release 2018.01.18

[ci skip]

.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 *2018.01.07*. 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 Issues with outdated version will be rejected.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 **2018.01.07**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.01.18*. 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 Issues with outdated version will be rejected.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 **2018.01.18**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2018.01.07
+[debug] youtube-dl version 2018.01.18
 [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

@@ -231,3 +231,5 @@ John Dong
 Tatsuyuki Ishi
 Daniel Weber
 Kay Bouché
+Yang Hongbo
+Lei Wang

ChangeLog

@@ -1,3 +1,34 @@
+version 2018.01.18
+
+Extractors
+* [soundcloud] Update client id (#15306)
+- [kamcord] Remove extractor (#15322)
++ [spiegel] Add support for nexx videos (#15285)
+* [twitch] Fix authentication and error capture (#14090, #15264)
+* [vk] Detect more errors due to copyright complaints (#15259)
+
+
+version 2018.01.14
+
+Extractors
+* [youtube] Fix live streams extraction (#15202)
+* [wdr] Bypass geo restriction
+* [wdr] Rework extractors (#14598)
++ [wdr] Add support for wdrmaus.de/elefantenseite (#14598)
++ [gamestar] Add support for gamepro.de (#3384)
+* [viafree] Skip rtmp formats (#15232)
++ [pandoratv] Add support for mobile URLs (#12441)
++ [pandoratv] Add support for new URL format (#15131)
++ [ximalaya] Add support for ximalaya.com (#14687)
++ [digg] Add support for digg.com (#15214)
+* [limelight] Tolerate empty pc formats (#15150, #15151, #15207)
+* [ndr:embed:base] Make separate formats extraction non fatal (#15203)
++ [weibo] Add extractor (#15079)
++ [ok] Add support for live streams
+* [canalplus] Fix extraction (#15072)
+* [bilibili] Fix extraction (#15188)
+
+
 version 2018.01.07
 
 Core

README.md

@@ -46,7 +46,7 @@ Or with [MacPorts](https://www.macports.org/):
 Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
-**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
+**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
 
     youtube-dl [OPTIONS] URL [URL...]
 
@@ -863,7 +863,7 @@ 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 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.
+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, macOS, 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

@@ -128,7 +128,7 @@
  - **CamdemyFolder**
  - **CamWithHer**
  - **canalc2.tv**
- - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
+ - **Canalplus**: mycanal.fr and piwiplus.fr
  - **Canvas**
  - **CanvasEen**: canvas.be and een.be
  - **CarambaTV**
@@ -210,6 +210,7 @@
  - **defense.gouv.fr**
  - **democracynow**
  - **DHM**: Filmarchiv - Deutsches Historisches Museum
+ - **Digg**
  - **DigitallySpeaking**
  - **Digiteka**
  - **Discovery**
@@ -382,7 +383,6 @@
  - **JWPlatform**
  - **Kakao**
  - **Kaltura**
- - **Kamcord**
  - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
@@ -773,7 +773,6 @@
  - **Sport5**
  - **SportBoxEmbed**
  - **SportDeutschland**
- - **Sportschau**
  - **Sprout**
  - **sr:mediathek**: Saarländischer Rundfunk
  - **SRGSSR**
@@ -1002,10 +1001,14 @@
  - **WatchIndianPorn**: Watch Indian Porn
  - **WDR**
  - **wdr:mobile**
+ - **WDRElefant**
+ - **WDRPage**
  - **Webcaster**
  - **WebcasterFeed**
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
+ - **Weibo**
+ - **WeiboMobile**
  - **WeiqiTV**: WQTV
  - **wholecloud**: WholeCloud
  - **Wimp**
@@ -1025,6 +1028,8 @@
  - **xiami:artist**: 虾米音乐 - 歌手
  - **xiami:collection**: 虾米音乐 - 精选集
  - **xiami:song**: 虾米音乐
+ - **ximalaya**: 喜马拉雅FM
+ - **ximalaya:album**: 喜马拉雅FM 专辑
  - **XMinus**
  - **XNXX**
  - **Xstream**

youtube_dl/extractor/bilibili.py

@@ -102,6 +102,7 @@ class BiliBiliIE(InfoExtractor):
                     video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
             headers = {
                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'Referer': url
             }
             headers.update(self.geo_verification_headers())
 
@@ -116,10 +117,15 @@ class BiliBiliIE(InfoExtractor):
         payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
         sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
 
+        headers = {
+            'Referer': url
+        }
+        headers.update(self.geo_verification_headers())
+
         video_info = self._download_json(
             'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
             video_id, note='Downloading video info page',
-            headers=self.geo_verification_headers())
+            headers=headers)
 
         if 'durl' not in video_info:
             self._report_error(video_info)

youtube_dl/extractor/canalplus.py

@@ -4,59 +4,36 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
-    dict_get,
     # ExtractorError,
     # HEADRequest,
     int_or_none,
     qualities,
-    remove_end,
     unified_strdate,
 )
 
 
 class CanalplusIE(InfoExtractor):
-    IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
-    _VALID_URL = r'''(?x)
-                        https?://
-                            (?:
-                                (?:
-                                    (?:(?:www|m)\.)?canalplus\.fr|
-                                    (?:www\.)?piwiplus\.fr|
-                                    (?:www\.)?d8\.tv|
-                                    (?:www\.)?c8\.fr|
-                                    (?:www\.)?d17\.tv|
-                                    (?:(?:football|www)\.)?cstar\.fr|
-                                    (?:www\.)?itele\.fr
-                                )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
-                                player\.canalplus\.fr/#/(?P<id>\d+)
-                            )
-
-                    '''
+    IE_DESC = 'mycanal.fr and piwiplus.fr'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>mycanal|piwiplus)\.fr/(?:[^/]+/)*(?P<display_id>[^?/]+)(?:\.html\?.*\bvid=|/p/)(?P<id>\d+)'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
     _SITE_ID_MAP = {
-        'canalplus': 'cplus',
+        'mycanal': 'cplus',
         'piwiplus': 'teletoon',
-        'd8': 'd8',
-        'c8': 'd8',
-        'd17': 'd17',
-        'cstar': 'd17',
-        'itele': 'itele',
     }
 
     # Only works for direct mp4 URLs
     _GEO_COUNTRIES = ['FR']
 
     _TESTS = [{
-        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
+        'url': 'https://www.mycanal.fr/d17-emissions/lolywood/p/1397061',
         'info_dict': {
-            'id': '1405510',
-            'display_id': 'pid1830-c-zapping',
+            'id': '1397061',
+            'display_id': 'lolywood',
             'ext': 'mp4',
-            'title': 'Zapping - 02/07/2016',
-            'description': 'Le meilleur de toutes les chaînes, tous les jours',
-            'upload_date': '20160702',
+            'title': 'Euro 2016 : Je préfère te prévenir - Lolywood - Episode 34',
+            'description': 'md5:7d97039d455cb29cdba0d652a0efaa5e',
+            'upload_date': '20160602',
         },
     }, {
         # geo restricted, bypassed
@@ -70,64 +47,12 @@ class CanalplusIE(InfoExtractor):
             'upload_date': '20140724',
         },
         'expected_warnings': ['HTTP Error 403: Forbidden'],
-    }, {
-        # geo restricted, bypassed
-        'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684',
-        'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d',
-        'info_dict': {
-            'id': '1443684',
-            'display_id': 'pid6318-videos-integrales',
-            'ext': 'mp4',
-            'title': 'Guess my iep ! - TPMP - 07/04/2017',
-            'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa',
-            'upload_date': '20170407',
-        },
-        'expected_warnings': ['HTTP Error 403: Forbidden'],
-    }, {
-        'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
-        'info_dict': {
-            'id': '1420176',
-            'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
-            'ext': 'mp4',
-            'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
-            'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
-            'upload_date': '20161014',
-        },
-    }, {
-        'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
-        'info_dict': {
-            'id': '1416769',
-            'display_id': 'pid7566-feminines-videos',
-            'ext': 'mp4',
-            'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
-            'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
-            'upload_date': '20160921',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://m.canalplus.fr/?vid=1398231',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        site, display_id, video_id = re.match(self._VALID_URL, url).groups()
 
-        site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
-
-        # Beware, some subclasses do not define an id group
-        display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')
-
-        webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(
-            [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
-             r'id=["\']canal_video_player(?P<id>\d+)',
-             r'data-video=["\'](?P<id>\d+)'],
-            webpage, 'video id', default=mobj.group('vid'), group='id')
+        site_id = self._SITE_ID_MAP[site]
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
@@ -161,7 +86,7 @@ class CanalplusIE(InfoExtractor):
                     format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
             else:
                 formats.append({
-                    # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
+                    # the secret extracted from ya function in http://player.canalplus.fr/common/js/canalPlayer.js
                     'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
                     'format_id': format_id,
                     'preference': preference(format_id),

youtube_dl/extractor/digg.py

@@ -0,0 +1,56 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class DiggIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?digg\.com/video/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        # JWPlatform via provider
+        'url': 'http://digg.com/video/sci-fi-short-jonah-daniel-kaluuya-get-out',
+        'info_dict': {
+            'id': 'LcqvmS0b',
+            'ext': 'mp4',
+            'title': "'Get Out' Star Daniel Kaluuya Goes On 'Moby Dick'-Like Journey In Sci-Fi Short 'Jonah'",
+            'description': 'md5:541bb847648b6ee3d6514bc84b82efda',
+            'upload_date': '20180109',
+            'timestamp': 1515530551,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # Youtube via provider
+        'url': 'http://digg.com/video/dog-boat-seal-play',
+        'only_matching': True,
+    }, {
+        # vimeo as regular embed
+        'url': 'http://digg.com/video/dream-girl-short-film',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        info = self._parse_json(
+            self._search_regex(
+                r'(?s)video_info\s*=\s*({.+?});\n', webpage, 'video info',
+                default='{}'), display_id, transform_source=js_to_json,
+            fatal=False)
+
+        video_id = info.get('video_id')
+
+        if video_id:
+            provider = info.get('provider_name')
+            if provider == 'youtube':
+                return self.url_result(
+                    video_id, ie='Youtube', video_id=video_id)
+            elif provider == 'jwplayer':
+                return self.url_result(
+                    'jwplatform:%s' % video_id, ie='JWPlatform',
+                    video_id=video_id)
+
+        return self.url_result(url, 'Generic')

youtube_dl/extractor/extractors.py

@@ -259,6 +259,7 @@ from .deezer import DeezerPlaylistIE
 from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE
+from .digg import DiggIE
 from .dotsub import DotsubIE
 from .douyutv import (
     DouyuShowIE,
@@ -489,7 +490,6 @@ from .jwplatform import JWPlatformIE
 from .jpopsukitv import JpopsukiIE
 from .kakao import KakaoIE
 from .kaltura import KalturaIE
-from .kamcord import KamcordIE
 from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
@@ -990,7 +990,6 @@ from .stitcher import StitcherIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxEmbedIE
 from .sportdeutschland import SportDeutschlandIE
-from .sportschau import SportschauIE
 from .sprout import SproutIE
 from .srgssr import (
     SRGSSRIE,
@@ -1288,6 +1287,8 @@ from .watchbox import WatchBoxIE
 from .watchindianporn import WatchIndianPornIE
 from .wdr import (
     WDRIE,
+    WDRPageIE,
+    WDRElefantIE,
     WDRMobileIE,
 )
 from .webcaster import (
@@ -1298,6 +1299,10 @@ from .webofstories import (
     WebOfStoriesIE,
     WebOfStoriesPlaylistIE,
 )
+from .weibo import (
+    WeiboIE, 
+    WeiboMobileIE
+)
 from .weiqitv import WeiqiTVIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
@@ -1323,6 +1328,10 @@ from .xiami import (
     XiamiArtistIE,
     XiamiCollectionIE
 )
+from .ximalaya import (
+    XimalayaIE,
+    XimalayaAlbumIE
+)
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xstream import XstreamIE

youtube_dl/extractor/gamestar.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -9,27 +11,34 @@ from ..utils import (
 
 
 class GameStarIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?game(?P<site>pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html'
+    _TESTS = [{
         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
-        'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
+        'md5': 'ee782f1f8050448c95c5cacd63bc851c',
         'info_dict': {
             'id': '76110',
             'ext': 'mp4',
             'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
             'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
             'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1406542020,
+            'timestamp': 1406542380,
             'upload_date': '20140728',
-            'duration': 17
+            'duration': 17,
         }
-    }
+    }, {
+        'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.gamestar.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        site = mobj.group('site')
+        video_id = mobj.group('id')
 
-        url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
+        webpage = self._download_webpage(url, video_id)
 
         # TODO: there are multiple ld+json objects in the webpage,
         # while _search_json_ld finds only the first one
@@ -37,16 +46,17 @@ class GameStarIE(InfoExtractor):
             r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
             webpage, 'JSON-LD', group='json_ld'), video_id)
         info_dict = self._json_ld(json_ld, video_id)
-        info_dict['title'] = remove_end(info_dict['title'], ' - GameStar')
+        info_dict['title'] = remove_end(
+            info_dict['title'], ' - Game%s' % site.title())
 
-        view_count = json_ld.get('interactionCount')
+        view_count = int_or_none(json_ld.get('interactionCount'))
         comment_count = int_or_none(self._html_search_regex(
-            r'([0-9]+) Kommentare</span>', webpage, 'comment_count',
-            fatal=False))
+            r'<span>Kommentare</span>\s*<span[^>]+class=["\']count[^>]+>\s*\(\s*([0-9]+)',
+            webpage, 'comment count', fatal=False))
 
         info_dict.update({
             'id': video_id,
-            'url': url,
+            'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id,
             'ext': 'mp4',
             'view_count': view_count,
             'comment_count': comment_count

youtube_dl/extractor/kamcord.py

@@ -1,71 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    int_or_none,
-    qualities,
-)
-
-
-class KamcordIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?kamcord\.com/v/(?P<id>[^/?#&]+)'
-    _TEST = {
-        'url': 'https://www.kamcord.com/v/hNYRduDgWb4',
-        'md5': 'c3180e8a9cfac2e86e1b88cb8751b54c',
-        'info_dict': {
-            'id': 'hNYRduDgWb4',
-            'ext': 'mp4',
-            'title': 'Drinking Madness',
-            'uploader': 'jacksfilms',
-            'uploader_id': '3044562',
-            'view_count': int,
-            'like_count': int,
-            'comment_count': int,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        video = self._parse_json(
-            self._search_regex(
-                r'window\.__props\s*=\s*({.+?});?(?:\n|\s*</script)',
-                webpage, 'video'),
-            video_id)['video']
-
-        title = video['title']
-
-        formats = self._extract_m3u8_formats(
-            video['play']['hls'], video_id, 'mp4', entry_protocol='m3u8_native')
-        self._sort_formats(formats)
-
-        uploader = video.get('user', {}).get('username')
-        uploader_id = video.get('user', {}).get('id')
-
-        view_count = int_or_none(video.get('viewCount'))
-        like_count = int_or_none(video.get('heartCount'))
-        comment_count = int_or_none(video.get('messageCount'))
-
-        preference_key = qualities(('small', 'medium', 'large'))
-
-        thumbnails = [{
-            'url': thumbnail_url,
-            'id': thumbnail_id,
-            'preference': preference_key(thumbnail_id),
-        } for thumbnail_id, thumbnail_url in (video.get('thumbnail') or {}).items()
-            if isinstance(thumbnail_id, compat_str) and isinstance(thumbnail_url, compat_str)]
-
-        return {
-            'id': video_id,
-            'title': title,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'view_count': view_count,
-            'like_count': like_count,
-            'comment_count': comment_count,
-            'thumbnails': thumbnails,
-            'formats': formats,
-        }

youtube_dl/extractor/limelight.py

@@ -10,6 +10,7 @@ from ..utils import (
     float_or_none,
     int_or_none,
     smuggle_url,
+    try_get,
     unsmuggle_url,
     ExtractorError,
 )
@@ -220,6 +221,12 @@ class LimelightBaseIE(InfoExtractor):
             'subtitles': subtitles,
         }
 
+    def _extract_info_helper(self, pc, mobile, i, metadata):
+        return self._extract_info(
+            try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [],
+            try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [],
+            metadata)
+
 
 class LimelightMediaIE(LimelightBaseIE):
     IE_NAME = 'limelight'
@@ -282,10 +289,7 @@ class LimelightMediaIE(LimelightBaseIE):
             'getMobilePlaylistByMediaId', 'properties',
             smuggled_data.get('source_url'))
 
-        return self._extract_info(
-            pc['playlistItems'][0].get('streams', []),
-            mobile['mediaList'][0].get('mobileUrls', []) if mobile else [],
-            metadata)
+        return self._extract_info_helper(pc, mobile, 0, metadata)
 
 
 class LimelightChannelIE(LimelightBaseIE):
@@ -326,10 +330,7 @@ class LimelightChannelIE(LimelightBaseIE):
             'media', smuggled_data.get('source_url'))
 
         entries = [
-            self._extract_info(
-                pc['playlistItems'][i].get('streams', []),
-                mobile['mediaList'][i].get('mobileUrls', []) if mobile else [],
-                medias['media_list'][i])
+            self._extract_info_helper(pc, mobile, i, medias['media_list'][i])
             for i in range(len(medias['media_list']))]
 
         return self.playlist_result(entries, channel_id, pc['title'])

youtube_dl/extractor/ndr.py

@@ -190,10 +190,12 @@ class NDREmbedBaseIE(InfoExtractor):
             ext = determine_ext(src, None)
             if ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
-                    src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, f4m_id='hds'))
+                    src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
+                    f4m_id='hds', fatal=False))
             elif ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native'))
+                    src, video_id, 'mp4', m3u8_id='hls',
+                    entry_protocol='m3u8_native', fatal=False))
             else:
                 quality = f.get('quality')
                 ff = {

youtube_dl/extractor/odnoklassniki.py

@@ -19,11 +19,11 @@ from ..utils import (
 
 
 class OdnoklassnikiIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|m|mobile)\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:(?:www|m|mobile)\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer|live)/(?P<id>[\d-]+)'
     _TESTS = [{
         # metadata in JSON
         'url': 'http://ok.ru/video/20079905452',
-        'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
+        'md5': '0b62089b479e06681abaaca9d204f152',
         'info_dict': {
             'id': '20079905452',
             'ext': 'mp4',
@@ -35,7 +35,6 @@ class OdnoklassnikiIE(InfoExtractor):
             'like_count': int,
             'age_limit': 0,
         },
-        'skip': 'Video has been blocked',
     }, {
         # metadataUrl
         'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
@@ -99,6 +98,9 @@ class OdnoklassnikiIE(InfoExtractor):
     }, {
         'url': 'http://mobile.ok.ru/video/20079905452',
         'only_matching': True,
+    }, {
+        'url': 'https://www.ok.ru/live/484531969818',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -184,6 +186,10 @@ class OdnoklassnikiIE(InfoExtractor):
             })
             return info
 
+        assert title
+        if provider == 'LIVE_TV_APP':
+            info['title'] = self._live_title(title)
+
         quality = qualities(('4', '0', '1', '2', '3', '5'))
 
         formats = [{
@@ -210,6 +216,20 @@ class OdnoklassnikiIE(InfoExtractor):
             if fmt_type:
                 fmt['quality'] = quality(fmt_type)
 
+        # Live formats
+        m3u8_url = metadata.get('hlsMasterPlaylistUrl')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8',
+                m3u8_id='hls', fatal=False))
+        rtmp_url = metadata.get('rtmpUrl')
+        if rtmp_url:
+            formats.append({
+                'url': rtmp_url,
+                'format_id': 'rtmp',
+                'ext': 'flv',
+            })
+
         self._sort_formats(formats)
 
         info['formats'] = formats

youtube_dl/extractor/pandoratv.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
@@ -18,7 +20,14 @@ from ..utils import (
 class PandoraTVIE(InfoExtractor):
     IE_NAME = 'pandora.tv'
     IE_DESC = '판도라TV'
-    _VALID_URL = r'https?://(?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:
+                                (?:www\.)?pandora\.tv/view/(?P<user_id>[^/]+)/(?P<id>\d+)|  # new format
+                                (?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?|        # old format
+                                m\.pandora\.tv/?\?                                          # mobile
+                            )
+                    '''
     _TESTS = [{
         'url': 'http://jp.channel.pandora.tv/channel/video.ptv?c1=&prgid=53294230&ch_userid=mikakim&ref=main&lot=cate_01_2',
         'info_dict': {
@@ -53,14 +62,25 @@ class PandoraTVIE(InfoExtractor):
             # Test metadata only
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.pandora.tv/view/mikakim/53294230#36797454_new',
+        'only_matching': True,
+    }, {
+        'url': 'http://m.pandora.tv/?c=view&ch_userid=mikakim&prgid=54600346',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
-        video_id = qs.get('prgid', [None])[0]
-        user_id = qs.get('ch_userid', [None])[0]
-        if any(not f for f in (video_id, user_id,)):
-            raise ExtractorError('Invalid URL', expected=True)
+        mobj = re.match(self._VALID_URL, url)
+        user_id = mobj.group('user_id')
+        video_id = mobj.group('id')
+
+        if not user_id or not video_id:
+            qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+            video_id = qs.get('prgid', [None])[0]
+            user_id = qs.get('ch_userid', [None])[0]
+            if any(not f for f in (video_id, user_id,)):
+                raise ExtractorError('Invalid URL', expected=True)
 
         data = self._download_json(
             'http://m.pandora.tv/?c=view&m=viewJsonApi&ch_userid=%s&prgid=%s'

youtube_dl/extractor/soundcloud.py

@@ -157,7 +157,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = 'c6CU49JDMapyrQo06UxU9xouB9ZVzqCn'
+    _CLIENT_ID = 'DQskPX1pntALRzMp4HSxya3Mc0AO66Ro'
     _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
 
     @staticmethod

youtube_dl/extractor/spiegel.py

@@ -4,7 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .nexx import NexxEmbedIE
+from .nexx import (
+    NexxIE,
+    NexxEmbedIE,
+)
 from .spiegeltv import SpiegeltvIE
 from ..compat import compat_urlparse
 from ..utils import (
@@ -51,6 +54,10 @@ class SpiegelIE(InfoExtractor):
     }, {
         'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
         'only_matching': True,
+    }, {
+        # nexx video
+        'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -61,6 +68,14 @@ class SpiegelIE(InfoExtractor):
         if SpiegeltvIE.suitable(handle.geturl()):
             return self.url_result(handle.geturl(), 'Spiegeltv')
 
+        nexx_id = self._search_regex(
+            r'nexxOmniaId\s*:\s*(\d+)', webpage, 'nexx id', default=None)
+        if nexx_id:
+            domain_id = NexxIE._extract_domain_id(webpage) or '748'
+            return self.url_result(
+                'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(),
+                video_id=nexx_id)
+
         video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default=''))
 
         title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage)

youtube_dl/extractor/sportschau.py

@@ -1,38 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .wdr import WDRBaseIE
-from ..utils import get_element_by_attribute
-
-
-class SportschauIE(WDRBaseIE):
-    IE_NAME = 'Sportschau'
-    _VALID_URL = r'https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video-?(?P<id>[^/#?]+)\.html'
-    _TEST = {
-        'url': 'http://www.sportschau.de/uefaeuro2016/videos/video-dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100.html',
-        'info_dict': {
-            'id': 'mdb-1140188',
-            'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100',
-            'ext': 'mp4',
-            'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen',
-            'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.',
-            'upload_date': '20160615',
-        },
-        'skip': 'Geo-restricted to Germany',
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        title = get_element_by_attribute('class', 'headline', webpage)
-        description = self._html_search_meta('description', webpage, 'description')
-
-        info = self._extract_wdr_video(webpage, video_id)
-
-        info.update({
-            'title': title,
-            'description': description,
-        })
-
-        return info

youtube_dl/extractor/tvplay.py

@@ -273,6 +273,8 @@ class TVPlayIE(InfoExtractor):
                     'ext': ext,
                 }
                 if video_url.startswith('rtmp'):
+                    if smuggled_data.get('skip_rtmp'):
+                        continue
                     m = re.search(
                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
                     if not m:
@@ -434,6 +436,10 @@ class ViafreeIE(InfoExtractor):
         return self.url_result(
             smuggle_url(
                 'mtg:%s' % video_id,
-                {'geo_countries': [
-                    compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]]}),
+                {
+                    'geo_countries': [
+                        compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]],
+                    # rtmp host mtgfs.fplive.net for viafree is unresolvable
+                    'skip_rtmp': True,
+                }),
             ie=TVPlayIE.ie_key(), video_id=video_id)

youtube_dl/extractor/twitch.py

@@ -85,10 +85,15 @@ class TwitchBaseIE(InfoExtractor):
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
                     response = self._parse_json(
                         e.cause.read().decode('utf-8'), None)
-                    fail(response['message'])
+                    fail(response.get('message') or response['errors'][0])
                 raise
 
-            redirect_url = urljoin(post_url, response['redirect'])
+            if 'Authenticated successfully' in response.get('message', ''):
+                return None, None
+
+            redirect_url = urljoin(
+                post_url,
+                response.get('redirect') or response['redirect_path'])
             return self._download_webpage_handle(
                 redirect_url, None, 'Downloading login redirect page',
                 headers=headers)
@@ -106,6 +111,10 @@ class TwitchBaseIE(InfoExtractor):
                 'password': password,
             })
 
+        # Successful login
+        if not redirect_page:
+            return
+
         if re.search(r'(?i)<form[^>]+id="two-factor-submit"', redirect_page) is not None:
             # TODO: Add mechanism to request an SMS or phone call
             tfa_token = self._get_tfa_info('two-factor authentication token')

youtube_dl/extractor/vk.py

@@ -318,9 +318,14 @@ class VKIE(VKBaseIE):
                 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
                 expected=True)
 
+        ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
+
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
-            'Video %s has been removed from public access due to rightholder complaint.',
+            ERROR_COPYRIGHT,
+
+            r'>The video .*? was removed from public access by request of the copyright holder.<':
+            ERROR_COPYRIGHT,
 
             r'<!>Please log in or <':
             'Video %s is only available for registered users, '

youtube_dl/extractor/wdr.py

@@ -4,49 +4,50 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     determine_ext,
     ExtractorError,
     js_to_json,
     strip_jsonp,
+    try_get,
     unified_strdate,
     update_url_query,
     urlhandle_detect_ext,
 )
 
 
-class WDRBaseIE(InfoExtractor):
-    def _extract_wdr_video(self, webpage, display_id):
-        # for wdr.de the data-extension is in a tag with the class "mediaLink"
-        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
-        # for wdrmaus, in a tag with the class "videoButton" (previously a link
-        # to the page in a multiline "videoLink"-tag)
-        json_metadata = self._html_search_regex(
-            r'''(?sx)class=
-                    (?:
-                        (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
-                        (["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
-                    )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
-            ''',
-            webpage, 'media link', default=None, group='data')
+class WDRIE(InfoExtractor):
+    _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js'
+    _GEO_COUNTRIES = ['DE']
+    _TEST = {
+        'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
+        'info_dict': {
+            'id': 'mdb-1557833',
+            'ext': 'mp4',
+            'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe',
+            'upload_date': '20180112',
+        },
+    }
 
-        if not json_metadata:
-            return
-
-        media_link_obj = self._parse_json(json_metadata, display_id,
-                                          transform_source=js_to_json)
-        jsonp_url = media_link_obj['mediaObj']['url']
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
 
         metadata = self._download_json(
-            jsonp_url, display_id, transform_source=strip_jsonp)
+            url, video_id, transform_source=strip_jsonp)
 
-        metadata_tracker_data = metadata['trackerData']
-        metadata_media_resource = metadata['mediaResource']
+        is_live = metadata.get('mediaType') == 'live'
+
+        tracker_data = metadata['trackerData']
+        media_resource = metadata['mediaResource']
 
         formats = []
 
         # check if the metadata contains a direct URL to a file
-        for kind, media_resource in metadata_media_resource.items():
+        for kind, media_resource in media_resource.items():
             if kind not in ('dflt', 'alt'):
                 continue
 
@@ -57,13 +58,13 @@ class WDRBaseIE(InfoExtractor):
                 ext = determine_ext(medium_url)
                 if ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        medium_url, display_id, 'mp4', 'm3u8_native',
+                        medium_url, video_id, 'mp4', 'm3u8_native',
                         m3u8_id='hls'))
                 elif ext == 'f4m':
                     manifest_url = update_url_query(
                         medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
                     formats.extend(self._extract_f4m_formats(
-                        manifest_url, display_id, f4m_id='hds', fatal=False))
+                        manifest_url, video_id, f4m_id='hds', fatal=False))
                 elif ext == 'smil':
                     formats.extend(self._extract_smil_formats(
                         medium_url, 'stream', fatal=False))
@@ -73,7 +74,7 @@ class WDRBaseIE(InfoExtractor):
                     }
                     if ext == 'unknown_video':
                         urlh = self._request_webpage(
-                            medium_url, display_id, note='Determining extension')
+                            medium_url, video_id, note='Determining extension')
                         ext = urlhandle_detect_ext(urlh)
                         a_format['ext'] = ext
                     formats.append(a_format)
@@ -81,30 +82,30 @@ class WDRBaseIE(InfoExtractor):
         self._sort_formats(formats)
 
         subtitles = {}
-        caption_url = metadata_media_resource.get('captionURL')
+        caption_url = media_resource.get('captionURL')
         if caption_url:
             subtitles['de'] = [{
                 'url': caption_url,
                 'ext': 'ttml',
             }]
 
-        title = metadata_tracker_data['trackerClipTitle']
+        title = tracker_data['trackerClipTitle']
 
         return {
-            'id': metadata_tracker_data.get('trackerClipId', display_id),
-            'display_id': display_id,
-            'title': title,
-            'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
+            'id': tracker_data.get('trackerClipId', video_id),
+            'title': self._live_title(title) if is_live else title,
+            'alt_title': tracker_data.get('trackerClipSubcategory'),
             'formats': formats,
             'subtitles': subtitles,
-            'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')),
+            'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')),
+            'is_live': is_live,
         }
 
 
-class WDRIE(WDRBaseIE):
+class WDRPageIE(InfoExtractor):
     _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
-    _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
-    _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
+    _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
 
     _TESTS = [
         {
@@ -124,6 +125,7 @@ class WDRIE(WDRBaseIE):
                     'ext': 'ttml',
                 }]},
             },
+            'skip': 'HTTP Error 404: Not Found',
         },
         {
             'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
@@ -139,19 +141,17 @@ class WDRIE(WDRBaseIE):
                 'is_live': False,
                 'subtitles': {}
             },
+            'skip': 'HTTP Error 404: Not Found',
         },
         {
             'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
             'info_dict': {
-                'id': 'mdb-103364',
+                'id': 'mdb-1406149',
                 'ext': 'mp4',
-                'display_id': 'index',
-                'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                 'alt_title': 'WDR Fernsehen Live',
-                'upload_date': None,
-                'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
+                'upload_date': '20150101',
                 'is_live': True,
-                'subtitles': {}
             },
             'params': {
                 'skip_download': True,  # m3u8 download
@@ -159,19 +159,18 @@ class WDRIE(WDRBaseIE):
         },
         {
             'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
-            'playlist_mincount': 8,
+            'playlist_mincount': 7,
             'info_dict': {
-                'id': 'aktuelle-stunde/aktuelle-stunde-120',
+                'id': 'aktuelle-stunde-120',
             },
         },
         {
             'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
             'info_dict': {
-                'id': 'mdb-1323501',
+                'id': 'mdb-1552552',
                 'ext': 'mp4',
                 'upload_date': 're:^[0-9]{8}$',
                 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
-                'description': 'Die Seite mit der Maus -',
             },
             'skip': 'The id changes from week to week because of the new episode'
         },
@@ -183,7 +182,6 @@ class WDRIE(WDRBaseIE):
                 'ext': 'mp4',
                 'upload_date': '20130919',
                 'title': 'Sachgeschichte - Achterbahn ',
-                'description': 'Die Seite mit der Maus -',
             },
         },
         {
@@ -191,52 +189,114 @@ class WDRIE(WDRBaseIE):
             # Live stream, MD5 unstable
             'info_dict': {
                 'id': 'mdb-869971',
-                'ext': 'flv',
-                'title': 'COSMO Livestream',
-                'description': 'md5:2309992a6716c347891c045be50992e4',
+                'ext': 'mp4',
+                'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                 'upload_date': '20160101',
             },
+            'params': {
+                'skip_download': True,  # m3u8 download
+            }
+        },
+        {
+            'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html',
+            'info_dict': {
+                'id': 'mdb-1556012',
+                'ext': 'mp4',
+                'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"',
+                'upload_date': '20180111',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
+            'only_matching': True,
         }
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        url_type = mobj.group('type')
-        page_url = mobj.group('page_url')
         display_id = mobj.group('display_id')
         webpage = self._download_webpage(url, display_id)
 
-        info_dict = self._extract_wdr_video(webpage, display_id)
+        entries = []
 
-        if not info_dict:
+        # Article with several videos
+
+        # for wdr.de the data-extension is in a tag with the class "mediaLink"
+        # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
+        # for wdrmaus, in a tag with the class "videoButton" (previously a link
+        # to the page in a multiline "videoLink"-tag)
+        for mobj in re.finditer(
+            r'''(?sx)class=
+                    (?:
+                        (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
+                        (["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
+                    )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
+                    ''', webpage):
+            media_link_obj = self._parse_json(
+                mobj.group('data'), display_id, transform_source=js_to_json,
+                fatal=False)
+            if not media_link_obj:
+                continue
+            jsonp_url = try_get(
+                media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
+            if jsonp_url:
+                entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))
+
+        # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
+        if not entries:
             entries = [
-                self.url_result(page_url + href[0], 'WDR')
-                for href in re.findall(
-                    r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX,
-                    webpage)
+                self.url_result(
+                    compat_urlparse.urljoin(url, mobj.group('href')),
+                    ie=WDRPageIE.ie_key())
+                for mobj in re.finditer(
+                    r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=',
+                    webpage) if re.match(self._PAGE_REGEX, mobj.group('href'))
             ]
 
-            if entries:  # Playlist page
-                return self.playlist_result(entries, playlist_id=display_id)
+        return self.playlist_result(entries, playlist_id=display_id)
 
-            raise ExtractorError('No downloadable streams found', expected=True)
 
-        is_live = url_type == 'live'
+class WDRElefantIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
+    _TEST = {
+        'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015',
+        'info_dict': {
+            'title': 'Folge Oster-Spezial 2015',
+            'id': 'mdb-1088195',
+            'ext': 'mp4',
+            'age_limit': None,
+            'upload_date': '20150406'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
 
-        if is_live:
-            info_dict.update({
-                'title': self._live_title(info_dict['title']),
-                'upload_date': None,
-            })
-        elif 'upload_date' not in info_dict:
-            info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date'))
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
 
-        info_dict.update({
-            'description': self._html_search_meta('Description', webpage),
-            'is_live': is_live,
-        })
-
-        return info_dict
+        # Table of Contents seems to always be at this address, so fetch it directly.
+        # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5.
+        table_of_contents = self._download_json(
+            'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5',
+            display_id)
+        if display_id not in table_of_contents:
+            raise ExtractorError(
+                'No entry in site\'s table of contents for this URL. '
+                'Is the fragment part of the URL (after the #) correct?',
+                expected=True)
+        xml_metadata_path = table_of_contents[display_id]['xmlPath']
+        xml_metadata = self._download_xml(
+            'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path,
+            display_id)
+        zmdb_url_element = xml_metadata.find('./movie/zmdb_url')
+        if zmdb_url_element is None:
+            raise ExtractorError(
+                '%s is not a video' % display_id, expected=True)
+        return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key())
 
 
 class WDRMobileIE(InfoExtractor):

youtube_dl/extractor/weibo.py

@@ -0,0 +1,140 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+import json
+import random
+import re
+
+from ..compat import (
+    compat_parse_qs,
+    compat_str,
+)
+from ..utils import (
+    js_to_json,
+    strip_jsonp,
+    urlencode_postdata,
+)
+
+
+class WeiboIE(InfoExtractor):
+    _VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)'
+    _TEST = {
+        'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment',
+        'info_dict': {
+            'id': 'Fp6RGfbff',
+            'ext': 'mp4',
+            'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        # to get Referer url for genvisitor
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        visitor_url = urlh.geturl()
+
+        if 'passport.weibo.com' in visitor_url:
+            # first visit
+            visitor_data = self._download_json(
+                'https://passport.weibo.com/visitor/genvisitor', video_id,
+                note='Generating first-visit data',
+                transform_source=strip_jsonp,
+                headers={'Referer': visitor_url},
+                data=urlencode_postdata({
+                    'cb': 'gen_callback',
+                    'fp': json.dumps({
+                        'os': '2',
+                        'browser': 'Gecko57,0,0,0',
+                        'fonts': 'undefined',
+                        'screenInfo': '1440*900*24',
+                        'plugins': '',
+                    }),
+                }))
+
+            tid = visitor_data['data']['tid']
+            cnfd = '%03d' % visitor_data['data']['confidence']
+
+            self._download_webpage(
+                'https://passport.weibo.com/visitor/visitor', video_id,
+                note='Running first-visit callback',
+                query={
+                    'a': 'incarnate',
+                    't': tid,
+                    'w': 2,
+                    'c': cnfd,
+                    'cb': 'cross_domain',
+                    'from': 'weibo',
+                    '_rand': random.random(),
+                })
+
+            webpage = self._download_webpage(
+                url, video_id, note='Revisiting webpage')
+
+        title = self._html_search_regex(
+            r'<title>(.+?)</title>', webpage, 'title')
+
+        video_formats = compat_parse_qs(self._search_regex(
+            r'video-sources=\\\"(.+?)\"', webpage, 'video_sources'))
+
+        formats = []
+        supported_resolutions = (480, 720)
+        for res in supported_resolutions:
+            vid_urls = video_formats.get(compat_str(res))
+            if not vid_urls or not isinstance(vid_urls, list):
+                continue
+
+            vid_url = vid_urls[0]
+            formats.append({
+                'url': vid_url,
+                'height': res,
+            })
+
+        self._sort_formats(formats)
+
+        uploader = self._og_search_property(
+            'nick-name', webpage, 'uploader', default=None)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'uploader': uploader,
+            'formats': formats
+        }
+
+
+class WeiboMobileIE(InfoExtractor):
+    _VALID_URL = r'https?://m\.weibo\.cn/status/(?P<id>[0-9]+)(\?.+)?'
+    _TEST = {
+        'url': 'https://m.weibo.cn/status/4189191225395228?wm=3333_2001&sourcetype=weixin&featurecode=newtitle&from=singlemessage&isappinstalled=0',
+        'info_dict': {
+            'id': '4189191225395228',
+            'ext': 'mp4',
+            'title': '午睡当然是要甜甜蜜蜜的啦',
+            'uploader': '柴犬柴犬'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        # to get Referer url for genvisitor
+        webpage = self._download_webpage(url, video_id, note='visit the page')
+
+        weibo_info = self._parse_json(self._search_regex(
+            r'var\s+\$render_data\s*=\s*\[({.*})\]\[0\]\s*\|\|\s*{};',
+            webpage, 'js_code', flags=re.DOTALL),
+            video_id, transform_source=js_to_json)
+
+        status_data = weibo_info.get('status', {})
+        page_info = status_data.get('page_info')
+        title = status_data['status_title']
+        uploader = status_data.get('user', {}).get('screen_name')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'uploader': uploader,
+            'url': page_info['media_info']['stream_url']
+        }

youtube_dl/extractor/ximalaya.py

@@ -0,0 +1,233 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import itertools
+import re
+
+from .common import InfoExtractor
+
+
+class XimalayaBaseIE(InfoExtractor):
+    _GEO_COUNTRIES = ['CN']
+
+
+class XimalayaIE(XimalayaBaseIE):
+    IE_NAME = 'ximalaya'
+    IE_DESC = '喜马拉雅FM'
+    _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?P<uid>[0-9]+)/sound/(?P<id>[0-9]+)'
+    _USER_URL_FORMAT = '%s://www.ximalaya.com/zhubo/%i/'
+    _TESTS = [
+        {
+            'url': 'http://www.ximalaya.com/61425525/sound/47740352/',
+            'info_dict': {
+                'id': '47740352',
+                'ext': 'm4a',
+                'uploader': '小彬彬爱听书',
+                'uploader_id': 61425525,
+                'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/',
+                'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白',
+                'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。",
+                'thumbnails': [
+                    {
+                        'name': 'cover_url',
+                        'url': r're:^https?://.*\.jpg$',
+                    },
+                    {
+                        'name': 'cover_url_142',
+                        'url': r're:^https?://.*\.jpg$',
+                        'width': 180,
+                        'height': 180
+                    }
+                ],
+                'categories': ['renwen', '人文'],
+                'duration': 93,
+                'view_count': int,
+                'like_count': int,
+            }
+        },
+        {
+            'url': 'http://m.ximalaya.com/61425525/sound/47740352/',
+            'info_dict': {
+                'id': '47740352',
+                'ext': 'm4a',
+                'uploader': '小彬彬爱听书',
+                'uploader_id': 61425525,
+                'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/',
+                'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白',
+                'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。",
+                'thumbnails': [
+                    {
+                        'name': 'cover_url',
+                        'url': r're:^https?://.*\.jpg$',
+                    },
+                    {
+                        'name': 'cover_url_142',
+                        'url': r're:^https?://.*\.jpg$',
+                        'width': 180,
+                        'height': 180
+                    }
+                ],
+                'categories': ['renwen', '人文'],
+                'duration': 93,
+                'view_count': int,
+                'like_count': int,
+            }
+        },
+        {
+            'url': 'https://www.ximalaya.com/11045267/sound/15705996/',
+            'info_dict': {
+                'id': '15705996',
+                'ext': 'm4a',
+                'uploader': '李延隆老师',
+                'uploader_id': 11045267,
+                'uploader_url': 'https://www.ximalaya.com/zhubo/11045267/',
+                'title': 'Lesson 1 Excuse me!',
+                'description': "contains:Listen to the tape then answer\xa0this question. Whose handbag is it?\n"
+                               "听录音，然后回答问题，这是谁的手袋？",
+                'thumbnails': [
+                    {
+                        'name': 'cover_url',
+                        'url': r're:^https?://.*\.jpg$',
+                    },
+                    {
+                        'name': 'cover_url_142',
+                        'url': r're:^https?://.*\.jpg$',
+                        'width': 180,
+                        'height': 180
+                    }
+                ],
+                'categories': ['train', '外语'],
+                'duration': 40,
+                'view_count': int,
+                'like_count': int,
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+
+        is_m = 'm.ximalaya' in url
+        scheme = 'https' if url.startswith('https') else 'http'
+
+        audio_id = self._match_id(url)
+        webpage = self._download_webpage(url, audio_id,
+                                         note='Download sound page for %s' % audio_id,
+                                         errnote='Unable to get sound page')
+
+        audio_info_file = '%s://m.ximalaya.com/tracks/%s.json' % (scheme, audio_id)
+        audio_info = self._download_json(audio_info_file, audio_id,
+                                         'Downloading info json %s' % audio_info_file,
+                                         'Unable to download info file')
+
+        formats = []
+        for bps, k in (('24k', 'play_path_32'), ('64k', 'play_path_64')):
+            if audio_info.get(k):
+                formats.append({
+                    'format_id': bps,
+                    'url': audio_info[k],
+                })
+
+        thumbnails = []
+        for k in audio_info.keys():
+            # cover pics kyes like: cover_url', 'cover_url_142'
+            if k.startswith('cover_url'):
+                thumbnail = {'name': k, 'url': audio_info[k]}
+                if k == 'cover_url_142':
+                    thumbnail['width'] = 180
+                    thumbnail['height'] = 180
+                thumbnails.append(thumbnail)
+
+        audio_uploader_id = audio_info.get('uid')
+
+        if is_m:
+            audio_description = self._html_search_regex(r'(?s)<section\s+class=["\']content[^>]+>(.+?)</section>',
+                                                        webpage, 'audio_description', fatal=False)
+        else:
+            audio_description = self._html_search_regex(r'(?s)<div\s+class=["\']rich_intro[^>]*>(.+?</article>)',
+                                                        webpage, 'audio_description', fatal=False)
+
+        if not audio_description:
+            audio_description_file = '%s://www.ximalaya.com/sounds/%s/rich_intro' % (scheme, audio_id)
+            audio_description = self._download_webpage(audio_description_file, audio_id,
+                                                       note='Downloading description file %s' % audio_description_file,
+                                                       errnote='Unable to download descrip file',
+                                                       fatal=False)
+            audio_description = audio_description.strip() if audio_description else None
+
+        return {
+            'id': audio_id,
+            'uploader': audio_info.get('nickname'),
+            'uploader_id': audio_uploader_id,
+            'uploader_url': self._USER_URL_FORMAT % (scheme, audio_uploader_id) if audio_uploader_id else None,
+            'title': audio_info['title'],
+            'thumbnails': thumbnails,
+            'description': audio_description,
+            'categories': list(filter(None, (audio_info.get('category_name'), audio_info.get('category_title')))),
+            'duration': audio_info.get('duration'),
+            'view_count': audio_info.get('play_count'),
+            'like_count': audio_info.get('favorites_count'),
+            'formats': formats,
+        }
+
+
+class XimalayaAlbumIE(XimalayaBaseIE):
+    IE_NAME = 'ximalaya:album'
+    IE_DESC = '喜马拉雅FM 专辑'
+    _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?P<uid>[0-9]+)/album/(?P<id>[0-9]+)'
+    _TEMPLATE_URL = '%s://www.ximalaya.com/%s/album/%s/'
+    _BASE_URL_TEMPL = '%s://www.ximalaya.com%s'
+    _LIST_VIDEO_RE = r'<a[^>]+?href="(?P<url>/%s/sound/(?P<id>\d+)/?)"[^>]+?title="(?P<title>[^>]+)">'
+    _TESTS = [{
+        'url': 'http://www.ximalaya.com/61425525/album/5534601/',
+        'info_dict': {
+            'title': '唐诗三百首（含赏析）',
+            'id': '5534601',
+        },
+        'playlist_count': 312,
+    }, {
+        'url': 'http://m.ximalaya.com/61425525/album/5534601',
+        'info_dict': {
+            'title': '唐诗三百首（含赏析）',
+            'id': '5534601',
+        },
+        'playlist_count': 312,
+    },
+    ]
+
+    def _real_extract(self, url):
+        self.scheme = scheme = 'https' if url.startswith('https') else 'http'
+
+        mobj = re.match(self._VALID_URL, url)
+        uid, playlist_id = mobj.group('uid'), mobj.group('id')
+
+        webpage = self._download_webpage(self._TEMPLATE_URL % (scheme, uid, playlist_id), playlist_id,
+                                         note='Download album page for %s' % playlist_id,
+                                         errnote='Unable to get album info')
+
+        title = self._html_search_regex(r'detailContent_title[^>]*><h1(?:[^>]+)?>([^<]+)</h1>',
+                                        webpage, 'title', fatal=False)
+
+        return self.playlist_result(self._entries(webpage, playlist_id, uid), playlist_id, title)
+
+    def _entries(self, page, playlist_id, uid):
+        html = page
+        for page_num in itertools.count(1):
+            for entry in self._process_page(html, uid):
+                yield entry
+
+            next_url = self._search_regex(r'<a\s+href=(["\'])(?P<more>[\S]+)\1[^>]+rel=(["\'])next\3',
+                                          html, 'list_next_url', default=None, group='more')
+            if not next_url:
+                break
+
+            next_full_url = self._BASE_URL_TEMPL % (self.scheme, next_url)
+            html = self._download_webpage(next_full_url, playlist_id)
+
+    def _process_page(self, html, uid):
+        find_from = html.index('album_soundlist')
+        for mobj in re.finditer(self._LIST_VIDEO_RE % uid, html[find_from:]):
+            yield self.url_result(self._BASE_URL_TEMPL % (self.scheme, mobj.group('url')),
+                                  XimalayaIE.ie_key(),
+                                  mobj.group('id'),
+                                  mobj.group('title'))

youtube_dl/extractor/youtube.py

@@ -1810,7 +1810,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'url': video_info['conn'][0],
                 'player_url': player_url,
             }]
-        elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
+        elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
             encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
             if 'rtmpe%3Dyes' in encoded_url_map:
                 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2018.01.07'
+__version__ = '2018.01.18'