[funk] Add extractor (closes #14464)
[ytdl] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12     compat_etree_fromstring,
13     compat_str,
14     compat_urllib_parse_unquote,
15     compat_urlparse,
16     compat_xml_parse_error,
17 )
18 from ..utils import (
19     determine_ext,
20     ExtractorError,
21     float_or_none,
22     HEADRequest,
23     is_html,
24     js_to_json,
25     KNOWN_EXTENSIONS,
26     mimetype2ext,
27     orderedSet,
28     sanitized_Request,
29     smuggle_url,
30     unescapeHTML,
31     unified_strdate,
32     unsmuggle_url,
33     UnsupportedError,
34     xpath_text,
35 )
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
38     BrightcoveLegacyIE,
39     BrightcoveNewIE,
40 )
41 from .nexx import (
42     NexxIE,
43     NexxEmbedIE,
44 )
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .vimeo import VimeoIE
62 from .dailymotion import (
63     DailymotionIE,
64     DailymotionCloudIE,
65 )
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
105
106
107 class GenericIE(InfoExtractor):
108     IE_DESC = 'Generic downloader that works on some sites'
109     _VALID_URL = r'.*'
110     IE_NAME = 'generic'
111     _TESTS = [
112         # Direct link to a video
113         {
114             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
115             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
116             'info_dict': {
117                 'id': 'trailer',
118                 'ext': 'mp4',
119                 'title': 'trailer',
120                 'upload_date': '20100513',
121             }
122         },
123         # Direct link to media delivered compressed (until Accept-Encoding is *)
124         {
125             'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
126             'md5': '128c42e68b13950268b648275386fc74',
127             'info_dict': {
128                 'id': 'FictionJunction-Parallel_Hearts',
129                 'ext': 'flac',
130                 'title': 'FictionJunction-Parallel_Hearts',
131                 'upload_date': '20140522',
132             },
133             'expected_warnings': [
134                 'URL could be a direct video link, returning it as such.'
135             ],
136             'skip': 'URL invalid',
137         },
138         # Direct download with broken HEAD
139         {
140             'url': 'http://ai-radio.org:8000/radio.opus',
141             'info_dict': {
142                 'id': 'radio',
143                 'ext': 'opus',
144                 'title': 'radio',
145             },
146             'params': {
147                 'skip_download': True,  # infinite live stream
148             },
149             'expected_warnings': [
150                 r'501.*Not Implemented',
151                 r'400.*Bad Request',
152             ],
153         },
154         # Direct link with incorrect MIME type
155         {
156             'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157             'md5': '4ccbebe5f36706d85221f204d7eb5913',
158             'info_dict': {
159                 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
160                 'id': '5_Lennart_Poettering_-_Systemd',
161                 'ext': 'webm',
162                 'title': '5_Lennart_Poettering_-_Systemd',
163                 'upload_date': '20141120',
164             },
165             'expected_warnings': [
166                 'URL could be a direct video link, returning it as such.'
167             ]
168         },
169         # RSS feed
170         {
171             'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
172             'info_dict': {
173                 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
174                 'title': 'Zero Punctuation',
175                 'description': 're:.*groundbreaking video review series.*'
176             },
177             'playlist_mincount': 11,
178         },
179         # RSS feed with enclosure
180         {
181             'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
182             'info_dict': {
183                 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
184                 'ext': 'm4v',
185                 'upload_date': '20150228',
186                 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
187             }
188         },
189         # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
190         {
191             'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
192             'info_dict': {
193                 'id': 'smil',
194                 'ext': 'mp4',
195                 'title': 'Automatics, robotics and biocybernetics',
196                 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
197                 'upload_date': '20130627',
198                 'formats': 'mincount:16',
199                 'subtitles': 'mincount:1',
200             },
201             'params': {
202                 'force_generic_extractor': True,
203                 'skip_download': True,
204             },
205         },
206         # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
207         {
208             'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
209             'info_dict': {
210                 'id': 'hds',
211                 'ext': 'flv',
212                 'title': 'hds',
213                 'formats': 'mincount:1',
214             },
215             'params': {
216                 'skip_download': True,
217             },
218         },
219         # SMIL from https://www.restudy.dk/video/play/id/1637
220         {
221             'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
222             'info_dict': {
223                 'id': 'video_1637',
224                 'ext': 'flv',
225                 'title': 'video_1637',
226                 'formats': 'mincount:3',
227             },
228             'params': {
229                 'skip_download': True,
230             },
231         },
232         # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
233         {
234             'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
235             'info_dict': {
236                 'id': 'smil-service',
237                 'ext': 'flv',
238                 'title': 'smil-service',
239                 'formats': 'mincount:1',
240             },
241             'params': {
242                 'skip_download': True,
243             },
244         },
245         # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
246         {
247             'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
248             'info_dict': {
249                 'id': '4719370',
250                 'ext': 'mp4',
251                 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
252                 'formats': 'mincount:3',
253             },
254             'params': {
255                 'skip_download': True,
256             },
257         },
258         # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
259         {
260             'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
261             'info_dict': {
262                 'id': 'mZlp2ctYIUEB',
263                 'ext': 'mp4',
264                 'title': 'Tikibad ontruimd wegens brand',
265                 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
266                 'thumbnail': r're:^https?://.*\.jpg$',
267                 'duration': 33,
268             },
269             'params': {
270                 'skip_download': True,
271             },
272         },
273         # MPD from http://dash-mse-test.appspot.com/media.html
274         {
275             'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
276             'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
277             'info_dict': {
278                 'id': 'car-20120827-manifest',
279                 'ext': 'mp4',
280                 'title': 'car-20120827-manifest',
281                 'formats': 'mincount:9',
282                 'upload_date': '20130904',
283             },
284             'params': {
285                 'format': 'bestvideo',
286             },
287         },
288         # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
289         {
290             'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
291             'info_dict': {
292                 'id': 'content',
293                 'ext': 'mp4',
294                 'title': 'content',
295                 'formats': 'mincount:8',
296             },
297             'params': {
298                 # m3u8 downloads
299                 'skip_download': True,
300             },
301             'skip': 'video gone',
302         },
303         # m3u8 served with Content-Type: text/plain
304         {
305             'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
306             'info_dict': {
307                 'id': 'index',
308                 'ext': 'mp4',
309                 'title': 'index',
310                 'upload_date': '20140720',
311                 'formats': 'mincount:11',
312             },
313             'params': {
314                 # m3u8 downloads
315                 'skip_download': True,
316             },
317             'skip': 'video gone',
318         },
319         # google redirect
320         {
321             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
322             'info_dict': {
323                 'id': 'cmQHVoWB5FY',
324                 'ext': 'mp4',
325                 'upload_date': '20130224',
326                 'uploader_id': 'TheVerge',
327                 'description': r're:^Chris Ziegler takes a look at the\.*',
328                 'uploader': 'The Verge',
329                 'title': 'First Firefox OS phones side-by-side',
330             },
331             'params': {
332                 'skip_download': False,
333             }
334         },
335         {
336             # redirect in Refresh HTTP header
337             'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
338             'info_dict': {
339                 'id': 'pO8h3EaFRdo',
340                 'ext': 'mp4',
341                 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
342                 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
343                 'upload_date': '20150917',
344                 'uploader_id': 'brtvofficial',
345                 'uploader': 'Boiler Room',
346             },
347             'params': {
348                 'skip_download': False,
349             },
350         },
351         {
352             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
353             'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
354             'info_dict': {
355                 'id': '13601338388002',
356                 'ext': 'mp4',
357                 'uploader': 'www.hodiho.fr',
358                 'title': 'R\u00e9gis plante sa Jeep',
359             }
360         },
361         # bandcamp page with custom domain
362         {
363             'add_ie': ['Bandcamp'],
364             'url': 'http://bronyrock.com/track/the-pony-mash',
365             'info_dict': {
366                 'id': '3235767654',
367                 'ext': 'mp3',
368                 'title': 'The Pony Mash',
369                 'uploader': 'M_Pallante',
370             },
371             'skip': 'There is a limit of 200 free downloads / month for the test song',
372         },
373         {
374             # embedded brightcove video
375             # it also tests brightcove videos that need to set the 'Referer'
376             # in the http requests
377             'add_ie': ['BrightcoveLegacy'],
378             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
379             'info_dict': {
380                 'id': '2765128793001',
381                 'ext': 'mp4',
382                 'title': 'Le cours de bourse : l’analyse technique',
383                 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
384                 'uploader': 'BFM BUSINESS',
385             },
386             'params': {
387                 'skip_download': True,
388             },
389         },
390         {
391             # embedded with itemprop embedURL and video id spelled as `idVideo`
392             'add_id': ['BrightcoveLegacy'],
393             'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
394             'info_dict': {
395                 'id': '5255628253001',
396                 'ext': 'mp4',
397                 'title': 'md5:37c519b1128915607601e75a87995fc0',
398                 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
399                 'uploader': 'BFM BUSINESS',
400                 'uploader_id': '876450612001',
401                 'timestamp': 1482255315,
402                 'upload_date': '20161220',
403             },
404             'params': {
405                 'skip_download': True,
406             },
407         },
408         {
409             # https://github.com/rg3/youtube-dl/issues/2253
410             'url': 'http://bcove.me/i6nfkrc3',
411             'md5': '0ba9446db037002366bab3b3eb30c88c',
412             'info_dict': {
413                 'id': '3101154703001',
414                 'ext': 'mp4',
415                 'title': 'Still no power',
416                 'uploader': 'thestar.com',
417                 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
418             },
419             'add_ie': ['BrightcoveLegacy'],
420             'skip': 'video gone',
421         },
422         {
423             'url': 'http://www.championat.com/video/football/v/87/87499.html',
424             'md5': 'fb973ecf6e4a78a67453647444222983',
425             'info_dict': {
426                 'id': '3414141473001',
427                 'ext': 'mp4',
428                 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
429                 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
430                 'uploader': 'Championat',
431             },
432         },
433         {
434             # https://github.com/rg3/youtube-dl/issues/3541
435             'add_ie': ['BrightcoveLegacy'],
436             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
437             'info_dict': {
438                 'id': '3866516442001',
439                 'ext': 'mp4',
440                 'title': 'Leer mij vrouwen kennen: Aflevering 1',
441                 'description': 'Leer mij vrouwen kennen: Aflevering 1',
442                 'uploader': 'SBS Broadcasting',
443             },
444             'skip': 'Restricted to Netherlands',
445             'params': {
446                 'skip_download': True,  # m3u8 download
447             },
448         },
449         {
450             # Brightcove video in <iframe>
451             'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
452             'md5': '36d74ef5e37c8b4a2ce92880d208b968',
453             'info_dict': {
454                 'id': '5360463607001',
455                 'ext': 'mp4',
456                 'title': '叙利亚失明儿童在废墟上演唱《心跳》  呼吁获得正常童年生活',
457                 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
458                 'uploader': 'United Nations',
459                 'uploader_id': '1362235914001',
460                 'timestamp': 1489593889,
461                 'upload_date': '20170315',
462             },
463             'add_ie': ['BrightcoveLegacy'],
464         },
465         {
466             # Brightcove with alternative playerID key
467             'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
468             'info_dict': {
469                 'id': 'nmeth.2062_SV1',
470                 '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',
471             },
472             'playlist': [{
473                 'info_dict': {
474                     'id': '2228375078001',
475                     'ext': 'mp4',
476                     'title': 'nmeth.2062-sv1',
477                     'description': 'nmeth.2062-sv1',
478                     'timestamp': 1363357591,
479                     'upload_date': '20130315',
480                     'uploader': 'Nature Publishing Group',
481                     'uploader_id': '1964492299001',
482                 },
483             }],
484         },
485         {
486             # Brightcove with UUID in videoPlayer
487             'url': 'http://www8.hp.com/cn/zh/home.html',
488             'info_dict': {
489                 'id': '5255815316001',
490                 'ext': 'mp4',
491                 'title': 'Sprocket Video - China',
492                 'description': 'Sprocket Video - China',
493                 'uploader': 'HP-Video Gallery',
494                 'timestamp': 1482263210,
495                 'upload_date': '20161220',
496                 'uploader_id': '1107601872001',
497             },
498             'params': {
499                 'skip_download': True,  # m3u8 download
500             },
501             'skip': 'video rotates...weekly?',
502         },
503         {
504             # Brightcove:new type [2].
505             'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
506             'md5': '2b35148fcf48da41c9fb4591650784f3',
507             'info_dict': {
508                 'id': '5348741021001',
509                 'ext': 'mp4',
510                 'upload_date': '20170306',
511                 'uploader_id': '4191638492001',
512                 'timestamp': 1488769918,
513                 'title': 'VIDEO:  St. Thomas More earns first trip to basketball semis',
514
515             },
516         },
517         {
518             # Alternative brightcove <video> attributes
519             'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
520             'info_dict': {
521                 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
522                 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
523             },
524             'playlist': [{
525                 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
526                 'info_dict': {
527                     'id': '5311302538001',
528                     'ext': 'mp4',
529                     'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
530                     'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
531                     'timestamp': 1486321708,
532                     'upload_date': '20170205',
533                     'uploader_id': '800000640001',
534                 },
535                 'only_matching': True,
536             }],
537         },
538         {
539             # Brightcove with UUID in videoPlayer
540             'url': 'http://www8.hp.com/cn/zh/home.html',
541             'info_dict': {
542                 'id': '5255815316001',
543                 'ext': 'mp4',
544                 'title': 'Sprocket Video - China',
545                 'description': 'Sprocket Video - China',
546                 'uploader': 'HP-Video Gallery',
547                 'timestamp': 1482263210,
548                 'upload_date': '20161220',
549                 'uploader_id': '1107601872001',
550             },
551             'params': {
552                 'skip_download': True,  # m3u8 download
553             },
554         },
555         # ooyala video
556         {
557             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
558             'md5': '166dd577b433b4d4ebfee10b0824d8ff',
559             'info_dict': {
560                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
561                 'ext': 'mp4',
562                 'title': '2cc213299525360.mov',  # that's what we get
563                 'duration': 238.231,
564             },
565             'add_ie': ['Ooyala'],
566         },
567         {
568             # ooyala video embedded with http://player.ooyala.com/iframe.js
569             'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
570             'info_dict': {
571                 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
572                 'ext': 'mp4',
573                 'title': '"Steve Jobs: Man in the Machine" trailer',
574                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
575                 'duration': 135.427,
576             },
577             'params': {
578                 'skip_download': True,
579             },
580             'skip': 'movie expired',
581         },
582         # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
583         {
584             'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
585             'info_dict': {
586                 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
587                 'ext': 'mp4',
588                 'title': 'Steampunk Fest Comes to Honesdale',
589                 'duration': 43.276,
590             },
591             'params': {
592                 'skip_download': True,
593             }
594         },
595         # embed.ly video
596         {
597             'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
598             'info_dict': {
599                 'id': '9ODmcdjQcHQ',
600                 'ext': 'mp4',
601                 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
602                 'upload_date': '20140225',
603                 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
604                 'uploader': 'Tested',
605                 'uploader_id': 'testedcom',
606             },
607             # No need to test YoutubeIE here
608             'params': {
609                 'skip_download': True,
610             },
611         },
612         # funnyordie embed
613         {
614             'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
615             'info_dict': {
616                 'id': '18e820ec3f',
617                 'ext': 'mp4',
618                 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
619                 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
620             },
621             # HEAD requests lead to endless 301, while GET is OK
622             'expected_warnings': ['301'],
623         },
624         # RUTV embed
625         {
626             'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
627             'info_dict': {
628                 'id': '776940',
629                 'ext': 'mp4',
630                 'title': 'Охотское море стало целиком российским',
631                 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
632             },
633             'params': {
634                 # m3u8 download
635                 'skip_download': True,
636             },
637         },
638         # TVC embed
639         {
640             'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
641             'info_dict': {
642                 'id': '55304',
643                 'ext': 'mp4',
644                 'title': 'Дошкольное воспитание',
645             },
646         },
647         # SportBox embed
648         {
649             'url': 'http://www.vestifinance.ru/articles/25753',
650             'info_dict': {
651                 'id': '25753',
652                 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
653             },
654             'playlist': [{
655                 'info_dict': {
656                     'id': '370908',
657                     'title': 'Госзаказ. День 3',
658                     'ext': 'mp4',
659                 }
660             }, {
661                 'info_dict': {
662                     'id': '370905',
663                     'title': 'Госзаказ. День 2',
664                     'ext': 'mp4',
665                 }
666             }, {
667                 'info_dict': {
668                     'id': '370902',
669                     'title': 'Госзаказ. День 1',
670                     'ext': 'mp4',
671                 }
672             }],
673             'params': {
674                 # m3u8 download
675                 'skip_download': True,
676             },
677         },
678         # Myvi.ru embed
679         {
680             'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
681             'info_dict': {
682                 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
683                 'ext': 'mp4',
684                 'title': 'Ужастики, русский трейлер (2015)',
685                 'thumbnail': r're:^https?://.*\.jpg$',
686                 'duration': 153,
687             }
688         },
689         # XHamster embed
690         {
691             'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
692             'info_dict': {
693                 'id': 'showthread',
694                 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
695             },
696             'playlist_mincount': 7,
697             # This forum does not allow <iframe> syntaxes anymore
698             # Now HTML tags are displayed as-is
699             'skip': 'No videos on this page',
700         },
701         # Embedded TED video
702         {
703             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
704             'md5': '65fdff94098e4a607385a60c5177c638',
705             'info_dict': {
706                 'id': '1969',
707                 'ext': 'mp4',
708                 'title': 'Hidden miracles of the natural world',
709                 'uploader': 'Louie Schwartzberg',
710                 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
711             }
712         },
713         # nowvideo embed hidden behind percent encoding
714         {
715             'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
716             'md5': '2baf4ddd70f697d94b1c18cf796d5107',
717             'info_dict': {
718                 'id': '06e53103ca9aa',
719                 'ext': 'flv',
720                 'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
721                 'description': 'No description',
722             },
723         },
724         # arte embed
725         {
726             'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
727             'md5': '7653032cbb25bf6c80d80f217055fa43',
728             'info_dict': {
729                 'id': '048195-004_PLUS7-F',
730                 'ext': 'flv',
731                 'title': 'X:enius',
732                 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
733                 'upload_date': '20140320',
734             },
735             'params': {
736                 'skip_download': 'Requires rtmpdump'
737             },
738             'skip': 'video gone',
739         },
740         # francetv embed
741         {
742             'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
743             'info_dict': {
744                 'id': 'EV_30231',
745                 'ext': 'mp4',
746                 'title': 'Alcaline, le concert avec Calogero',
747                 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
748                 'upload_date': '20150226',
749                 'timestamp': 1424989860,
750                 'duration': 5400,
751             },
752             'params': {
753                 # m3u8 downloads
754                 'skip_download': True,
755             },
756             'expected_warnings': [
757                 'Forbidden'
758             ]
759         },
760         # Condé Nast embed
761         {
762             'url': 'http://www.wired.com/2014/04/honda-asimo/',
763             'md5': 'ba0dfe966fa007657bd1443ee672db0f',
764             'info_dict': {
765                 'id': '53501be369702d3275860000',
766                 'ext': 'mp4',
767                 'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
768             }
769         },
770         # Dailymotion embed
771         {
772             'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
773             'md5': '441aeeb82eb72c422c7f14ec533999cd',
774             'info_dict': {
775                 'id': 'k2mm4bCdJ6CQ2i7c8o2',
776                 'ext': 'mp4',
777                 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
778                 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
779                 'uploader': 'Spi0n',
780                 'uploader_id': 'xgditw',
781                 'upload_date': '20140425',
782                 'timestamp': 1398441542,
783             },
784             'add_ie': ['Dailymotion'],
785         },
786         # DailyMail embed
787         {
788             'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
789             'info_dict': {
790                 'id': '1495629',
791                 'ext': 'mp4',
792                 'title': 'Care worker punches elderly dementia patient in head 11 times',
793                 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
794             },
795             'add_ie': ['DailyMail'],
796             'params': {
797                 'skip_download': True,
798             },
799         },
800         # YouTube embed
801         {
802             'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
803             'info_dict': {
804                 'id': 'FXRb4ykk4S0',
805                 'ext': 'mp4',
806                 'title': 'The NBL Auction 2014',
807                 'uploader': 'BADMINTON England',
808                 'uploader_id': 'BADMINTONEvents',
809                 'upload_date': '20140603',
810                 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
811             },
812             'add_ie': ['Youtube'],
813             'params': {
814                 'skip_download': True,
815             }
816         },
817         # MTVSercices embed
818         {
819             'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
820             'md5': 'ca1aef97695ef2c1d6973256a57e5252',
821             'info_dict': {
822                 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
823                 'ext': 'mp4',
824                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
825                 'description': 'Two valets share their love for movie star Liam Neesons.',
826                 'timestamp': 1349922600,
827                 'upload_date': '20121011',
828             },
829         },
830         # YouTube embed via <data-embed-url="">
831         {
832             'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
833             'info_dict': {
834                 'id': '4vAffPZIT44',
835                 'ext': 'mp4',
836                 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
837                 'uploader': 'Gameloft',
838                 'uploader_id': 'gameloft',
839                 'upload_date': '20140828',
840                 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
841             },
842             'params': {
843                 'skip_download': True,
844             }
845         },
846         # YouTube <object> embed
847         {
848             'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
849             'md5': '516718101ec834f74318df76259fb3cc',
850             'info_dict': {
851                 'id': 'msN87y-iEx0',
852                 'ext': 'webm',
853                 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
854                 'upload_date': '20080526',
855                 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
856                 'uploader': 'Christopher Sykes',
857                 'uploader_id': 'ChristopherJSykes',
858             },
859             'add_ie': ['Youtube'],
860         },
861         # Camtasia studio
862         {
863             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
864             'playlist': [{
865                 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
866                 'info_dict': {
867                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
868                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
869                     'ext': 'flv',
870                     'duration': 2235.90,
871                 }
872             }, {
873                 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
874                 'info_dict': {
875                     'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
876                     'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
877                     'ext': 'flv',
878                     'duration': 2235.93,
879                 }
880             }],
881             'info_dict': {
882                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
883             }
884         },
885         # Flowplayer
886         {
887             'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
888             'md5': '9d65602bf31c6e20014319c7d07fba27',
889             'info_dict': {
890                 'id': '5123ea6d5e5a7',
891                 'ext': 'mp4',
892                 'age_limit': 18,
893                 'uploader': 'www.handjobhub.com',
894                 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
895             }
896         },
897         # Multiple brightcove videos
898         # https://github.com/rg3/youtube-dl/issues/2283
899         {
900             'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
901             'info_dict': {
902                 'id': 'always-never',
903                 'title': 'Always / Never - The New Yorker',
904             },
905             'playlist_count': 3,
906             'params': {
907                 'extract_flat': False,
908                 'skip_download': True,
909             }
910         },
911         # MLB embed
912         {
913             'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
914             'md5': '96f09a37e44da40dd083e12d9a683327',
915             'info_dict': {
916                 'id': '33322633',
917                 'ext': 'mp4',
918                 'title': 'Ump changes call to ball',
919                 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
920                 'duration': 48,
921                 'timestamp': 1401537900,
922                 'upload_date': '20140531',
923                 'thumbnail': r're:^https?://.*\.jpg$',
924             },
925         },
926         # Wistia embed
927         {
928             'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
929             'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
930             'info_dict': {
931                 'id': '6e2wtrbdaf',
932                 'ext': 'mov',
933                 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
934                 'description': 'a Paywall Videos video from Remilon',
935                 'duration': 644.072,
936                 'uploader': 'study.com',
937                 'timestamp': 1459678540,
938                 'upload_date': '20160403',
939                 'filesize': 24687186,
940             },
941         },
942         {
943             'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
944             'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
945             'info_dict': {
946                 'id': 'uxjb0lwrcz',
947                 'ext': 'mp4',
948                 'title': 'Conversation about Hexagonal Rails Part 1',
949                 'description': 'a Martin Fowler video from ThoughtWorks',
950                 'duration': 1715.0,
951                 'uploader': 'thoughtworks.wistia.com',
952                 'timestamp': 1401832161,
953                 'upload_date': '20140603',
954             },
955         },
956         # Wistia standard embed (async)
957         {
958             'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
959             'info_dict': {
960                 'id': '807fafadvk',
961                 'ext': 'mp4',
962                 'title': 'Drip Brennan Dunn Workshop',
963                 'description': 'a JV Webinars video from getdrip-1',
964                 'duration': 4986.95,
965                 'timestamp': 1463607249,
966                 'upload_date': '20160518',
967             },
968             'params': {
969                 'skip_download': True,
970             }
971         },
972         # Soundcloud embed
973         {
974             'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
975             'info_dict': {
976                 'id': '174391317',
977                 'ext': 'mp3',
978                 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
979                 'uploader': 'Sophos Security',
980                 'title': 'Chet Chat 171 - Oct 29, 2014',
981                 'upload_date': '20141029',
982             }
983         },
984         # Soundcloud multiple embeds
985         {
986             'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
987             'info_dict': {
988                 'id': '52809',
989                 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
990             },
991             'playlist_mincount': 7,
992         },
993         # TuneIn station embed
994         {
995             'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
996             'info_dict': {
997                 'id': '204146',
998                 'ext': 'mp3',
999                 'title': 'CNRV',
1000                 'location': 'Paris, France',
1001                 'is_live': True,
1002             },
1003             'params': {
1004                 # Live stream
1005                 'skip_download': True,
1006             },
1007         },
1008         # Livestream embed
1009         {
1010             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1011             'info_dict': {
1012                 'id': '67864563',
1013                 'ext': 'flv',
1014                 'upload_date': '20141112',
1015                 'title': 'Rosetta #CometLanding webcast HL 10',
1016             }
1017         },
1018         # Another Livestream embed, without 'new.' in URL
1019         {
1020             'url': 'https://www.freespeech.org/',
1021             'info_dict': {
1022                 'id': '123537347',
1023                 'ext': 'mp4',
1024                 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1025             },
1026             'params': {
1027                 # Live stream
1028                 'skip_download': True,
1029             },
1030         },
1031         # LazyYT
1032         {
1033             'url': 'https://skiplagged.com/',
1034             'info_dict': {
1035                 'id': 'skiplagged',
1036                 'title': 'Skiplagged: The smart way to find cheap flights',
1037             },
1038             'playlist_mincount': 1,
1039             'add_ie': ['Youtube'],
1040         },
1041         # Cinchcast embed
1042         {
1043             'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1044             'info_dict': {
1045                 'id': '7141703',
1046                 'ext': 'mp3',
1047                 'upload_date': '20141126',
1048                 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1049             }
1050         },
1051         # Cinerama player
1052         {
1053             'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1054             'info_dict': {
1055                 'id': '730m_DandD_1901_512k',
1056                 'ext': 'mp4',
1057                 'uploader': 'www.abc.net.au',
1058                 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1059             }
1060         },
1061         # embedded viddler video
1062         {
1063             'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1064             'info_dict': {
1065                 'id': '4d03aad9',
1066                 'ext': 'mp4',
1067                 'uploader': 'deadspin',
1068                 'title': 'WALL-TO-GORTAT',
1069                 'timestamp': 1422285291,
1070                 'upload_date': '20150126',
1071             },
1072             'add_ie': ['Viddler'],
1073         },
1074         # Libsyn embed
1075         {
1076             'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1077             'info_dict': {
1078                 'id': '3377616',
1079                 'ext': 'mp3',
1080                 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1081                 'description': 'md5:601cb790edd05908957dae8aaa866465',
1082                 'upload_date': '20150220',
1083             },
1084             'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1085         },
1086         # jwplayer YouTube
1087         {
1088             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1089             'info_dict': {
1090                 'id': 'Mrj4DVp2zeA',
1091                 'ext': 'mp4',
1092                 'upload_date': '20150212',
1093                 'uploader': 'The National Archives UK',
1094                 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1095                 'uploader_id': 'NationalArchives08',
1096                 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1097             },
1098         },
1099         # jwplayer rtmp
1100         {
1101             'url': 'http://www.suffolk.edu/sjc/',
1102             'info_dict': {
1103                 'id': 'sjclive',
1104                 'ext': 'flv',
1105                 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1106                 'uploader': 'www.suffolk.edu',
1107             },
1108             'params': {
1109                 'skip_download': True,
1110             }
1111         },
1112         # Complex jwplayer
1113         {
1114             'url': 'http://www.indiedb.com/games/king-machine/videos',
1115             'info_dict': {
1116                 'id': 'videos',
1117                 'ext': 'mp4',
1118                 'title': 'king machine trailer 1',
1119                 'thumbnail': r're:^https?://.*\.jpg$',
1120             },
1121         },
1122         {
1123             # JWPlayer config passed as variable
1124             'url': 'http://www.txxx.com/videos/3326530/ariele/',
1125             'info_dict': {
1126                 'id': '3326530_hq',
1127                 'ext': 'mp4',
1128                 'title': 'ARIELE | Tube Cup',
1129                 'uploader': 'www.txxx.com',
1130                 'age_limit': 18,
1131             },
1132             'params': {
1133                 'skip_download': True,
1134             }
1135         },
1136         {
1137             # Video.js embed, multiple formats
1138             'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1139             'info_dict': {
1140                 'id': 'yygqldloqIk',
1141                 'ext': 'mp4',
1142                 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1143                 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1144                 'upload_date': '20130314',
1145                 'uploader': 'PROстое3D',
1146                 'uploader_id': 'PROstoe3D',
1147             },
1148             'params': {
1149                 'skip_download': True,
1150             },
1151         },
1152         {
1153             # Video.js embed, single format
1154             'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1155             'info_dict': {
1156                 'id': 'watch',
1157                 'ext': 'mp4',
1158                 'title': 'Step 1 -  Good Foundation',
1159                 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1160             },
1161             'params': {
1162                 'skip_download': True,
1163             },
1164         },
1165         # rtl.nl embed
1166         {
1167             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1168             'playlist_mincount': 5,
1169             'info_dict': {
1170                 'id': 'aanslagen-kopenhagen',
1171                 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1172             }
1173         },
1174         # Zapiks embed
1175         {
1176             'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1177             'info_dict': {
1178                 'id': '118046',
1179                 'ext': 'mp4',
1180                 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1181             }
1182         },
1183         # Kaltura embed (different embed code)
1184         {
1185             'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1186             'info_dict': {
1187                 'id': '1_a52wc67y',
1188                 'ext': 'flv',
1189                 'upload_date': '20150127',
1190                 'uploader_id': 'PremierMedia',
1191                 'timestamp': int,
1192                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1193             },
1194         },
1195         # Kaltura embed with single quotes
1196         {
1197             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1198             'info_dict': {
1199                 'id': '0_izeg5utt',
1200                 'ext': 'mp4',
1201                 'title': '35871',
1202                 'timestamp': 1355743100,
1203                 'upload_date': '20121217',
1204                 'uploader_id': 'batchUser',
1205             },
1206             'add_ie': ['Kaltura'],
1207         },
1208         {
1209             # Kaltura embedded via quoted entry_id
1210             'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1211             'info_dict': {
1212                 'id': '0_utuok90b',
1213                 'ext': 'mp4',
1214                 'title': '06_matthew_brender_raj_dutt',
1215                 'timestamp': 1466638791,
1216                 'upload_date': '20160622',
1217             },
1218             'add_ie': ['Kaltura'],
1219             'expected_warnings': [
1220                 'Could not send HEAD request'
1221             ],
1222             'params': {
1223                 'skip_download': True,
1224             }
1225         },
1226         {
1227             # Kaltura embedded, some fileExt broken (#11480)
1228             'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1229             'info_dict': {
1230                 'id': '1_sgtvehim',
1231                 'ext': 'mp4',
1232                 'title': 'Our "Standard Models" of particle physics and cosmology',
1233                 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1234                 'timestamp': 1321158993,
1235                 'upload_date': '20111113',
1236                 'uploader_id': 'kps1',
1237             },
1238             'add_ie': ['Kaltura'],
1239         },
1240         {
1241             # Kaltura iframe embed
1242             'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1243             'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1244             'info_dict': {
1245                 'id': '0_f2cfbpwy',
1246                 'ext': 'mp4',
1247                 'title': 'I. M. Pei: A Centennial Celebration',
1248                 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1249                 'upload_date': '20170403',
1250                 'uploader_id': 'batchUser',
1251                 'timestamp': 1491232186,
1252             },
1253             'add_ie': ['Kaltura'],
1254         },
1255         # EaglePlatform embed (generic URL)
1256         {
1257             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1258             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1259             'info_dict': {
1260                 'id': '227304',
1261                 'ext': 'mp4',
1262                 'title': 'Навальный вышел на свободу',
1263                 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1264                 'thumbnail': r're:^https?://.*\.jpg$',
1265                 'duration': 87,
1266                 'view_count': int,
1267                 'age_limit': 0,
1268             },
1269             'params': {
1270                 'skip_download': True,
1271             },
1272         },
1273         # referrer protected EaglePlatform embed
1274         {
1275             'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1276             'info_dict': {
1277                 'id': '582306',
1278                 'ext': 'mp4',
1279                 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1280                 'thumbnail': r're:^https?://.*\.jpg$',
1281                 'duration': 3382,
1282                 'view_count': int,
1283             },
1284             'params': {
1285                 'skip_download': True,
1286             },
1287         },
1288         # ClipYou (EaglePlatform) embed (custom URL)
1289         {
1290             'url': 'http://muz-tv.ru/play/7129/',
1291             # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1292             'info_dict': {
1293                 'id': '12820',
1294                 'ext': 'mp4',
1295                 'title': "'O Sole Mio",
1296                 'thumbnail': r're:^https?://.*\.jpg$',
1297                 'duration': 216,
1298                 'view_count': int,
1299             },
1300             'params': {
1301                 'skip_download': True,
1302             },
1303         },
1304         # Pladform embed
1305         {
1306             'url': 'http://muz-tv.ru/kinozal/view/7400/',
1307             'info_dict': {
1308                 'id': '100183293',
1309                 'ext': 'mp4',
1310                 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1311                 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1312                 'thumbnail': r're:^https?://.*\.jpg$',
1313                 'duration': 694,
1314                 'age_limit': 0,
1315             },
1316         },
1317         # Playwire embed
1318         {
1319             'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1320             'info_dict': {
1321                 'id': '3519514',
1322                 'ext': 'mp4',
1323                 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1324                 'thumbnail': r're:^https?://.*\.png$',
1325                 'duration': 45.115,
1326             },
1327         },
1328         # 5min embed
1329         {
1330             'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1331             'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1332             'info_dict': {
1333                 'id': '518726732',
1334                 'ext': 'mp4',
1335                 'title': 'Facebook Creates "On This Day" | Crunch Report',
1336             },
1337         },
1338         # SVT embed
1339         {
1340             'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1341             'info_dict': {
1342                 'id': '2900353',
1343                 'ext': 'flv',
1344                 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1345                 'duration': 27,
1346                 'age_limit': 0,
1347             },
1348         },
1349         # Crooks and Liars embed
1350         {
1351             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1352             'info_dict': {
1353                 'id': '8RUoRhRi',
1354                 'ext': 'mp4',
1355                 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1356                 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1357                 'timestamp': 1428207000,
1358                 'upload_date': '20150405',
1359                 'uploader': 'Heather',
1360             },
1361         },
1362         # Crooks and Liars external embed
1363         {
1364             'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1365             'info_dict': {
1366                 'id': 'MTE3MjUtMzQ2MzA',
1367                 'ext': 'mp4',
1368                 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1369                 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1370                 'timestamp': 1265032391,
1371                 'upload_date': '20100201',
1372                 'uploader': 'Heather',
1373             },
1374         },
1375         # NBC Sports vplayer embed
1376         {
1377             'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1378             'info_dict': {
1379                 'id': 'ln7x1qSThw4k',
1380                 'ext': 'flv',
1381                 'title': "PFT Live: New leader in the 'new-look' defense",
1382                 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1383                 'uploader': 'NBCU-SPORTS',
1384                 'upload_date': '20140107',
1385                 'timestamp': 1389118457,
1386             },
1387         },
1388         # NBC News embed
1389         {
1390             'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1391             'md5': '1aa589c675898ae6d37a17913cf68d66',
1392             'info_dict': {
1393                 'id': '701714499682',
1394                 'ext': 'mp4',
1395                 'title': 'PREVIEW: On Assignment: David Letterman',
1396                 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1397             },
1398         },
1399         # UDN embed
1400         {
1401             'url': 'https://video.udn.com/news/300346',
1402             'md5': 'fd2060e988c326991037b9aff9df21a6',
1403             'info_dict': {
1404                 'id': '300346',
1405                 'ext': 'mp4',
1406                 'title': '中一中男師變性 全校師生力挺',
1407                 'thumbnail': r're:^https?://.*\.jpg$',
1408             },
1409             'params': {
1410                 # m3u8 download
1411                 'skip_download': True,
1412             },
1413         },
1414         # Ooyala embed
1415         {
1416             'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1417             'info_dict': {
1418                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1419                 'ext': 'mp4',
1420                 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1421                 'title': 'This is what separates the Excel masters from the wannabes',
1422                 'duration': 191.933,
1423             },
1424             'params': {
1425                 # m3u8 downloads
1426                 'skip_download': True,
1427             }
1428         },
1429         # Brightcove URL in single quotes
1430         {
1431             'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1432             'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1433             'info_dict': {
1434                 'id': '4255764656001',
1435                 'ext': 'mp4',
1436                 'title': 'SN Presents: Russell Martin, World Citizen',
1437                 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1438                 'uploader': 'Rogers Sportsnet',
1439                 'uploader_id': '1704050871',
1440                 'upload_date': '20150525',
1441                 'timestamp': 1432570283,
1442             },
1443         },
1444         # Dailymotion Cloud video
1445         {
1446             'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1447             'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1448             'info_dict': {
1449                 'id': 'x2uy8t3',
1450                 'ext': 'mp4',
1451                 'title': 'Sauvons les abeilles ! - Le débat',
1452                 'description': 'md5:d9082128b1c5277987825d684939ca26',
1453                 'thumbnail': r're:^https?://.*\.jpe?g$',
1454                 'timestamp': 1434970506,
1455                 'upload_date': '20150622',
1456                 'uploader': 'Public Sénat',
1457                 'uploader_id': 'xa9gza',
1458             }
1459         },
1460         # OnionStudios embed
1461         {
1462             'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1463             'info_dict': {
1464                 'id': '2855',
1465                 'ext': 'mp4',
1466                 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1467                 'thumbnail': r're:^https?://.*\.jpe?g$',
1468                 'uploader': 'ClickHole',
1469                 'uploader_id': 'clickhole',
1470             }
1471         },
1472         # SnagFilms embed
1473         {
1474             'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1475             'info_dict': {
1476                 'id': '74849a00-85a9-11e1-9660-123139220831',
1477                 'ext': 'mp4',
1478                 'title': '#whilewewatch',
1479             }
1480         },
1481         # AdobeTVVideo embed
1482         {
1483             'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1484             'md5': '43662b577c018ad707a63766462b1e87',
1485             'info_dict': {
1486                 'id': '2456',
1487                 'ext': 'mp4',
1488                 'title': 'New experience with Acrobat DC',
1489                 'description': 'New experience with Acrobat DC',
1490                 'duration': 248.667,
1491             },
1492         },
1493         # BrightcoveInPageEmbed embed
1494         {
1495             'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1496             'info_dict': {
1497                 'id': '4238694884001',
1498                 'ext': 'flv',
1499                 'title': 'Tabletop: Dread, Last Thoughts',
1500                 'description': 'Tabletop: Dread, Last Thoughts',
1501                 'duration': 51690,
1502             },
1503         },
1504         # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1505         # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1506         {
1507             'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1508             'info_dict': {
1509                 'id': '4785848093001',
1510                 'ext': 'mp4',
1511                 'title': 'The Cardinal Pell Interview',
1512                 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1513                 'uploader': 'GlobeCast Australia - GlobeStream',
1514                 'uploader_id': '2733773828001',
1515                 'upload_date': '20160304',
1516                 'timestamp': 1457083087,
1517             },
1518             'params': {
1519                 # m3u8 downloads
1520                 'skip_download': True,
1521             },
1522         },
1523         {
1524             # Brightcove embed with whitespace around attribute names
1525             'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1526             'info_dict': {
1527                 'id': '3167554373001',
1528                 'ext': 'mp4',
1529                 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1530                 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1531                 'uploader_id': '1079349493',
1532                 'upload_date': '20140207',
1533                 'timestamp': 1391810548,
1534             },
1535             'params': {
1536                 'skip_download': True,
1537             },
1538         },
1539         # Another form of arte.tv embed
1540         {
1541             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1542             'md5': '850bfe45417ddf221288c88a0cffe2e2',
1543             'info_dict': {
1544                 'id': '030273-562_PLUS7-F',
1545                 'ext': 'mp4',
1546                 'title': 'ARTE Reportage - Nulle part, en France',
1547                 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1548                 'upload_date': '20160409',
1549             },
1550         },
1551         # LiveLeak embed
1552         {
1553             'url': 'http://www.wykop.pl/link/3088787/',
1554             'md5': '7619da8c820e835bef21a1efa2a0fc71',
1555             'info_dict': {
1556                 'id': '874_1459135191',
1557                 'ext': 'mp4',
1558                 'title': 'Man shows poor quality of new apartment building',
1559                 'description': 'The wall is like a sand pile.',
1560                 'uploader': 'Lake8737',
1561             },
1562             'add_ie': [LiveLeakIE.ie_key()],
1563         },
1564         # Another LiveLeak embed pattern (#13336)
1565         {
1566             'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1567             'info_dict': {
1568                 'id': '2eb_1496309988',
1569                 'ext': 'mp4',
1570                 'title': 'Thief robs place where everyone was armed',
1571                 'description': 'md5:694d73ee79e535953cf2488562288eee',
1572                 'uploader': 'brazilwtf',
1573             },
1574             'add_ie': [LiveLeakIE.ie_key()],
1575         },
1576         # Duplicated embedded video URLs
1577         {
1578             'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1579             'info_dict': {
1580                 'id': '149298443_480_16c25b74_2',
1581                 'ext': 'mp4',
1582                 'title': 'vs. Blue Orange Spring Game',
1583                 'uploader': 'www.hudl.com',
1584             },
1585         },
1586         # twitter:player:stream embed
1587         {
1588             'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1589             'info_dict': {
1590                 'id': 'master',
1591                 'ext': 'mp4',
1592                 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1593                 'uploader': 'www.rtl.be',
1594             },
1595             'params': {
1596                 # m3u8 downloads
1597                 'skip_download': True,
1598             },
1599         },
1600         # twitter:player embed
1601         {
1602             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1603             'md5': 'a3e0df96369831de324f0778e126653c',
1604             'info_dict': {
1605                 'id': '4909620399001',
1606                 'ext': 'mp4',
1607                 'title': 'What Do Black Holes Sound Like?',
1608                 'description': 'what do black holes sound like',
1609                 'upload_date': '20160524',
1610                 'uploader_id': '29913724001',
1611                 'timestamp': 1464107587,
1612                 'uploader': 'TheAtlantic',
1613             },
1614             'add_ie': ['BrightcoveLegacy'],
1615         },
1616         # Facebook <iframe> embed
1617         {
1618             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1619             'md5': 'fbcde74f534176ecb015849146dd3aee',
1620             'info_dict': {
1621                 'id': '599637780109885',
1622                 'ext': 'mp4',
1623                 'title': 'Facebook video #599637780109885',
1624             },
1625         },
1626         # Facebook <iframe> embed, plugin video
1627         {
1628             'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1629             'info_dict': {
1630                 'id': '1754168231264132',
1631                 'ext': 'mp4',
1632                 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1633                 'uploader': 'Tariq Ramadan (official)',
1634                 'timestamp': 1496758379,
1635                 'upload_date': '20170606',
1636             },
1637             'params': {
1638                 'skip_download': True,
1639             },
1640         },
1641         # Facebook API embed
1642         {
1643             'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1644             'md5': 'a47372ee61b39a7b90287094d447d94e',
1645             'info_dict': {
1646                 'id': '10153467542406923',
1647                 'ext': 'mp4',
1648                 'title': 'Facebook video #10153467542406923',
1649             },
1650         },
1651         # Wordpress "YouTube Video Importer" plugin
1652         {
1653             'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1654             'md5': 'd16797741b560b485194eddda8121b48',
1655             'info_dict': {
1656                 'id': 'HNTXWDXV9Is',
1657                 'ext': 'mp4',
1658                 'title': 'Blue Devils Drumline Stanford lot 2016',
1659                 'upload_date': '20160627',
1660                 'uploader_id': 'GENOCIDE8GENERAL10',
1661                 'uploader': 'cylus cyrus',
1662             },
1663         },
1664         {
1665             # video stored on custom kaltura server
1666             'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1667             'md5': '537617d06e64dfed891fa1593c4b30cc',
1668             'info_dict': {
1669                 'id': '0_1iotm5bh',
1670                 'ext': 'mp4',
1671                 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1672                 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1673                 'uploader_id': 'videos.expansion@el-mundo.net',
1674                 'upload_date': '20150429',
1675                 'timestamp': 1430303472,
1676             },
1677             'add_ie': ['Kaltura'],
1678         },
1679         {
1680             # Non-standard Vimeo embed
1681             'url': 'https://openclassrooms.com/courses/understanding-the-web',
1682             'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1683             'info_dict': {
1684                 'id': '148867247',
1685                 'ext': 'mp4',
1686                 'title': 'Understanding the web - Teaser',
1687                 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1688                 'upload_date': '20151214',
1689                 'uploader': 'OpenClassrooms',
1690                 'uploader_id': 'openclassrooms',
1691             },
1692             'add_ie': ['Vimeo'],
1693         },
1694         {
1695             # generic vimeo embed that requires original URL passed as Referer
1696             'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1697             'only_matching': True,
1698         },
1699         {
1700             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1701             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1702             'info_dict': {
1703                 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1704                 'ext': 'mp4',
1705                 'title': 'Big Buck Bunny',
1706                 'description': 'Royalty free test video',
1707                 'timestamp': 1432816365,
1708                 'upload_date': '20150528',
1709                 'is_live': False,
1710             },
1711             'params': {
1712                 'skip_download': True,
1713             },
1714             'add_ie': [ArkenaIE.ie_key()],
1715         },
1716         {
1717             'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1718             'info_dict': {
1719                 'id': '1c7141f46c',
1720                 'ext': 'mp4',
1721                 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1722             },
1723             'params': {
1724                 'skip_download': True,
1725             },
1726             'add_ie': [Vbox7IE.ie_key()],
1727         },
1728         {
1729             # DBTV embeds
1730             'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1731             'info_dict': {
1732                 'id': '43254897',
1733                 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1734             },
1735             'playlist_mincount': 3,
1736         },
1737         {
1738             # Videa embeds
1739             'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1740             'info_dict': {
1741                 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1742                 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1743             },
1744             'playlist_mincount': 2,
1745         },
1746         {
1747             # 20 minuten embed
1748             'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1749             'info_dict': {
1750                 'id': '523629',
1751                 'ext': 'mp4',
1752                 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1753                 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1754             },
1755             'params': {
1756                 'skip_download': True,
1757             },
1758             'add_ie': [TwentyMinutenIE.ie_key()],
1759         },
1760         {
1761             # VideoPress embed
1762             'url': 'https://en.support.wordpress.com/videopress/',
1763             'info_dict': {
1764                 'id': 'OcobLTqC',
1765                 'ext': 'm4v',
1766                 'title': 'IMG_5786',
1767                 'timestamp': 1435711927,
1768                 'upload_date': '20150701',
1769             },
1770             'params': {
1771                 'skip_download': True,
1772             },
1773             'add_ie': [VideoPressIE.ie_key()],
1774         },
1775         {
1776             # Rutube embed
1777             'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1778             'info_dict': {
1779                 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1780                 'ext': 'flv',
1781                 'title': 'Магаззино: Казань 2',
1782                 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1783                 'uploader': 'Магаззино',
1784                 'upload_date': '20170228',
1785                 'uploader_id': '996642',
1786             },
1787             'params': {
1788                 'skip_download': True,
1789             },
1790             'add_ie': [RutubeIE.ie_key()],
1791         },
1792         {
1793             # ThePlatform embedded with whitespaces in URLs
1794             'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1795             'only_matching': True,
1796         },
1797         {
1798             # Senate ISVP iframe https
1799             'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1800             'md5': 'fb8c70b0b515e5037981a2492099aab8',
1801             'info_dict': {
1802                 'id': 'govtaff020316',
1803                 'ext': 'mp4',
1804                 'title': 'Integrated Senate Video Player',
1805             },
1806             'add_ie': [SenateISVPIE.ie_key()],
1807         },
1808         {
1809             # Limelight embeds (1 channel embed + 4 media embeds)
1810             'url': 'http://www.sedona.com/FacilitatorTraining2017',
1811             'info_dict': {
1812                 'id': 'FacilitatorTraining2017',
1813                 'title': 'Facilitator Training 2017',
1814             },
1815             'playlist_mincount': 5,
1816         },
1817         {
1818             # Limelight embed (LimelightPlayerUtil.embed)
1819             'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1820             'info_dict': {
1821                 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1822                 'ext': 'mp4',
1823                 'title': '07448641',
1824                 'timestamp': 1499890639,
1825                 'upload_date': '20170712',
1826             },
1827             'params': {
1828                 'skip_download': True,
1829             },
1830             'add_ie': ['LimelightMedia'],
1831         },
1832         {
1833             'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1834             'info_dict': {
1835                 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1836                 'title': 'Standoff with Walnut Creek murder suspect ends',
1837                 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1838             },
1839             'playlist_mincount': 4,
1840         },
1841         {
1842             # WashingtonPost embed
1843             'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1844             'info_dict': {
1845                 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1846                 'ext': 'mp4',
1847                 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1848                 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1849                 'timestamp': 1455216756,
1850                 'uploader': 'The Washington Post',
1851                 'upload_date': '20160211',
1852             },
1853             'add_ie': [WashingtonPostIE.ie_key()],
1854         },
1855         {
1856             # Mediaset embed
1857             'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1858             'info_dict': {
1859                 'id': '720642',
1860                 'ext': 'mp4',
1861                 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1862             },
1863             'params': {
1864                 'skip_download': True,
1865             },
1866             'add_ie': [MediasetIE.ie_key()],
1867         },
1868         {
1869             # JOJ.sk embeds
1870             'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1871             'info_dict': {
1872                 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1873                 'title': 'Slovenskom sa prehnala vlna silných búrok',
1874             },
1875             'playlist_mincount': 5,
1876             'add_ie': [JojIE.ie_key()],
1877         },
1878         {
1879             # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1880             'url': 'https://tvrain.ru/amp/418921/',
1881             'md5': 'cc00413936695987e8de148b67d14f1d',
1882             'info_dict': {
1883                 'id': '418921',
1884                 'ext': 'mp4',
1885                 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1886             },
1887         },
1888         {
1889             # vzaar embed
1890             'url': 'http://help.vzaar.com/article/165-embedding-video',
1891             'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1892             'info_dict': {
1893                 'id': '8707641',
1894                 'ext': 'mp4',
1895                 'title': 'Building A Business Online: Principal Chairs Q & A',
1896             },
1897         },
1898         {
1899             # multiple HTML5 videos on one page
1900             'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1901             'info_dict': {
1902                 'id': 'keyscenarios',
1903                 'title': 'Rescue Kit 14 Free Edition - Getting started',
1904             },
1905             'playlist_count': 4,
1906         }
1907         # {
1908         #     # TODO: find another test
1909         #     # http://schema.org/VideoObject
1910         #     'url': 'https://flipagram.com/f/nyvTSJMKId',
1911         #     'md5': '888dcf08b7ea671381f00fab74692755',
1912         #     'info_dict': {
1913         #         'id': 'nyvTSJMKId',
1914         #         'ext': 'mp4',
1915         #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1916         #         'description': '#love for cats.',
1917         #         'timestamp': 1461244995,
1918         #         'upload_date': '20160421',
1919         #     },
1920         #     'params': {
1921         #         'force_generic_extractor': True,
1922         #     },
1923         # }
1924     ]
1925
1926     def report_following_redirect(self, new_url):
1927         """Report information extraction."""
1928         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1929
1930     def _extract_rss(self, url, video_id, doc):
1931         playlist_title = doc.find('./channel/title').text
1932         playlist_desc_el = doc.find('./channel/description')
1933         playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1934
1935         entries = []
1936         for it in doc.findall('./channel/item'):
1937             next_url = xpath_text(it, 'link', fatal=False)
1938             if not next_url:
1939                 enclosure_nodes = it.findall('./enclosure')
1940                 for e in enclosure_nodes:
1941                     next_url = e.attrib.get('url')
1942                     if next_url:
1943                         break
1944
1945             if not next_url:
1946                 continue
1947
1948             entries.append({
1949                 '_type': 'url_transparent',
1950                 'url': next_url,
1951                 'title': it.find('title').text,
1952             })
1953
1954         return {
1955             '_type': 'playlist',
1956             'id': url,
1957             'title': playlist_title,
1958             'description': playlist_desc,
1959             'entries': entries,
1960         }
1961
1962     def _extract_camtasia(self, url, video_id, webpage):
1963         """ Returns None if no camtasia video can be found. """
1964
1965         camtasia_cfg = self._search_regex(
1966             r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1967             webpage, 'camtasia configuration file', default=None)
1968         if camtasia_cfg is None:
1969             return None
1970
1971         title = self._html_search_meta('DC.title', webpage, fatal=True)
1972
1973         camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1974         camtasia_cfg = self._download_xml(
1975             camtasia_url, video_id,
1976             note='Downloading camtasia configuration',
1977             errnote='Failed to download camtasia configuration')
1978         fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1979
1980         entries = []
1981         for n in fileset_node.getchildren():
1982             url_n = n.find('./uri')
1983             if url_n is None:
1984                 continue
1985
1986             entries.append({
1987                 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1988                 'title': '%s - %s' % (title, n.tag),
1989                 'url': compat_urlparse.urljoin(url, url_n.text),
1990                 'duration': float_or_none(n.find('./duration').text),
1991             })
1992
1993         return {
1994             '_type': 'playlist',
1995             'entries': entries,
1996             'title': title,
1997         }
1998
1999     def _real_extract(self, url):
2000         if url.startswith('//'):
2001             return {
2002                 '_type': 'url',
2003                 'url': self.http_scheme() + url,
2004             }
2005
2006         parsed_url = compat_urlparse.urlparse(url)
2007         if not parsed_url.scheme:
2008             default_search = self._downloader.params.get('default_search')
2009             if default_search is None:
2010                 default_search = 'fixup_error'
2011
2012             if default_search in ('auto', 'auto_warning', 'fixup_error'):
2013                 if '/' in url:
2014                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2015                     return self.url_result('http://' + url)
2016                 elif default_search != 'fixup_error':
2017                     if default_search == 'auto_warning':
2018                         if re.match(r'^(?:url|URL)$', url):
2019                             raise ExtractorError(
2020                                 'Invalid URL:  %r . Call youtube-dl like this:  youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc"  ' % url,
2021                                 expected=True)
2022                         else:
2023                             self._downloader.report_warning(
2024                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
2025                     return self.url_result('ytsearch:' + url)
2026
2027             if default_search in ('error', 'fixup_error'):
2028                 raise ExtractorError(
2029                     '%r is not a valid URL. '
2030                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
2031                     % (url, url), expected=True)
2032             else:
2033                 if ':' not in default_search:
2034                     default_search += ':'
2035                 return self.url_result(default_search + url)
2036
2037         url, smuggled_data = unsmuggle_url(url)
2038         force_videoid = None
2039         is_intentional = smuggled_data and smuggled_data.get('to_generic')
2040         if smuggled_data and 'force_videoid' in smuggled_data:
2041             force_videoid = smuggled_data['force_videoid']
2042             video_id = force_videoid
2043         else:
2044             video_id = self._generic_id(url)
2045
2046         self.to_screen('%s: Requesting header' % video_id)
2047
2048         head_req = HEADRequest(url)
2049         head_response = self._request_webpage(
2050             head_req, video_id,
2051             note=False, errnote='Could not send HEAD request to %s' % url,
2052             fatal=False)
2053
2054         if head_response is not False:
2055             # Check for redirect
2056             new_url = compat_str(head_response.geturl())
2057             if url != new_url:
2058                 self.report_following_redirect(new_url)
2059                 if force_videoid:
2060                     new_url = smuggle_url(
2061                         new_url, {'force_videoid': force_videoid})
2062                 return self.url_result(new_url)
2063
2064         full_response = None
2065         if head_response is False:
2066             request = sanitized_Request(url)
2067             request.add_header('Accept-Encoding', '*')
2068             full_response = self._request_webpage(request, video_id)
2069             head_response = full_response
2070
2071         info_dict = {
2072             'id': video_id,
2073             'title': self._generic_title(url),
2074             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2075         }
2076
2077         # Check for direct link to a video
2078         content_type = head_response.headers.get('Content-Type', '').lower()
2079         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2080         if m:
2081             format_id = compat_str(m.group('format_id'))
2082             if format_id.endswith('mpegurl'):
2083                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2084             elif format_id == 'f4m':
2085                 formats = self._extract_f4m_formats(url, video_id)
2086             else:
2087                 formats = [{
2088                     'format_id': format_id,
2089                     'url': url,
2090                     'vcodec': 'none' if m.group('type') == 'audio' else None
2091                 }]
2092                 info_dict['direct'] = True
2093             self._sort_formats(formats)
2094             info_dict['formats'] = formats
2095             return info_dict
2096
2097         if not self._downloader.params.get('test', False) and not is_intentional:
2098             force = self._downloader.params.get('force_generic_extractor', False)
2099             self._downloader.report_warning(
2100                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2101
2102         if not full_response:
2103             request = sanitized_Request(url)
2104             # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2105             # making it impossible to download only chunk of the file (yet we need only 512kB to
2106             # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2107             # that will always result in downloading the whole file that is not desirable.
2108             # Therefore for extraction pass we have to override Accept-Encoding to any in order
2109             # to accept raw bytes and being able to download only a chunk.
2110             # It may probably better to solve this by checking Content-Type for application/octet-stream
2111             # after HEAD request finishes, but not sure if we can rely on this.
2112             request.add_header('Accept-Encoding', '*')
2113             full_response = self._request_webpage(request, video_id)
2114
2115         first_bytes = full_response.read(512)
2116
2117         # Is it an M3U playlist?
2118         if first_bytes.startswith(b'#EXTM3U'):
2119             info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2120             self._sort_formats(info_dict['formats'])
2121             return info_dict
2122
2123         # Maybe it's a direct link to a video?
2124         # Be careful not to download the whole thing!
2125         if not is_html(first_bytes):
2126             self._downloader.report_warning(
2127                 'URL could be a direct video link, returning it as such.')
2128             info_dict.update({
2129                 'direct': True,
2130                 'url': url,
2131             })
2132             return info_dict
2133
2134         webpage = self._webpage_read_content(
2135             full_response, url, video_id, prefix=first_bytes)
2136
2137         self.report_extraction(video_id)
2138
2139         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2140         try:
2141             doc = compat_etree_fromstring(webpage.encode('utf-8'))
2142             if doc.tag == 'rss':
2143                 return self._extract_rss(url, video_id, doc)
2144             elif doc.tag == 'SmoothStreamingMedia':
2145                 info_dict['formats'] = self._parse_ism_formats(doc, url)
2146                 self._sort_formats(info_dict['formats'])
2147                 return info_dict
2148             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2149                 smil = self._parse_smil(doc, url, video_id)
2150                 self._sort_formats(smil['formats'])
2151                 return smil
2152             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2153                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2154             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2155                 info_dict['formats'] = self._parse_mpd_formats(
2156                     doc, video_id,
2157                     mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2158                     mpd_url=url)
2159                 self._sort_formats(info_dict['formats'])
2160                 return info_dict
2161             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2162                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2163                 self._sort_formats(info_dict['formats'])
2164                 return info_dict
2165         except compat_xml_parse_error:
2166             pass
2167
2168         # Is it a Camtasia project?
2169         camtasia_res = self._extract_camtasia(url, video_id, webpage)
2170         if camtasia_res is not None:
2171             return camtasia_res
2172
2173         # Sometimes embedded video player is hidden behind percent encoding
2174         # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2175         # Unescaping the whole page allows to handle those cases in a generic way
2176         webpage = compat_urllib_parse_unquote(webpage)
2177
2178         # it's tempting to parse this further, but you would
2179         # have to take into account all the variations like
2180         #   Video Title - Site Name
2181         #   Site Name | Video Title
2182         #   Video Title - Tagline | Site Name
2183         # and so on and so forth; it's just not practical
2184         video_title = self._og_search_title(
2185             webpage, default=None) or self._html_search_regex(
2186             r'(?s)<title>(.*?)</title>', webpage, 'video title',
2187             default='video')
2188
2189         # Try to detect age limit automatically
2190         age_limit = self._rta_search(webpage)
2191         # And then there are the jokers who advertise that they use RTA,
2192         # but actually don't.
2193         AGE_LIMIT_MARKERS = [
2194             r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2195         ]
2196         if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2197             age_limit = 18
2198
2199         # video uploader is domain name
2200         video_uploader = self._search_regex(
2201             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2202
2203         video_description = self._og_search_description(webpage, default=None)
2204         video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2205
2206         info_dict.update({
2207             'title': video_title,
2208             'description': video_description,
2209             'thumbnail': video_thumbnail,
2210             'age_limit': age_limit,
2211         })
2212
2213         # Look for Brightcove Legacy Studio embeds
2214         bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2215         if bc_urls:
2216             entries = [{
2217                 '_type': 'url',
2218                 'url': smuggle_url(bc_url, {'Referer': url}),
2219                 'ie_key': 'BrightcoveLegacy'
2220             } for bc_url in bc_urls]
2221
2222             return {
2223                 '_type': 'playlist',
2224                 'title': video_title,
2225                 'id': video_id,
2226                 'entries': entries,
2227             }
2228
2229         # Look for Brightcove New Studio embeds
2230         bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2231         if bc_urls:
2232             return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2233
2234         # Look for Nexx embeds
2235         nexx_urls = NexxIE._extract_urls(webpage)
2236         if nexx_urls:
2237             return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2238
2239         # Look for Nexx iFrame embeds
2240         nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2241         if nexx_embed_urls:
2242             return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2243
2244         # Look for ThePlatform embeds
2245         tp_urls = ThePlatformIE._extract_urls(webpage)
2246         if tp_urls:
2247             return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2248
2249         # Look for Vessel embeds
2250         vessel_urls = VesselIE._extract_urls(webpage)
2251         if vessel_urls:
2252             return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2253
2254         # Look for embedded rtl.nl player
2255         matches = re.findall(
2256             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2257             webpage)
2258         if matches:
2259             return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2260
2261         vimeo_urls = VimeoIE._extract_urls(url, webpage)
2262         if vimeo_urls:
2263             return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2264
2265         vid_me_embed_url = self._search_regex(
2266             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2267             webpage, 'vid.me embed', default=None)
2268         if vid_me_embed_url is not None:
2269             return self.url_result(vid_me_embed_url, 'Vidme')
2270
2271         # Look for YouTube embeds
2272         youtube_urls = YoutubeIE._extract_urls(webpage)
2273         if youtube_urls:
2274             return self.playlist_from_matches(
2275                 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2276
2277         matches = DailymotionIE._extract_urls(webpage)
2278         if matches:
2279             return self.playlist_from_matches(matches, video_id, video_title)
2280
2281         # Look for embedded Dailymotion playlist player (#3822)
2282         m = re.search(
2283             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2284         if m:
2285             playlists = re.findall(
2286                 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2287             if playlists:
2288                 return self.playlist_from_matches(
2289                     playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2290
2291         # Look for DailyMail embeds
2292         dailymail_urls = DailyMailIE._extract_urls(webpage)
2293         if dailymail_urls:
2294             return self.playlist_from_matches(
2295                 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2296
2297         # Look for embedded Wistia player
2298         wistia_url = WistiaIE._extract_url(webpage)
2299         if wistia_url:
2300             return {
2301                 '_type': 'url_transparent',
2302                 'url': self._proto_relative_url(wistia_url),
2303                 'ie_key': WistiaIE.ie_key(),
2304                 'uploader': video_uploader,
2305             }
2306
2307         # Look for SVT player
2308         svt_url = SVTIE._extract_url(webpage)
2309         if svt_url:
2310             return self.url_result(svt_url, 'SVT')
2311
2312         # Look for Bandcamp pages with custom domain
2313         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2314         if mobj is not None:
2315             burl = unescapeHTML(mobj.group(1))
2316             # Don't set the extractor because it can be a track url or an album
2317             return self.url_result(burl)
2318
2319         # Look for embedded Vevo player
2320         mobj = re.search(
2321             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2322         if mobj is not None:
2323             return self.url_result(mobj.group('url'))
2324
2325         # Look for embedded Viddler player
2326         mobj = re.search(
2327             r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2328             webpage)
2329         if mobj is not None:
2330             return self.url_result(mobj.group('url'))
2331
2332         # Look for NYTimes player
2333         mobj = re.search(
2334             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2335             webpage)
2336         if mobj is not None:
2337             return self.url_result(mobj.group('url'))
2338
2339         # Look for Libsyn player
2340         mobj = re.search(
2341             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2342         if mobj is not None:
2343             return self.url_result(mobj.group('url'))
2344
2345         # Look for Ooyala videos
2346         mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2347                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2348                 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2349                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2350                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2351         if mobj is not None:
2352             embed_token = self._search_regex(
2353                 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2354                 webpage, 'ooyala embed token', default=None)
2355             return OoyalaIE._build_url_result(smuggle_url(
2356                 mobj.group('ec'), {
2357                     'domain': url,
2358                     'embed_token': embed_token,
2359                 }))
2360
2361         # Look for multiple Ooyala embeds on SBN network websites
2362         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2363         if mobj is not None:
2364             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2365             if embeds:
2366                 return self.playlist_from_matches(
2367                     embeds, video_id, video_title,
2368                     getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2369
2370         # Look for Aparat videos
2371         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2372         if mobj is not None:
2373             return self.url_result(mobj.group(1), 'Aparat')
2374
2375         # Look for MPORA videos
2376         mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2377         if mobj is not None:
2378             return self.url_result(mobj.group(1), 'Mpora')
2379
2380         # Look for embedded NovaMov-based player
2381         mobj = re.search(
2382             r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2383                     (?P<url>http://(?:(?:embed|www)\.)?
2384                         (?:novamov\.com|
2385                            nowvideo\.(?:ch|sx|eu|at|ag|co)|
2386                            videoweed\.(?:es|com)|
2387                            movshare\.(?:net|sx|ag)|
2388                            divxstage\.(?:eu|net|ch|co|at|ag))
2389                         /embed\.php.+?)\1''', webpage)
2390         if mobj is not None:
2391             return self.url_result(mobj.group('url'))
2392
2393         # Look for embedded Facebook player
2394         facebook_urls = FacebookIE._extract_urls(webpage)
2395         if facebook_urls:
2396             return self.playlist_from_matches(facebook_urls, video_id, video_title)
2397
2398         # Look for embedded VK player
2399         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2400         if mobj is not None:
2401             return self.url_result(mobj.group('url'), 'VK')
2402
2403         # Look for embedded Odnoklassniki player
2404         mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2405         if mobj is not None:
2406             return self.url_result(mobj.group('url'), 'Odnoklassniki')
2407
2408         # Look for embedded ivi player
2409         mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2410         if mobj is not None:
2411             return self.url_result(mobj.group('url'), 'Ivi')
2412
2413         # Look for embedded Huffington Post player
2414         mobj = re.search(
2415             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2416         if mobj is not None:
2417             return self.url_result(mobj.group('url'), 'HuffPost')
2418
2419         # Look for embed.ly
2420         mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2421         if mobj is not None:
2422             return self.url_result(mobj.group('url'))
2423         mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2424         if mobj is not None:
2425             return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2426
2427         # Look for funnyordie embed
2428         matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2429         if matches:
2430             return self.playlist_from_matches(
2431                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2432
2433         # Look for BBC iPlayer embed
2434         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2435         if matches:
2436             return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2437
2438         # Look for embedded RUTV player
2439         rutv_url = RUTVIE._extract_url(webpage)
2440         if rutv_url:
2441             return self.url_result(rutv_url, 'RUTV')
2442
2443         # Look for embedded TVC player
2444         tvc_url = TVCIE._extract_url(webpage)
2445         if tvc_url:
2446             return self.url_result(tvc_url, 'TVC')
2447
2448         # Look for embedded SportBox player
2449         sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2450         if sportbox_urls:
2451             return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2452
2453         # Look for embedded XHamster player
2454         xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2455         if xhamster_urls:
2456             return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2457
2458         # Look for embedded TNAFlixNetwork player
2459         tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2460         if tnaflix_urls:
2461             return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2462
2463         # Look for embedded PornHub player
2464         pornhub_urls = PornHubIE._extract_urls(webpage)
2465         if pornhub_urls:
2466             return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2467
2468         # Look for embedded DrTuber player
2469         drtuber_urls = DrTuberIE._extract_urls(webpage)
2470         if drtuber_urls:
2471             return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2472
2473         # Look for embedded RedTube player
2474         redtube_urls = RedTubeIE._extract_urls(webpage)
2475         if redtube_urls:
2476             return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2477
2478         # Look for embedded Tvigle player
2479         mobj = re.search(
2480             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2481         if mobj is not None:
2482             return self.url_result(mobj.group('url'), 'Tvigle')
2483
2484         # Look for embedded TED player
2485         mobj = re.search(
2486             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2487         if mobj is not None:
2488             return self.url_result(mobj.group('url'), 'TED')
2489
2490         # Look for embedded Ustream videos
2491         ustream_url = UstreamIE._extract_url(webpage)
2492         if ustream_url:
2493             return self.url_result(ustream_url, UstreamIE.ie_key())
2494
2495         # Look for embedded arte.tv player
2496         mobj = re.search(
2497             r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2498             webpage)
2499         if mobj is not None:
2500             return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2501
2502         # Look for embedded francetv player
2503         mobj = re.search(
2504             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2505             webpage)
2506         if mobj is not None:
2507             return self.url_result(mobj.group('url'))
2508
2509         # Look for embedded smotri.com player
2510         smotri_url = SmotriIE._extract_url(webpage)
2511         if smotri_url:
2512             return self.url_result(smotri_url, 'Smotri')
2513
2514         # Look for embedded Myvi.ru player
2515         myvi_url = MyviIE._extract_url(webpage)
2516         if myvi_url:
2517             return self.url_result(myvi_url)
2518
2519         # Look for embedded soundcloud player
2520         soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2521         if soundcloud_urls:
2522             return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2523
2524         # Look for tunein player
2525         tunein_urls = TuneInBaseIE._extract_urls(webpage)
2526         if tunein_urls:
2527             return self.playlist_from_matches(tunein_urls, video_id, video_title)
2528
2529         # Look for embedded mtvservices player
2530         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2531         if mtvservices_url:
2532             return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2533
2534         # Look for embedded yahoo player
2535         mobj = re.search(
2536             r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2537             webpage)
2538         if mobj is not None:
2539             return self.url_result(mobj.group('url'), 'Yahoo')
2540
2541         # Look for embedded sbs.com.au player
2542         mobj = re.search(
2543             r'''(?x)
2544             (?:
2545                 <meta\s+property="og:video"\s+content=|
2546                 <iframe[^>]+?src=
2547             )
2548             (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2549             webpage)
2550         if mobj is not None:
2551             return self.url_result(mobj.group('url'), 'SBS')
2552
2553         # Look for embedded Cinchcast player
2554         mobj = re.search(
2555             r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2556             webpage)
2557         if mobj is not None:
2558             return self.url_result(mobj.group('url'), 'Cinchcast')
2559
2560         mobj = re.search(
2561             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2562             webpage)
2563         if not mobj:
2564             mobj = re.search(
2565                 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2566                 webpage)
2567         if mobj is not None:
2568             return self.url_result(mobj.group('url'), 'MLB')
2569
2570         mobj = re.search(
2571             r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2572             webpage)
2573         if mobj is not None:
2574             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2575
2576         mobj = re.search(
2577             r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2578             webpage)
2579         if mobj is not None:
2580             return self.url_result(mobj.group('url'), 'Livestream')
2581
2582         # Look for Zapiks embed
2583         mobj = re.search(
2584             r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2585         if mobj is not None:
2586             return self.url_result(mobj.group('url'), 'Zapiks')
2587
2588         # Look for Kaltura embeds
2589         kaltura_url = KalturaIE._extract_url(webpage)
2590         if kaltura_url:
2591             return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2592
2593         # Look for EaglePlatform embeds
2594         eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2595         if eagleplatform_url:
2596             return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2597
2598         # Look for ClipYou (uses EaglePlatform) embeds
2599         mobj = re.search(
2600             r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2601         if mobj is not None:
2602             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2603
2604         # Look for Pladform embeds
2605         pladform_url = PladformIE._extract_url(webpage)
2606         if pladform_url:
2607             return self.url_result(pladform_url)
2608
2609         # Look for Videomore embeds
2610         videomore_url = VideomoreIE._extract_url(webpage)
2611         if videomore_url:
2612             return self.url_result(videomore_url)
2613
2614         # Look for Webcaster embeds
2615         webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2616         if webcaster_url:
2617             return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2618
2619         # Look for Playwire embeds
2620         mobj = re.search(
2621             r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2622         if mobj is not None:
2623             return self.url_result(mobj.group('url'))
2624
2625         # Look for 5min embeds
2626         mobj = re.search(
2627             r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2628         if mobj is not None:
2629             return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2630
2631         # Look for Crooks and Liars embeds
2632         mobj = re.search(
2633             r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2634         if mobj is not None:
2635             return self.url_result(mobj.group('url'))
2636
2637         # Look for NBC Sports VPlayer embeds
2638         nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2639         if nbc_sports_url:
2640             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2641
2642         # Look for NBC News embeds
2643         nbc_news_embed_url = re.search(
2644             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2645         if nbc_news_embed_url:
2646             return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2647
2648         # Look for Google Drive embeds
2649         google_drive_url = GoogleDriveIE._extract_url(webpage)
2650         if google_drive_url:
2651             return self.url_result(google_drive_url, 'GoogleDrive')
2652
2653         # Look for UDN embeds
2654         mobj = re.search(
2655             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2656         if mobj is not None:
2657             return self.url_result(
2658                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2659
2660         # Look for Senate ISVP iframe
2661         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2662         if senate_isvp_url:
2663             return self.url_result(senate_isvp_url, 'SenateISVP')
2664
2665         # Look for Dailymotion Cloud videos
2666         dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2667         if dmcloud_url:
2668             return self.url_result(dmcloud_url, 'DailymotionCloud')
2669
2670         # Look for OnionStudios embeds
2671         onionstudios_url = OnionStudiosIE._extract_url(webpage)
2672         if onionstudios_url:
2673             return self.url_result(onionstudios_url)
2674
2675         # Look for ViewLift embeds
2676         viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2677         if viewlift_url:
2678             return self.url_result(viewlift_url)
2679
2680         # Look for JWPlatform embeds
2681         jwplatform_url = JWPlatformIE._extract_url(webpage)
2682         if jwplatform_url:
2683             return self.url_result(jwplatform_url, 'JWPlatform')
2684
2685         # Look for Digiteka embeds
2686         digiteka_url = DigitekaIE._extract_url(webpage)
2687         if digiteka_url:
2688             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2689
2690         # Look for Arkena embeds
2691         arkena_url = ArkenaIE._extract_url(webpage)
2692         if arkena_url:
2693             return self.url_result(arkena_url, ArkenaIE.ie_key())
2694
2695         # Look for Piksel embeds
2696         piksel_url = PikselIE._extract_url(webpage)
2697         if piksel_url:
2698             return self.url_result(piksel_url, PikselIE.ie_key())
2699
2700         # Look for Limelight embeds
2701         limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2702         if limelight_urls:
2703             return self.playlist_result(
2704                 limelight_urls, video_id, video_title, video_description)
2705
2706         # Look for Anvato embeds
2707         anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2708         if anvato_urls:
2709             return self.playlist_result(
2710                 anvato_urls, video_id, video_title, video_description)
2711
2712         # Look for AdobeTVVideo embeds
2713         mobj = re.search(
2714             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2715             webpage)
2716         if mobj is not None:
2717             return self.url_result(
2718                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2719                 'AdobeTVVideo')
2720
2721         # Look for Vine embeds
2722         mobj = re.search(
2723             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2724             webpage)
2725         if mobj is not None:
2726             return self.url_result(
2727                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2728
2729         # Look for VODPlatform embeds
2730         mobj = re.search(
2731             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2732             webpage)
2733         if mobj is not None:
2734             return self.url_result(
2735                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2736
2737         # Look for Mangomolo embeds
2738         mobj = re.search(
2739             r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2740                 (?:
2741                     video\?.*?\bid=(?P<video_id>\d+)|
2742                     index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2743                 ).+?)\1''', webpage)
2744         if mobj is not None:
2745             info = {
2746                 '_type': 'url_transparent',
2747                 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2748                 'title': video_title,
2749                 'description': video_description,
2750                 'thumbnail': video_thumbnail,
2751                 'uploader': video_uploader,
2752             }
2753             video_id = mobj.group('video_id')
2754             if video_id:
2755                 info.update({
2756                     'ie_key': 'MangomoloVideo',
2757                     'id': video_id,
2758                 })
2759             else:
2760                 info.update({
2761                     'ie_key': 'MangomoloLive',
2762                     'id': mobj.group('channel_id'),
2763                 })
2764             return info
2765
2766         # Look for Instagram embeds
2767         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2768         if instagram_embed_url is not None:
2769             return self.url_result(
2770                 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2771
2772         # Look for LiveLeak embeds
2773         liveleak_urls = LiveLeakIE._extract_urls(webpage)
2774         if liveleak_urls:
2775             return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2776
2777         # Look for 3Q SDN embeds
2778         threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2779         if threeqsdn_url:
2780             return {
2781                 '_type': 'url_transparent',
2782                 'ie_key': ThreeQSDNIE.ie_key(),
2783                 'url': self._proto_relative_url(threeqsdn_url),
2784                 'title': video_title,
2785                 'description': video_description,
2786                 'thumbnail': video_thumbnail,
2787                 'uploader': video_uploader,
2788             }
2789
2790         # Look for VBOX7 embeds
2791         vbox7_url = Vbox7IE._extract_url(webpage)
2792         if vbox7_url:
2793             return self.url_result(vbox7_url, Vbox7IE.ie_key())
2794
2795         # Look for DBTV embeds
2796         dbtv_urls = DBTVIE._extract_urls(webpage)
2797         if dbtv_urls:
2798             return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2799
2800         # Look for Videa embeds
2801         videa_urls = VideaIE._extract_urls(webpage)
2802         if videa_urls:
2803             return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2804
2805         # Look for 20 minuten embeds
2806         twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2807         if twentymin_urls:
2808             return self.playlist_from_matches(
2809                 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2810
2811         # Look for Openload embeds
2812         openload_urls = OpenloadIE._extract_urls(webpage)
2813         if openload_urls:
2814             return self.playlist_from_matches(
2815                 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2816
2817         # Look for VideoPress embeds
2818         videopress_urls = VideoPressIE._extract_urls(webpage)
2819         if videopress_urls:
2820             return self.playlist_from_matches(
2821                 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2822
2823         # Look for Rutube embeds
2824         rutube_urls = RutubeIE._extract_urls(webpage)
2825         if rutube_urls:
2826             return self.playlist_from_matches(
2827                 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2828
2829         # Look for WashingtonPost embeds
2830         wapo_urls = WashingtonPostIE._extract_urls(webpage)
2831         if wapo_urls:
2832             return self.playlist_from_matches(
2833                 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2834
2835         # Look for Mediaset embeds
2836         mediaset_urls = MediasetIE._extract_urls(webpage)
2837         if mediaset_urls:
2838             return self.playlist_from_matches(
2839                 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2840
2841         # Look for JOJ.sk embeds
2842         joj_urls = JojIE._extract_urls(webpage)
2843         if joj_urls:
2844             return self.playlist_from_matches(
2845                 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2846
2847         # Look for megaphone.fm embeds
2848         mpfn_urls = MegaphoneIE._extract_urls(webpage)
2849         if mpfn_urls:
2850             return self.playlist_from_matches(
2851                 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2852
2853         # Look for vzaar embeds
2854         vzaar_urls = VzaarIE._extract_urls(webpage)
2855         if vzaar_urls:
2856             return self.playlist_from_matches(
2857                 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2858
2859         channel9_urls = Channel9IE._extract_urls(webpage)
2860         if channel9_urls:
2861             return self.playlist_from_matches(
2862                 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2863
2864         def merge_dicts(dict1, dict2):
2865             merged = {}
2866             for k, v in dict1.items():
2867                 if v is not None:
2868                     merged[k] = v
2869             for k, v in dict2.items():
2870                 if v is None:
2871                     continue
2872                 if (k not in merged or
2873                         (isinstance(v, compat_str) and v and
2874                             isinstance(merged[k], compat_str) and
2875                             not merged[k])):
2876                     merged[k] = v
2877             return merged
2878
2879         # Look for HTML5 media
2880         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2881         if entries:
2882             if len(entries) == 1:
2883                 entries[0].update({
2884                     'id': video_id,
2885                     'title': video_title,
2886                 })
2887             else:
2888                 for num, entry in enumerate(entries, start=1):
2889                     entry.update({
2890                         'id': '%s-%s' % (video_id, num),
2891                         'title': '%s (%d)' % (video_title, num),
2892                     })
2893             for entry in entries:
2894                 self._sort_formats(entry['formats'])
2895             return self.playlist_result(entries, video_id, video_title)
2896
2897         jwplayer_data = self._find_jwplayer_data(
2898             webpage, video_id, transform_source=js_to_json)
2899         if jwplayer_data:
2900             info = self._parse_jwplayer_data(
2901                 jwplayer_data, video_id, require_title=False, base_url=url)
2902             return merge_dicts(info, info_dict)
2903
2904         # Video.js embed
2905         mobj = re.search(
2906             r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2907             webpage)
2908         if mobj is not None:
2909             sources = self._parse_json(
2910                 mobj.group(1), video_id, transform_source=js_to_json,
2911                 fatal=False) or []
2912             if not isinstance(sources, list):
2913                 sources = [sources]
2914             formats = []
2915             for source in sources:
2916                 src = source.get('src')
2917                 if not src or not isinstance(src, compat_str):
2918                     continue
2919                 src = compat_urlparse.urljoin(url, src)
2920                 src_type = source.get('type')
2921                 if isinstance(src_type, compat_str):
2922                     src_type = src_type.lower()
2923                 ext = determine_ext(src).lower()
2924                 if src_type == 'video/youtube':
2925                     return self.url_result(src, YoutubeIE.ie_key())
2926                 if src_type == 'application/dash+xml' or ext == 'mpd':
2927                     formats.extend(self._extract_mpd_formats(
2928                         src, video_id, mpd_id='dash', fatal=False))
2929                 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2930                     formats.extend(self._extract_m3u8_formats(
2931                         src, video_id, 'mp4', entry_protocol='m3u8_native',
2932                         m3u8_id='hls', fatal=False))
2933                 else:
2934                     formats.append({
2935                         'url': src,
2936                         'ext': (mimetype2ext(src_type) or
2937                                 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2938                     })
2939             if formats:
2940                 self._sort_formats(formats)
2941                 info_dict['formats'] = formats
2942                 return info_dict
2943
2944         # Looking for http://schema.org/VideoObject
2945         json_ld = self._search_json_ld(
2946             webpage, video_id, default={}, expected_type='VideoObject')
2947         if json_ld.get('url'):
2948             return merge_dicts(json_ld, info_dict)
2949
2950         def check_video(vurl):
2951             if YoutubeIE.suitable(vurl):
2952                 return True
2953             if RtmpIE.suitable(vurl):
2954                 return True
2955             vpath = compat_urlparse.urlparse(vurl).path
2956             vext = determine_ext(vpath)
2957             return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2958
2959         def filter_video(urls):
2960             return list(filter(check_video, urls))
2961
2962         # Start with something easy: JW Player in SWFObject
2963         found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2964         if not found:
2965             # Look for gorilla-vid style embedding
2966             found = filter_video(re.findall(r'''(?sx)
2967                 (?:
2968                     jw_plugins|
2969                     JWPlayerOptions|
2970                     jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2971                 )
2972                 .*?
2973                 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2974         if not found:
2975             # Broaden the search a little bit
2976             found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2977         if not found:
2978             # Broaden the findall a little bit: JWPlayer JS loader
2979             found = filter_video(re.findall(
2980                 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2981         if not found:
2982             # Flow player
2983             found = filter_video(re.findall(r'''(?xs)
2984                 flowplayer\("[^"]+",\s*
2985                     \{[^}]+?\}\s*,
2986                     \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2987                         ["']?url["']?\s*:\s*["']([^"']+)["']
2988             ''', webpage))
2989         if not found:
2990             # Cinerama player
2991             found = re.findall(
2992                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2993         if not found:
2994             # Try to find twitter cards info
2995             # twitter:player:stream should be checked before twitter:player since
2996             # it is expected to contain a raw stream (see
2997             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2998             found = filter_video(re.findall(
2999                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3000         if not found:
3001             # We look for Open Graph info:
3002             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3003             m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3004             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3005             if m_video_type is not None:
3006                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3007         if not found:
3008             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3009             found = re.search(
3010                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3011                 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3012                 webpage)
3013             if not found:
3014                 # Look also in Refresh HTTP header
3015                 refresh_header = head_response.headers.get('Refresh')
3016                 if refresh_header:
3017                     # In python 2 response HTTP headers are bytestrings
3018                     if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3019                         refresh_header = refresh_header.decode('iso-8859-1')
3020                     found = re.search(REDIRECT_REGEX, refresh_header)
3021             if found:
3022                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3023                 if new_url != url:
3024                     self.report_following_redirect(new_url)
3025                     return {
3026                         '_type': 'url',
3027                         'url': new_url,
3028                     }
3029                 else:
3030                     found = None
3031
3032         if not found:
3033             # twitter:player is a https URL to iframe player that may or may not
3034             # be supported by youtube-dl thus this is checked the very last (see
3035             # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3036             embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3037             if embed_url and embed_url != url:
3038                 return self.url_result(embed_url)
3039
3040         if not found:
3041             raise UnsupportedError(url)
3042
3043         entries = []
3044         for video_url in orderedSet(found):
3045             video_url = unescapeHTML(video_url)
3046             video_url = video_url.replace('\\/', '/')
3047             video_url = compat_urlparse.urljoin(url, video_url)
3048             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3049
3050             # Sometimes, jwplayer extraction will result in a YouTube URL
3051             if YoutubeIE.suitable(video_url):
3052                 entries.append(self.url_result(video_url, 'Youtube'))
3053                 continue
3054
3055             # here's a fun little line of code for you:
3056             video_id = os.path.splitext(video_id)[0]
3057
3058             entry_info_dict = {
3059                 'id': video_id,
3060                 'uploader': video_uploader,
3061                 'title': video_title,
3062                 'age_limit': age_limit,
3063             }
3064
3065             if RtmpIE.suitable(video_url):
3066                 entry_info_dict.update({
3067                     '_type': 'url_transparent',
3068                     'ie_key': RtmpIE.ie_key(),
3069                     'url': video_url,
3070                 })
3071                 entries.append(entry_info_dict)
3072                 continue
3073
3074             ext = determine_ext(video_url)
3075             if ext == 'smil':
3076                 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3077             elif ext == 'xspf':
3078                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3079             elif ext == 'm3u8':
3080                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3081             elif ext == 'mpd':
3082                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3083             elif ext == 'f4m':
3084                 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3085             elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3086                 # Just matching .ism/manifest is not enough to be reliably sure
3087                 # whether it's actually an ISM manifest or some other streaming
3088                 # manifest since there are various streaming URL formats
3089                 # possible (see [1]) as well as some other shenanigans like
3090                 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3091                 # so on.
3092                 # Thus the most reasonable way to solve this is to delegate
3093                 # to generic extractor in order to look into the contents of
3094                 # the manifest itself.
3095                 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3096                 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3097                 entry_info_dict = self.url_result(
3098                     smuggle_url(video_url, {'to_generic': True}),
3099                     GenericIE.ie_key())
3100             else:
3101                 entry_info_dict['url'] = video_url
3102
3103             if entry_info_dict.get('formats'):
3104                 self._sort_formats(entry_info_dict['formats'])
3105
3106             entries.append(entry_info_dict)
3107
3108         if len(entries) == 1:
3109             return entries[0]
3110         else:
3111             for num, e in enumerate(entries, start=1):
3112                 # 'url' results don't have a title
3113                 if e.get('title') is not None:
3114                     e['title'] = '%s (%d)' % (e['title'], num)
3115             return {
3116                 '_type': 'playlist',
3117                 'entries': entries,
3118             }