3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
39 from .nexx import NexxIE
40 from .nbc import NBCSportsVPlayerIE
41 from .ooyala import OoyalaIE
42 from .rutv import RUTVIE
43 from .tvc import TVCIE
44 from .sportbox import SportBoxEmbedIE
45 from .smotri import SmotriIE
46 from .myvi import MyviIE
47 from .condenast import CondeNastIE
48 from .udn import UDNEmbedIE
49 from .senateisvp import SenateISVPIE
50 from .svt import SVTIE
51 from .pornhub import PornHubIE
52 from .xhamster import XHamsterEmbedIE
53 from .tnaflix import TNAFlixNetworkEmbedIE
54 from .drtuber import DrTuberIE
55 from .redtube import RedTubeIE
56 from .vimeo import VimeoIE
57 from .dailymotion import (
61 from .dailymail import DailyMailIE
62 from .onionstudios import OnionStudiosIE
63 from .viewlift import ViewLiftEmbedIE
64 from .mtv import MTVServicesEmbeddedIE
65 from .pladform import PladformIE
66 from .videomore import VideomoreIE
67 from .webcaster import WebcasterFeedIE
68 from .googledrive import GoogleDriveIE
69 from .jwplatform import JWPlatformIE
70 from .digiteka import DigitekaIE
71 from .arkena import ArkenaIE
72 from .instagram import InstagramIE
73 from .liveleak import LiveLeakIE
74 from .threeqsdn import ThreeQSDNIE
75 from .theplatform import ThePlatformIE
76 from .vessel import VesselIE
77 from .kaltura import KalturaIE
78 from .eagleplatform import EaglePlatformIE
79 from .facebook import FacebookIE
80 from .soundcloud import SoundcloudIE
81 from .tunein import TuneInBaseIE
82 from .vbox7 import Vbox7IE
83 from .dbtv import DBTVIE
84 from .piksel import PikselIE
85 from .videa import VideaIE
86 from .twentymin import TwentyMinutenIE
87 from .ustream import UstreamIE
88 from .openload import OpenloadIE
89 from .videopress import VideoPressIE
90 from .rutube import RutubeIE
91 from .limelight import LimelightBaseIE
92 from .anvato import AnvatoIE
93 from .washingtonpost import WashingtonPostIE
94 from .wistia import WistiaIE
95 from .mediaset import MediasetIE
96 from .joj import JojIE
99 class GenericIE(InfoExtractor):
100 IE_DESC = 'Generic downloader that works on some sites'
104 # Direct link to a video
106 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
107 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
112 'upload_date': '20100513',
115 # Direct link to media delivered compressed (until Accept-Encoding is *)
117 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
118 'md5': '128c42e68b13950268b648275386fc74',
120 'id': 'FictionJunction-Parallel_Hearts',
122 'title': 'FictionJunction-Parallel_Hearts',
123 'upload_date': '20140522',
125 'expected_warnings': [
126 'URL could be a direct video link, returning it as such.'
128 'skip': 'URL invalid',
130 # Direct download with broken HEAD
132 'url': 'http://ai-radio.org:8000/radio.opus',
139 'skip_download': True, # infinite live stream
141 'expected_warnings': [
142 r'501.*Not Implemented',
146 # Direct link with incorrect MIME type
148 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
149 'md5': '4ccbebe5f36706d85221f204d7eb5913',
151 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
152 'id': '5_Lennart_Poettering_-_Systemd',
154 'title': '5_Lennart_Poettering_-_Systemd',
155 'upload_date': '20141120',
157 'expected_warnings': [
158 'URL could be a direct video link, returning it as such.'
163 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
165 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
166 'title': 'Zero Punctuation',
167 'description': 're:.*groundbreaking video review series.*'
169 'playlist_mincount': 11,
171 # RSS feed with enclosure
173 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
175 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
177 'upload_date': '20150228',
178 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
181 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
183 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
187 'title': 'Automatics, robotics and biocybernetics',
188 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
189 'upload_date': '20130627',
190 'formats': 'mincount:16',
191 'subtitles': 'mincount:1',
194 'force_generic_extractor': True,
195 'skip_download': True,
198 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
200 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
205 'formats': 'mincount:1',
208 'skip_download': True,
211 # SMIL from https://www.restudy.dk/video/play/id/1637
213 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
217 'title': 'video_1637',
218 'formats': 'mincount:3',
221 'skip_download': True,
224 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
226 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
228 'id': 'smil-service',
230 'title': 'smil-service',
231 'formats': 'mincount:1',
234 'skip_download': True,
237 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
239 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
243 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
244 'formats': 'mincount:3',
247 'skip_download': True,
250 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
252 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
254 'id': 'mZlp2ctYIUEB',
256 'title': 'Tikibad ontruimd wegens brand',
257 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
258 'thumbnail': r're:^https?://.*\.jpg$',
262 'skip_download': True,
265 # MPD from http://dash-mse-test.appspot.com/media.html
267 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
268 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
270 'id': 'car-20120827-manifest',
272 'title': 'car-20120827-manifest',
273 'formats': 'mincount:9',
274 'upload_date': '20130904',
277 'format': 'bestvideo',
280 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
282 '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',
287 'formats': 'mincount:8',
291 'skip_download': True,
293 'skip': 'video gone',
295 # m3u8 served with Content-Type: text/plain
297 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
302 'upload_date': '20140720',
303 'formats': 'mincount:11',
307 'skip_download': True,
309 'skip': 'video gone',
313 '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',
317 'upload_date': '20130224',
318 'uploader_id': 'TheVerge',
319 'description': r're:^Chris Ziegler takes a look at the\.*',
320 'uploader': 'The Verge',
321 'title': 'First Firefox OS phones side-by-side',
324 'skip_download': False,
328 # redirect in Refresh HTTP header
329 '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',
333 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
334 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
335 'upload_date': '20150917',
336 'uploader_id': 'brtvofficial',
337 'uploader': 'Boiler Room',
340 'skip_download': False,
344 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
345 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
347 'id': '13601338388002',
349 'uploader': 'www.hodiho.fr',
350 'title': 'R\u00e9gis plante sa Jeep',
353 # bandcamp page with custom domain
355 'add_ie': ['Bandcamp'],
356 'url': 'http://bronyrock.com/track/the-pony-mash',
360 'title': 'The Pony Mash',
361 'uploader': 'M_Pallante',
363 'skip': 'There is a limit of 200 free downloads / month for the test song',
366 # embedded brightcove video
367 # it also tests brightcove videos that need to set the 'Referer'
368 # in the http requests
369 'add_ie': ['BrightcoveLegacy'],
370 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
372 'id': '2765128793001',
374 'title': 'Le cours de bourse : l’analyse technique',
375 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
376 'uploader': 'BFM BUSINESS',
379 'skip_download': True,
383 # embedded with itemprop embedURL and video id spelled as `idVideo`
384 'add_id': ['BrightcoveLegacy'],
385 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
387 'id': '5255628253001',
389 'title': 'md5:37c519b1128915607601e75a87995fc0',
390 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
391 'uploader': 'BFM BUSINESS',
392 'uploader_id': '876450612001',
393 'timestamp': 1482255315,
394 'upload_date': '20161220',
397 'skip_download': True,
401 # https://github.com/rg3/youtube-dl/issues/2253
402 'url': 'http://bcove.me/i6nfkrc3',
403 'md5': '0ba9446db037002366bab3b3eb30c88c',
405 'id': '3101154703001',
407 'title': 'Still no power',
408 'uploader': 'thestar.com',
409 '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.',
411 'add_ie': ['BrightcoveLegacy'],
412 'skip': 'video gone',
415 'url': 'http://www.championat.com/video/football/v/87/87499.html',
416 'md5': 'fb973ecf6e4a78a67453647444222983',
418 'id': '3414141473001',
420 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
421 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
422 'uploader': 'Championat',
426 # https://github.com/rg3/youtube-dl/issues/3541
427 'add_ie': ['BrightcoveLegacy'],
428 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
430 'id': '3866516442001',
432 'title': 'Leer mij vrouwen kennen: Aflevering 1',
433 'description': 'Leer mij vrouwen kennen: Aflevering 1',
434 'uploader': 'SBS Broadcasting',
436 'skip': 'Restricted to Netherlands',
438 'skip_download': True, # m3u8 download
442 # Brightcove video in <iframe>
443 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
444 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
446 'id': '5360463607001',
448 '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',
449 '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。',
450 'uploader': 'United Nations',
451 'uploader_id': '1362235914001',
452 'timestamp': 1489593889,
453 'upload_date': '20170315',
455 'add_ie': ['BrightcoveLegacy'],
458 # Brightcove with alternative playerID key
459 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
461 'id': 'nmeth.2062_SV1',
462 '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',
466 'id': '2228375078001',
468 'title': 'nmeth.2062-sv1',
469 'description': 'nmeth.2062-sv1',
470 'timestamp': 1363357591,
471 'upload_date': '20130315',
472 'uploader': 'Nature Publishing Group',
473 'uploader_id': '1964492299001',
478 # Brightcove with UUID in videoPlayer
479 'url': 'http://www8.hp.com/cn/zh/home.html',
481 'id': '5255815316001',
483 'title': 'Sprocket Video - China',
484 'description': 'Sprocket Video - China',
485 'uploader': 'HP-Video Gallery',
486 'timestamp': 1482263210,
487 'upload_date': '20161220',
488 'uploader_id': '1107601872001',
491 'skip_download': True, # m3u8 download
493 'skip': 'video rotates...weekly?',
496 # Brightcove:new type [2].
497 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
498 'md5': '2b35148fcf48da41c9fb4591650784f3',
500 'id': '5348741021001',
502 'upload_date': '20170306',
503 'uploader_id': '4191638492001',
504 'timestamp': 1488769918,
505 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
510 # Alternative brightcove <video> attributes
511 '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/',
513 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
514 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
517 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
519 'id': '5311302538001',
521 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
522 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
523 'timestamp': 1486321708,
524 'upload_date': '20170205',
525 'uploader_id': '800000640001',
527 'only_matching': True,
531 # Brightcove with UUID in videoPlayer
532 'url': 'http://www8.hp.com/cn/zh/home.html',
534 'id': '5255815316001',
536 'title': 'Sprocket Video - China',
537 'description': 'Sprocket Video - China',
538 'uploader': 'HP-Video Gallery',
539 'timestamp': 1482263210,
540 'upload_date': '20161220',
541 'uploader_id': '1107601872001',
544 'skip_download': True, # m3u8 download
549 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
550 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
552 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
554 'title': '2cc213299525360.mov', # that's what we get
557 'add_ie': ['Ooyala'],
560 # ooyala video embedded with http://player.ooyala.com/iframe.js
561 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
563 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
565 'title': '"Steve Jobs: Man in the Machine" trailer',
566 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
570 'skip_download': True,
572 'skip': 'movie expired',
576 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
580 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
581 'upload_date': '20140225',
582 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
583 'uploader': 'Tested',
584 'uploader_id': 'testedcom',
586 # No need to test YoutubeIE here
588 'skip_download': True,
593 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
597 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
598 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
600 # HEAD requests lead to endless 301, while GET is OK
601 'expected_warnings': ['301'],
605 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
609 'title': 'Охотское море стало целиком российским',
610 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
614 'skip_download': True,
619 '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/',
623 'title': 'Дошкольное воспитание',
628 'url': 'http://www.vestifinance.ru/articles/25753',
631 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
636 'title': 'Госзаказ. День 3',
642 'title': 'Госзаказ. День 2',
648 'title': 'Госзаказ. День 1',
654 'skip_download': True,
659 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
661 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
663 'title': 'Ужастики, русский трейлер (2015)',
664 'thumbnail': r're:^https?://.*\.jpg$',
670 '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',
673 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
675 'playlist_mincount': 7,
676 # This forum does not allow <iframe> syntaxes anymore
677 # Now HTML tags are displayed as-is
678 'skip': 'No videos on this page',
682 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
683 'md5': '65fdff94098e4a607385a60c5177c638',
687 'title': 'Hidden miracles of the natural world',
688 'uploader': 'Louie Schwartzberg',
689 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
692 # nowvideo embed hidden behind percent encoding
694 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
695 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
697 'id': '06e53103ca9aa',
699 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
700 'description': 'No description',
705 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
706 'md5': '7653032cbb25bf6c80d80f217055fa43',
708 'id': '048195-004_PLUS7-F',
711 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
712 'upload_date': '20140320',
715 'skip_download': 'Requires rtmpdump'
717 'skip': 'video gone',
721 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
725 'title': 'Alcaline, le concert avec Calogero',
726 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
727 'upload_date': '20150226',
728 'timestamp': 1424989860,
733 'skip_download': True,
735 'expected_warnings': [
741 'url': 'http://www.wired.com/2014/04/honda-asimo/',
742 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
744 'id': '53501be369702d3275860000',
746 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
751 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
752 'md5': '441aeeb82eb72c422c7f14ec533999cd',
754 'id': 'k2mm4bCdJ6CQ2i7c8o2',
756 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
757 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
759 'uploader_id': 'xgditw',
760 'upload_date': '20140425',
761 'timestamp': 1398441542,
763 'add_ie': ['Dailymotion'],
767 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
771 'title': 'Care worker punches elderly dementia patient in head 11 times',
772 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
774 'add_ie': ['DailyMail'],
776 'skip_download': True,
781 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
785 'title': 'The NBL Auction 2014',
786 'uploader': 'BADMINTON England',
787 'uploader_id': 'BADMINTONEvents',
788 'upload_date': '20140603',
789 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
791 'add_ie': ['Youtube'],
793 'skip_download': True,
798 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
799 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
801 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
803 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
804 'description': 'Two valets share their love for movie star Liam Neesons.',
805 'timestamp': 1349922600,
806 'upload_date': '20121011',
809 # YouTube embed via <data-embed-url="">
811 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
815 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
816 'uploader': 'Gameloft',
817 'uploader_id': 'gameloft',
818 'upload_date': '20140828',
819 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
822 'skip_download': True,
825 # YouTube <object> embed
827 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
828 'md5': '516718101ec834f74318df76259fb3cc',
832 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
833 'upload_date': '20080526',
834 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
835 'uploader': 'Christopher Sykes',
836 'uploader_id': 'ChristopherJSykes',
838 'add_ie': ['Youtube'],
842 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
844 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
846 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
847 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
852 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
854 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
855 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
861 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
866 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
867 'md5': '9d65602bf31c6e20014319c7d07fba27',
869 'id': '5123ea6d5e5a7',
872 'uploader': 'www.handjobhub.com',
873 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
876 # Multiple brightcove videos
877 # https://github.com/rg3/youtube-dl/issues/2283
879 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
881 'id': 'always-never',
882 'title': 'Always / Never - The New Yorker',
886 'extract_flat': False,
887 'skip_download': True,
892 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
893 'md5': '96f09a37e44da40dd083e12d9a683327',
897 'title': 'Ump changes call to ball',
898 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
900 'timestamp': 1401537900,
901 'upload_date': '20140531',
902 'thumbnail': r're:^https?://.*\.jpg$',
907 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
908 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
912 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
913 'description': 'a Paywall Videos video from Remilon',
915 'uploader': 'study.com',
916 'timestamp': 1459678540,
917 'upload_date': '20160403',
918 'filesize': 24687186,
922 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
923 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
927 'title': 'Conversation about Hexagonal Rails Part 1',
928 'description': 'a Martin Fowler video from ThoughtWorks',
930 'uploader': 'thoughtworks.wistia.com',
931 'timestamp': 1401832161,
932 'upload_date': '20140603',
935 # Wistia standard embed (async)
937 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
941 'title': 'Drip Brennan Dunn Workshop',
942 'description': 'a JV Webinars video from getdrip-1',
944 'timestamp': 1463607249,
945 'upload_date': '20160518',
948 'skip_download': True,
953 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
957 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
958 'uploader': 'Sophos Security',
959 'title': 'Chet Chat 171 - Oct 29, 2014',
960 'upload_date': '20141029',
963 # Soundcloud multiple embeds
965 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
968 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
970 'playlist_mincount': 7,
972 # TuneIn station embed
974 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
979 'location': 'Paris, France',
984 'skip_download': True,
989 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
993 'upload_date': '20141112',
994 'title': 'Rosetta #CometLanding webcast HL 10',
997 # Another Livestream embed, without 'new.' in URL
999 'url': 'https://www.freespeech.org/',
1003 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1007 'skip_download': True,
1012 'url': 'https://skiplagged.com/',
1015 'title': 'Skiplagged: The smart way to find cheap flights',
1017 'playlist_mincount': 1,
1018 'add_ie': ['Youtube'],
1022 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1026 'upload_date': '20141126',
1027 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1032 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1034 'id': '730m_DandD_1901_512k',
1036 'uploader': 'www.abc.net.au',
1037 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1040 # embedded viddler video
1042 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1046 'uploader': 'deadspin',
1047 'title': 'WALL-TO-GORTAT',
1048 'timestamp': 1422285291,
1049 'upload_date': '20150126',
1051 'add_ie': ['Viddler'],
1055 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1059 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1060 'description': 'md5:601cb790edd05908957dae8aaa866465',
1061 'upload_date': '20150220',
1063 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1067 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1069 'id': 'Mrj4DVp2zeA',
1071 'upload_date': '20150212',
1072 'uploader': 'The National Archives UK',
1073 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1074 'uploader_id': 'NationalArchives08',
1075 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1080 'url': 'http://www.suffolk.edu/sjc/',
1084 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1085 'uploader': 'www.suffolk.edu',
1088 'skip_download': True,
1093 'url': 'http://www.indiedb.com/games/king-machine/videos',
1097 'title': 'king machine trailer 1',
1098 'thumbnail': r're:^https?://.*\.jpg$',
1102 # JWPlayer config passed as variable
1103 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1107 'title': 'ARIELE | Tube Cup',
1108 'uploader': 'www.txxx.com',
1112 'skip_download': True,
1117 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1118 'playlist_mincount': 5,
1120 'id': 'aanslagen-kopenhagen',
1121 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1126 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1130 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1133 # Kaltura embed (different embed code)
1135 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1139 'upload_date': '20150127',
1140 'uploader_id': 'PremierMedia',
1142 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1145 # Kaltura embed with single quotes
1147 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1152 'timestamp': 1355743100,
1153 'upload_date': '20121217',
1154 'uploader_id': 'batchUser',
1156 'add_ie': ['Kaltura'],
1159 # Kaltura embedded via quoted entry_id
1160 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1164 'title': '06_matthew_brender_raj_dutt',
1165 'timestamp': 1466638791,
1166 'upload_date': '20160622',
1168 'add_ie': ['Kaltura'],
1169 'expected_warnings': [
1170 'Could not send HEAD request'
1173 'skip_download': True,
1177 # Kaltura embedded, some fileExt broken (#11480)
1178 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1182 'title': 'Our "Standard Models" of particle physics and cosmology',
1183 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1184 'timestamp': 1321158993,
1185 'upload_date': '20111113',
1186 'uploader_id': 'kps1',
1188 'add_ie': ['Kaltura'],
1191 # Kaltura iframe embed
1192 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1193 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1197 'title': 'I. M. Pei: A Centennial Celebration',
1198 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1199 'upload_date': '20170403',
1200 'uploader_id': 'batchUser',
1201 'timestamp': 1491232186,
1203 'add_ie': ['Kaltura'],
1205 # EaglePlatform embed (generic URL)
1207 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1208 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1212 'title': 'Навальный вышел на свободу',
1213 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1214 'thumbnail': r're:^https?://.*\.jpg$',
1220 'skip_download': True,
1223 # referrer protected EaglePlatform embed
1225 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1229 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1230 'thumbnail': r're:^https?://.*\.jpg$',
1235 'skip_download': True,
1238 # ClipYou (EaglePlatform) embed (custom URL)
1240 'url': 'http://muz-tv.ru/play/7129/',
1241 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1245 'title': "'O Sole Mio",
1246 'thumbnail': r're:^https?://.*\.jpg$',
1251 'skip_download': True,
1256 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1260 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1261 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1262 'thumbnail': r're:^https?://.*\.jpg$',
1269 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1273 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1274 'thumbnail': r're:^https?://.*\.png$',
1280 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1281 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1285 'title': 'Facebook Creates "On This Day" | Crunch Report',
1290 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1294 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1299 # Crooks and Liars embed
1301 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1305 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1306 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1307 'timestamp': 1428207000,
1308 'upload_date': '20150405',
1309 'uploader': 'Heather',
1312 # Crooks and Liars external embed
1314 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1316 'id': 'MTE3MjUtMzQ2MzA',
1318 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1319 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1320 'timestamp': 1265032391,
1321 'upload_date': '20100201',
1322 'uploader': 'Heather',
1325 # NBC Sports vplayer embed
1327 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1329 'id': 'ln7x1qSThw4k',
1331 'title': "PFT Live: New leader in the 'new-look' defense",
1332 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1333 'uploader': 'NBCU-SPORTS',
1334 'upload_date': '20140107',
1335 'timestamp': 1389118457,
1340 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1341 'md5': '1aa589c675898ae6d37a17913cf68d66',
1343 'id': '701714499682',
1345 'title': 'PREVIEW: On Assignment: David Letterman',
1346 '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.',
1351 'url': 'https://video.udn.com/news/300346',
1352 'md5': 'fd2060e988c326991037b9aff9df21a6',
1356 'title': '中一中男師變性 全校師生力挺',
1357 'thumbnail': r're:^https?://.*\.jpg$',
1361 'skip_download': True,
1366 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1368 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1370 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1371 'title': 'This is what separates the Excel masters from the wannabes',
1372 'duration': 191.933,
1376 'skip_download': True,
1379 # Brightcove URL in single quotes
1381 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1382 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1384 'id': '4255764656001',
1386 'title': 'SN Presents: Russell Martin, World Citizen',
1387 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1388 'uploader': 'Rogers Sportsnet',
1389 'uploader_id': '1704050871',
1390 'upload_date': '20150525',
1391 'timestamp': 1432570283,
1394 # Dailymotion Cloud video
1396 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1397 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1401 'title': 'Sauvons les abeilles ! - Le débat',
1402 'description': 'md5:d9082128b1c5277987825d684939ca26',
1403 'thumbnail': r're:^https?://.*\.jpe?g$',
1404 'timestamp': 1434970506,
1405 'upload_date': '20150622',
1406 'uploader': 'Public Sénat',
1407 'uploader_id': 'xa9gza',
1410 # OnionStudios embed
1412 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1416 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1417 'thumbnail': r're:^https?://.*\.jpe?g$',
1418 'uploader': 'ClickHole',
1419 'uploader_id': 'clickhole',
1424 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1426 'id': '74849a00-85a9-11e1-9660-123139220831',
1428 'title': '#whilewewatch',
1431 # AdobeTVVideo embed
1433 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1434 'md5': '43662b577c018ad707a63766462b1e87',
1438 'title': 'New experience with Acrobat DC',
1439 'description': 'New experience with Acrobat DC',
1440 'duration': 248.667,
1443 # BrightcoveInPageEmbed embed
1445 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1447 'id': '4238694884001',
1449 'title': 'Tabletop: Dread, Last Thoughts',
1450 'description': 'Tabletop: Dread, Last Thoughts',
1454 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1455 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1457 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1459 'id': '4785848093001',
1461 'title': 'The Cardinal Pell Interview',
1462 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1463 'uploader': 'GlobeCast Australia - GlobeStream',
1464 'uploader_id': '2733773828001',
1465 'upload_date': '20160304',
1466 'timestamp': 1457083087,
1470 'skip_download': True,
1474 # Brightcove embed with whitespace around attribute names
1475 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1477 'id': '3167554373001',
1479 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1480 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1481 'uploader_id': '1079349493',
1482 'upload_date': '20140207',
1483 'timestamp': 1391810548,
1486 'skip_download': True,
1489 # Another form of arte.tv embed
1491 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1492 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1494 'id': '030273-562_PLUS7-F',
1496 'title': 'ARTE Reportage - Nulle part, en France',
1497 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1498 'upload_date': '20160409',
1503 'url': 'http://www.wykop.pl/link/3088787/',
1504 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1506 'id': '874_1459135191',
1508 'title': 'Man shows poor quality of new apartment building',
1509 'description': 'The wall is like a sand pile.',
1510 'uploader': 'Lake8737',
1513 # Duplicated embedded video URLs
1515 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1517 'id': '149298443_480_16c25b74_2',
1519 'title': 'vs. Blue Orange Spring Game',
1520 'uploader': 'www.hudl.com',
1523 # twitter:player:stream embed
1525 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1529 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1530 'uploader': 'www.rtl.be',
1534 'skip_download': True,
1537 # twitter:player embed
1539 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1540 'md5': 'a3e0df96369831de324f0778e126653c',
1542 'id': '4909620399001',
1544 'title': 'What Do Black Holes Sound Like?',
1545 'description': 'what do black holes sound like',
1546 'upload_date': '20160524',
1547 'uploader_id': '29913724001',
1548 'timestamp': 1464107587,
1549 'uploader': 'TheAtlantic',
1551 'add_ie': ['BrightcoveLegacy'],
1555 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1559 'title': "Yesterday's Jam (OV)",
1560 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1561 'timestamp': 1492594816,
1562 'upload_date': '20170419',
1565 'format': 'bestvideo',
1566 'skip_download': True,
1569 # Facebook <iframe> embed
1571 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1572 'md5': 'fbcde74f534176ecb015849146dd3aee',
1574 'id': '599637780109885',
1576 'title': 'Facebook video #599637780109885',
1579 # Facebook <iframe> embed, plugin video
1581 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1583 'id': '1754168231264132',
1585 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1586 'uploader': 'Tariq Ramadan (official)',
1587 'timestamp': 1496758379,
1588 'upload_date': '20170606',
1591 'skip_download': True,
1594 # Facebook API embed
1596 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1597 'md5': 'a47372ee61b39a7b90287094d447d94e',
1599 'id': '10153467542406923',
1601 'title': 'Facebook video #10153467542406923',
1604 # Wordpress "YouTube Video Importer" plugin
1606 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1607 'md5': 'd16797741b560b485194eddda8121b48',
1609 'id': 'HNTXWDXV9Is',
1611 'title': 'Blue Devils Drumline Stanford lot 2016',
1612 'upload_date': '20160627',
1613 'uploader_id': 'GENOCIDE8GENERAL10',
1614 'uploader': 'cylus cyrus',
1618 # video stored on custom kaltura server
1619 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1620 'md5': '537617d06e64dfed891fa1593c4b30cc',
1624 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1625 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1626 'uploader_id': 'videos.expansion@el-mundo.net',
1627 'upload_date': '20150429',
1628 'timestamp': 1430303472,
1630 'add_ie': ['Kaltura'],
1633 # Non-standard Vimeo embed
1634 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1635 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1639 'title': 'Understanding the web - Teaser',
1640 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1641 'upload_date': '20151214',
1642 'uploader': 'OpenClassrooms',
1643 'uploader_id': 'openclassrooms',
1645 'add_ie': ['Vimeo'],
1648 # generic vimeo embed that requires original URL passed as Referer
1649 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1650 'only_matching': True,
1653 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1654 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1656 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1658 'title': 'Big Buck Bunny',
1659 'description': 'Royalty free test video',
1660 'timestamp': 1432816365,
1661 'upload_date': '20150528',
1665 'skip_download': True,
1667 'add_ie': [ArkenaIE.ie_key()],
1670 '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/',
1674 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1677 'skip_download': True,
1679 'add_ie': [Vbox7IE.ie_key()],
1683 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1686 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1688 'playlist_mincount': 3,
1692 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1694 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1695 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1697 'playlist_mincount': 2,
1701 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1705 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1706 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1709 'skip_download': True,
1711 'add_ie': [TwentyMinutenIE.ie_key()],
1715 'url': 'https://en.support.wordpress.com/videopress/',
1719 'title': 'IMG_5786',
1720 'timestamp': 1435711927,
1721 'upload_date': '20150701',
1724 'skip_download': True,
1726 'add_ie': [VideoPressIE.ie_key()],
1730 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1732 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1734 'title': 'Магаззино: Казань 2',
1735 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1736 'uploader': 'Магаззино',
1737 'upload_date': '20170228',
1738 'uploader_id': '996642',
1741 'skip_download': True,
1743 'add_ie': [RutubeIE.ie_key()],
1746 # ThePlatform embedded with whitespaces in URLs
1747 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1748 'only_matching': True,
1751 # Senate ISVP iframe https
1752 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1753 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1755 'id': 'govtaff020316',
1757 'title': 'Integrated Senate Video Player',
1759 'add_ie': [SenateISVPIE.ie_key()],
1762 # Limelight embeds (1 channel embed + 4 media embeds)
1763 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1765 'id': 'FacilitatorTraining2017',
1766 'title': 'Facilitator Training 2017',
1768 'playlist_mincount': 5,
1771 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1773 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1774 'title': 'Standoff with Walnut Creek murder suspect ends',
1775 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1777 'playlist_mincount': 4,
1780 # WashingtonPost embed
1781 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1783 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1785 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1786 '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.',
1787 'timestamp': 1455216756,
1788 'uploader': 'The Washington Post',
1789 'upload_date': '20160211',
1791 'add_ie': [WashingtonPostIE.ie_key()],
1795 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1799 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1802 'skip_download': True,
1804 'add_ie': [MediasetIE.ie_key()],
1808 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1810 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1811 'title': 'Slovenskom sa prehnala vlna silných búrok',
1813 'playlist_mincount': 5,
1814 'add_ie': [JojIE.ie_key()],
1817 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1818 'url': 'https://tvrain.ru/amp/418921/',
1819 'md5': 'cc00413936695987e8de148b67d14f1d',
1823 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1827 # # TODO: find another test
1828 # # http://schema.org/VideoObject
1829 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1830 # 'md5': '888dcf08b7ea671381f00fab74692755',
1832 # 'id': 'nyvTSJMKId',
1834 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1835 # 'description': '#love for cats.',
1836 # 'timestamp': 1461244995,
1837 # 'upload_date': '20160421',
1840 # 'force_generic_extractor': True,
1845 def report_following_redirect(self, new_url):
1846 """Report information extraction."""
1847 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1849 def _extract_rss(self, url, video_id, doc):
1850 playlist_title = doc.find('./channel/title').text
1851 playlist_desc_el = doc.find('./channel/description')
1852 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1855 for it in doc.findall('./channel/item'):
1856 next_url = xpath_text(it, 'link', fatal=False)
1858 enclosure_nodes = it.findall('./enclosure')
1859 for e in enclosure_nodes:
1860 next_url = e.attrib.get('url')
1868 '_type': 'url_transparent',
1870 'title': it.find('title').text,
1874 '_type': 'playlist',
1876 'title': playlist_title,
1877 'description': playlist_desc,
1881 def _extract_camtasia(self, url, video_id, webpage):
1882 """ Returns None if no camtasia video can be found. """
1884 camtasia_cfg = self._search_regex(
1885 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1886 webpage, 'camtasia configuration file', default=None)
1887 if camtasia_cfg is None:
1890 title = self._html_search_meta('DC.title', webpage, fatal=True)
1892 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1893 camtasia_cfg = self._download_xml(
1894 camtasia_url, video_id,
1895 note='Downloading camtasia configuration',
1896 errnote='Failed to download camtasia configuration')
1897 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1900 for n in fileset_node.getchildren():
1901 url_n = n.find('./uri')
1906 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1907 'title': '%s - %s' % (title, n.tag),
1908 'url': compat_urlparse.urljoin(url, url_n.text),
1909 'duration': float_or_none(n.find('./duration').text),
1913 '_type': 'playlist',
1918 def _real_extract(self, url):
1919 if url.startswith('//'):
1922 'url': self.http_scheme() + url,
1925 parsed_url = compat_urlparse.urlparse(url)
1926 if not parsed_url.scheme:
1927 default_search = self._downloader.params.get('default_search')
1928 if default_search is None:
1929 default_search = 'fixup_error'
1931 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1933 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1934 return self.url_result('http://' + url)
1935 elif default_search != 'fixup_error':
1936 if default_search == 'auto_warning':
1937 if re.match(r'^(?:url|URL)$', url):
1938 raise ExtractorError(
1939 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1942 self._downloader.report_warning(
1943 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1944 return self.url_result('ytsearch:' + url)
1946 if default_search in ('error', 'fixup_error'):
1947 raise ExtractorError(
1948 '%r is not a valid URL. '
1949 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1950 % (url, url), expected=True)
1952 if ':' not in default_search:
1953 default_search += ':'
1954 return self.url_result(default_search + url)
1956 url, smuggled_data = unsmuggle_url(url)
1957 force_videoid = None
1958 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1959 if smuggled_data and 'force_videoid' in smuggled_data:
1960 force_videoid = smuggled_data['force_videoid']
1961 video_id = force_videoid
1963 video_id = self._generic_id(url)
1965 self.to_screen('%s: Requesting header' % video_id)
1967 head_req = HEADRequest(url)
1968 head_response = self._request_webpage(
1970 note=False, errnote='Could not send HEAD request to %s' % url,
1973 if head_response is not False:
1974 # Check for redirect
1975 new_url = head_response.geturl()
1977 self.report_following_redirect(new_url)
1979 new_url = smuggle_url(
1980 new_url, {'force_videoid': force_videoid})
1981 return self.url_result(new_url)
1983 full_response = None
1984 if head_response is False:
1985 request = sanitized_Request(url)
1986 request.add_header('Accept-Encoding', '*')
1987 full_response = self._request_webpage(request, video_id)
1988 head_response = full_response
1992 'title': self._generic_title(url),
1993 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1996 # Check for direct link to a video
1997 content_type = head_response.headers.get('Content-Type', '').lower()
1998 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2000 format_id = compat_str(m.group('format_id'))
2001 if format_id.endswith('mpegurl'):
2002 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2003 elif format_id == 'f4m':
2004 formats = self._extract_f4m_formats(url, video_id)
2007 'format_id': format_id,
2009 'vcodec': 'none' if m.group('type') == 'audio' else None
2011 info_dict['direct'] = True
2012 self._sort_formats(formats)
2013 info_dict['formats'] = formats
2016 if not self._downloader.params.get('test', False) and not is_intentional:
2017 force = self._downloader.params.get('force_generic_extractor', False)
2018 self._downloader.report_warning(
2019 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2021 if not full_response:
2022 request = sanitized_Request(url)
2023 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2024 # making it impossible to download only chunk of the file (yet we need only 512kB to
2025 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2026 # that will always result in downloading the whole file that is not desirable.
2027 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2028 # to accept raw bytes and being able to download only a chunk.
2029 # It may probably better to solve this by checking Content-Type for application/octet-stream
2030 # after HEAD request finishes, but not sure if we can rely on this.
2031 request.add_header('Accept-Encoding', '*')
2032 full_response = self._request_webpage(request, video_id)
2034 first_bytes = full_response.read(512)
2036 # Is it an M3U playlist?
2037 if first_bytes.startswith(b'#EXTM3U'):
2038 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2039 self._sort_formats(info_dict['formats'])
2042 # Maybe it's a direct link to a video?
2043 # Be careful not to download the whole thing!
2044 if not is_html(first_bytes):
2045 self._downloader.report_warning(
2046 'URL could be a direct video link, returning it as such.')
2053 webpage = self._webpage_read_content(
2054 full_response, url, video_id, prefix=first_bytes)
2056 self.report_extraction(video_id)
2058 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2060 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2061 if doc.tag == 'rss':
2062 return self._extract_rss(url, video_id, doc)
2063 elif doc.tag == 'SmoothStreamingMedia':
2064 info_dict['formats'] = self._parse_ism_formats(doc, url)
2065 self._sort_formats(info_dict['formats'])
2067 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2068 smil = self._parse_smil(doc, url, video_id)
2069 self._sort_formats(smil['formats'])
2071 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2072 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2073 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2074 info_dict['formats'] = self._parse_mpd_formats(
2076 mpd_base_url=full_response.geturl().rpartition('/')[0],
2078 self._sort_formats(info_dict['formats'])
2080 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2081 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2082 self._sort_formats(info_dict['formats'])
2084 except compat_xml_parse_error:
2087 # Is it a Camtasia project?
2088 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2089 if camtasia_res is not None:
2092 # Sometimes embedded video player is hidden behind percent encoding
2093 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2094 # Unescaping the whole page allows to handle those cases in a generic way
2095 webpage = compat_urllib_parse_unquote(webpage)
2097 # it's tempting to parse this further, but you would
2098 # have to take into account all the variations like
2099 # Video Title - Site Name
2100 # Site Name | Video Title
2101 # Video Title - Tagline | Site Name
2102 # and so on and so forth; it's just not practical
2103 video_title = self._og_search_title(
2104 webpage, default=None) or self._html_search_regex(
2105 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2108 # Try to detect age limit automatically
2109 age_limit = self._rta_search(webpage)
2110 # And then there are the jokers who advertise that they use RTA,
2111 # but actually don't.
2112 AGE_LIMIT_MARKERS = [
2113 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2115 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2118 # video uploader is domain name
2119 video_uploader = self._search_regex(
2120 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2122 video_description = self._og_search_description(webpage, default=None)
2123 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2126 'title': video_title,
2127 'description': video_description,
2128 'thumbnail': video_thumbnail,
2129 'age_limit': age_limit,
2132 # Look for Brightcove Legacy Studio embeds
2133 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2137 'url': smuggle_url(bc_url, {'Referer': url}),
2138 'ie_key': 'BrightcoveLegacy'
2139 } for bc_url in bc_urls]
2142 '_type': 'playlist',
2143 'title': video_title,
2148 # Look for Brightcove New Studio embeds
2149 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2151 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2153 # Look for Nexx embeds
2154 nexx_urls = NexxIE._extract_urls(webpage)
2156 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2158 # Look for ThePlatform embeds
2159 tp_urls = ThePlatformIE._extract_urls(webpage)
2161 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2163 # Look for Vessel embeds
2164 vessel_urls = VesselIE._extract_urls(webpage)
2166 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2168 # Look for embedded rtl.nl player
2169 matches = re.findall(
2170 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2173 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2175 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2177 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2179 vid_me_embed_url = self._search_regex(
2180 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2181 webpage, 'vid.me embed', default=None)
2182 if vid_me_embed_url is not None:
2183 return self.url_result(vid_me_embed_url, 'Vidme')
2185 # Look for embedded YouTube player
2186 matches = re.findall(r'''(?x)
2196 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2200 return self.playlist_from_matches(
2201 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2203 # Look for lazyYT YouTube embed
2204 matches = re.findall(
2205 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2207 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2209 # Look for Wordpress "YouTube Video Importer" plugin
2210 matches = re.findall(r'''(?x)<div[^>]+
2211 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2212 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2214 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2216 matches = DailymotionIE._extract_urls(webpage)
2218 return self.playlist_from_matches(matches, video_id, video_title)
2220 # Look for embedded Dailymotion playlist player (#3822)
2222 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2224 playlists = re.findall(
2225 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2227 return self.playlist_from_matches(
2228 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2230 # Look for DailyMail embeds
2231 dailymail_urls = DailyMailIE._extract_urls(webpage)
2233 return self.playlist_from_matches(
2234 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2236 # Look for embedded Wistia player
2237 wistia_url = WistiaIE._extract_url(webpage)
2240 '_type': 'url_transparent',
2241 'url': self._proto_relative_url(wistia_url),
2242 'ie_key': WistiaIE.ie_key(),
2243 'uploader': video_uploader,
2246 # Look for SVT player
2247 svt_url = SVTIE._extract_url(webpage)
2249 return self.url_result(svt_url, 'SVT')
2251 # Look for Bandcamp pages with custom domain
2252 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2253 if mobj is not None:
2254 burl = unescapeHTML(mobj.group(1))
2255 # Don't set the extractor because it can be a track url or an album
2256 return self.url_result(burl)
2258 # Look for embedded Vevo player
2260 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2261 if mobj is not None:
2262 return self.url_result(mobj.group('url'))
2264 # Look for embedded Viddler player
2266 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2268 if mobj is not None:
2269 return self.url_result(mobj.group('url'))
2271 # Look for NYTimes player
2273 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2275 if mobj is not None:
2276 return self.url_result(mobj.group('url'))
2278 # Look for Libsyn player
2280 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2281 if mobj is not None:
2282 return self.url_result(mobj.group('url'))
2284 # Look for Ooyala videos
2285 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2286 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2287 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2288 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2289 if mobj is not None:
2290 embed_token = self._search_regex(
2291 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2292 webpage, 'ooyala embed token', default=None)
2293 return OoyalaIE._build_url_result(smuggle_url(
2296 'embed_token': embed_token,
2299 # Look for multiple Ooyala embeds on SBN network websites
2300 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2301 if mobj is not None:
2302 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2304 return self.playlist_from_matches(
2305 embeds, video_id, video_title,
2306 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2308 # Look for Aparat videos
2309 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2310 if mobj is not None:
2311 return self.url_result(mobj.group(1), 'Aparat')
2313 # Look for MPORA videos
2314 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2315 if mobj is not None:
2316 return self.url_result(mobj.group(1), 'Mpora')
2318 # Look for embedded NovaMov-based player
2320 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2321 (?P<url>http://(?:(?:embed|www)\.)?
2323 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2324 videoweed\.(?:es|com)|
2325 movshare\.(?:net|sx|ag)|
2326 divxstage\.(?:eu|net|ch|co|at|ag))
2327 /embed\.php.+?)\1''', webpage)
2328 if mobj is not None:
2329 return self.url_result(mobj.group('url'))
2331 # Look for embedded Facebook player
2332 facebook_urls = FacebookIE._extract_urls(webpage)
2334 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2336 # Look for embedded VK player
2337 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2338 if mobj is not None:
2339 return self.url_result(mobj.group('url'), 'VK')
2341 # Look for embedded Odnoklassniki player
2342 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2343 if mobj is not None:
2344 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2346 # Look for embedded ivi player
2347 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2348 if mobj is not None:
2349 return self.url_result(mobj.group('url'), 'Ivi')
2351 # Look for embedded Huffington Post player
2353 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2354 if mobj is not None:
2355 return self.url_result(mobj.group('url'), 'HuffPost')
2358 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2359 if mobj is not None:
2360 return self.url_result(mobj.group('url'))
2361 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2362 if mobj is not None:
2363 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2365 # Look for funnyordie embed
2366 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2368 return self.playlist_from_matches(
2369 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2371 # Look for BBC iPlayer embed
2372 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2374 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2376 # Look for embedded RUTV player
2377 rutv_url = RUTVIE._extract_url(webpage)
2379 return self.url_result(rutv_url, 'RUTV')
2381 # Look for embedded TVC player
2382 tvc_url = TVCIE._extract_url(webpage)
2384 return self.url_result(tvc_url, 'TVC')
2386 # Look for embedded SportBox player
2387 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2389 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2391 # Look for embedded XHamster player
2392 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2394 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2396 # Look for embedded TNAFlixNetwork player
2397 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2399 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2401 # Look for embedded PornHub player
2402 pornhub_urls = PornHubIE._extract_urls(webpage)
2404 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2406 # Look for embedded DrTuber player
2407 drtuber_urls = DrTuberIE._extract_urls(webpage)
2409 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2411 # Look for embedded RedTube player
2412 redtube_urls = RedTubeIE._extract_urls(webpage)
2414 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2416 # Look for embedded Tvigle player
2418 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2419 if mobj is not None:
2420 return self.url_result(mobj.group('url'), 'Tvigle')
2422 # Look for embedded TED player
2424 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2425 if mobj is not None:
2426 return self.url_result(mobj.group('url'), 'TED')
2428 # Look for embedded Ustream videos
2429 ustream_url = UstreamIE._extract_url(webpage)
2431 return self.url_result(ustream_url, UstreamIE.ie_key())
2433 # Look for embedded arte.tv player
2435 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2437 if mobj is not None:
2438 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2440 # Look for embedded francetv player
2442 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2444 if mobj is not None:
2445 return self.url_result(mobj.group('url'))
2447 # Look for embedded smotri.com player
2448 smotri_url = SmotriIE._extract_url(webpage)
2450 return self.url_result(smotri_url, 'Smotri')
2452 # Look for embedded Myvi.ru player
2453 myvi_url = MyviIE._extract_url(webpage)
2455 return self.url_result(myvi_url)
2457 # Look for embedded soundcloud player
2458 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2460 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2462 # Look for tunein player
2463 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2465 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2467 # Look for embedded mtvservices player
2468 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2470 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2472 # Look for embedded yahoo player
2474 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2476 if mobj is not None:
2477 return self.url_result(mobj.group('url'), 'Yahoo')
2479 # Look for embedded sbs.com.au player
2483 <meta\s+property="og:video"\s+content=|
2486 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2488 if mobj is not None:
2489 return self.url_result(mobj.group('url'), 'SBS')
2491 # Look for embedded Cinchcast player
2493 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2495 if mobj is not None:
2496 return self.url_result(mobj.group('url'), 'Cinchcast')
2499 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2503 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2505 if mobj is not None:
2506 return self.url_result(mobj.group('url'), 'MLB')
2509 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2511 if mobj is not None:
2512 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2515 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2517 if mobj is not None:
2518 return self.url_result(mobj.group('url'), 'Livestream')
2520 # Look for Zapiks embed
2522 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2523 if mobj is not None:
2524 return self.url_result(mobj.group('url'), 'Zapiks')
2526 # Look for Kaltura embeds
2527 kaltura_url = KalturaIE._extract_url(webpage)
2529 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2531 # Look for EaglePlatform embeds
2532 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2533 if eagleplatform_url:
2534 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2536 # Look for ClipYou (uses EaglePlatform) embeds
2538 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2539 if mobj is not None:
2540 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2542 # Look for Pladform embeds
2543 pladform_url = PladformIE._extract_url(webpage)
2545 return self.url_result(pladform_url)
2547 # Look for Videomore embeds
2548 videomore_url = VideomoreIE._extract_url(webpage)
2550 return self.url_result(videomore_url)
2552 # Look for Webcaster embeds
2553 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2555 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2557 # Look for Playwire embeds
2559 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2560 if mobj is not None:
2561 return self.url_result(mobj.group('url'))
2563 # Look for 5min embeds
2565 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2566 if mobj is not None:
2567 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2569 # Look for Crooks and Liars embeds
2571 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'))
2575 # Look for NBC Sports VPlayer embeds
2576 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2578 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2580 # Look for NBC News embeds
2581 nbc_news_embed_url = re.search(
2582 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2583 if nbc_news_embed_url:
2584 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2586 # Look for Google Drive embeds
2587 google_drive_url = GoogleDriveIE._extract_url(webpage)
2588 if google_drive_url:
2589 return self.url_result(google_drive_url, 'GoogleDrive')
2591 # Look for UDN embeds
2593 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2594 if mobj is not None:
2595 return self.url_result(
2596 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2598 # Look for Senate ISVP iframe
2599 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2601 return self.url_result(senate_isvp_url, 'SenateISVP')
2603 # Look for Dailymotion Cloud videos
2604 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2606 return self.url_result(dmcloud_url, 'DailymotionCloud')
2608 # Look for OnionStudios embeds
2609 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2610 if onionstudios_url:
2611 return self.url_result(onionstudios_url)
2613 # Look for ViewLift embeds
2614 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2616 return self.url_result(viewlift_url)
2618 # Look for JWPlatform embeds
2619 jwplatform_url = JWPlatformIE._extract_url(webpage)
2621 return self.url_result(jwplatform_url, 'JWPlatform')
2623 # Look for Digiteka embeds
2624 digiteka_url = DigitekaIE._extract_url(webpage)
2626 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2628 # Look for Arkena embeds
2629 arkena_url = ArkenaIE._extract_url(webpage)
2631 return self.url_result(arkena_url, ArkenaIE.ie_key())
2633 # Look for Piksel embeds
2634 piksel_url = PikselIE._extract_url(webpage)
2636 return self.url_result(piksel_url, PikselIE.ie_key())
2638 # Look for Limelight embeds
2639 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2641 return self.playlist_result(
2642 limelight_urls, video_id, video_title, video_description)
2644 # Look for Anvato embeds
2645 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2647 return self.playlist_result(
2648 anvato_urls, video_id, video_title, video_description)
2650 # Look for AdobeTVVideo embeds
2652 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2654 if mobj is not None:
2655 return self.url_result(
2656 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2659 # Look for Vine embeds
2661 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2663 if mobj is not None:
2664 return self.url_result(
2665 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2667 # Look for VODPlatform embeds
2669 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2671 if mobj is not None:
2672 return self.url_result(
2673 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2675 # Look for Mangomolo embeds
2677 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2679 video\?.*?\bid=(?P<video_id>\d+)|
2680 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2681 ).+?)\1''', webpage)
2682 if mobj is not None:
2684 '_type': 'url_transparent',
2685 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2686 'title': video_title,
2687 'description': video_description,
2688 'thumbnail': video_thumbnail,
2689 'uploader': video_uploader,
2691 video_id = mobj.group('video_id')
2694 'ie_key': 'MangomoloVideo',
2699 'ie_key': 'MangomoloLive',
2700 'id': mobj.group('channel_id'),
2704 # Look for Instagram embeds
2705 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2706 if instagram_embed_url is not None:
2707 return self.url_result(
2708 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2710 # Look for LiveLeak embeds
2711 liveleak_url = LiveLeakIE._extract_url(webpage)
2713 return self.url_result(liveleak_url, 'LiveLeak')
2715 # Look for 3Q SDN embeds
2716 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2719 '_type': 'url_transparent',
2720 'ie_key': ThreeQSDNIE.ie_key(),
2721 'url': self._proto_relative_url(threeqsdn_url),
2722 'title': video_title,
2723 'description': video_description,
2724 'thumbnail': video_thumbnail,
2725 'uploader': video_uploader,
2728 # Look for VBOX7 embeds
2729 vbox7_url = Vbox7IE._extract_url(webpage)
2731 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2733 # Look for DBTV embeds
2734 dbtv_urls = DBTVIE._extract_urls(webpage)
2736 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2738 # Look for Videa embeds
2739 videa_urls = VideaIE._extract_urls(webpage)
2741 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2743 # Look for 20 minuten embeds
2744 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2746 return self.playlist_from_matches(
2747 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2749 # Look for Openload embeds
2750 openload_urls = OpenloadIE._extract_urls(webpage)
2752 return self.playlist_from_matches(
2753 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2755 # Look for VideoPress embeds
2756 videopress_urls = VideoPressIE._extract_urls(webpage)
2758 return self.playlist_from_matches(
2759 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2761 # Look for Rutube embeds
2762 rutube_urls = RutubeIE._extract_urls(webpage)
2764 return self.playlist_from_matches(
2765 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2767 # Look for WashingtonPost embeds
2768 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2770 return self.playlist_from_matches(
2771 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2773 # Look for Mediaset embeds
2774 mediaset_urls = MediasetIE._extract_urls(webpage)
2776 return self.playlist_from_matches(
2777 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2779 # Look for JOJ.sk embeds
2780 joj_urls = JojIE._extract_urls(webpage)
2782 return self.playlist_from_matches(
2783 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2785 def merge_dicts(dict1, dict2):
2787 for k, v in dict1.items():
2790 for k, v in dict2.items():
2793 if (k not in merged or
2794 (isinstance(v, compat_str) and v and
2795 isinstance(merged[k], compat_str) and
2800 # Looking for http://schema.org/VideoObject
2801 json_ld = self._search_json_ld(
2802 webpage, video_id, default={}, expected_type='VideoObject')
2803 if json_ld.get('url'):
2804 return merge_dicts(json_ld, info_dict)
2806 # Look for HTML5 media
2807 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2809 for entry in entries:
2812 'title': video_title,
2814 self._sort_formats(entry['formats'])
2815 return self.playlist_result(entries)
2817 jwplayer_data = self._find_jwplayer_data(
2818 webpage, video_id, transform_source=js_to_json)
2820 info = self._parse_jwplayer_data(
2821 jwplayer_data, video_id, require_title=False, base_url=url)
2822 return merge_dicts(info, info_dict)
2824 def check_video(vurl):
2825 if YoutubeIE.suitable(vurl):
2827 if RtmpIE.suitable(vurl):
2829 vpath = compat_urlparse.urlparse(vurl).path
2830 vext = determine_ext(vpath)
2831 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2833 def filter_video(urls):
2834 return list(filter(check_video, urls))
2836 # Start with something easy: JW Player in SWFObject
2837 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2839 # Look for gorilla-vid style embedding
2840 found = filter_video(re.findall(r'''(?sx)
2844 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2847 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2849 # Broaden the search a little bit
2850 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2852 # Broaden the findall a little bit: JWPlayer JS loader
2853 found = filter_video(re.findall(
2854 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2857 found = filter_video(re.findall(r'''(?xs)
2858 flowplayer\("[^"]+",\s*
2860 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2861 ["']?url["']?\s*:\s*["']([^"']+)["']
2866 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2868 # Try to find twitter cards info
2869 # twitter:player:stream should be checked before twitter:player since
2870 # it is expected to contain a raw stream (see
2871 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2872 found = filter_video(re.findall(
2873 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2875 # We look for Open Graph info:
2876 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2877 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2878 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2879 if m_video_type is not None:
2880 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2882 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2884 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2885 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2888 # Look also in Refresh HTTP header
2889 refresh_header = head_response.headers.get('Refresh')
2891 # In python 2 response HTTP headers are bytestrings
2892 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2893 refresh_header = refresh_header.decode('iso-8859-1')
2894 found = re.search(REDIRECT_REGEX, refresh_header)
2896 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2898 self.report_following_redirect(new_url)
2907 # twitter:player is a https URL to iframe player that may or may not
2908 # be supported by youtube-dl thus this is checked the very last (see
2909 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2910 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2912 return self.url_result(embed_url)
2915 raise UnsupportedError(url)
2918 for video_url in orderedSet(found):
2919 video_url = unescapeHTML(video_url)
2920 video_url = video_url.replace('\\/', '/')
2921 video_url = compat_urlparse.urljoin(url, video_url)
2922 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2924 # Sometimes, jwplayer extraction will result in a YouTube URL
2925 if YoutubeIE.suitable(video_url):
2926 entries.append(self.url_result(video_url, 'Youtube'))
2929 # here's a fun little line of code for you:
2930 video_id = os.path.splitext(video_id)[0]
2934 'uploader': video_uploader,
2935 'title': video_title,
2936 'age_limit': age_limit,
2939 if RtmpIE.suitable(video_url):
2940 entry_info_dict.update({
2941 '_type': 'url_transparent',
2942 'ie_key': RtmpIE.ie_key(),
2945 entries.append(entry_info_dict)
2948 ext = determine_ext(video_url)
2950 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2952 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2954 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2956 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2958 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2959 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2960 # Just matching .ism/manifest is not enough to be reliably sure
2961 # whether it's actually an ISM manifest or some other streaming
2962 # manifest since there are various streaming URL formats
2963 # possible (see [1]) as well as some other shenanigans like
2964 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2966 # Thus the most reasonable way to solve this is to delegate
2967 # to generic extractor in order to look into the contents of
2968 # the manifest itself.
2969 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2970 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2971 entry_info_dict = self.url_result(
2972 smuggle_url(video_url, {'to_generic': True}),
2975 entry_info_dict['url'] = video_url
2977 if entry_info_dict.get('formats'):
2978 self._sort_formats(entry_info_dict['formats'])
2980 entries.append(entry_info_dict)
2982 if len(entries) == 1:
2985 for num, e in enumerate(entries, start=1):
2986 # 'url' results don't have a title
2987 if e.get('title') is not None:
2988 e['title'] = '%s (%d)' % (e['title'], num)
2990 '_type': 'playlist',