumber_size) + 'd'
-            template_dict['autonumber'] = autonumber_templ % self._num_downloads
+            template_dict['autonumber'] = autonumber_templ % (self.params.get('autonumber_start', 1) - 1 + self._num_downloads)
             if template_dict.get('playlist_index') is not None:
                 template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
             if template_dict.get('resolution') is None:
@@ -1363,7 +1363,7 @@ class YoutubeDL(object):
                 format['ext'] = determine_ext(format['url']).lower()
             # Automatically determine protocol if missing (useful for format
             # selection purposes)
-            if 'protocol' not in format:
+            if format.get('protocol') is None:
                 format['protocol'] = determine_protocol(format)
             # Add HTTP headers, so that external programs can use them from the
             # json output

youtube_dl/__init__.py

@@ -133,6 +133,12 @@ def _real_main(argv=None):
         parser.error('TV Provider account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')
+    if opts.autonumber_size is not None:
+        if opts.autonumber_size <= 0:
+            parser.error('auto number size must be positive')
+    if opts.autonumber_start is not None:
+        if opts.autonumber_start < 0:
+            parser.error('auto number start must be positive or 0')
     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
@@ -321,6 +327,7 @@ def _real_main(argv=None):
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,
+        'autonumber_start': opts.autonumber_start,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'force_generic_extractor': opts.force_generic_extractor,

youtube_dl/compat.py

@@ -2529,6 +2529,24 @@ else:
                 el.text = el.text.decode('utf-8')
         return doc
 
+if hasattr(etree, 'register_namespace'):
+    compat_etree_register_namespace = etree.register_namespace
+else:
+    def compat_etree_register_namespace(prefix, uri):
+        """Register a namespace prefix.
+        The registry is global, and any existing mapping for either the
+        given prefix or the namespace URI will be removed.
+        *prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
+        attributes in this namespace will be serialized with prefix if possible.
+        ValueError is raised if prefix is reserved or is invalid.
+        """
+        if re.match(r"ns\d+$", prefix):
+            raise ValueError("Prefix format reserved for internal use")
+        for k, v in list(etree._namespace_map.items()):
+            if k == uri or v == prefix:
+                del etree._namespace_map[k]
+        etree._namespace_map[uri] = prefix
+
 if sys.version_info < (2, 7):
     # Here comes the crazy part: In 2.6, if the xpath is a unicode,
     # .//node does not match if a node is a direct child of . !

youtube_dl/extractor/aenetworks.py

@@ -87,7 +87,7 @@ class AENetworksIE(AENetworksBaseIE):
                     self._html_search_meta('aetn:SeriesTitle', webpage))
             elif url_parts_len == 2:
                 entries = []
-                for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
+                for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
                     episode_attributes = extract_attributes(episode_item)
                     episode_url = compat_urlparse.urljoin(
                         url, episode_attributes['data-canonical'])

youtube_dl/extractor/afreecatv.py

@@ -18,6 +18,7 @@ from ..utils import (
 
 
 class AfreecaTVIE(InfoExtractor):
+    IE_NAME = 'afreecatv'
     IE_DESC = 'afreecatv.com'
     _VALID_URL = r'''(?x)
                     https?://
@@ -143,3 +144,94 @@ class AfreecaTVIE(InfoExtractor):
                 expected=True)
 
         return info
+
+
+class AfreecaTVGlobalIE(AfreecaTVIE):
+    IE_NAME = 'afreecatv:global'
+    _VALID_URL = r'https?://(?:www\.)?afreeca\.tv/(?P<channel_id>\d+)(?:/v/(?P<video_id>\d+))?'
+    _TESTS = [{
+        'url': 'http://afreeca.tv/36853014/v/58301',
+        'info_dict': {
+            'id': '58301',
+            'title': 'tryhard top100',
+            'uploader_id': '36853014',
+            'uploader': 'makgi Hearthstone Live!',
+        },
+        'playlist_count': 3,
+    }]
+
+    def _real_extract(self, url):
+        channel_id, video_id = re.match(self._VALID_URL, url).groups()
+        video_type = 'video' if video_id else 'live'
+        query = {
+            'pt': 'view',
+            'bid': channel_id,
+        }
+        if video_id:
+            query['vno'] = video_id
+        video_data = self._download_json(
+            'http://api.afreeca.tv/%s/view_%s.php' % (video_type, video_type),
+            video_id or channel_id, query=query)['channel']
+
+        if video_data.get('result') != 1:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, video_data['remsg']))
+
+        title = video_data['title']
+
+        info = {
+            'thumbnail': video_data.get('thumb'),
+            'view_count': int_or_none(video_data.get('vcnt')),
+            'age_limit': int_or_none(video_data.get('grade')),
+            'uploader_id': channel_id,
+            'uploader': video_data.get('cname'),
+        }
+
+        if video_id:
+            entries = []
+            for i, f in enumerate(video_data.get('flist', [])):
+                video_key = self.parse_video_key(f.get('key', ''))
+                f_url = f.get('file')
+                if not video_key or not f_url:
+                    continue
+                entries.append({
+                    'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
+                    'title': title,
+                    'upload_date': video_key.get('upload_date'),
+                    'duration': int_or_none(f.get('length')),
+                    'url': f_url,
+                    'protocol': 'm3u8_native',
+                    'ext': 'mp4',
+                })
+
+            info.update({
+                'id': video_id,
+                'title': title,
+                'duration': int_or_none(video_data.get('length')),
+            })
+            if len(entries) > 1:
+                info['_type'] = 'multi_video'
+                info['entries'] = entries
+            elif len(entries) == 1:
+                i = entries[0].copy()
+                i.update(info)
+                info = i
+        else:
+            formats = []
+            for s in video_data.get('strm', []):
+                s_url = s.get('purl')
+                if not s_url:
+                    continue
+                # TODO: extract rtmp formats
+                if s.get('stype') == 'HLS':
+                    formats.extend(self._extract_m3u8_formats(
+                        s_url, channel_id, 'mp4', fatal=False))
+            self._sort_formats(formats)
+
+            info.update({
+                'id': channel_id,
+                'title': self._live_title(title),
+                'is_live': True,
+                'formats': formats,
+            })
+
+        return info

youtube_dl/extractor/azmedien.py

@@ -0,0 +1,172 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .kaltura import KalturaIE
+from ..utils import (
+    get_element_by_id,
+    strip_or_none,
+    urljoin,
+)
+
+
+class AZMedienBaseIE(InfoExtractor):
+    def _kaltura_video(self, partner_id, entry_id):
+        return self.url_result(
+            'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
+            video_id=entry_id)
+
+
+class AZMedienIE(AZMedienBaseIE):
+    IE_DESC = 'AZ Medien videos'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            telezueri\.ch|
+                            telebaern\.tv|
+                            telem1\.ch
+                        )/
+                        [0-9]+-show-[^/\#]+
+                        (?:
+                            /[0-9]+-episode-[^/\#]+
+                            (?:
+                                /[0-9]+-segment-(?:[^/\#]+\#)?|
+                                \#
+                            )|
+                            \#
+                        )
+                        (?P<id>[^\#]+)
+                    '''
+
+    _TESTS = [{
+        # URL with 'segment'
+        'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
+        'info_dict': {
+            'id': '1_2444peh4',
+            'ext': 'mov',
+            'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
+            'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
+            'uploader_id': 'TeleZ?ri',
+            'upload_date': '20161218',
+            'timestamp': 1482084490,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # URL with 'segment' and fragment:
+        'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
+        'only_matching': True
+    }, {
+        # URL with 'episode' and fragment:
+        'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
+        'only_matching': True
+    }, {
+        # URL with 'show' and fragment:
+        'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        partner_id = self._search_regex(
+            r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
+            webpage, 'kaltura partner id')
+        entry_id = self._html_search_regex(
+            r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
+            % re.escape(video_id), webpage, 'kaltura entry id', group='id')
+
+        return self._kaltura_video(partner_id, entry_id)
+
+
+class AZMedienPlaylistIE(AZMedienBaseIE):
+    IE_DESC = 'AZ Medien playlists'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            telezueri\.ch|
+                            telebaern\.tv|
+                            telem1\.ch
+                        )/
+                        (?P<id>[0-9]+-
+                            (?:
+                                show|
+                                topic|
+                                themen
+                            )-[^/\#]+
+                            (?:
+                                /[0-9]+-episode-[^/\#]+
+                            )?
+                        )$
+                    '''
+
+    _TESTS = [{
+        # URL with 'episode'
+        'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
+        'info_dict': {
+            'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
+            'title': 'News - Donnerstag, 15. Dezember 2016',
+        },
+        'playlist_count': 9,
+    }, {
+        # URL with 'themen'
+        'url': 'http://www.telem1.ch/258-themen-tele-m1-classics',
+        'info_dict': {
+            'id': '258-themen-tele-m1-classics',
+            'title': 'Tele M1 Classics',
+        },
+        'playlist_mincount': 15,
+    }, {
+        # URL with 'topic', contains nested playlists
+        'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen',
+        'only_matching': True,
+    }, {
+        # URL with 'show' only
+        'url': 'http://www.telezueri.ch/86-show-talktaeglich',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+
+        entries = []
+
+        partner_id = self._search_regex(
+            r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
+            webpage, 'kaltura partner id', default=None)
+
+        if partner_id:
+            entries = [
+                self._kaltura_video(partner_id, m.group('id'))
+                for m in re.finditer(
+                    r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
+
+        if not entries:
+            entries = [
+                self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
+                for m in re.finditer(
+                    r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
+
+        if not entries:
+            entries = [
+                # May contain nested playlists (e.g. [1]) thus no explicit
+                # ie_key
+                # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen)
+                self.url_result(urljoin(url, m.group('url')))
+                for m in re.finditer(
+                    r'<a[^>]+name=[^>]+href=(["\'])(?P<url>/.+?)\1', webpage)]
+
+        title = self._search_regex(
+            r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
+            webpage, 'title',
+            default=strip_or_none(get_element_by_id(
+                'video-title', webpage)), group='title')
+
+        return self.playlist_result(entries, show_id, title)

youtube_dl/extractor/beampro.py

@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    compat_str,
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class BeamProLiveIE(InfoExtractor):
+    IE_NAME = 'Beam:live'
+    _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
+    _RATINGS = {'family': 0, 'teen': 13, '18+': 18}
+    _TEST = {
+        'url': 'http://www.beam.pro/niterhayven',
+        'info_dict': {
+            'id': '261562',
+            'ext': 'mp4',
+            'title': 'Introducing The Witcher 3 //  The Grind Starts Now!',
+            'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
+            'thumbnail': r're:https://.*\.jpg$',
+            'timestamp': 1483477281,
+            'upload_date': '20170103',
+            'uploader': 'niterhayven',
+            'uploader_id': '373396',
+            'age_limit': 18,
+            'is_live': True,
+            'view_count': int,
+        },
+        'skip': 'niterhayven is offline',
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        channel_name = self._match_id(url)
+
+        chan = self._download_json(
+            'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
+
+        if chan.get('online') is False:
+            raise ExtractorError(
+                '{0} is offline'.format(channel_name), expected=True)
+
+        channel_id = chan['id']
+
+        formats = self._extract_m3u8_formats(
+            'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
+            channel_name, ext='mp4', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+
+        user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
+
+        return {
+            'id': compat_str(chan.get('id') or channel_name),
+            'title': self._live_title(chan.get('name') or channel_name),
+            'description': clean_html(chan.get('description')),
+            'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
+            'timestamp': parse_iso8601(chan.get('updatedAt')),
+            'uploader': chan.get('token') or try_get(
+                chan, lambda x: x['user']['username'], compat_str),
+            'uploader_id': compat_str(user_id) if user_id else None,
+            'age_limit': self._RATINGS.get(chan.get('audience')),
+            'is_live': True,
+            'view_count': int_or_none(chan.get('viewersTotal')),
+            'formats': formats,
+        }

youtube_dl/extractor/bilibili.py

@@ -34,8 +34,8 @@ class BiliBiliIE(InfoExtractor):
         },
     }
 
-    _APP_KEY = '6f90a59ac58a4123'
-    _BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
+    _APP_KEY = '84956560bc028eb7'
+    _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/brightcove.py

@@ -179,7 +179,7 @@ class BrightcoveLegacyIE(InfoExtractor):
 
         params = {}
 
-        playerID = find_param('playerID')
+        playerID = find_param('playerID') or find_param('playerId')
         if playerID is None:
             raise ExtractorError('Cannot find player ID')
         params['playerID'] = playerID
@@ -204,7 +204,7 @@ class BrightcoveLegacyIE(InfoExtractor):
         #   // build Brightcove <object /> XML
         # }
         m = re.search(
-            r'''(?x)customBC.\createVideo\(
+            r'''(?x)customBC\.createVideo\(
                 .*?                                                  # skipping width and height
                 ["\'](?P<playerID>\d+)["\']\s*,\s*                   # playerID
                 ["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s*  # playerKey begins with AQ and is 50 characters

youtube_dl/extractor/canalplus.py

@@ -107,7 +107,7 @@ class CanalplusIE(InfoExtractor):
             [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
              r'id=["\']canal_video_player(?P<id>\d+)',
              r'data-video=["\'](?P<id>\d+)'],
-            webpage, 'video id', group='id')
+            webpage, 'video id', default=mobj.group('vid'), group='id')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')

youtube_dl/extractor/cbc.py

@@ -90,36 +90,49 @@ class CBCIE(InfoExtractor):
             },
         }],
         'skip': 'Geo-restricted to Canada',
+    }, {
+        # multiple CBC.APP.Caffeine.initInstance(...)
+        'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
+        'info_dict': {
+            'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
+            'id': 'dog-indoor-exercise-winter-1.3928238',
+        },
+        'playlist_mincount': 6,
     }]
 
     @classmethod
     def suitable(cls, url):
         return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
 
+    def _extract_player_init(self, player_init, display_id):
+        player_info = self._parse_json(player_init, display_id, js_to_json)
+        media_id = player_info.get('mediaId')
+        if not media_id:
+            clip_id = player_info['clipId']
+            feed = self._download_json(
+                'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
+                clip_id, fatal=False)
+            if feed:
+                media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
+            if not media_id:
+                media_id = self._download_json(
+                    'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
+                    clip_id)['entries'][0]['id'].split('/')[-1]
+        return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        player_init = self._search_regex(
-            r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
-            default=None)
-        if player_init:
-            player_info = self._parse_json(player_init, display_id, js_to_json)
-            media_id = player_info.get('mediaId')
-            if not media_id:
-                clip_id = player_info['clipId']
-                feed = self._download_json(
-                    'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
-                    clip_id, fatal=False)
-                if feed:
-                    media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
-                if not media_id:
-                    media_id = self._download_json(
-                        'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
-                        clip_id)['entries'][0]['id'].split('/')[-1]
-            return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
-        else:
-            entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
-            return self.playlist_result(entries)
+        entries = [
+            self._extract_player_init(player_init, display_id)
+            for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
+        entries.extend([
+            self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
+            for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
+        return self.playlist_result(
+            entries, display_id,
+            self._og_search_title(webpage, fatal=False),
+            self._og_search_description(webpage))
 
 
 class CBCPlayerIE(InfoExtractor):

youtube_dl/extractor/chaturbate.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import ExtractorError
 
@@ -31,30 +33,35 @@ class ChaturbateIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        m3u8_url = self._search_regex(
-            r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
-            'playlist', default=None, group='url')
+        m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer(
+            r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)]
 
-        if not m3u8_url:
+        if not m3u8_formats:
             error = self._search_regex(
                 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
                  r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
                 webpage, 'error', group='error', default=None)
             if not error:
-                if any(p not in webpage for p in (
+                if any(p in webpage for p in (
                         self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
                     error = self._ROOM_OFFLINE
             if error:
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('Unable to find stream URL')
 
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        formats = []
+        for m3u8_id, m3u8_url in m3u8_formats:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, ext='mp4',
+                # ffmpeg skips segments for fast m3u8
+                preference=-10 if m3u8_id == 'fast' else None,
+                m3u8_id=m3u8_id, fatal=False, live=True))
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': self._live_title(video_id),
-            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
+            'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
             'age_limit': self._rta_search(webpage),
             'is_live': True,
             'formats': formats,

youtube_dl/extractor/chirbit.py

@@ -19,6 +19,7 @@ class ChirbitIE(InfoExtractor):
             'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
             'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
             'duration': 306,
+            'uploader': 'Gerryaudio',
         },
         'params': {
             'skip_download': True,
@@ -54,6 +55,9 @@ class ChirbitIE(InfoExtractor):
         duration = parse_duration(self._search_regex(
             r'class=["\']c-length["\'][^>]*>([^<]+)',
             webpage, 'duration', fatal=False))
+        uploader = self._search_regex(
+            r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
+            webpage, 'uploader', fatal=False)
 
         return {
             'id': audio_id,
@@ -61,6 +65,7 @@ class ChirbitIE(InfoExtractor):
             'title': title,
             'description': description,
             'duration': duration,
+            'uploader': uploader,
         }
 
 

youtube_dl/extractor/cmt.py

@@ -1,13 +1,11 @@
 from __future__ import unicode_literals
 
 from .mtv import MTVIE
-from ..utils import ExtractorError
 
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
-    _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
+    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows|(?:full-)?episodes|video-clips)/(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
@@ -33,17 +31,24 @@ class CMTIE(MTVIE):
     }, {
         'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
         'only_matching': True,
+    }, {
+        'url': 'http://www.cmt.com/full-episodes/537qb3/nashville-the-wayfaring-stranger-season-5-ep-501',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.cmt.com/video-clips/t9e4ci/nashville-juliette-in-2-minutes',
+        'only_matching': True,
     }]
 
-    @classmethod
-    def _transform_rtmp_url(cls, rtmp_video_url):
-        if 'error_not_available.swf' in rtmp_video_url:
-            raise ExtractorError(
-                '%s said: video is not available' % cls.IE_NAME, expected=True)
-
-        return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)
-
     def _extract_mgid(self, webpage):
-        return self._search_regex(
+        mgid = self._search_regex(
             r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P<mgid>.+?)\1',
-            webpage, 'mgid', group='mgid')
+            webpage, 'mgid', group='mgid', default=None)
+        if not mgid:
+            mgid = self._extract_triforce_mgid(webpage)
+        return mgid
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        mgid = self._extract_mgid(webpage)
+        return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)

youtube_dl/extractor/comedycentral.py

@@ -48,17 +48,8 @@ class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
         webpage = self._download_webpage(url, playlist_id)
-
-        feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
-        feed = self._parse_json(feed_json, playlist_id)
-        zones = feed['manifest']['zones']
-
-        video_zone = zones['t2_lc_promo1']
-        feed = self._download_json(video_zone['feed'], playlist_id)
-        mgid = feed['result']['data']['id']
-
-        videos_info = self._get_videos_info(mgid, use_hls=True)
-
+        mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
+        videos_info = self._get_videos_info(mgid)
         return videos_info
 
 
@@ -94,12 +85,6 @@ class ToshIE(MTVServicesInfoExtractor):
         'only_matching': True,
     }]
 
-    @classmethod
-    def _transform_rtmp_url(cls, rtmp_video_url):
-        new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
-        new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
-        return new_urls
-
 
 class ComedyCentralTVIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'

youtube_dl/extractor/common.py

@@ -121,9 +121,19 @@ class InfoExtractor(object):
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
                                  "m3u8", "m3u8_native" or "http_dash_segments".
-                    * fragments  A list of fragments of the fragmented media,
-                                 with the following entries:
-                                 * "url" (mandatory) - fragment's URL
+                    * fragment_base_url
+                                 Base URL for fragments. Each fragment's path
+                                 value (if present) will be relative to
+                                 this URL.
+                    * fragments  A list of fragments of a fragmented media.
+                                 Each fragment entry must contain either an url
+                                 or a path. If an url is present it should be
+                                 considered by a client. Otherwise both path and
+                                 fragment_base_url must be present. Here is
+                                 the list of all potential fields:
+                                 * "url" - fragment's URL
+                                 * "path" - fragment's path relative to
+                                            fragment_base_url
                                  * "duration" (optional, int or float)
                                  * "filesize" (optional, int)
                     * preference Order number of this format. If this field is
@@ -1627,12 +1637,12 @@ class InfoExtractor(object):
                 segment_template = element.find(_add_ns('SegmentTemplate'))
                 if segment_template is not None:
                     extract_common(segment_template)
-                    media_template = segment_template.get('media')
-                    if media_template:
-                        ms_info['media_template'] = media_template
+                    media = segment_template.get('media')
+                    if media:
+                        ms_info['media'] = media
                     initialization = segment_template.get('initialization')
                     if initialization:
-                        ms_info['initialization_url'] = initialization
+                        ms_info['initialization'] = initialization
                     else:
                         extract_Initialization(segment_template)
             return ms_info
@@ -1676,6 +1686,7 @@ class InfoExtractor(object):
                         lang = representation_attrib.get('lang')
                         url_el = representation.find(_add_ns('BaseURL'))
                         filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None)
+                        bandwidth = int_or_none(representation_attrib.get('bandwidth'))
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
@@ -1683,7 +1694,7 @@ class InfoExtractor(object):
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
-                            'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),
+                            'tbr': int_or_none(bandwidth, 1000),
                             'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
                             'fps': int_or_none(representation_attrib.get('frameRate')),
                             'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
@@ -1692,13 +1703,32 @@ class InfoExtractor(object):
                         }
                         f.update(parse_codecs(representation_attrib.get('codecs')))
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
-                        if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
 
-                            media_template = representation_ms_info['media_template']
-                            media_template = media_template.replace('$RepresentationID$', representation_id)
-                            media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
-                            media_template = re.sub(r'\$(Number|Bandwidth|Time)%([^$]+)\$', r'%(\1)\2', media_template)
-                            media_template.replace('$$', '$')
+                        def prepare_template(template_name, identifiers):
+                            t = representation_ms_info[template_name]
+                            t = t.replace('$RepresentationID$', representation_id)
+                            t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t)
+                            t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t)
+                            t.replace('$$', '$')
+                            return t
+
+                        # @initialization is a regular template like @media one
+                        # so it should be handled just the same way (see
+                        # https://github.com/rg3/youtube-dl/issues/11605)
+                        if 'initialization' in representation_ms_info:
+                            initialization_template = prepare_template(
+                                'initialization',
+                                # As per [1, 5.3.9.4.2, Table 15, page 54] $Number$ and
+                                # $Time$ shall not be included for @initialization thus
+                                # only $Bandwidth$ remains
+                                ('Bandwidth', ))
+                            representation_ms_info['initialization_url'] = initialization_template % {
+                                'Bandwidth': bandwidth,
+                            }
+
+                        if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
+
+                            media_template = prepare_template('media', ('Number', 'Bandwidth', 'Time'))
 
                             # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
                             # can't be used at the same time
@@ -1710,7 +1740,7 @@ class InfoExtractor(object):
                                 representation_ms_info['fragments'] = [{
                                     'url': media_template % {
                                         'Number': segment_number,
-                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
+                                        'Bandwidth': bandwidth,
                                     },
                                     'duration': segment_duration,
                                 } for segment_number in range(
@@ -1728,7 +1758,7 @@ class InfoExtractor(object):
                                 def add_segment_url():
                                     segment_url = media_template % {
                                         'Time': segment_time,
-                                        'Bandwidth': int_or_none(representation_attrib.get('bandwidth')),
+                                        'Bandwidth': bandwidth,
                                         'Number': segment_number,
                                     }
                                     representation_ms_info['fragments'].append({
@@ -1751,14 +1781,16 @@ class InfoExtractor(object):
                             # Example: https://www.youtube.com/watch?v=iXZV5uAYMJI
                             # or any YouTube dashsegments video
                             fragments = []
-                            s_num = 0
-                            for segment_url in representation_ms_info['segment_urls']:
-                                s = representation_ms_info['s'][s_num]
+                            segment_index = 0
+                            timescale = representation_ms_info['timescale']
+                            for s in representation_ms_info['s']:
+                                duration = float_or_none(s['d'], timescale)
                                 for r in range(s.get('r', 0) + 1):
                                     fragments.append({
-                                        'url': segment_url,
-                                        'duration': float_or_none(s['d'], representation_ms_info['timescale']),
+                                        'url': representation_ms_info['segment_urls'][segment_index],
+                                        'duration': duration,
                                     })
+                                    segment_index += 1
                             representation_ms_info['fragments'] = fragments
                         # NB: MPD manifest may contain direct URLs to unfragmented media.
                         # No fragments key is present in this case.
@@ -1768,7 +1800,7 @@ class InfoExtractor(object):
                                 'protocol': 'http_dash_segments',
                             })
                             if 'initialization_url' in representation_ms_info:
-                                initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
+                                initialization_url = representation_ms_info['initialization_url']
                                 if not f.get('url'):
                                     f['url'] = initialization_url
                                 f['fragments'].append({'url': initialization_url})
@@ -1967,10 +1999,13 @@ class InfoExtractor(object):
                 entries.append(media_info)
         return entries
 
-    def _extract_akamai_formats(self, manifest_url, video_id):
+    def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
         formats = []
         hdcore_sign = 'hdcore=3.7.0'
-        f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        f4m_url = re.sub(r'(https?://[^/+])/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        hds_host = hosts.get('hds')
+        if hds_host:
+            f4m_url = re.sub(r'(https?://)[^/]+', r'\1' + hds_host, f4m_url)
         if 'hdcore=' not in f4m_url:
             f4m_url += ('&' if '?' in f4m_url else '?') + hdcore_sign
         f4m_formats = self._extract_f4m_formats(
@@ -1978,7 +2013,10 @@ class InfoExtractor(object):
         for entry in f4m_formats:
             entry.update({'extra_param_to_segment_url': hdcore_sign})
         formats.extend(f4m_formats)
-        m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
+        m3u8_url = re.sub(r'(https?://[^/]+)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
+        hls_host = hosts.get('hls')
+        if hls_host:
+            m3u8_url = re.sub(r'(https?://)[^/]+', r'\1' + hls_host, m3u8_url)
         formats.extend(self._extract_m3u8_formats(
             m3u8_url, video_id, 'mp4', 'm3u8_native',
             m3u8_id='hls', fatal=False))

youtube_dl/extractor/crackle.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class CrackleIE(InfoExtractor):
-    _VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
+    _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
         'info_dict': {
@@ -31,8 +31,32 @@ class CrackleIE(InfoExtractor):
         }
     }
 
+    _THUMBNAIL_RES = [
+        (120, 90),
+        (208, 156),
+        (220, 124),
+        (220, 220),
+        (240, 180),
+        (250, 141),
+        (315, 236),
+        (320, 180),
+        (360, 203),
+        (400, 300),
+        (421, 316),
+        (460, 330),
+        (460, 460),
+        (462, 260),
+        (480, 270),
+        (587, 330),
+        (640, 480),
+        (700, 330),
+        (700, 394),
+        (854, 480),
+        (1024, 1024),
+        (1920, 1080),
+    ]
+
     # extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
-    _THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
     _MEDIA_FILE_SLOTS = {
         'c544.flv': {
             'width': 544,
@@ -61,17 +85,25 @@ class CrackleIE(InfoExtractor):
 
         item = self._download_xml(
             'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
-            video_id).find('i')
+            video_id, headers=self.geo_verification_headers()).find('i')
         title = item.attrib['t']
 
         subtitles = {}
         formats = self._extract_m3u8_formats(
             'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
             video_id, 'mp4', m3u8_id='hls', fatal=None)
-        thumbnail = None
+        thumbnails = []
         path = item.attrib.get('p')
         if path:
-            thumbnail = self._THUMBNAIL_TEMPLATE % path
+            for width, height in self._THUMBNAIL_RES:
+                res = '%dx%d' % (width, height)
+                thumbnails.append({
+                    'id': res,
+                    'url': 'http://images-us-am.crackle.com/%stnl_%s.jpg' % (path, res),
+                    'width': width,
+                    'height': height,
+                    'resolution': res,
+                })
             http_base_url = 'http://ahttp.crackle.com/' + path
             for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
                 formats.append({
@@ -86,10 +118,11 @@ class CrackleIE(InfoExtractor):
                 if locale and v:
                     if locale not in subtitles:
                         subtitles[locale] = []
-                    subtitles[locale] = [{
-                        'url': '%s/%s%s_%s.xml' % (config_doc.attrib['strSubtitleServer'], path, locale, v),
-                        'ext': 'ttml',
-                    }]
+                    for url_ext, ext in (('vtt', 'vtt'), ('xml', 'tt')):
+                        subtitles.setdefault(locale, []).append({
+                            'url': '%s/%s%s_%s.%s' % (config_doc.attrib['strSubtitleServer'], path, locale, v, url_ext),
+                            'ext': ext,
+                        })
         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
 
         return {
@@ -100,7 +133,7 @@ class CrackleIE(InfoExtractor):
             'series': item.attrib.get('sn'),
             'season_number': int_or_none(item.attrib.get('se')),
             'episode_number': int_or_none(item.attrib.get('ep')),
-            'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/crunchyroll.py

@@ -166,6 +166,25 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
+        'info_dict': {
+            'id': '727589',
+            'ext': 'mp4',
+            'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
+            'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Kadokawa Pictures Inc.',
+            'upload_date': '20170118',
+            'series': "KONOSUBA -God's blessing on this wonderful world!",
+            'season_number': 2,
+            'episode': 'Give Me Deliverance from this Judicial Injustice!',
+            'episode_number': 1,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -236,8 +255,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
         output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
         output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
-        output += """ScaledBorderAndShadow: no
-
+        output += """
 [V4+ Styles]
 Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
 """
@@ -439,6 +457,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         subtitles = self.extract_subtitles(video_id, webpage)
 
+        # webpage provide more accurate data than series_title from XML
+        series = self._html_search_regex(
+            r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
+            webpage, 'series', default=xpath_text(metadata, 'series_title'))
+
+        episode = xpath_text(metadata, 'episode_title')
+        episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
+
+        season_number = int_or_none(self._search_regex(
+            r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
+            webpage, 'season number', default=None))
+
         return {
             'id': video_id,
             'title': video_title,
@@ -446,9 +476,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'thumbnail': xpath_text(metadata, 'episode_image_url'),
             'uploader': video_uploader,
             'upload_date': video_upload_date,
-            'series': xpath_text(metadata, 'series_title'),
-            'episode': xpath_text(metadata, 'episode_title'),
-            'episode_number': int_or_none(xpath_text(metadata, 'episode_number')),
+            'series': series,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/cspan.py

@@ -12,6 +12,7 @@ from ..utils import (
     ExtractorError,
 )
 from .senateisvp import SenateISVPIE
+from .ustream import UstreamIE
 
 
 class CSpanIE(InfoExtractor):
@@ -22,14 +23,13 @@ class CSpanIE(InfoExtractor):
         'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',
-            'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
         },
+        'playlist_mincount': 2,
         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
-        'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
+        # md5 is unstable
         'info_dict': {
             'id': 'c4486943',
             'ext': 'mp4',
@@ -38,14 +38,11 @@ class CSpanIE(InfoExtractor):
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
-        'md5': '2ae5051559169baadba13fc35345ae74',
         'info_dict': {
             'id': '342759',
-            'ext': 'mp4',
             'title': 'General Motors Ignition Switch Recall',
-            'duration': 14848,
-            'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
         },
+        'playlist_mincount': 6,
     }, {
         # Video from senate.gov
         'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
@@ -57,12 +54,30 @@ class CSpanIE(InfoExtractor):
         'params': {
             'skip_download': True,  # m3u8 downloads
         }
+    }, {
+        # Ustream embedded video
+        'url': 'https://www.c-span.org/video/?114917-1/armed-services',
+        'info_dict': {
+            'id': '58428542',
+            'ext': 'flv',
+            'title': 'USHR07 Armed Services Committee',
+            'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
+            'timestamp': 1423060374,
+            'upload_date': '20150204',
+            'uploader': 'HouseCommittee',
+            'uploader_id': '12987475',
+        },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_type = None
         webpage = self._download_webpage(url, video_id)
+
+        ustream_url = UstreamIE._extract_url(webpage)
+        if ustream_url:
+            return self.url_result(ustream_url, UstreamIE.ie_key())
+
         # We first look for clipid, because clipprog always appears before
         patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
         results = list(filter(None, (re.search(p, webpage) for p in patterns)))

youtube_dl/extractor/disney.py

@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    compat_str,
+    determine_ext,
+)
+
+
+class DisneyIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
+    _TESTS = [{
+        'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
+        'info_dict': {
+            'id': '545ed1857afee5a0ec239977',
+            'ext': 'mp4',
+            'title': 'Moana - Trailer',
+            'description': 'A fun adventure for the entire Family!  Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
+            'upload_date': '20170112',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(
+            'http://%s/embed/%s' % (domain, video_id), video_id)
+        video_data = self._parse_json(self._search_regex(
+            r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
+
+        for external in video_data.get('externals', []):
+            if external.get('source') == 'vevo':
+                return self.url_result('vevo:' + external['data_id'], 'Vevo')
+
+        title = video_data['title']
+
+        formats = []
+        for flavor in video_data.get('flavors', []):
+            flavor_format = flavor.get('format')
+            flavor_url = flavor.get('url')
+            if not flavor_url or not re.match(r'https?://', flavor_url):
+                continue
+            tbr = int_or_none(flavor.get('bitrate'))
+            if tbr == 99999:
+                formats.extend(self._extract_m3u8_formats(
+                    flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
+                continue
+            format_id = []
+            if flavor_format:
+                format_id.append(flavor_format)
+            if tbr:
+                format_id.append(compat_str(tbr))
+            ext = determine_ext(flavor_url)
+            if flavor_format == 'applehttp' or ext == 'm3u8':
+                ext = 'mp4'
+            width = int_or_none(flavor.get('width'))
+            height = int_or_none(flavor.get('height'))
+            formats.append({
+                'format_id': '-'.join(format_id),
+                'url': flavor_url,
+                'width': width,
+                'height': height,
+                'tbr': tbr,
+                'ext': ext,
+                'vcodec': 'none' if (width == 0 and height == 0) else None,
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for caption in video_data.get('captions', []):
+            caption_url = caption.get('url')
+            caption_format = caption.get('format')
+            if not caption_url or caption_format.startswith('unknown'):
+                continue
+            subtitles.setdefault(caption.get('language', 'en'), []).append({
+                'url': caption_url,
+                'ext': {
+                    'webvtt': 'vtt',
+                }.get(caption_format, caption_format),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description') or video_data.get('short_desc'),
+            'thumbnail': video_data.get('thumb') or video_data.get('thumb_secure'),
+            'duration': int_or_none(video_data.get('duration_sec')),
+            'upload_date': unified_strdate(video_data.get('publish_date')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/dramafever.py

@@ -66,7 +66,7 @@ class DramaFeverBaseIE(AMPIE):
 
 class DramaFeverIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever'
-    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
     _TESTS = [{
         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
         'info_dict': {
@@ -103,6 +103,9 @@ class DramaFeverIE(DramaFeverBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -148,7 +151,7 @@ class DramaFeverIE(DramaFeverBaseIE):
 
 class DramaFeverSeriesIE(DramaFeverBaseIE):
     IE_NAME = 'dramafever:series'
-    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
+    _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
     _TESTS = [{
         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
         'info_dict': {

youtube_dl/extractor/egghead.py

@@ -0,0 +1,39 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class EggheadCourseIE(InfoExtractor):
+    IE_DESC = 'egghead.io course'
+    IE_NAME = 'egghead:course'
+    _VALID_URL = r'https://egghead\.io/courses/(?P<id>[a-zA-Z_0-9-]+)'
+    _TEST = {
+        'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
+        'playlist_count': 29,
+        'info_dict': {
+            'id': 'professor-frisby-introduces-composable-functional-javascript',
+            'title': 'Professor Frisby Introduces Composable Functional JavaScript',
+            'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
+        },
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
+        ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
+
+        found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
+        entries = [self.url_result(m) for m in found]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'entries': entries,
+        }

youtube_dl/extractor/extractors.py

@@ -30,7 +30,10 @@ from .aenetworks import (
     AENetworksIE,
     HistoryTopicIE,
 )
-from .afreecatv import AfreecaTVIE
+from .afreecatv import (
+    AfreecaTVIE,
+    AfreecaTVGlobalIE,
+)
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
@@ -77,6 +80,10 @@ from .awaan import (
     AWAANLiveIE,
     AWAANSeasonIE,
 )
+from .azmedien import (
+    AZMedienIE,
+    AZMedienPlaylistIE,
+)
 from .azubu import AzubuIE, AzubuLiveIE
 from .baidu import BaiduVideoIE
 from .bambuser import BambuserIE, BambuserChannelIE
@@ -88,6 +95,7 @@ from .bbc import (
     BBCCoUkPlaylistIE,
     BBCIE,
 )
+from .beampro import BeamProLiveIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .bellmedia import BellMediaIE
@@ -243,6 +251,7 @@ from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .discoverygo import DiscoveryGoIE
+from .disney import DisneyIE
 from .dispeak import DigitallySpeakingIE
 from .dropbox import DropboxIE
 from .dw import (
@@ -252,6 +261,7 @@ from .dw import (
 from .eagleplatform import EaglePlatformIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
+from .egghead import EggheadCourseIE
 from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .einthusan import EinthusanIE
@@ -394,6 +404,7 @@ from .imgur import (
     ImgurAlbumIE,
 )
 from .ina import InaIE
+from .inc import IncIE
 from .indavideo import (
     IndavideoIE,
     IndavideoEmbedIE,
@@ -404,6 +415,7 @@ from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .iqiyi import IqiyiIE
 from .ir90tv import Ir90TvIE
+from .itv import ITVIE
 from .ivi import (
     IviIE,
     IviCompilationIE
@@ -542,6 +554,7 @@ from .mtv import (
     MTVVideoIE,
     MTVServicesEmbeddedIE,
     MTVDEIE,
+    MTV81IE,
 )
 from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
@@ -591,6 +604,7 @@ from .nextmedia import (
     NextMediaIE,
     NextMediaActionNewsIE,
     AppleDailyIE,
+    NextTVIE,
 )
 from .nfb import NFBIE
 from .nfl import NFLIE
@@ -654,6 +668,7 @@ from .nrk import (
     NRKTVIE,
     NRKTVDirekteIE,
     NRKTVEpisodesIE,
+    NRKTVSeriesIE,
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
@@ -717,6 +732,7 @@ from .polskieradio import (
 )
 from .porn91 import Porn91IE
 from .porncom import PornComIE
+from .pornflip import PornFlipIE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
@@ -972,6 +988,7 @@ from .tv2 import (
 )
 from .tv3 import TV3IE
 from .tv4 import TV4IE
+from .tva import TVAIE
 from .tvanouvelles import (
     TVANouvellesIE,
     TVANouvellesArticleIE,
@@ -1115,7 +1132,10 @@ from .vk import (
     VKUserVideosIE,
     VKWallPostIE,
 )
-from .vlive import VLiveIE
+from .vlive import (
+    VLiveIE,
+    VLiveChannelIE
+)
 from .vodlocker import VodlockerIE
 from .vodplatform import VODPlatformIE
 from .voicerepublic import VoiceRepublicIE

youtube_dl/extractor/facebook.py

@@ -12,14 +12,16 @@ from ..compat import (
     compat_urllib_parse_unquote_plus,
 )
 from ..utils import (
+    clean_html,
     error_to_compat_str,
     ExtractorError,
+    get_element_by_id,
     int_or_none,
+    js_to_json,
     limit_length,
     sanitized_Request,
+    try_get,
     urlencode_postdata,
-    get_element_by_id,
-    clean_html,
 )
 
 
@@ -243,14 +245,30 @@ class FacebookIE(InfoExtractor):
 
         video_data = None
 
+        def extract_video_data(instances):
+            for item in instances:
+                if item[1][0] == 'VideoConfig':
+                    video_item = item[2][0]
+                    if video_item.get('video_id') == video_id:
+                        return video_item['videoData']
+
         server_js_data = self._parse_json(self._search_regex(
-            r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
-        for item in server_js_data.get('instances', []):
-            if item[1][0] == 'VideoConfig':
-                video_item = item[2][0]
-                if video_item.get('video_id') == video_id:
-                    video_data = video_item['videoData']
-                    break
+            r'handleServerJS\(({.+})(?:\);|,")', webpage,
+            'server js data', default='{}'), video_id, fatal=False)
+
+        if server_js_data:
+            video_data = extract_video_data(server_js_data.get('instances', []))
+
+        if not video_data:
+            server_js_data = self._parse_json(
+                self._search_regex(
+                    r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet',
+                    webpage, 'js data', default='{}'),
+                video_id, transform_source=js_to_json, fatal=False)
+            if server_js_data:
+                video_data = extract_video_data(try_get(
+                    server_js_data, lambda x: x['jsmods']['instances'],
+                    list) or [])
 
         if not video_data:
             if not fatal_if_no_video:

youtube_dl/extractor/firsttv.py

@@ -86,18 +86,43 @@ class FirstTVIE(InfoExtractor):
             title = item['title']
             quality = qualities(QUALITIES)
             formats = []
+            path = None
             for f in item.get('mbr', []):
                 src = f.get('src')
                 if not src or not isinstance(src, compat_str):
                     continue
                 tbr = int_or_none(self._search_regex(
                     r'_(\d{3,})\.mp4', src, 'tbr', default=None))
+                if not path:
+                    path = self._search_regex(
+                        r'//[^/]+/(.+?)_\d+\.mp4', src,
+                        'm3u8 path', default=None)
                 formats.append({
                     'url': src,
                     'format_id': f.get('name'),
                     'tbr': tbr,
-                    'quality': quality(f.get('name')),
+                    'source_preference': quality(f.get('name')),
                 })
+            # m3u8 URL format is reverse engineered from [1] (search for
+            # master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
+            # is taken from [2].
+            # 1. http://static.1tv.ru/player/eump1tv-current/eump-1tv.all.min.js?rnd=9097422834:formatted
+            # 2. http://static.1tv.ru/player/eump1tv-config/config-main.js?rnd=9097422834
+            if not path and len(formats) == 1:
+                path = self._search_regex(
+                    r'//[^/]+/(.+?$)', formats[0]['url'],
+                    'm3u8 path', default=None)
+            if path:
+                if len(formats) == 1:
+                    m3u8_path = ','
+                else:
+                    tbrs = [compat_str(t) for t in sorted(f['tbr'] for f in formats)]
+                    m3u8_path = '_,%s,%s' % (','.join(tbrs), '.mp4')
+                formats.extend(self._extract_m3u8_formats(
+                    'http://balancer-vod.1tv.ru/%s%s.urlset/master.m3u8'
+                    % (path, m3u8_path),
+                    display_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
             self._sort_formats(formats)
 
             thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)

youtube_dl/extractor/flipagram.py

@@ -81,7 +81,7 @@ class FlipagramIE(InfoExtractor):
             'filesize': int_or_none(cover.get('size')),
         } for cover in flipagram.get('covers', []) if cover.get('url')]
 
-        # Note that this only retrieves comments that are initally loaded.
+        # Note that this only retrieves comments that are initially loaded.
         # For videos with large amounts of comments, most won't be retrieved.
         comments = []
         for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):

youtube_dl/extractor/freesound.py

@@ -3,10 +3,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    get_element_by_class,
+    get_element_by_id,
+    unified_strdate,
+)
 
 
 class FreesoundIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/[^/]+/sounds/(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
         'md5': '12280ceb42c81f19a515c745eae07650',
@@ -14,26 +20,60 @@ class FreesoundIE(InfoExtractor):
             'id': '194503',
             'ext': 'mp3',
             'title': 'gulls in the city.wav',
-            'uploader': 'miklovan',
             'description': 'the sounds of seagulls in the city',
+            'duration': 130.233,
+            'uploader': 'miklovan',
+            'upload_date': '20130715',
+            'tags': list,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        music_id = mobj.group('id')
-        webpage = self._download_webpage(url, music_id)
-        title = self._html_search_regex(
-            r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
-            webpage, 'music title', flags=re.DOTALL)
+        audio_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, audio_id)
+
+        audio_url = self._og_search_property('audio', webpage, 'song url')
+        title = self._og_search_property('audio:title', webpage, 'song title')
+
         description = self._html_search_regex(
-            r'<div id="sound_description">(.*?)</div>', webpage, 'description',
-            fatal=False, flags=re.DOTALL)
+            r'(?s)id=["\']sound_description["\'][^>]*>(.+?)</div>',
+            webpage, 'description', fatal=False)
+
+        duration = float_or_none(
+            get_element_by_class('duration', webpage), scale=1000)
+
+        upload_date = unified_strdate(get_element_by_id('sound_date', webpage))
+        uploader = self._og_search_property(
+            'audio:artist', webpage, 'uploader', fatal=False)
+
+        channels = self._html_search_regex(
+            r'Channels</dt><dd>(.+?)</dd>', webpage,
+            'channels info', fatal=False)
+
+        tags_str = get_element_by_class('tags', webpage)
+        tags = re.findall(r'<a[^>]+>([^<]+)', tags_str) if tags_str else None
+
+        audio_urls = [audio_url]
+
+        LQ_FORMAT = '-lq.mp3'
+        if LQ_FORMAT in audio_url:
+            audio_urls.append(audio_url.replace(LQ_FORMAT, '-hq.mp3'))
+
+        formats = [{
+            'url': format_url,
+            'format_note': channels,
+            'quality': quality,
+        } for quality, format_url in enumerate(audio_urls)]
+        self._sort_formats(formats)
 
         return {
-            'id': music_id,
+            'id': audio_id,
             'title': title,
-            'url': self._og_search_property('audio', webpage, 'music url'),
-            'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
             'description': description,
+            'duration': duration,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'tags': tags,
+            'formats': formats,
         }

youtube_dl/extractor/generic.py

@@ -78,6 +78,9 @@ from .vbox7 import Vbox7IE
 from .dbtv import DBTVIE
 from .piksel import PikselIE
 from .videa import VideaIE
+from .twentymin import TwentyMinutenIE
+from .ustream import UstreamIE
+from .openload import OpenloadIE
 
 
 class GenericIE(InfoExtractor):
@@ -422,6 +425,26 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,  # m3u8 download
             },
         },
+        {
+            # Brightcove with alternative playerID key
+            'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
+            'info_dict': {
+                'id': 'nmeth.2062_SV1',
+                'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '2228375078001',
+                    'ext': 'mp4',
+                    'title': 'nmeth.2062-sv1',
+                    'description': 'nmeth.2062-sv1',
+                    'timestamp': 1363357591,
+                    'upload_date': '20130315',
+                    'uploader': 'Nature Publishing Group',
+                    'uploader_id': '1964492299001',
+                },
+            }],
+        },
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
@@ -567,17 +590,6 @@ class GenericIE(InfoExtractor):
                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
             }
         },
-        # Embedded Ustream video
-        {
-            'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
-            'md5': '27b99cdb639c9b12a79bca876a073417',
-            'info_dict': {
-                'id': '45734260',
-                'ext': 'flv',
-                'uploader': 'AU SPA:  The NSA and Privacy',
-                'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
-            }
-        },
         # nowvideo embed hidden behind percent encoding
         {
             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
@@ -1448,6 +1460,20 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 2,
         },
+        {
+            # 20 minuten embed
+            'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
+            'info_dict': {
+                'id': '523629',
+                'ext': 'mp4',
+                'title': 'So kommen Sie bei Eis und Schnee sicher an',
+                'description': 'md5:117c212f64b25e3d95747e5276863f7d',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': [TwentyMinutenIE.ie_key()],
+        }
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -1939,7 +1965,14 @@ class GenericIE(InfoExtractor):
                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
-            return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
+            embed_token = self._search_regex(
+                r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
+                webpage, 'ooyala embed token', default=None)
+            return OoyalaIE._build_url_result(smuggle_url(
+                mobj.group('ec'), {
+                    'domain': url,
+                    'embed_token': embed_token,
+                }))
 
         # Look for multiple Ooyala embeds on SBN network websites
         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
@@ -2070,10 +2103,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'TED')
 
         # Look for embedded Ustream videos
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
-        if mobj is not None:
-            return self.url_result(mobj.group('url'), 'Ustream')
+        ustream_url = UstreamIE._extract_url(webpage)
+        if ustream_url:
+            return self.url_result(ustream_url, UstreamIE.ie_key())
 
         # Look for embedded arte.tv player
         mobj = re.search(
@@ -2394,6 +2426,18 @@ class GenericIE(InfoExtractor):
         if videa_urls:
             return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
 
+        # Look for 20 minuten embeds
+        twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
+        if twentymin_urls:
+            return _playlist_from_matches(
+                twentymin_urls, ie=TwentyMinutenIE.ie_key())
+
+        # Look for Openload embeds
+        openload_urls = OpenloadIE._extract_urls(webpage)
+        if openload_urls:
+            return _playlist_from_matches(
+                openload_urls, ie=OpenloadIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')

youtube_dl/extractor/imdb.py

@@ -13,7 +13,7 @@ from ..utils import (
 class ImdbIE(InfoExtractor):
     IE_NAME = 'imdb'
     IE_DESC = 'Internet Movie Database trailers'
-    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-)vi(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-|videoplayer/)vi(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
@@ -32,6 +32,9 @@ class ImdbIE(InfoExtractor):
     }, {
         'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
         'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/videoplayer/vi1562949145',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/inc.py

@@ -0,0 +1,41 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .kaltura import KalturaIE
+
+
+class IncIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?inc\.com/(?:[^/]+/)+(?P<id>[^.]+).html'
+    _TESTS = [{
+        'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html',
+        'md5': '7416739c9c16438c09fa35619d6ba5cb',
+        'info_dict': {
+            'id': '1_wqig47aq',
+            'ext': 'mov',
+            'title': 'Bill Gates Says These 5 Books Will Make You Smarter',
+            'description': 'md5:bea7ff6cce100886fc1995acb743237e',
+            'timestamp': 1474414430,
+            'upload_date': '20160920',
+            'uploader_id': 'video@inc.com',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        partner_id = self._search_regex(
+            r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage, 'partner id')
+
+        kaltura_id = self._parse_json(self._search_regex(
+            r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
+            display_id)['vid_kaltura_id']
+
+        return self.url_result(
+            'kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())

youtube_dl/extractor/itv.py

@@ -0,0 +1,196 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import uuid
+import xml.etree.ElementTree as etree
+import json
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_etree_register_namespace,
+)
+from ..utils import (
+    extract_attributes,
+    xpath_with_ns,
+    xpath_element,
+    xpath_text,
+    int_or_none,
+    parse_duration,
+    ExtractorError,
+    determine_ext,
+)
+
+
+class ITVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
+    _TEST = {
+        'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
+        'info_dict': {
+            'id': '2a2936a0053',
+            'ext': 'flv',
+            'title': 'Home Movie',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        params = extract_attributes(self._search_regex(
+            r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
+
+        ns_map = {
+            'soapenv': 'http://schemas.xmlsoap.org/soap/envelope/',
+            'tem': 'http://tempuri.org/',
+            'itv': 'http://schemas.datacontract.org/2004/07/Itv.BB.Mercury.Common.Types',
+            'com': 'http://schemas.itv.com/2009/05/Common',
+        }
+        for ns, full_ns in ns_map.items():
+            compat_etree_register_namespace(ns, full_ns)
+
+        def _add_ns(name):
+            return xpath_with_ns(name, ns_map)
+
+        def _add_sub_element(element, name):
+            return etree.SubElement(element, _add_ns(name))
+
+        req_env = etree.Element(_add_ns('soapenv:Envelope'))
+        _add_sub_element(req_env, 'soapenv:Header')
+        body = _add_sub_element(req_env, 'soapenv:Body')
+        get_playlist = _add_sub_element(body, ('tem:GetPlaylist'))
+        request = _add_sub_element(get_playlist, 'tem:request')
+        _add_sub_element(request, 'itv:ProductionId').text = params['data-video-id']
+        _add_sub_element(request, 'itv:RequestGuid').text = compat_str(uuid.uuid4()).upper()
+        vodcrid = _add_sub_element(request, 'itv:Vodcrid')
+        _add_sub_element(vodcrid, 'com:Id')
+        _add_sub_element(request, 'itv:Partition')
+        user_info = _add_sub_element(get_playlist, 'tem:userInfo')
+        _add_sub_element(user_info, 'itv:Broadcaster').text = 'Itv'
+        _add_sub_element(user_info, 'itv:DM')
+        _add_sub_element(user_info, 'itv:RevenueScienceValue')
+        _add_sub_element(user_info, 'itv:SessionId')
+        _add_sub_element(user_info, 'itv:SsoToken')
+        _add_sub_element(user_info, 'itv:UserToken')
+        site_info = _add_sub_element(get_playlist, 'tem:siteInfo')
+        _add_sub_element(site_info, 'itv:AdvertisingRestriction').text = 'None'
+        _add_sub_element(site_info, 'itv:AdvertisingSite').text = 'ITV'
+        _add_sub_element(site_info, 'itv:AdvertisingType').text = 'Any'
+        _add_sub_element(site_info, 'itv:Area').text = 'ITVPLAYER.VIDEO'
+        _add_sub_element(site_info, 'itv:Category')
+        _add_sub_element(site_info, 'itv:Platform').text = 'DotCom'
+        _add_sub_element(site_info, 'itv:Site').text = 'ItvCom'
+        device_info = _add_sub_element(get_playlist, 'tem:deviceInfo')
+        _add_sub_element(device_info, 'itv:ScreenSize').text = 'Big'
+        player_info = _add_sub_element(get_playlist, 'tem:playerInfo')
+        _add_sub_element(player_info, 'itv:Version').text = '2'
+
+        headers = self.geo_verification_headers()
+        headers.update({
+            'Content-Type': 'text/xml; charset=utf-8',
+            'SOAPAction': 'http://tempuri.org/PlaylistService/GetPlaylist',
+        })
+        resp_env = self._download_xml(
+            params['data-playlist-url'], video_id,
+            headers=headers, data=etree.tostring(req_env))
+        playlist = xpath_element(resp_env, './/Playlist')
+        if playlist is None:
+            fault_string = xpath_text(resp_env, './/faultstring')
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string))
+        title = xpath_text(playlist, 'EpisodeTitle', fatal=True)
+        video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
+        media_files = xpath_element(video_element, 'MediaFiles', fatal=True)
+        rtmp_url = media_files.attrib['base']
+
+        formats = []
+        for media_file in media_files.findall('MediaFile'):
+            play_path = xpath_text(media_file, 'URL')
+            if not play_path:
+                continue
+            tbr = int_or_none(media_file.get('bitrate'), 1000)
+            formats.append({
+                'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
+                'url': rtmp_url,
+                'play_path': play_path,
+                'tbr': tbr,
+                'ext': 'flv',
+            })
+
+        ios_playlist_url = params.get('data-video-playlist')
+        hmac = params.get('data-video-hmac')
+        if ios_playlist_url and hmac:
+            headers = self.geo_verification_headers()
+            headers.update({
+                'Accept': 'application/vnd.itv.vod.playlist.v2+json',
+                'Content-Type': 'application/json',
+                'hmac': hmac.upper(),
+            })
+            ios_playlist = self._download_json(
+                ios_playlist_url, video_id, data=json.dumps({
+                    'user': {
+                        'itvUserId': '',
+                        'entitlements': [],
+                        'token': ''
+                    },
+                    'device': {
+                        'manufacturer': 'Apple',
+                        'model': 'iPad',
+                        'os': {
+                            'name': 'iPhone OS',
+                            'version': '9.3',
+                            'type': 'ios'
+                        }
+                    },
+                    'client': {
+                        'version': '4.1',
+                        'id': 'browser'
+                    },
+                    'variantAvailability': {
+                        'featureset': {
+                            'min': ['hls', 'aes'],
+                            'max': ['hls', 'aes']
+                        },
+                        'platformTag': 'mobile'
+                    }
+                }).encode(), headers=headers, fatal=False)
+            if ios_playlist:
+                video_data = ios_playlist.get('Playlist', {}).get('Video', {})
+                ios_base_url = video_data.get('Base')
+                for media_file in video_data.get('MediaFiles', []):
+                    href = media_file.get('Href')
+                    if not href:
+                        continue
+                    if ios_base_url:
+                        href = ios_base_url + href
+                    ext = determine_ext(href)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(href, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                    else:
+                        formats.append({
+                            'url': href,
+                        })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for caption_url in video_element.findall('ClosedCaptioningURIs/URL'):
+            if not caption_url.text:
+                continue
+            ext = determine_ext(caption_url.text, 'ttml')
+            subtitles.setdefault('en', []).append({
+                'url': caption_url.text,
+                'ext': 'ttml' if ext == 'xml' else ext,
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'subtitles': subtitles,
+            'episode_title': title,
+            'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
+            'series': xpath_text(playlist, 'ProgrammeTitle'),
+            'duartion': parse_duration(xpath_text(playlist, 'Duration')),
+        }

youtube_dl/extractor/jamendo.py

@@ -5,9 +5,27 @@ import re
 
 from ..compat import compat_urlparse
 from .common import InfoExtractor
+from ..utils import parse_duration
 
 
-class JamendoIE(InfoExtractor):
+class JamendoBaseIE(InfoExtractor):
+    def _extract_meta(self, webpage, fatal=True):
+        title = self._og_search_title(
+            webpage, default=None) or self._search_regex(
+            r'<title>([^<]+)', webpage,
+            'title', default=None)
+        if title:
+            title = self._search_regex(
+                r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
+        if not title:
+            title = self._html_search_meta(
+                'name', webpage, 'title', fatal=fatal)
+        mobj = re.search(r'(.+) - (.+)', title or '')
+        artist, second = mobj.groups() if mobj else [None] * 2
+        return title, artist, second
+
+
+class JamendoIE(JamendoBaseIE):
     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
     _TEST = {
         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
@@ -16,7 +34,10 @@ class JamendoIE(InfoExtractor):
             'id': '196219',
             'display_id': 'stories-from-emona-i',
             'ext': 'flac',
-            'title': 'Stories from Emona I',
+            'title': 'Maya Filipič - Stories from Emona I',
+            'artist': 'Maya Filipič',
+            'track': 'Stories from Emona I',
+            'duration': 210,
             'thumbnail': r're:^https?://.*\.jpg'
         }
     }
@@ -28,7 +49,7 @@ class JamendoIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._html_search_meta('name', webpage, 'title')
+        title, artist, track = self._extract_meta(webpage)
 
         formats = [{
             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
@@ -46,37 +67,47 @@ class JamendoIE(InfoExtractor):
 
         thumbnail = self._html_search_meta(
             'image', webpage, 'thumbnail', fatal=False)
+        duration = parse_duration(self._search_regex(
+            r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
+            webpage, 'duration', fatal=False))
 
         return {
             'id': track_id,
             'display_id': display_id,
             'thumbnail': thumbnail,
             'title': title,
+            'duration': duration,
+            'artist': artist,
+            'track': track,
             'formats': formats
         }
 
 
-class JamendoAlbumIE(InfoExtractor):
+class JamendoAlbumIE(JamendoBaseIE):
     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
     _TEST = {
         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
         'info_dict': {
             'id': '121486',
-            'title': 'Duck On Cover'
+            'title': 'Shearer - Duck On Cover'
         },
         'playlist': [{
             'md5': 'e1a2fcb42bda30dfac990212924149a8',
             'info_dict': {
                 'id': '1032333',
                 'ext': 'flac',
-                'title': 'Warmachine'
+                'title': 'Shearer - Warmachine',
+                'artist': 'Shearer',
+                'track': 'Warmachine',
             }
         }, {
             'md5': '1f358d7b2f98edfe90fd55dac0799d50',
             'info_dict': {
                 'id': '1032330',
                 'ext': 'flac',
-                'title': 'Without Your Ghost'
+                'title': 'Shearer - Without Your Ghost',
+                'artist': 'Shearer',
+                'track': 'Without Your Ghost',
             }
         }],
         'params': {
@@ -90,18 +121,18 @@ class JamendoAlbumIE(InfoExtractor):
 
         webpage = self._download_webpage(url, mobj.group('display_id'))
 
-        title = self._html_search_meta('name', webpage, 'title')
+        title, artist, album = self._extract_meta(webpage, fatal=False)
 
-        entries = [
-            self.url_result(
-                compat_urlparse.urljoin(url, m.group('path')),
-                ie=JamendoIE.ie_key(),
-                video_id=self._search_regex(
-                    r'/track/(\d+)', m.group('path'),
-                    'track id', default=None))
-            for m in re.finditer(
-                r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
-                webpage)
-        ]
+        entries = [{
+            '_type': 'url_transparent',
+            'url': compat_urlparse.urljoin(url, m.group('path')),
+            'ie_key': JamendoIE.ie_key(),
+            'id': self._search_regex(
+                r'/track/(\d+)', m.group('path'), 'track id', default=None),
+            'artist': artist,
+            'album': album,
+        } for m in re.finditer(
+            r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
+            webpage)]
 
         return self.playlist_result(entries, album_id, title)

youtube_dl/extractor/kaltura.py

@@ -266,9 +266,12 @@ class KalturaIE(InfoExtractor):
             # skip for now.
             if f.get('fileExt') == 'chun':
                 continue
-            if not f.get('fileExt') and f.get('containerFormat') == 'qt':
+            if not f.get('fileExt'):
                 # QT indicates QuickTime; some videos have broken fileExt
-                f['fileExt'] = 'mov'
+                if f.get('containerFormat') == 'qt':
+                    f['fileExt'] = 'mov'
+                else:
+                    f['fileExt'] = 'mp4'
             video_url = sign_url(
                 '%s/flavorId/%s' % (data_url, f['id']))
             # audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g
@@ -319,6 +322,6 @@ class KalturaIE(InfoExtractor):
             'thumbnail': info.get('thumbnailUrl'),
             'duration': info.get('duration'),
             'timestamp': info.get('createdAt'),
-            'uploader_id': info.get('userId'),
+            'uploader_id': info.get('userId') if info.get('userId') != 'None' else None,
             'view_count': info.get('plays'),
         }

youtube_dl/extractor/konserthusetplay.py

@@ -2,29 +2,31 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     float_or_none,
     int_or_none,
 )
 
 
 class KonserthusetPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?konserthusetplay\.se/\?.*\bm=(?P<id>[^&]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?:konserthusetplay|rspoplay)\.se/\?.*\bm=(?P<id>[^&]+)'
+    _TESTS = [{
         'url': 'http://www.konserthusetplay.se/?m=CKDDnlCY-dhWAAqiMERd-A',
+        'md5': 'e3fd47bf44e864bd23c08e487abe1967',
         'info_dict': {
             'id': 'CKDDnlCY-dhWAAqiMERd-A',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Orkesterns instrument: Valthornen',
             'description': 'md5:f10e1f0030202020396a4d712d2fa827',
             'thumbnail': 're:^https?://.*$',
-            'duration': 398.8,
+            'duration': 398.76,
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
-    }
+    }, {
+        'url': 'http://rspoplay.se/?m=elWuEH34SMKvaO4wO_cHBw',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -42,12 +44,18 @@ class KonserthusetPlayIE(InfoExtractor):
         player_config = media['playerconfig']
         playlist = player_config['playlist']
 
-        source = next(f for f in playlist if f.get('bitrates'))
+        source = next(f for f in playlist if f.get('bitrates') or f.get('provider'))
 
         FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4'
 
         formats = []
 
+        m3u8_url = source.get('url')
+        if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
         fallback_url = source.get('fallbackUrl')
         fallback_format_id = None
         if fallback_url:
@@ -97,6 +105,13 @@ class KonserthusetPlayIE(InfoExtractor):
         thumbnail = media.get('image')
         duration = float_or_none(media.get('duration'), 1000)
 
+        subtitles = {}
+        captions = source.get('captionsAvailableLanguages')
+        if isinstance(captions, dict):
+            for lang, subtitle_url in captions.items():
+                if lang != 'none' and isinstance(subtitle_url, compat_str):
+                    subtitles.setdefault(lang, []).append({'url': subtitle_url})
+
         return {
             'id': video_id,
             'title': title,
@@ -104,4 +119,5 @@ class KonserthusetPlayIE(InfoExtractor):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/limelight.py

@@ -59,14 +59,26 @@ class LimelightBaseIE(InfoExtractor):
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])
-                    http_url = 'http://cpl.delvenetworks.com/' + rtmp.group('playpath')[4:]
-                    urls.append(http_url)
-                    http_fmt = fmt.copy()
-                    http_fmt.update({
-                        'url': http_url,
-                        'format_id': format_id.replace('rtmp', 'http'),
-                    })
-                    formats.append(http_fmt)
+                    http_format_id = format_id.replace('rtmp', 'http')
+
+                    CDN_HOSTS = (
+                        ('delvenetworks.com', 'cpl.delvenetworks.com'),
+                        ('video.llnw.net', 's2.content.video.llnw.net'),
+                    )
+                    for cdn_host, http_host in CDN_HOSTS:
+                        if cdn_host not in rtmp.group('host').lower():
+                            continue
+                        http_url = 'http://%s/%s' % (http_host, rtmp.group('playpath')[4:])
+                        urls.append(http_url)
+                        if self._is_valid_url(http_url, video_id, http_format_id):
+                            http_fmt = fmt.copy()
+                            http_fmt.update({
+                                'url': http_url,
+                                'format_id': http_format_id,
+                            })
+                            formats.append(http_fmt)
+                            break
+
                     fmt.update({
                         'url': rtmp.group('url'),
                         'play_path': rtmp.group('playpath'),

youtube_dl/extractor/mitele.py

@@ -190,7 +190,7 @@ class MiTeleIE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             # for some reason only HLS is supported
-            'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
+            'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
             'id': video_id,
             'title': title,
             'description': description,

youtube_dl/extractor/mixcloud.py

@@ -16,7 +16,6 @@ from ..utils import (
     clean_html,
     ExtractorError,
     OnDemandPagedList,
-    parse_count,
     str_to_int,
 )
 
@@ -36,7 +35,6 @@ class MixcloudIE(InfoExtractor):
             'uploader_id': 'dholbach',
             'thumbnail': r're:https?://.*\.jpg',
             'view_count': int,
-            'like_count': int,
         },
     }, {
         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
@@ -49,7 +47,6 @@ class MixcloudIE(InfoExtractor):
             'uploader_id': 'gillespeterson',
             'thumbnail': 're:https?://.*',
             'view_count': int,
-            'like_count': int,
         },
     }, {
         'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
@@ -89,26 +86,18 @@ class MixcloudIE(InfoExtractor):
 
         song_url = play_info['stream_url']
 
-        PREFIX = (
-            r'm-play-on-spacebar[^>]+'
-            r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
-        title = self._html_search_regex(
-            PREFIX + r'm-title="([^"]+)"', webpage, 'title')
+        title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
         thumbnail = self._proto_relative_url(self._html_search_regex(
-            PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
-            fatal=False))
+            r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
         uploader = self._html_search_regex(
-            PREFIX + r'm-owner-name="([^"]+)"',
-            webpage, 'uploader', fatal=False)
+            r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
         uploader_id = self._search_regex(
             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
         description = self._og_search_description(webpage)
-        like_count = parse_count(self._search_regex(
-            r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
-            webpage, 'like count', default=None))
         view_count = str_to_int(self._search_regex(
             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
-             r'/listeners/?">([0-9,.]+)</a>'],
+             r'/listeners/?">([0-9,.]+)</a>',
+             r'm-tooltip=["\']([\d,.]+) plays'],
             webpage, 'play count', default=None))
 
         return {
@@ -120,7 +109,6 @@ class MixcloudIE(InfoExtractor):
             'uploader': uploader,
             'uploader_id': uploader_id,
             'view_count': view_count,
-            'like_count': like_count,
         }
 
 

youtube_dl/extractor/mtv.py

@@ -13,11 +13,11 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     HEADRequest,
-    NO_DEFAULT,
     RegexNotFoundError,
     sanitized_Request,
     strip_or_none,
     timeconvert,
+    try_get,
     unescapeHTML,
     update_url_query,
     url_basename,
@@ -42,15 +42,6 @@ class MTVServicesInfoExtractor(InfoExtractor):
         # Remove the templates, like &device={device}
         return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
 
-    # This was originally implemented for ComedyCentral, but it also works here
-    @classmethod
-    def _transform_rtmp_url(cls, rtmp_video_url):
-        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
-        if not m:
-            return {'rtmp': rtmp_video_url}
-        base = 'http://viacommtvstrmfs.fplive.net/'
-        return {'http': base + m.group('finalid')}
-
     def _get_feed_url(self, uri):
         return self._FEED_URL
 
@@ -88,24 +79,31 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
         formats = []
         for rendition in mdoc.findall('.//rendition'):
-            if rendition.attrib['method'] == 'hls':
+            if rendition.get('method') == 'hls':
                 hls_url = rendition.find('./src').text
-                formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4'))
+                formats.extend(self._extract_m3u8_formats(
+                    hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls'))
             else:
                 # fms
                 try:
                     _, _, ext = rendition.attrib['type'].partition('/')
                     rtmp_video_url = rendition.find('./src').text
+                    if 'error_not_available.swf' in rtmp_video_url:
+                        raise ExtractorError(
+                            '%s said: video is not available' % self.IE_NAME,
+                            expected=True)
                     if rtmp_video_url.endswith('siteunavail.png'):
                         continue
-                    new_urls = self._transform_rtmp_url(rtmp_video_url)
                     formats.extend([{
-                        'ext': 'flv' if new_url.startswith('rtmp') else ext,
-                        'url': new_url,
-                        'format_id': '-'.join(filter(None, [kind, rendition.get('bitrate')])),
+                        'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
+                        'url': rtmp_video_url,
+                        'format_id': '-'.join(filter(None, [
+                            'rtmp' if rtmp_video_url.startswith('rtmp') else None,
+                            rendition.get('bitrate')])),
                         'width': int(rendition.get('width')),
                         'height': int(rendition.get('height')),
-                    } for kind, new_url in new_urls.items()])
+                    }])
                 except (KeyError, TypeError):
                     raise ExtractorError('Invalid rendition field.')
         self._sort_formats(formats)
@@ -123,7 +121,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             } for typographic in transcript.findall('./typographic')]
         return subtitles
 
-    def _get_video_info(self, itemdoc, use_hls):
+    def _get_video_info(self, itemdoc, use_hls=True):
         uri = itemdoc.find('guid').text
         video_id = self._id_from_uri(uri)
         self.report_extraction(video_id)
@@ -193,13 +191,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
             data['lang'] = self._LANG
         return data
 
-    def _get_videos_info(self, uri, use_hls=False):
+    def _get_videos_info(self, uri, use_hls=True):
         video_id = self._id_from_uri(uri)
         feed_url = self._get_feed_url(uri)
         info_url = update_url_query(feed_url, self._get_feed_query(uri))
         return self._get_videos_info_from_url(info_url, video_id, use_hls)
 
-    def _get_videos_info_from_url(self, url, video_id, use_hls):
+    def _get_videos_info_from_url(self, url, video_id, use_hls=True):
         idoc = self._download_xml(
             url, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
@@ -211,7 +209,28 @@ class MTVServicesInfoExtractor(InfoExtractor):
             [self._get_video_info(item, use_hls) for item in idoc.findall('.//item')],
             playlist_title=title, playlist_description=description)
 
-    def _extract_mgid(self, webpage, default=NO_DEFAULT):
+    def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
+        triforce_feed = self._parse_json(self._search_regex(
+            r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
+            'triforce feed', default='{}'), video_id, fatal=False)
+
+        data_zone = self._search_regex(
+            r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
+            'data zone', default=data_zone, group='zone')
+
+        feed_url = try_get(
+            triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
+            compat_str)
+        if not feed_url:
+            return
+
+        feed = self._download_json(feed_url, video_id, fatal=False)
+        if not feed:
+            return
+
+        return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
+
+    def _extract_mgid(self, webpage):
         try:
             # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
             # or http://media.mtvnservices.com/{mgid}
@@ -231,7 +250,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
             sm4_embed = self._html_search_meta(
                 'sm4:video:embed', webpage, 'sm4 embed', default='')
             mgid = self._search_regex(
-                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
+                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
+
+        if not mgid:
+            mgid = self._extract_triforce_mgid(webpage)
+
         return mgid
 
     def _real_extract(self, url):
@@ -281,7 +304,7 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
 
 class MTVIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtv'
-    _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|full-episodes)/(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
     _FEED_URL = 'http://www.mtv.com/feeds/mrss/'
 
     _TESTS = [{
@@ -298,9 +321,41 @@ class MTVIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
         'only_matching': True,
+    }, {
+        'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
+        'only_matching': True,
     }]
 
 
+class MTV81IE(InfoExtractor):
+    IE_NAME = 'mtv81'
+    _VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P<id>[^/?#.]+)'
+
+    _TEST = {
+        'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/',
+        'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
+        'info_dict': {
+            'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
+            'ext': 'mp4',
+            'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
+            'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
+            'timestamp': 1468846800,
+            'upload_date': '20160718',
+        },
+    }
+
+    def _extract_mgid(self, webpage):
+        return self._search_regex(
+            r'getTheVideo\((["\'])(?P<id>mgid:.+?)\1', webpage,
+            'mgid', group='id')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        mgid = self._extract_mgid(webpage)
+        return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
+
+
 class MTVVideoIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtv:video'
     _VALID_URL = r'''(?x)^https?://

youtube_dl/extractor/naver.py

@@ -12,10 +12,10 @@ from ..utils import (
 
 
 class NaverIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://tvcast.naver.com/v/81652',
+        'url': 'http://tv.naver.com/v/81652',
         'info_dict': {
             'id': '81652',
             'ext': 'mp4',
@@ -24,7 +24,7 @@ class NaverIE(InfoExtractor):
             'upload_date': '20130903',
         },
     }, {
-        'url': 'http://tvcast.naver.com/v/395837',
+        'url': 'http://tv.naver.com/v/395837',
         'md5': '638ed4c12012c458fefcddfd01f173cd',
         'info_dict': {
             'id': '395837',
@@ -34,6 +34,9 @@ class NaverIE(InfoExtractor):
             'upload_date': '20150519',
         },
         'skip': 'Georestricted',
+    }, {
+        'url': 'http://tvcast.naver.com/v/81652',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/nextmedia.py

@@ -2,7 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..compat import compat_urlparse
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    int_or_none,
+    parse_iso8601,
+    remove_start,
+    unified_timestamp,
+)
 
 
 class NextMediaIE(InfoExtractor):
@@ -30,6 +38,12 @@ class NextMediaIE(InfoExtractor):
         return self._extract_from_nextmedia_page(news_id, url, page)
 
     def _extract_from_nextmedia_page(self, news_id, url, page):
+        redirection_url = self._search_regex(
+            r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
+            page, 'redirection URL', default=None, group='url')
+        if redirection_url:
+            return self.url_result(compat_urlparse.urljoin(url, redirection_url))
+
         title = self._fetch_title(page)
         video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
 
@@ -93,7 +107,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 class AppleDailyIE(NextMediaIE):
     IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -157,6 +171,10 @@ class AppleDailyIE(NextMediaIE):
     }, {
         'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
         'only_matching': True,
+    }, {
+        # Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
+        'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
+        'only_matching': True,
     }]
 
     _URL_PATTERN = r'\{url: \'(.+)\'\}'
@@ -173,3 +191,48 @@ class AppleDailyIE(NextMediaIE):
 
     def _fetch_description(self, page):
         return self._html_search_meta('description', page, 'news description')
+
+
+class NextTVIE(InfoExtractor):
+    IE_DESC = '壹電視'
+    _VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.nexttv.com.tw/news/realtime/politics/11779671',
+        'info_dict': {
+            'id': '11779671',
+            'ext': 'mp4',
+            'title': '「超收稅」近4千億！　藍議員籲發消費券',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1484825400,
+            'upload_date': '20170119',
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h1[^>]*>([^<]+)</h1>', webpage, 'title')
+
+        data = self._hidden_inputs(webpage)
+
+        video_url = data['ntt-vod-src-detailview']
+
+        date_str = get_element_by_class('date', webpage)
+        timestamp = unified_timestamp(date_str + '+0800') if date_str else None
+
+        view_count = int_or_none(remove_start(
+            clean_html(get_element_by_class('click', webpage)), '點閱：'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'thumbnail': data.get('ntt-vod-img-src'),
+            'timestamp': timestamp,
+            'view_count': view_count,
+        }

youtube_dl/extractor/nick.py

@@ -10,7 +10,7 @@ from ..utils import update_url_query
 class NickIE(MTVServicesInfoExtractor):
     # None of videos on the website are still alive?
     IE_NAME = 'nick.com'
-    _VALID_URL = r'https?://(?:www\.)?nick(?:jr)?\.com/(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?:(?:www|beta)\.)?nick(?:jr)?\.com/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
     _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
     _TESTS = [{
         'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
@@ -57,6 +57,9 @@ class NickIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/',
         'only_matching': True,
+    }, {
+        'url': 'http://beta.nick.com/nicky-ricky-dicky-and-dawn/videos/nicky-ricky-dicky-dawn-301-full-episode/',
+        'only_matching': True,
     }]
 
     def _get_feed_query(self, uri):

youtube_dl/extractor/niconico.py

@@ -7,7 +7,6 @@ import datetime
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -40,6 +39,7 @@ class NiconicoIE(InfoExtractor):
             'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
             'duration': 33,
         },
+        'skip': 'Requires an account',
     }, {
         # File downloaded with and without credentials are different, so omit
         # the md5 field
@@ -55,6 +55,7 @@ class NiconicoIE(InfoExtractor):
             'timestamp': 1304065916,
             'duration': 209,
         },
+        'skip': 'Requires an account',
     }, {
         # 'video exists but is marked as "deleted"
         # md5 is unstable
@@ -65,9 +66,10 @@ class NiconicoIE(InfoExtractor):
             '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
+            'timestamp': int,  # timestamp field has different value if logged in
             'duration': 304,
         },
+        'skip': 'Requires an account',
     }, {
         'url': 'http://www.nicovideo.jp/watch/so22543406',
         'info_dict': {
@@ -79,13 +81,12 @@ class NiconicoIE(InfoExtractor):
             'upload_date': '20140104',
             'uploader': 'アニメロチャンネル',
             'uploader_id': '312',
-        }
+        },
+        'skip': 'The viewing period of the video you were searching for has expired.',
     }]
 
     _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
     _NETRC_MACHINE = 'niconico'
-    # Determine whether the downloader used authentication to download video
-    _AUTHENTICATED = False
 
     def _real_initialize(self):
         self._login()
@@ -109,8 +110,6 @@ class NiconicoIE(InfoExtractor):
         if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
             self._downloader.report_warning('unable to log in: bad username or password')
             return False
-        # Successful login
-        self._AUTHENTICATED = True
         return True
 
     def _real_extract(self, url):
@@ -128,35 +127,19 @@ class NiconicoIE(InfoExtractor):
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
             note='Downloading video info page')
 
-        if self._AUTHENTICATED:
-            # Get flv info
-            flv_info_webpage = self._download_webpage(
-                'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
-                video_id, 'Downloading flv info')
-        else:
-            # Get external player info
-            ext_player_info = self._download_webpage(
-                'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
-            thumb_play_key = self._search_regex(
-                r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
-
-            # Get flv info
-            flv_info_data = compat_urllib_parse_urlencode({
-                'k': thumb_play_key,
-                'v': video_id
-            })
-            flv_info_request = sanitized_Request(
-                'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
-                {'Content-Type': 'application/x-www-form-urlencoded'})
-            flv_info_webpage = self._download_webpage(
-                flv_info_request, video_id,
-                note='Downloading flv info', errnote='Unable to download flv info')
+        # Get flv info
+        flv_info_webpage = self._download_webpage(
+            'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
+            video_id, 'Downloading flv info')
 
         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)
+            elif 'closed' in flv_info:
+                raise ExtractorError('Niconico videos now require logging in',
+                                     expected=True)
             else:
                 raise ExtractorError('Unable to find video URL')
 

youtube_dl/extractor/npo.py

@@ -241,7 +241,7 @@ class NPOIE(NPOBaseIE):
         if metadata.get('tt888') == 'ja':
             subtitles['nl'] = [{
                 'ext': 'vtt',
-                'url': 'http://e.omroep.nl/tt888/%s' % video_id,
+                'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
             }]
 
         return {

youtube_dl/extractor/nrk.py

@@ -128,6 +128,22 @@ class NRKBaseIE(InfoExtractor):
         series = conviva.get('seriesName') or data.get('seriesTitle')
         episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
 
+        season_number = None
+        episode_number = None
+        if data.get('mediaElementType') == 'Episode':
+            _season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \
+                data.get('relativeOriginUrl', '')
+            EPISODENUM_RE = [
+                r'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',
+                r'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',
+            ]
+            season_number = int_or_none(self._search_regex(
+                EPISODENUM_RE, _season_episode, 'season number',
+                default=None, group='season'))
+            episode_number = int_or_none(self._search_regex(
+                EPISODENUM_RE, _season_episode, 'episode number',
+                default=None, group='episode'))
+
         thumbnails = None
         images = data.get('images')
         if images and isinstance(images, dict):
@@ -140,11 +156,15 @@ class NRKBaseIE(InfoExtractor):
                 } for image in web_images if image.get('imageUrl')]
 
         description = data.get('description')
+        category = data.get('mediaAnalytics', {}).get('category')
 
         common_info = {
             'description': description,
             'series': series,
             'episode': episode,
+            'season_number': season_number,
+            'episode_number': episode_number,
+            'categories': [category] if category else None,
             'age_limit': parse_age_limit(data.get('legalAge')),
             'thumbnails': thumbnails,
         }
@@ -227,54 +247,102 @@ class NRKTVIE(NRKBaseIE):
             'title': '20 spørsmål 23.05.2014',
             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
             'duration': 1741,
+            'series': '20 spørsmål - TV',
+            'episode': '23.05.2014',
         },
     }, {
         'url': 'https://tv.nrk.no/program/mdfp15000514',
-        'md5': '43d0be26663d380603a9cf0c24366531',
         'info_dict': {
             'id': 'MDFP15000514CA',
             'ext': 'mp4',
             'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
             'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
             'duration': 4605,
+            'series': 'Kunnskapskanalen',
+            'episode': '24.05.2014',
+        },
+        'params': {
+            'skip_download': True,
         },
     }, {
         # single playlist video
         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
-        'md5': 'adbd1dbd813edaf532b0a253780719c2',
         'info_dict': {
             'id': 'MSPO40010515-part2',
             'ext': 'flv',
             'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
             'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
         },
-        'skip': 'Only works from Norway',
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Video is geo restricted'],
+        'skip': 'particular part is not supported currently',
     }, {
         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
         'playlist': [{
-            'md5': '9480285eff92d64f06e02a5367970a7a',
             'info_dict': {
-                'id': 'MSPO40010515-part1',
-                'ext': 'flv',
-                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
-                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                'id': 'MSPO40010515AH',
+                'ext': 'mp4',
+                'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
+                'description': 'md5:c03aba1e917561eface5214020551b7a',
+                'duration': 772,
+                'series': 'Tour de Ski',
+                'episode': '06.01.2015',
+            },
+            'params': {
+                'skip_download': True,
             },
         }, {
-            'md5': 'adbd1dbd813edaf532b0a253780719c2',
             'info_dict': {
-                'id': 'MSPO40010515-part2',
-                'ext': 'flv',
-                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
-                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
+                'id': 'MSPO40010515BH',
+                'ext': 'mp4',
+                'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
+                'description': 'md5:c03aba1e917561eface5214020551b7a',
+                'duration': 6175,
+                'series': 'Tour de Ski',
+                'episode': '06.01.2015',
+            },
+            'params': {
+                'skip_download': True,
             },
         }],
         'info_dict': {
             'id': 'MSPO40010515',
-            'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
-            'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
-            'duration': 6947.52,
+            'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
+            'description': 'md5:c03aba1e917561eface5214020551b7a',
+        },
+        'expected_warnings': ['Video is geo restricted'],
+    }, {
+        'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
+        'info_dict': {
+            'id': 'KMTE50001317AA',
+            'ext': 'mp4',
+            'title': 'Anno 13:30',
+            'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
+            'duration': 2340,
+            'series': 'Anno',
+            'episode': '13:30',
+            'season_number': 3,
+            'episode_number': 13,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
+        'info_dict': {
+            'id': 'MUHH46000317AA',
+            'ext': 'mp4',
+            'title': 'Nytt på Nytt 27.01.2017',
+            'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
+            'duration': 1796,
+            'series': 'Nytt på nytt',
+            'episode': '27.01.2017',
+        },
+        'params': {
+            'skip_download': True,
         },
-        'skip': 'Only works from Norway',
     }, {
         'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
         'only_matching': True,
@@ -360,6 +428,64 @@ class NRKTVEpisodesIE(NRKPlaylistBaseIE):
             r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 
 
+class NRKTVSeriesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
+    _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://tv.nrk.no/serie/groenn-glede',
+        'info_dict': {
+            'id': 'groenn-glede',
+            'title': 'Grønn glede',
+            'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
+        },
+        'playlist_mincount': 9,
+    }, {
+        'url': 'http://tv.nrksuper.no/serie/labyrint',
+        'info_dict': {
+            'id': 'labyrint',
+            'title': 'Labyrint',
+            'description': 'md5:58afd450974c89e27d5a19212eee7115',
+        },
+        'playlist_mincount': 3,
+    }, {
+        'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
+        'only_matching': True,
+    }, {
+        'url': 'https://tv.nrk.no/serie/saving-the-human-race',
+        'only_matching': True,
+    }, {
+        'url': 'https://tv.nrk.no/serie/postmann-pat',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, series_id)
+
+        entries = [
+            self.url_result(
+                'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
+                    series=series_id, season=season_id))
+            for season_id in re.findall(self._ITEM_RE, webpage)
+        ]
+
+        title = self._html_search_meta(
+            'seriestitle', webpage,
+            'title', default=None) or self._og_search_title(
+            webpage, fatal=False)
+
+        description = self._html_search_meta(
+            'series_description', webpage,
+            'description', default=None) or self._og_search_description(webpage)
+
+        return self.playlist_result(entries, series_id, title, description)
+
+
 class NRKSkoleIE(InfoExtractor):
     IE_DESC = 'NRK Skole'
     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'

youtube_dl/extractor/ooyala.py

@@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor):
     _CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
     _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
 
-    def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None):
+    def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None, embed_token=None):
         content_tree = self._download_json(content_tree_url, video_id)['content_tree']
         metadata = content_tree[list(content_tree)[0]]
         embed_code = metadata['embed_code']
@@ -29,7 +29,8 @@ class OoyalaBaseIE(InfoExtractor):
             self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
             compat_urllib_parse_urlencode({
                 'domain': domain,
-                'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds',
+                'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
+                'embedToken': embed_token,
             }), video_id)
 
         cur_auth_data = auth_data['authorization_data'][embed_code]
@@ -52,6 +53,12 @@ class OoyalaBaseIE(InfoExtractor):
                 elif delivery_type == 'hds' or ext == 'f4m':
                     formats.extend(self._extract_f4m_formats(
                         s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False))
+                elif delivery_type == 'dash' or ext == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        s_url, embed_code, mpd_id='dash', fatal=False))
+                elif delivery_type == 'smooth':
+                    self._extract_ism_formats(
+                        s_url, embed_code, ism_id='mss', fatal=False)
                 elif ext == 'smil':
                     formats.extend(self._extract_smil_formats(
                         s_url, embed_code, fatal=False))
@@ -146,8 +153,9 @@ class OoyalaIE(OoyalaBaseIE):
         embed_code = self._match_id(url)
         domain = smuggled_data.get('domain')
         supportedformats = smuggled_data.get('supportedformats')
+        embed_token = smuggled_data.get('embed_token')
         content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
-        return self._extract(content_tree_url, embed_code, domain, supportedformats)
+        return self._extract(content_tree_url, embed_code, domain, supportedformats, embed_token)
 
 
 class OoyalaExternalIE(OoyalaBaseIE):

youtube_dl/extractor/openload.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_chr
 from ..utils import (
@@ -56,6 +58,12 @@ class OpenloadIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
+            webpage)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
@@ -64,16 +72,17 @@ class OpenloadIE(InfoExtractor):
             raise ExtractorError('File not found', expected=True)
 
         ol_id = self._search_regex(
-            '<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
+            '<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
             webpage, 'openload ID')
 
-        first_two_chars = int(float(ol_id[0:][:2]))
+        first_three_chars = int(float(ol_id[0:][:3]))
+        fifth_char = int(float(ol_id[3:5]))
         urlcode = ''
-        num = 2
+        num = 5
 
         while num < len(ol_id):
-            urlcode += compat_chr(int(float(ol_id[num:][:3])) -
-                                  first_two_chars * int(float(ol_id[num + 3:][:2])))
+            urlcode += compat_chr(int(float(ol_id[num:][:3])) +
+                                  first_three_chars - fifth_char * int(float(ol_id[num + 3:][:2])))
             num += 5
 
         video_url = 'https://openload.co/stream/' + urlcode
@@ -92,7 +101,7 @@ class OpenloadIE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             # Seems all videos have extensions in their titles
-            'ext': determine_ext(title),
+            'ext': determine_ext(title, 'mp4'),
             'subtitles': subtitles,
         }
         return info_dict

youtube_dl/extractor/pluralsight.py

@@ -157,13 +157,10 @@ class PluralsightIE(PluralsightBaseIE):
 
         display_id = '%s-%s' % (name, clip_id)
 
-        parsed_url = compat_urlparse.urlparse(url)
-
-        payload_url = compat_urlparse.urlunparse(parsed_url._replace(
-            netloc='app.pluralsight.com', path='player/api/v1/payload'))
-
         course = self._download_json(
-            payload_url, display_id, headers={'Referer': url})['payload']['course']
+            'https://app.pluralsight.com/player/user/api/v1/player/payload',
+            display_id, data=urlencode_postdata({'courseId': course_name}),
+            headers={'Referer': url})
 
         collection = course['modules']
 

youtube_dl/extractor/pornflip.py

@@ -0,0 +1,92 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_str,
+)
+from ..utils import (
+    int_or_none,
+    try_get,
+    unified_timestamp,
+)
+
+
+class PornFlipIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[0-9A-Za-z]{11})'
+    _TESTS = [{
+        'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
+        'md5': '98c46639849145ae1fd77af532a9278c',
+        'info_dict': {
+            'id': 'wz7DfNhMmep',
+            'ext': 'mp4',
+            'title': '2 Amateurs swallow make his dream cumshots true',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 112,
+            'timestamp': 1481655502,
+            'upload_date': '20161213',
+            'uploader_id': '106786',
+            'uploader': 'figifoto',
+            'view_count': int,
+            'age_limit': 18,
+        }
+    }, {
+        'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://www.pornflip.com/v/%s' % video_id, video_id)
+
+        flashvars = compat_parse_qs(self._search_regex(
+            r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
+            webpage, 'flashvars', group='flashvars'))
+
+        title = flashvars['video_vars[title]'][0]
+
+        def flashvar(kind):
+            return try_get(
+                flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
+
+        formats = []
+        for key, value in flashvars.items():
+            if not (value and isinstance(value, list)):
+                continue
+            format_url = value[0]
+            if key == 'video_vars[hds_manifest]':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, video_id, mpd_id='dash', fatal=False))
+                continue
+            height = self._search_regex(
+                r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
+            if not height:
+                continue
+            formats.append({
+                'url': format_url,
+                'format_id': 'http-%s' % height,
+                'height': int_or_none(height),
+            })
+        self._sort_formats(formats)
+
+        uploader = self._html_search_regex(
+            (r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
+             r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
+            webpage, 'uploader', fatal=False, group='uploader')
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'thumbnail': flashvar('big_thumb'),
+            'duration': int_or_none(flashvar('duration')),
+            'timestamp': unified_timestamp(self._html_search_meta(
+                'uploadDate', webpage, 'timestamp')),
+            'uploader_id': flashvar('author_id'),
+            'uploader': uploader,
+            'view_count': int_or_none(flashvar('views')),
+            'age_limit': 18,
+        }

youtube_dl/extractor/prosiebensat1.py

@@ -147,16 +147,12 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
             'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
             'info_dict': {
                 'id': '2104602',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Episode 18 - Staffel 2',
                 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
                 'upload_date': '20131231',
                 'duration': 5845.04,
             },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
         },
         {
             'url': 'http://www.prosieben.de/videokatalog/Gesellschaft/Leben/Trends/video-Lady-Umstyling-f%C3%BCr-Audrina-Rebekka-Audrina-Fergen-billig-aussehen-Battal-Modica-700544.html',
@@ -258,7 +254,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
             'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
             'info_dict': {
                 'id': '2572814',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Andreas Kümmert: Rocket Man',
                 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
                 'upload_date': '20131017',
@@ -272,7 +268,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
             'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
             'info_dict': {
                 'id': '2156342',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Kurztrips zum Valentinstag',
                 'description': 'Romantischer Kurztrip zum Valentinstag? Nina Heinemann verrät, was sich hier wirklich lohnt.',
                 'duration': 307.24,
@@ -289,12 +285,13 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
                 'description': 'md5:63b8963e71f481782aeea877658dec84',
             },
             'playlist_count': 2,
+            'skip': 'This video is unavailable',
         },
         {
             'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge',
             'info_dict': {
                 'id': '4187506',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Best of Circus HalliGalli',
                 'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
                 'upload_date': '20151229',
@@ -375,7 +372,9 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
         title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
         info = self._extract_video_info(url, clip_id)
         description = self._html_search_regex(
-            self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
+            self._DESCRIPTION_REGEXES, webpage, 'description', default=None)
+        if description is None:
+            description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
         upload_date = unified_strdate(self._html_search_regex(
             self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))

youtube_dl/extractor/ruutu.py

@@ -81,6 +81,9 @@ class RuutuIE(InfoExtractor):
                     elif ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
                             video_url, video_id, f4m_id='hds', fatal=False))
+                    elif ext == 'mpd':
+                        formats.extend(self._extract_mpd_formats(
+                            video_url, video_id, mpd_id='dash', fatal=False))
                     else:
                         proto = compat_urllib_parse_urlparse(video_url).scheme
                         if not child.tag.startswith('HTTP') and proto != 'rtmp':

youtube_dl/extractor/soundcloud.py

@@ -173,46 +173,54 @@ class SoundcloudIE(InfoExtractor):
             })
 
         # We have to retrieve the url
-        streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
-                       'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
         format_dict = self._download_json(
-            streams_url,
-            track_id, 'Downloading track url')
+            'http://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
+            track_id, 'Downloading track url', query={
+                'client_id': self._CLIENT_ID,
+                'secret_token': secret_token,
+            })
 
         for key, stream_url in format_dict.items():
+            abr = int_or_none(self._search_regex(
+                r'_(\d+)_url', key, 'audio bitrate', default=None))
             if key.startswith('http'):
-                formats.append({
+                stream_formats = [{
                     'format_id': key,
                     'ext': ext,
                     'url': stream_url,
-                    'vcodec': 'none',
-                })
+                }]
             elif key.startswith('rtmp'):
                 # The url doesn't have an rtmp app, we have to extract the playpath
                 url, path = stream_url.split('mp3:', 1)
-                formats.append({
+                stream_formats = [{
                     'format_id': key,
                     'url': url,
                     'play_path': 'mp3:' + path,
                     'ext': 'flv',
-                    'vcodec': 'none',
-                })
+                }]
+            elif key.startswith('hls'):
+                stream_formats = self._extract_m3u8_formats(
+                    stream_url, track_id, 'mp3', entry_protocol='m3u8_native',
+                    m3u8_id=key, fatal=False)
+            else:
+                continue
 
-            if not formats:
-                # We fallback to the stream_url in the original info, this
-                # cannot be always used, sometimes it can give an HTTP 404 error
-                formats.append({
-                    'format_id': 'fallback',
-                    'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
-                    'ext': ext,
-                    'vcodec': 'none',
-                })
+            for f in stream_formats:
+                f['abr'] = abr
 
-            for f in formats:
-                if f['format_id'].startswith('http'):
-                    f['protocol'] = 'http'
-                if f['format_id'].startswith('rtmp'):
-                    f['protocol'] = 'rtmp'
+            formats.extend(stream_formats)
+
+        if not formats:
+            # We fallback to the stream_url in the original info, this
+            # cannot be always used, sometimes it can give an HTTP 404 error
+            formats.append({
+                'format_id': 'fallback',
+                'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+                'ext': ext,
+            })
+
+        for f in formats:
+            f['vcodec'] = 'none'
 
         self._check_formats(formats, track_id)
         self._sort_formats(formats)

youtube_dl/extractor/southpark.py

@@ -6,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
 
 class SouthParkIE(MTVServicesInfoExtractor):
     IE_NAME = 'southpark.cc.com'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
 
     _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
 
@@ -75,7 +75,7 @@ class SouthParkDeIE(SouthParkIE):
 
 class SouthParkNlIE(SouthParkIE):
     IE_NAME = 'southpark.nl'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))'
     _FEED_URL = 'http://www.southpark.nl/feeds/video-player/mrss/'
 
     _TESTS = [{

youtube_dl/extractor/spike.py

@@ -46,7 +46,7 @@ class SpikeIE(MTVServicesInfoExtractor):
     _CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)')
 
     def _extract_mgid(self, webpage):
-        mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None)
+        mgid = super(SpikeIE, self)._extract_mgid(webpage)
         if mgid is None:
             url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
             video_type, episode_id = url_parts.split('/', 1)

youtube_dl/extractor/srgssr.py

@@ -48,9 +48,6 @@ class SRGSSRIE(InfoExtractor):
     def _real_extract(self, url):
         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
 
-        if bu == 'rts':
-            return self.url_result('rts:%s' % media_id, 'RTS')
-
         media_data = self.get_media_data(bu, media_type, media_id)
 
         metadata = media_data['AssetMetadatas']['AssetMetadata'][0]

youtube_dl/extractor/tv4.py

@@ -4,11 +4,10 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
-    ExtractorError,
     int_or_none,
     parse_iso8601,
     try_get,
-    update_url_query,
+    determine_ext,
 )
 
 
@@ -28,7 +27,7 @@ class TV4IE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
-            'md5': '909d6454b87b10a25aa04c4bdd416a9b',
+            'md5': 'cb837212f342d77cec06e6dad190e96d',
             'info_dict': {
                 'id': '2491650',
                 'ext': 'mp4',
@@ -40,7 +39,7 @@ class TV4IE(InfoExtractor):
         },
         {
             'url': 'http://www.tv4play.se/iframe/video/3054113',
-            'md5': '77f851c55139ffe0ebd41b6a5552489b',
+            'md5': 'cb837212f342d77cec06e6dad190e96d',
             'info_dict': {
                 'id': '3054113',
                 'ext': 'mp4',
@@ -75,11 +74,10 @@ class TV4IE(InfoExtractor):
         # If is_geo_restricted is true, it doesn't necessarily mean we can't download it
         if info.get('is_geo_restricted'):
             self.report_warning('This content might not be available in your country due to licensing restrictions.')
-        if info.get('requires_subscription'):
-            raise ExtractorError('This content requires subscription.', expected=True)
 
         title = info['title']
 
+        subtitles = {}
         formats = []
         # http formats are linked with unresolvable host
         for kind in ('hls', ''):
@@ -87,26 +85,41 @@ class TV4IE(InfoExtractor):
                 'https://prima.tv4play.se/api/web/asset/%s/play.json' % video_id,
                 video_id, 'Downloading sources JSON', query={
                     'protocol': kind,
-                    'videoFormat': 'MP4+WEBVTTS+WEBVTT',
+                    'videoFormat': 'MP4+WEBVTT',
                 })
-            item = try_get(data, lambda x: x['playback']['items']['item'], dict)
-            manifest_url = item.get('url')
-            if not isinstance(manifest_url, compat_str):
+            items = try_get(data, lambda x: x['playback']['items']['item'])
+            if not items:
                 continue
-            if kind == 'hls':
-                formats.extend(self._extract_m3u8_formats(
-                    manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id=kind, fatal=False))
-            else:
-                formats.extend(self._extract_f4m_formats(
-                    update_url_query(manifest_url, {'hdcore': '3.8.0'}),
-                    video_id, f4m_id='hds', fatal=False))
+            if isinstance(items, dict):
+                items = [items]
+            for item in items:
+                manifest_url = item.get('url')
+                if not isinstance(manifest_url, compat_str):
+                    continue
+                ext = determine_ext(manifest_url)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id=kind, fatal=False))
+                elif ext == 'f4m':
+                    formats.extend(self._extract_akamai_formats(
+                        manifest_url, video_id, {
+                            'hls': 'tv4play-i.akamaihd.net',
+                        }))
+                elif ext == 'webvtt':
+                    subtitles = self._merge_subtitles(
+                        subtitles, {
+                            'sv': [{
+                                'url': manifest_url,
+                                'ext': 'vtt',
+                            }]})
         self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
+            'subtitles': subtitles,
             'description': info.get('description'),
             'timestamp': parse_iso8601(info.get('broadcast_date_time')),
             'duration': int_or_none(info.get('duration')),

youtube_dl/extractor/tva.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    smuggle_url,
+)
+
+
+class TVAIE(InfoExtractor):
+    _VALID_URL = r'https?://videos\.tva\.ca/episode/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://videos.tva.ca/episode/85538',
+        'info_dict': {
+            'id': '85538',
+            'ext': 'mp4',
+            'title': 'Épisode du 25 janvier 2017',
+            'description': 'md5:e9e7fb5532ab37984d2dc87229cadf98',
+            'upload_date': '20170126',
+            'timestamp': 1485442329,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            "https://d18jmrhziuoi7p.cloudfront.net/isl/api/v1/dataservice/Items('%s')" % video_id,
+            video_id, query={
+                '$expand': 'Metadata,CustomId',
+                '$select': 'Metadata,Id,Title,ShortDescription,LongDescription,CreatedDate,CustomId,AverageUserRating,Categories,ShowName',
+                '$format': 'json',
+            })
+        metadata = video_data.get('Metadata', {})
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': video_data['Title'],
+            'url': smuggle_url('ooyala:' + video_data['CustomId'], {'supportedformats': 'm3u8,hds'}),
+            'description': video_data.get('LongDescription') or video_data.get('ShortDescription'),
+            'series': video_data.get('ShowName'),
+            'episode': metadata.get('EpisodeTitle'),
+            'episode_number': int_or_none(metadata.get('EpisodeNumber')),
+            'categories': video_data.get('Categories'),
+            'average_rating': video_data.get('AverageUserRating'),
+            'timestamp': parse_iso8601(video_data.get('CreatedDate')),
+            'ie_key': 'Ooyala',
+        }

youtube_dl/extractor/twentyfourvideo.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class TwentyFourVideoIE(InfoExtractor):
     IE_NAME = '24video'
-    _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.24video.net/video/view/1044982',
@@ -43,7 +43,7 @@ class TwentyFourVideoIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            'http://www.24video.net/video/view/%s' % video_id, video_id)
+            'http://www.24video.sex/video/view/%s' % video_id, video_id)
 
         title = self._og_search_title(webpage)
         description = self._html_search_regex(
@@ -69,11 +69,11 @@ class TwentyFourVideoIE(InfoExtractor):
 
         # Sets some cookies
         self._download_xml(
-            r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
+            r'http://www.24video.sex/video/xml/%s?mode=init' % video_id,
             video_id, 'Downloading init XML')
 
         video_xml = self._download_xml(
-            'http://www.24video.net/video/xml/%s?mode=play' % video_id,
+            'http://www.24video.sex/video/xml/%s?mode=play' % video_id,
             video_id, 'Downloading video XML')
 
         video = xpath_element(video_xml, './/video', 'video', fatal=True)

youtube_dl/extractor/twentymin.py

@@ -4,91 +4,88 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import remove_end
+from ..utils import (
+    int_or_none,
+    try_get,
+)
 
 
 class TwentyMinutenIE(InfoExtractor):
     IE_NAME = '20min'
-    _VALID_URL = r'https?://(?:www\.)?20min\.ch/(?:videotv/*\?.*\bvid=(?P<id>\d+)|(?:[^/]+/)*(?P<display_id>[^/#?]+))'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?20min\.ch/
+                        (?:
+                            videotv/*\?.*?\bvid=|
+                            videoplayer/videoplayer\.html\?.*?\bvideoId@
+                        )
+                        (?P<id>\d+)
+                    '''
     _TESTS = [{
-        # regular video
         'url': 'http://www.20min.ch/videotv/?vid=469148&cid=2',
-        'md5': 'b52d6bc6ea6398e6a38f12cfd418149c',
+        'md5': 'e7264320db31eed8c38364150c12496e',
         'info_dict': {
             'id': '469148',
-            'ext': 'flv',
-            'title': '85 000 Franken für 15 perfekte Minuten',
-            'description': 'Was die Besucher vom Silvesterzauber erwarten können. (Video: Alice Grosjean/Murat Temel)',
-            'thumbnail': 'http://thumbnails.20min-tv.ch/server063/469148/frame-72-469148.jpg'
-        }
-    }, {
-        # news article with video
-        'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469',
-        'md5': 'cd4cbb99b94130cff423e967cd275e5e',
-        'info_dict': {
-            'id': '469408',
-            'display_id': '-Wir-muessen-mutig-nach-vorne-schauen--22050469',
-            'ext': 'flv',
-            'title': '«Wir müssen mutig nach vorne schauen»',
-            'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
-            'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
-        },
-        'skip': '"This video is no longer available" is shown both on the web page and in the downloaded file.',
-    }, {
-        # YouTube embed
-        'url': 'http://www.20min.ch/ro/sports/football/story/Il-marque-une-bicyclette-de-plus-de-30-metres--21115184',
-        'md5': 'cec64d59aa01c0ed9dbba9cf639dd82f',
-        'info_dict': {
-            'id': 'ivM7A7SpDOs',
             'ext': 'mp4',
-            'title': 'GOLAZO DE CHILENA DE JAVI GÓMEZ, FINALISTA AL BALÓN DE CLM 2016',
-            'description': 'md5:903c92fbf2b2f66c09de514bc25e9f5a',
-            'upload_date': '20160424',
-            'uploader': 'RTVCM Castilla-La Mancha',
-            'uploader_id': 'RTVCM',
+            'title': '85 000 Franken für 15 perfekte Minuten',
+            'thumbnail': r're:https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.20min.ch/videoplayer/videoplayer.html?params=client@twentyDE|videoId@523629',
+        'info_dict': {
+            'id': '523629',
+            'ext': 'mp4',
+            'title': 'So kommen Sie bei Eis und Schnee sicher an',
+            'description': 'md5:117c212f64b25e3d95747e5276863f7d',
+            'thumbnail': r're:https?://.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,
         },
-        'add_ie': ['Youtube'],
     }, {
         'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
         'only_matching': True,
-    }, {
-        'url': 'http://www.20min.ch/ro/sortir/cinema/story/Grandir-au-bahut--c-est-dur-18927411',
-        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [m.group('url') for m in re.finditer(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:www\.)?20min\.ch/videoplayer/videoplayer.html\?.*?\bvideoId@\d+.*?)\1',
+            webpage)]
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id') or video_id
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, display_id)
+        video = self._download_json(
+            'http://api.20min.ch/video/%s/show' % video_id,
+            video_id)['content']
 
-        youtube_url = self._html_search_regex(
-            r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
-            webpage, 'YouTube embed URL', default=None)
-        if youtube_url is not None:
-            return self.url_result(youtube_url, 'Youtube')
+        title = video['title']
 
-        title = self._html_search_regex(
-            r'<h1>.*?<span>(.+?)</span></h1>',
-            webpage, 'title', default=None)
-        if not title:
-            title = remove_end(re.sub(
-                r'^20 [Mm]inuten.*? -', '', self._og_search_title(webpage)), ' - News')
+        formats = [{
+            'format_id': format_id,
+            'url': 'http://podcast.20min-tv.ch/podcast/20min/%s%s.mp4' % (video_id, p),
+            'quality': quality,
+        } for quality, (format_id, p) in enumerate([('sd', ''), ('hd', 'h')])]
+        self._sort_formats(formats)
 
-        if not video_id:
-            video_id = self._search_regex(
-                r'"file\d?"\s*,\s*\"(\d+)', webpage, 'video id')
+        description = video.get('lead')
+        thumbnail = video.get('thumbnail')
 
-        description = self._html_search_meta(
-            'description', webpage, 'description')
-        thumbnail = self._og_search_thumbnail(webpage)
+        def extract_count(kind):
+            return try_get(
+                video,
+                lambda x: int_or_none(x['communityobject']['thumbs_%s' % kind]))
+
+        like_count = extract_count('up')
+        dislike_count = extract_count('down')
 
         return {
             'id': video_id,
-            'display_id': display_id,
-            'url': 'http://speed.20min-tv.ch/%sm.flv' % video_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'formats': formats,
         }

youtube_dl/extractor/twitch.py

@@ -209,7 +209,7 @@ class TwitchVodIE(TwitchItemBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?twitch\.tv/[^/]+/v/|
+                            (?:www\.)?twitch\.tv/(?:[^/]+/v|videos)/|
                             player\.twitch\.tv/\?.*?\bvideo=v
                         )
                         (?P<id>\d+)
@@ -259,6 +259,9 @@ class TwitchVodIE(TwitchItemBaseIE):
     }, {
         'url': 'http://player.twitch.tv/?t=5m10s&video=v6528877',
         'only_matching': True,
+    }, {
+        'url': 'https://www.twitch.tv/videos/6528877',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/uol.py

@@ -84,12 +84,27 @@ class UOLIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        if not video_id.isdigit():
-            embed_page = self._download_webpage('https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id, video_id)
-            video_id = self._search_regex(r'mediaId=(\d+)', embed_page, 'media id')
+        media_id = None
+
+        if video_id.isdigit():
+            media_id = video_id
+
+        if not media_id:
+            embed_page = self._download_webpage(
+                'https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id,
+                video_id, 'Downloading embed page', fatal=False)
+            if embed_page:
+                media_id = self._search_regex(
+                    (r'uol\.com\.br/(\d+)', r'mediaId=(\d+)'),
+                    embed_page, 'media id', default=None)
+
+        if not media_id:
+            webpage = self._download_webpage(url, video_id)
+            media_id = self._search_regex(r'mediaId=(\d+)', webpage, 'media id')
+
         video_data = self._download_json(
-            'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % video_id,
-            video_id)['item']
+            'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % media_id,
+            media_id)['item']
         title = video_data['title']
 
         query = {
@@ -118,7 +133,7 @@ class UOLIE(InfoExtractor):
             tags.append(tag_description)
 
         return {
-            'id': video_id,
+            'id': media_id,
             'title': title,
             'description': clean_html(video_data.get('desMedia')),
             'thumbnail': video_data.get('thumbnail'),

youtube_dl/extractor/ustream.py

@@ -69,6 +69,13 @@ class UstreamIE(InfoExtractor):
         },
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return mobj.group('url')
+
     def _get_stream_info(self, url, video_id, app_id_ver, extra_note=None):
         def num_to_hex(n):
             return hex(n)[2:]

youtube_dl/extractor/vevo.py

@@ -4,9 +4,9 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_etree_fromstring,
     compat_str,
     compat_urlparse,
+    compat_HTTPError,
 )
 from ..utils import (
     ExtractorError,
@@ -140,21 +140,6 @@ class VevoIE(VevoBaseIE):
         'url': 'http://www.vevo.com/watch/INS171400764',
         'only_matching': True,
     }]
-    _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com'
-    _SOURCE_TYPES = {
-        0: 'youtube',
-        1: 'brightcove',
-        2: 'http',
-        3: 'hls_ios',
-        4: 'hls',
-        5: 'smil',  # http
-        7: 'f4m_cc',
-        8: 'f4m_ak',
-        9: 'f4m_l3',
-        10: 'ism',
-        13: 'smil',  # rtmp
-        18: 'dash',
-    }
     _VERSIONS = {
         0: 'youtube',  # only in AuthenticateVideo videoVersions
         1: 'level3',
@@ -163,41 +148,6 @@ class VevoIE(VevoBaseIE):
         4: 'amazon',
     }
 
-    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
-        formats = []
-        els = smil.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
-        for el in els:
-            src = el.attrib['src']
-            m = re.match(r'''(?xi)
-                (?P<ext>[a-z0-9]+):
-                (?P<path>
-                    [/a-z0-9]+     # The directory and main part of the URL
-                    _(?P<tbr>[0-9]+)k
-                    _(?P<width>[0-9]+)x(?P<height>[0-9]+)
-                    _(?P<vcodec>[a-z0-9]+)
-                    _(?P<vbr>[0-9]+)
-                    _(?P<acodec>[a-z0-9]+)
-                    _(?P<abr>[0-9]+)
-                    \.[a-z0-9]+  # File extension
-                )''', src)
-            if not m:
-                continue
-
-            format_url = self._SMIL_BASE_URL + m.group('path')
-            formats.append({
-                'url': format_url,
-                'format_id': 'smil_' + m.group('tbr'),
-                'vcodec': m.group('vcodec'),
-                'acodec': m.group('acodec'),
-                'tbr': int(m.group('tbr')),
-                'vbr': int(m.group('vbr')),
-                'abr': int(m.group('abr')),
-                'ext': m.group('ext'),
-                'width': int(m.group('width')),
-                'height': int(m.group('height')),
-            })
-        return formats
-
     def _initialize_api(self, video_id):
         req = sanitized_Request(
             'http://www.vevo.com/auth', data=b'')
@@ -206,7 +156,7 @@ class VevoIE(VevoBaseIE):
             note='Retrieving oauth token',
             errnote='Unable to retrieve oauth token')
 
-        if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage:
+        if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
             self.raise_geo_restricted(
                 '%s said: This page is currently unavailable in your region' % self.IE_NAME)
 
@@ -214,148 +164,91 @@ class VevoIE(VevoBaseIE):
         self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
 
     def _call_api(self, path, *args, **kwargs):
-        return self._download_json(self._api_url_template % path, *args, **kwargs)
+        try:
+            data = self._download_json(self._api_url_template % path, *args, **kwargs)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                errors = self._parse_json(e.cause.read().decode(), None)['errors']
+                error_message = ', '.join([error['message'] for error in errors])
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
+            raise
+        return data
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        json_url = 'http://api.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
-        response = self._download_json(
-            json_url, video_id, 'Downloading video info',
-            'Unable to download info', fatal=False) or {}
-        video_info = response.get('video') or {}
+        self._initialize_api(video_id)
+
+        video_info = self._call_api(
+            'video/%s' % video_id, video_id, 'Downloading api video info',
+            'Failed to download video info')
+
+        video_versions = self._call_api(
+            'video/%s/streams' % video_id, video_id,
+            'Downloading video versions info',
+            'Failed to download video versions info',
+            fatal=False)
+
+        # Some videos are only available via webpage (e.g.
+        # https://github.com/rg3/youtube-dl/issues/9366)
+        if not video_versions:
+            webpage = self._download_webpage(url, video_id)
+            video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
+
+        uploader = None
         artist = None
         featured_artist = None
-        uploader = None
-        view_count = None
+        artists = video_info.get('artists')
+        for curr_artist in artists:
+            if curr_artist.get('role') == 'Featured':
+                featured_artist = curr_artist['name']
+            else:
+                artist = uploader = curr_artist['name']
+
         formats = []
+        for video_version in video_versions:
+            version = self._VERSIONS.get(video_version['version'])
+            version_url = video_version.get('url')
+            if not version_url:
+                continue
 
-        if not video_info:
-            try:
-                self._initialize_api(video_id)
-            except ExtractorError:
-                ytid = response.get('errorInfo', {}).get('ytid')
-                if ytid:
-                    self.report_warning(
-                        'Video is geoblocked, trying with the YouTube video %s' % ytid)
-                    return self.url_result(ytid, 'Youtube', ytid)
-
-                raise
-
-            video_info = self._call_api(
-                'video/%s' % video_id, video_id, 'Downloading api video info',
-                'Failed to download video info')
-
-            video_versions = self._call_api(
-                'video/%s/streams' % video_id, video_id,
-                'Downloading video versions info',
-                'Failed to download video versions info',
-                fatal=False)
-
-            # Some videos are only available via webpage (e.g.
-            # https://github.com/rg3/youtube-dl/issues/9366)
-            if not video_versions:
-                webpage = self._download_webpage(url, video_id)
-                video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
-
-            timestamp = parse_iso8601(video_info.get('releaseDate'))
-            artists = video_info.get('artists')
-            for curr_artist in artists:
-                if curr_artist.get('role') == 'Featured':
-                    featured_artist = curr_artist['name']
-                else:
-                    artist = uploader = curr_artist['name']
-            view_count = int_or_none(video_info.get('views', {}).get('total'))
-
-            for video_version in video_versions:
-                version = self._VERSIONS.get(video_version['version'])
-                version_url = video_version.get('url')
-                if not version_url:
+            if '.ism' in version_url:
+                continue
+            elif '.mpd' in version_url:
+                formats.extend(self._extract_mpd_formats(
+                    version_url, video_id, mpd_id='dash-%s' % version,
+                    note='Downloading %s MPD information' % version,
+                    errnote='Failed to download %s MPD information' % version,
+                    fatal=False))
+            elif '.m3u8' in version_url:
+                formats.extend(self._extract_m3u8_formats(
+                    version_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls-%s' % version,
+                    note='Downloading %s m3u8 information' % version,
+                    errnote='Failed to download %s m3u8 information' % version,
+                    fatal=False))
+            else:
+                m = re.search(r'''(?xi)
+                    _(?P<width>[0-9]+)x(?P<height>[0-9]+)
+                    _(?P<vcodec>[a-z0-9]+)
+                    _(?P<vbr>[0-9]+)
+                    _(?P<acodec>[a-z0-9]+)
+                    _(?P<abr>[0-9]+)
+                    \.(?P<ext>[a-z0-9]+)''', version_url)
+                if not m:
                     continue
 
-                if '.ism' in version_url:
-                    continue
-                elif '.mpd' in version_url:
-                    formats.extend(self._extract_mpd_formats(
-                        version_url, video_id, mpd_id='dash-%s' % version,
-                        note='Downloading %s MPD information' % version,
-                        errnote='Failed to download %s MPD information' % version,
-                        fatal=False))
-                elif '.m3u8' in version_url:
-                    formats.extend(self._extract_m3u8_formats(
-                        version_url, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls-%s' % version,
-                        note='Downloading %s m3u8 information' % version,
-                        errnote='Failed to download %s m3u8 information' % version,
-                        fatal=False))
-                else:
-                    m = re.search(r'''(?xi)
-                        _(?P<width>[0-9]+)x(?P<height>[0-9]+)
-                        _(?P<vcodec>[a-z0-9]+)
-                        _(?P<vbr>[0-9]+)
-                        _(?P<acodec>[a-z0-9]+)
-                        _(?P<abr>[0-9]+)
-                        \.(?P<ext>[a-z0-9]+)''', version_url)
-                    if not m:
-                        continue
-
-                    formats.append({
-                        'url': version_url,
-                        'format_id': 'http-%s-%s' % (version, video_version['quality']),
-                        'vcodec': m.group('vcodec'),
-                        'acodec': m.group('acodec'),
-                        'vbr': int(m.group('vbr')),
-                        'abr': int(m.group('abr')),
-                        'ext': m.group('ext'),
-                        'width': int(m.group('width')),
-                        'height': int(m.group('height')),
-                    })
-        else:
-            timestamp = int_or_none(self._search_regex(
-                r'/Date\((\d+)\)/',
-                video_info['releaseDate'], 'release date', fatal=False),
-                scale=1000)
-            artists = video_info.get('mainArtists')
-            if artists:
-                artist = uploader = artists[0]['artistName']
-
-            featured_artists = video_info.get('featuredArtists')
-            if featured_artists:
-                featured_artist = featured_artists[0]['artistName']
-
-            smil_parsed = False
-            for video_version in video_info['videoVersions']:
-                version = self._VERSIONS.get(video_version['version'])
-                if version == 'youtube':
-                    continue
-                else:
-                    source_type = self._SOURCE_TYPES.get(video_version['sourceType'])
-                    renditions = compat_etree_fromstring(video_version['data'])
-                    if source_type == 'http':
-                        for rend in renditions.findall('rendition'):
-                            attr = rend.attrib
-                            formats.append({
-                                'url': attr['url'],
-                                'format_id': 'http-%s-%s' % (version, attr['name']),
-                                'height': int_or_none(attr.get('frameheight')),
-                                'width': int_or_none(attr.get('frameWidth')),
-                                'tbr': int_or_none(attr.get('totalBitrate')),
-                                'vbr': int_or_none(attr.get('videoBitrate')),
-                                'abr': int_or_none(attr.get('audioBitrate')),
-                                'vcodec': attr.get('videoCodec'),
-                                'acodec': attr.get('audioCodec'),
-                            })
-                    elif source_type == 'hls':
-                        formats.extend(self._extract_m3u8_formats(
-                            renditions.find('rendition').attrib['url'], video_id,
-                            'mp4', 'm3u8_native', m3u8_id='hls-%s' % version,
-                            note='Downloading %s m3u8 information' % version,
-                            errnote='Failed to download %s m3u8 information' % version,
-                            fatal=False))
-                    elif source_type == 'smil' and version == 'level3' and not smil_parsed:
-                        formats.extend(self._extract_smil_formats(
-                            renditions.find('rendition').attrib['url'], video_id, False))
-                        smil_parsed = True
+                formats.append({
+                    'url': version_url,
+                    'format_id': 'http-%s-%s' % (version, video_version['quality']),
+                    'vcodec': m.group('vcodec'),
+                    'acodec': m.group('acodec'),
+                    'vbr': int(m.group('vbr')),
+                    'abr': int(m.group('abr')),
+                    'ext': m.group('ext'),
+                    'width': int(m.group('width')),
+                    'height': int(m.group('height')),
+                })
         self._sort_formats(formats)
 
         track = video_info['title']
@@ -376,17 +269,15 @@ class VevoIE(VevoBaseIE):
         else:
             age_limit = None
 
-        duration = video_info.get('duration')
-
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
             'thumbnail': video_info.get('imageUrl') or video_info.get('thumbnailUrl'),
-            'timestamp': timestamp,
+            'timestamp': parse_iso8601(video_info.get('releaseDate')),
             'uploader': uploader,
-            'duration': duration,
-            'view_count': view_count,
+            'duration': int_or_none(video_info.get('duration')),
+            'view_count': int_or_none(video_info.get('views', {}).get('total')),
             'age_limit': age_limit,
             'track': track,
             'artist': uploader,

youtube_dl/extractor/vimeo.py

@@ -21,12 +21,12 @@ from ..utils import (
     sanitized_Request,
     smuggle_url,
     std_headers,
-    unified_strdate,
+    try_get,
+    unified_timestamp,
     unsmuggle_url,
     urlencode_postdata,
     unescapeHTML,
     parse_filesize,
-    try_get,
 )
 
 
@@ -142,10 +142,19 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                         note='Downloading %s m3u8 information' % cdn_name,
                         fatal=False))
                 elif files_type == 'dash':
-                    formats.extend(self._extract_mpd_formats(
-                        manifest_url.replace('/master.json', '/master.mpd'), video_id, format_id,
-                        'Downloading %s MPD information' % cdn_name,
-                        fatal=False))
+                    mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
+                    mpd_manifest_urls = []
+                    if re.search(mpd_pattern, manifest_url):
+                        for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
+                            mpd_manifest_urls.append((format_id + suffix, re.sub(
+                                mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
+                    else:
+                        mpd_manifest_urls = [(format_id, manifest_url)]
+                    for f_id, m_url in mpd_manifest_urls:
+                        formats.extend(self._extract_mpd_formats(
+                            m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
+                            'Downloading %s MPD information' % cdn_name,
+                            fatal=False))
 
         subtitles = {}
         text_tracks = config['request'].get('text_tracks')
@@ -204,11 +213,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
+                'timestamp': 1355990239,
                 'upload_date': '20121220',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
                 'uploader_id': 'user7108434',
                 'uploader': 'Filippo Valsorda',
                 'duration': 10,
+                'license': 'by-sa',
             },
         },
         {
@@ -249,12 +260,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'id': '68375962',
                 'ext': 'mp4',
                 'title': 'youtube-dl password protected test video',
+                'timestamp': 1371200155,
                 'upload_date': '20130614',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
                 'uploader_id': 'user18948128',
                 'uploader': 'Jaime Marquínez Ferrándiz',
                 'duration': 10,
-                'description': 'This is "youtube-dl password protected test video" by  on Vimeo, the home for high quality videos and the people who love them.',
+                'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
             },
             'params': {
                 'videopassword': 'youtube-dl',
@@ -271,7 +283,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
                 'uploader_id': 'atencio',
                 'uploader': 'Peter Atencio',
-                'upload_date': '20130927',
+                'timestamp': 1380339469,
+                'upload_date': '20130928',
                 'duration': 187,
             },
         },
@@ -283,6 +296,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'The New Vimeo Player (You Know, For Videos)',
                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
+                'timestamp': 1381846109,
                 'upload_date': '20131015',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
                 'uploader_id': 'staff',
@@ -306,7 +320,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         {
             # contains original format
             'url': 'https://vimeo.com/33951933',
-            'md5': '2d9f5475e0537f013d0073e812ab89e6',
+            'md5': '53c688fa95a55bf4b7293d37a89c5c53',
             'info_dict': {
                 'id': '33951933',
                 'ext': 'mp4',
@@ -314,6 +328,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'uploader': 'The DMCI',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
                 'uploader_id': 'dmci',
+                'timestamp': 1324343742,
                 'upload_date': '20111220',
                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
             },
@@ -324,11 +339,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'url': 'https://vimeo.com/channels/tributes/6213729',
             'info_dict': {
                 'id': '6213729',
-                'ext': 'mp4',
+                'ext': 'mov',
                 'title': 'Vimeo Tribute: The Shining',
                 'uploader': 'Casey Donahue',
                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
                 'uploader_id': 'caseydonahue',
+                'timestamp': 1250886430,
                 'upload_date': '20090821',
                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
             },
@@ -338,7 +354,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'expected_warnings': ['Unable to download JSON metadata'],
         },
         {
-            # redirects to ondemand extractor and should be passed throught it
+            # redirects to ondemand extractor and should be passed through it
             # for successful extraction
             'url': 'https://vimeo.com/73445910',
             'info_dict': {
@@ -477,6 +493,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
                     expected=True)
 
+        cc_license = None
+        timestamp = None
+
         # Extract the config JSON
         try:
             try:
@@ -490,8 +509,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
                     vimeo_clip_page_config = self._search_regex(
                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
                         'vimeo clip page config')
-                    config_url = self._parse_json(
-                        vimeo_clip_page_config, video_id)['player']['config_url']
+                    page_config = self._parse_json(vimeo_clip_page_config, video_id)
+                    config_url = page_config['player']['config_url']
+                    cc_license = page_config.get('cc_license')
+                    timestamp = try_get(
+                        page_config, lambda x: x['clip']['uploaded_on'],
+                        compat_str)
                 config_json = self._download_webpage(config_url, video_id)
                 config = json.loads(config_json)
             except RegexNotFoundError:
@@ -560,10 +583,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
             self._downloader.report_warning('Cannot find video description')
 
         # Extract upload date
-        video_upload_date = None
-        mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
-        if mobj is not None:
-            video_upload_date = unified_strdate(mobj.group(1))
+        if not timestamp:
+            timestamp = self._search_regex(
+                r'<time[^>]+datetime="([^"]+)"', webpage,
+                'timestamp', default=None)
 
         try:
             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
@@ -600,15 +623,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
         info_dict = self._parse_config(config, video_id)
         formats.extend(info_dict['formats'])
         self._vimeo_sort_formats(formats)
+
+        if not cc_license:
+            cc_license = self._search_regex(
+                r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
+                webpage, 'license', default=None, group='license')
+
         info_dict.update({
             'id': video_id,
             'formats': formats,
-            'upload_date': video_upload_date,
+            'timestamp': unified_timestamp(timestamp),
             'description': video_description,
             'webpage_url': url,
             'view_count': view_count,
             'like_count': like_count,
             'comment_count': comment_count,
+            'license': cc_license,
         })
 
         return info_dict
@@ -629,6 +659,9 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor):
             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
             'uploader_id': 'gumfilms',
         },
+        'params': {
+            'format': 'best[protocol=https]',
+        },
     }, {
         # requires Referer to be passed along with og:video:url
         'url': 'https://vimeo.com/ondemand/36938/126682985',
@@ -727,12 +760,12 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
             # Try extracting href first since not all videos are available via
             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
             clips = re.findall(
-                r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage)
+                r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
             if clips:
-                for video_id, video_url in clips:
+                for video_id, video_url, video_title in clips:
                     yield self.url_result(
                         compat_urlparse.urljoin(base_url, video_url),
-                        VimeoIE.ie_key(), video_id=video_id)
+                        VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
             # More relaxed fallback
             else:
                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
@@ -881,10 +914,14 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
 
     def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
         webpage = self._download_webpage(webpage_url, video_id)
-        data = self._parse_json(self._search_regex(
-            r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
-            default=NO_DEFAULT if video_password_verified else '{}'), video_id)
-        config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
+        config_url = self._html_search_regex(
+            r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'config URL', default=None, group='url')
+        if not config_url:
+            data = self._parse_json(self._search_regex(
+                r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
+                default=NO_DEFAULT if video_password_verified else '{}'), video_id)
+            config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
         if config_url is None:
             self._verify_video_password(webpage_url, video_id, webpage)
             config_url = self._get_config_url(

youtube_dl/extractor/vlive.py

@@ -2,17 +2,23 @@
 from __future__ import unicode_literals
 
 import re
+import time
+import itertools
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_urlencode,
+    compat_str,
+)
 from ..utils import (
     dict_get,
     ExtractorError,
     float_or_none,
     int_or_none,
     remove_start,
+    try_get,
     urlencode_postdata,
 )
-from ..compat import compat_urllib_parse_urlencode
 
 
 class VLiveIE(InfoExtractor):
@@ -169,3 +175,89 @@ class VLiveIE(InfoExtractor):
             'subtitles': subtitles,
         })
         return info
+
+
+class VLiveChannelIE(InfoExtractor):
+    IE_NAME = 'vlive:channel'
+    _VALID_URL = r'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)'
+    _TEST = {
+        'url': 'http://channels.vlive.tv/FCD4B',
+        'info_dict': {
+            'id': 'FCD4B',
+            'title': 'MAMAMOO',
+        },
+        'playlist_mincount': 110
+    }
+    _APP_ID = '8c6cc7b45d2568fb668be6e05b6e5a3b'
+
+    def _real_extract(self, url):
+        channel_code = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://channels.vlive.tv/%s/video' % channel_code, channel_code)
+
+        app_id = None
+
+        app_js_url = self._search_regex(
+            r'<script[^>]+src=(["\'])(?P<url>http.+?/app\.js.*?)\1',
+            webpage, 'app js', default=None, group='url')
+
+        if app_js_url:
+            app_js = self._download_webpage(
+                app_js_url, channel_code, 'Downloading app JS', fatal=False)
+            if app_js:
+                app_id = self._search_regex(
+                    r'Global\.VFAN_APP_ID\s*=\s*[\'"]([^\'"]+)[\'"]',
+                    app_js, 'app id', default=None)
+
+        app_id = app_id or self._APP_ID
+
+        channel_info = self._download_json(
+            'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode',
+            channel_code, note='Downloading decode channel code',
+            query={
+                'app_id': app_id,
+                'channelCode': channel_code,
+                '_': int(time.time())
+            })
+
+        channel_seq = channel_info['result']['channelSeq']
+        channel_name = None
+        entries = []
+
+        for page_num in itertools.count(1):
+            video_list = self._download_json(
+                'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList',
+                channel_code, note='Downloading channel list page #%d' % page_num,
+                query={
+                    'app_id': app_id,
+                    'channelSeq': channel_seq,
+                    'maxNumOfRows': 1000,
+                    '_': int(time.time()),
+                    'pageNo': page_num
+                }
+            )
+
+            if not channel_name:
+                channel_name = try_get(
+                    video_list,
+                    lambda x: x['result']['channelInfo']['channelName'],
+                    compat_str)
+
+            videos = try_get(
+                video_list, lambda x: x['result']['videoList'], list)
+            if not videos:
+                break
+
+            for video in videos:
+                video_id = video.get('videoSeq')
+                if not video_id:
+                    continue
+                video_id = compat_str(video_id)
+                entries.append(
+                    self.url_result(
+                        'http://www.vlive.tv/video/%s' % video_id,
+                        ie=VLiveIE.ie_key(), video_id=video_id))
+
+        return self.playlist_result(
+            entries, channel_code, channel_name)

youtube_dl/extractor/xiami.py

@@ -16,7 +16,9 @@ class XiamiBaseIE(InfoExtractor):
         return webpage
 
     def _extract_track(self, track, track_id=None):
-        title = track['title']
+        track_name = track.get('songName') or track.get('name') or track['subName']
+        artist = track.get('artist') or track.get('artist_name') or track.get('singers')
+        title = '%s - %s' % (artist, track_name) if artist else track_name
         track_url = self._decrypt(track['location'])
 
         subtitles = {}
@@ -31,9 +33,10 @@ class XiamiBaseIE(InfoExtractor):
             'thumbnail': track.get('pic') or track.get('album_pic'),
             'duration': int_or_none(track.get('length')),
             'creator': track.get('artist', '').split(';')[0],
-            'track': title,
-            'album': track.get('album_name'),
-            'artist': track.get('artist'),
+            'track': track_name,
+            'track_number': int_or_none(track.get('track')),
+            'album': track.get('album_name') or track.get('title'),
+            'artist': artist,
             'subtitles': subtitles,
         }
 
@@ -68,14 +71,14 @@ class XiamiBaseIE(InfoExtractor):
 class XiamiSongIE(XiamiBaseIE):
     IE_NAME = 'xiami:song'
     IE_DESC = '虾米音乐'
-    _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?xiami\.com/song/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.xiami.com/song/1775610518',
         'md5': '521dd6bea40fd5c9c69f913c232cb57e',
         'info_dict': {
             'id': '1775610518',
             'ext': 'mp3',
-            'title': 'Woman',
+            'title': 'HONNE - Woman',
             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
             'duration': 265,
             'creator': 'HONNE',
@@ -95,7 +98,7 @@ class XiamiSongIE(XiamiBaseIE):
         'info_dict': {
             'id': '1775256504',
             'ext': 'mp3',
-            'title': '悟空',
+            'title': '戴荃 - 悟空',
             'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
             'duration': 200,
             'creator': '戴荃',
@@ -109,6 +112,26 @@ class XiamiSongIE(XiamiBaseIE):
             },
         },
         'skip': 'Georestricted',
+    }, {
+        'url': 'http://www.xiami.com/song/1775953850',
+        'info_dict': {
+            'id': '1775953850',
+            'ext': 'mp3',
+            'title': 'До Скону - Чума Пожирает Землю',
+            'thumbnail': r're:http://img\.xiami\.net/images/album/.*\.jpg',
+            'duration': 683,
+            'creator': 'До Скону',
+            'track': 'Чума Пожирает Землю',
+            'track_number': 7,
+            'album': 'Ад',
+            'artist': 'До Скону',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.xiami.com/song/xLHGwgd07a1',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -124,7 +147,7 @@ class XiamiPlaylistBaseIE(XiamiBaseIE):
 class XiamiAlbumIE(XiamiPlaylistBaseIE):
     IE_NAME = 'xiami:album'
     IE_DESC = '虾米音乐 - 专辑'
-    _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?xiami\.com/album/(?P<id>[^/?#&]+)'
     _TYPE = '1'
     _TESTS = [{
         'url': 'http://www.xiami.com/album/2100300444',
@@ -136,28 +159,34 @@ class XiamiAlbumIE(XiamiPlaylistBaseIE):
     }, {
         'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
         'only_matching': True,
+    }, {
+        'url': 'http://www.xiami.com/album/URVDji2a506',
+        'only_matching': True,
     }]
 
 
 class XiamiArtistIE(XiamiPlaylistBaseIE):
     IE_NAME = 'xiami:artist'
     IE_DESC = '虾米音乐 - 歌手'
-    _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?xiami\.com/artist/(?P<id>[^/?#&]+)'
     _TYPE = '2'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.xiami.com/artist/2132?spm=0.0.0.0.dKaScp',
         'info_dict': {
             'id': '2132',
         },
         'playlist_count': 20,
         'skip': 'Georestricted',
-    }
+    }, {
+        'url': 'http://www.xiami.com/artist/bC5Tk2K6eb99',
+        'only_matching': True,
+    }]
 
 
 class XiamiCollectionIE(XiamiPlaylistBaseIE):
     IE_NAME = 'xiami:collection'
     IE_DESC = '虾米音乐 - 精选集'
-    _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?xiami\.com/collect/(?P<id>[^/?#&]+)'
     _TYPE = '3'
     _TEST = {
         'url': 'http://www.xiami.com/collect/156527391?spm=a1z1s.2943601.6856193.12.4jpBnr',

youtube_dl/extractor/yourupload.py

@@ -2,44 +2,37 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import urljoin
 
 
 class YourUploadIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?
-        (?:yourupload\.com/watch|
-           embed\.yourupload\.com|
-           embed\.yucache\.net
-        )/(?P<id>[A-Za-z0-9]+)
-        '''
-    _TESTS = [
-        {
-            'url': 'http://yourupload.com/watch/14i14h',
-            'md5': '5e2c63385454c557f97c4c4131a393cd',
-            'info_dict': {
-                'id': '14i14h',
-                'ext': 'mp4',
-                'title': 'BigBuckBunny_320x180.mp4',
-                'thumbnail': r're:^https?://.*\.jpe?g',
-            }
-        },
-        {
-            'url': 'http://embed.yourupload.com/14i14h',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://embed.yucache.net/14i14h?client_file_id=803349',
-            'only_matching': True,
-        },
-    ]
+    _VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://yourupload.com/watch/14i14h',
+        'md5': '5e2c63385454c557f97c4c4131a393cd',
+        'info_dict': {
+            'id': '14i14h',
+            'ext': 'mp4',
+            'title': 'BigBuckBunny_320x180.mp4',
+            'thumbnail': r're:^https?://.*\.jpe?g',
+        }
+    }, {
+        'url': 'http://www.yourupload.com/embed/14i14h',
+        'only_matching': True,
+    }, {
+        'url': 'http://embed.yourupload.com/14i14h',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        embed_url = 'http://embed.yucache.net/{0:}'.format(video_id)
+        embed_url = 'http://www.yourupload.com/embed/%s' % video_id
+
         webpage = self._download_webpage(embed_url, video_id)
 
         title = self._og_search_title(webpage)
-        video_url = self._og_search_video_url(webpage)
+        video_url = urljoin(embed_url, self._og_search_video_url(webpage))
         thumbnail = self._og_search_thumbnail(webpage, default=None)
 
         return {

youtube_dl/extractor/youtube.py

@@ -40,6 +40,7 @@ from ..utils import (
     sanitized_Request,
     smuggle_url,
     str_to_int,
+    try_get,
     unescapeHTML,
     unified_strdate,
     unsmuggle_url,
@@ -316,6 +317,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
         '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},  # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
         '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
+        '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
         '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
         '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
         '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
@@ -382,6 +384,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
                 'tags': ['youtube-dl'],
+                'duration': 10,
                 'like_count': int,
                 'dislike_count': int,
                 'start_time': 1,
@@ -401,6 +404,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
                          'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
                          'iconic ep', 'iconic', 'love', 'it'],
+                'duration': 180,
                 'uploader': 'Icona Pop',
                 'uploader_id': 'IconaPop',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
@@ -418,6 +422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
                 'alt_title': 'Tunnel Vision',
                 'description': 'md5:64249768eec3bc4276236606ea996373',
+                'duration': 419,
                 'uploader': 'justintimberlakeVEVO',
                 'uploader_id': 'justintimberlakeVEVO',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
@@ -457,6 +462,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'description': 'test chars:  "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
                 'categories': ['Science & Technology'],
                 'tags': ['youtube-dl'],
+                'duration': 10,
                 'like_count': int,
                 'dislike_count': int,
             },
@@ -492,6 +498,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'm4a',
                 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
                 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
+                'duration': 244,
                 'uploader': 'AfrojackVEVO',
                 'uploader_id': 'AfrojackVEVO',
                 'upload_date': '20131011',
@@ -511,6 +518,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': 'Taylor Swift - Shake It Off',
                 'alt_title': 'Shake It Off',
                 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
+                'duration': 242,
                 'uploader': 'TaylorSwiftVEVO',
                 'uploader_id': 'TaylorSwiftVEVO',
                 'upload_date': '20140818',
@@ -528,6 +536,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': 'T4XJQO3qol8',
                 'ext': 'mp4',
+                'duration': 219,
                 'upload_date': '20100909',
                 'uploader': 'The Amazing Atheist',
                 'uploader_id': 'TheAmazingAtheist',
@@ -545,6 +554,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
                 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
+                'duration': 142,
                 'uploader': 'The Witcher',
                 'uploader_id': 'WitcherGame',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
@@ -561,6 +571,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
                 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
+                'duration': 247,
                 'uploader': 'LloydVEVO',
                 'uploader_id': 'LloydVEVO',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
@@ -575,6 +586,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': '__2ABJjxzNo',
                 'ext': 'mp4',
+                'duration': 266,
                 'upload_date': '20100430',
                 'uploader_id': 'deadmau5',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
@@ -595,6 +607,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'info_dict': {
                 'id': 'lqQg6PlCWgI',
                 'ext': 'mp4',
+                'duration': 6085,
                 'upload_date': '20150827',
                 'uploader_id': 'olympic',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
@@ -614,6 +627,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': '_b-2C3KPAM0',
                 'ext': 'mp4',
                 'stretched_ratio': 16 / 9.,
+                'duration': 85,
                 'upload_date': '20110310',
                 'uploader_id': 'AllenMeow',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
@@ -648,6 +662,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'md5:7b81415841e02ecd4313668cde88737a',
                 'description': 'md5:116377fd2963b81ec4ce64b542173306',
+                'duration': 220,
                 'upload_date': '20150625',
                 'uploader_id': 'dorappi2000',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
@@ -690,6 +705,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7335,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -702,6 +718,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7337,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -714,6 +731,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7337,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -726,6 +744,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'ext': 'mp4',
                     'title': 'teamPGP: Rocket League Noob Stream (zim)',
                     'description': 'md5:dc7872fb300e143831327f1bae3af010',
+                    'duration': 7334,
                     'upload_date': '20150721',
                     'uploader': 'Beer Games Beer',
                     'uploader_id': 'beergamesbeer',
@@ -767,6 +786,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
                 'alt_title': 'Dark Walk',
                 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
+                'duration': 133,
                 'upload_date': '20151119',
                 'uploader_id': 'IronSoulElf',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
@@ -808,10 +828,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
                 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
+                'duration': 721,
                 'upload_date': '20150127',
                 'uploader_id': 'BerkmanCenter',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
-                'uploader': 'BerkmanCenter',
+                'uploader': 'The Berkman Klein Center for Internet & Society',
                 'license': 'Creative Commons Attribution license (reuse allowed)',
             },
             'params': {
@@ -826,6 +847,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
                 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
+                'duration': 4060,
                 'upload_date': '20151119',
                 'uploader': 'Bernie 2016',
                 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
@@ -862,6 +884,36 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'params': {
                 'skip_download': True,
             },
+        },
+        {
+            # YouTube Red video with episode data
+            'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
+            'info_dict': {
+                'id': 'iqKdEhx-dD4',
+                'ext': 'mp4',
+                'title': 'Isolation - Mind Field (Ep 1)',
+                'description': 'md5:8013b7ddea787342608f63a13ddc9492',
+                'duration': 2085,
+                'upload_date': '20170118',
+                'uploader': 'Vsauce',
+                'uploader_id': 'Vsauce',
+                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
+                'license': 'Standard YouTube License',
+                'series': 'Mind Field',
+                'season_number': 1,
+                'episode_number': 1,
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': [
+                'Skipping DASH manifest',
+            ],
+        },
+        {
+            # itag 212
+            'url': '1t24XAntNCY',
+            'only_matching': True,
         }
     ]
 
@@ -976,8 +1028,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _parse_sig_js(self, jscode):
         funcname = self._search_regex(
-            r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
-            'Initial JS player signature function name')
+            (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
+            jscode, 'Initial JS player signature function name', group='sig')
 
         jsi = JSInterpreter(jscode)
         initial_function = jsi.extract_function(funcname)
@@ -998,6 +1051,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         if player_url.startswith('//'):
             player_url = 'https:' + player_url
+        elif not re.match(r'https?://', player_url):
+            player_url = compat_urlparse.urljoin(
+                'https://www.youtube.com', player_url)
         try:
             player_id = (player_url, self._signature_cache_id(s))
             if player_id not in self._player_cache:
@@ -1448,6 +1504,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             video_alt_title = video_creator = None
 
+        m_episode = re.search(
+            r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
+            video_webpage)
+        if m_episode:
+            series = m_episode.group('series')
+            season_number = int(m_episode.group('season'))
+            episode_number = int(m_episode.group('episode'))
+        else:
+            series = season_number = episode_number = None
+
         m_cat_container = self._search_regex(
             r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
             video_webpage, 'categories', default=None)
@@ -1476,11 +1542,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_subtitles = self.extract_subtitles(video_id, video_webpage)
         automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
 
-        if 'length_seconds' not in video_info:
-            self._downloader.report_warning('unable to extract video duration')
-            video_duration = None
-        else:
-            video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
+        video_duration = try_get(
+            video_info, lambda x: int_or_none(x['length_seconds'][0]))
+        if not video_duration:
+            video_duration = parse_duration(self._html_search_meta(
+                'duration', video_webpage, 'video duration'))
 
         # annotations
         video_annotations = None
@@ -1737,6 +1803,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'is_live': is_live,
             'start_time': start_time,
             'end_time': end_time,
+            'series': series,
+            'season_number': season_number,
+            'episode_number': episode_number,
         }
 
 
@@ -1813,6 +1882,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             'title': 'YDL_Empty_List',
         },
         'playlist_count': 0,
+        'skip': 'This playlist is private',
     }, {
         'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
         'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
@@ -1844,6 +1914,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
         },
         'playlist_count': 2,
+        'skip': 'This playlist is private',
     }, {
         'note': 'embedded',
         'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
@@ -1955,14 +2026,18 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
         url = self._TEMPLATE_URL % playlist_id
         page = self._download_webpage(url, playlist_id)
 
-        for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
+        # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604)
+        for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
             match = match.strip()
             # Check if the playlist exists or is private
-            if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
-                raise ExtractorError(
-                    'The playlist doesn\'t exist or is private, use --username or '
-                    '--netrc to access it.',
-                    expected=True)
+            mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
+            if mobj:
+                reason = mobj.group('reason')
+                message = 'This playlist %s' % reason
+                if 'private' in reason:
+                    message += ', use --username or --netrc to access it'
+                message += '.'
+                raise ExtractorError(message, expected=True)
             elif re.match(r'[^<]*Invalid parameters[^<]*', match):
                 raise ExtractorError(
                     'Invalid parameters. Maybe URL is incorrect.',

youtube_dl/jsinterp.py

@@ -213,7 +213,7 @@ class JSInterpreter(object):
     def extract_object(self, objname):
         obj = {}
         obj_m = re.search(
-            (r'(?:var\s+)?%s\s*=\s*\{' % re.escape(objname)) +
+            (r'(?<!this\.)%s\s*=\s*\{' % re.escape(objname)) +
             r'\s*(?P<fields>([a-zA-Z$0-9]+\s*:\s*function\(.*?\)\s*\{.*?\}(?:,\s*)?)*)' +
             r'\}\s*;',
             self.code)

youtube_dl/options.py

@@ -216,23 +216,23 @@ def parseOpts(overrideArguments=None):
     network.add_option(
         '--source-address',
         metavar='IP', dest='source_address', default=None,
-        help='Client-side IP address to bind to (experimental)',
+        help='Client-side IP address to bind to',
     )
     network.add_option(
         '-4', '--force-ipv4',
         action='store_const', const='0.0.0.0', dest='source_address',
-        help='Make all connections via IPv4 (experimental)',
+        help='Make all connections via IPv4',
     )
     network.add_option(
         '-6', '--force-ipv6',
         action='store_const', const='::', dest='source_address',
-        help='Make all connections via IPv6 (experimental)',
+        help='Make all connections via IPv6',
     )
     network.add_option(
         '--geo-verification-proxy',
         dest='geo_verification_proxy', default=None, metavar='URL',
         help='Use this proxy to verify the IP address for some geo-restricted sites. '
-        'The default proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading. (experimental)'
+        'The default proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading.'
     )
     network.add_option(
         '--cn-verification-proxy',
@@ -297,7 +297,7 @@ def parseOpts(overrideArguments=None):
         '--match-filter',
         metavar='FILTER', dest='match_filter', default=None,
         help=(
-            'Generic video filter (experimental). '
+            'Generic video filter. '
             'Specify any key (see help for -o for a list of available keys) to'
             ' match if the key is present, '
             '!key to check if the key is not present,'
@@ -450,7 +450,7 @@ def parseOpts(overrideArguments=None):
         '--skip-unavailable-fragments',
         action='store_true', dest='skip_unavailable_fragments', default=True,
         help='Skip unavailable fragments (DASH and hlsnative only)')
-    general.add_option(
+    downloader.add_option(
         '--abort-on-unavailable-fragment',
         action='store_false', dest='skip_unavailable_fragments',
         help='Abort downloading when some fragment is not available')
@@ -661,8 +661,12 @@ def parseOpts(overrideArguments=None):
         help=('Output filename template, see the "OUTPUT TEMPLATE" for all the info'))
     filesystem.add_option(
         '--autonumber-size',
-        dest='autonumber_size', metavar='NUMBER',
-        help='Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
+        dest='autonumber_size', metavar='NUMBER', default=5, type=int,
+        help='Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given (default is %default)')
+    filesystem.add_option(
+        '--autonumber-start',
+        dest='autonumber_start', metavar='NUMBER', default=1, type=int,
+        help='Specify the start value for %(autonumber)s (default is %default)')
     filesystem.add_option(
         '--restrict-filenames',
         action='store_true', dest='restrictfilenames', default=False,
@@ -751,7 +755,7 @@ def parseOpts(overrideArguments=None):
         help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
     postproc.add_option(
         '--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-        help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default')
+        help='Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default; No effect without -x')
     postproc.add_option(
         '--audio-quality', metavar='QUALITY',
         dest='audioquality', default='5',
@@ -867,7 +871,7 @@ def parseOpts(overrideArguments=None):
             if '--ignore-config' not in system_conf:
                 user_conf = _readUserConf()
 
-        argv = system_conf + user_conf + command_line_conf
+        argv = system_conf + user_conf + custom_conf + command_line_conf
         opts, args = parser.parse_args(argv)
         if opts.verbose:
             for conf_label, conf in (

youtube_dl/utils.py

@@ -128,7 +128,13 @@ DATE_FORMATS = (
     '%d %B %Y',
     '%d %b %Y',
     '%B %d %Y',
+    '%B %dst %Y',
+    '%B %dnd %Y',
+    '%B %dth %Y',
     '%b %d %Y',
+    '%b %dst %Y',
+    '%b %dnd %Y',
+    '%b %dth %Y',
     '%b %dst %Y %I:%M',
     '%b %dnd %Y %I:%M',
     '%b %dth %Y %I:%M',
@@ -137,6 +143,7 @@ DATE_FORMATS = (
     '%Y/%m/%d',
     '%Y/%m/%d %H:%M',
     '%Y/%m/%d %H:%M:%S',
+    '%Y-%m-%d %H:%M',
     '%Y-%m-%d %H:%M:%S',
     '%Y-%m-%d %H:%M:%S.%f',
     '%d.%m.%Y %H:%M',
@@ -1766,7 +1773,7 @@ def parse_duration(s):
     s = s.strip()
 
     days, hours, mins, secs, ms = [None] * 5
-    m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?$', s)
+    m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
     if m:
         days, hours, mins, secs, ms = m.groups()
     else:
@@ -1783,11 +1790,11 @@ def parse_duration(s):
                 )?
                 (?:
                     (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
-                )?$''', s)
+                )?Z?$''', s)
         if m:
             days, hours, mins, secs, ms = m.groups()
         else:
-            m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)$', s)
+            m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
             if m:
                 hours, mins = m.groups()
             else:

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.01.08'
+__version__ = '2017.02.01'