3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import (
56 from .onionstudios import OnionStudiosIE
57 from .viewlift import ViewLiftEmbedIE
58 from .screenwavemedia import ScreenwaveMediaIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .googledrive import GoogleDriveIE
63 from .jwplatform import JWPlatformIE
64 from .digiteka import DigitekaIE
65 from .arkena import ArkenaIE
66 from .instagram import InstagramIE
67 from .liveleak import LiveLeakIE
68 from .threeqsdn import ThreeQSDNIE
69 from .theplatform import ThePlatformIE
70 from .vessel import VesselIE
71 from .kaltura import KalturaIE
72 from .eagleplatform import EaglePlatformIE
73 from .facebook import FacebookIE
74 from .soundcloud import SoundcloudIE
77 class GenericIE(InfoExtractor):
78 IE_DESC = 'Generic downloader that works on some sites'
82 # Direct link to a video
84 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
85 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
90 'upload_date': '20100513',
93 # Direct link to media delivered compressed (until Accept-Encoding is *)
95 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
96 'md5': '128c42e68b13950268b648275386fc74',
98 'id': 'FictionJunction-Parallel_Hearts',
100 'title': 'FictionJunction-Parallel_Hearts',
101 'upload_date': '20140522',
103 'expected_warnings': [
104 'URL could be a direct video link, returning it as such.'
107 # Direct download with broken HEAD
109 'url': 'http://ai-radio.org:8000/radio.opus',
116 'skip_download': True, # infinite live stream
118 'expected_warnings': [
119 r'501.*Not Implemented',
123 # Direct link with incorrect MIME type
125 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
126 'md5': '4ccbebe5f36706d85221f204d7eb5913',
128 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
129 'id': '5_Lennart_Poettering_-_Systemd',
131 'title': '5_Lennart_Poettering_-_Systemd',
132 'upload_date': '20141120',
134 'expected_warnings': [
135 'URL could be a direct video link, returning it as such.'
140 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
142 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
143 'title': 'Zero Punctuation',
144 'description': 're:.*groundbreaking video review series.*'
146 'playlist_mincount': 11,
148 # RSS feed with enclosure
150 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
152 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
154 'upload_date': '20150228',
155 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
158 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
160 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
164 'title': 'Automatics, robotics and biocybernetics',
165 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
166 'upload_date': '20130627',
167 'formats': 'mincount:16',
168 'subtitles': 'mincount:1',
171 'force_generic_extractor': True,
172 'skip_download': True,
175 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
177 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
182 'formats': 'mincount:1',
185 'skip_download': True,
188 # SMIL from https://www.restudy.dk/video/play/id/1637
190 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
194 'title': 'video_1637',
195 'formats': 'mincount:3',
198 'skip_download': True,
201 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
203 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
205 'id': 'smil-service',
207 'title': 'smil-service',
208 'formats': 'mincount:1',
211 'skip_download': True,
214 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
216 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
220 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
221 'formats': 'mincount:3',
224 'skip_download': True,
227 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
229 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
231 'id': 'mZlp2ctYIUEB',
233 'title': 'Tikibad ontruimd wegens brand',
234 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
235 'thumbnail': 're:^https?://.*\.jpg$',
239 'skip_download': True,
242 # MPD from http://dash-mse-test.appspot.com/media.html
244 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
245 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
247 'id': 'car-20120827-manifest',
249 'title': 'car-20120827-manifest',
250 'formats': 'mincount:9',
251 'upload_date': '20130904',
254 'format': 'bestvideo',
257 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
259 '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',
264 'formats': 'mincount:8',
268 'skip_download': True,
271 # m3u8 served with Content-Type: text/plain
273 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
278 'upload_date': '20140720',
279 'formats': 'mincount:11',
283 'skip_download': True,
288 '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',
292 'upload_date': '20130224',
293 'uploader_id': 'TheVerge',
294 'description': 're:^Chris Ziegler takes a look at the\.*',
295 'uploader': 'The Verge',
296 'title': 'First Firefox OS phones side-by-side',
299 'skip_download': False,
303 # redirect in Refresh HTTP header
304 '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',
308 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
309 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
310 'upload_date': '20150917',
311 'uploader_id': 'brtvofficial',
312 'uploader': 'Boiler Room',
315 'skip_download': False,
319 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
320 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
322 'id': '13601338388002',
324 'uploader': 'www.hodiho.fr',
325 'title': 'R\u00e9gis plante sa Jeep',
328 # bandcamp page with custom domain
330 'add_ie': ['Bandcamp'],
331 'url': 'http://bronyrock.com/track/the-pony-mash',
335 'title': 'The Pony Mash',
336 'uploader': 'M_Pallante',
338 'skip': 'There is a limit of 200 free downloads / month for the test song',
340 # embedded brightcove video
341 # it also tests brightcove videos that need to set the 'Referer' in the
344 'add_ie': ['BrightcoveLegacy'],
345 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
347 'id': '2765128793001',
349 'title': 'Le cours de bourse : l’analyse technique',
350 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
351 'uploader': 'BFM BUSINESS',
354 'skip_download': True,
358 # https://github.com/rg3/youtube-dl/issues/2253
359 'url': 'http://bcove.me/i6nfkrc3',
360 'md5': '0ba9446db037002366bab3b3eb30c88c',
362 'id': '3101154703001',
364 'title': 'Still no power',
365 'uploader': 'thestar.com',
366 '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.',
368 'add_ie': ['BrightcoveLegacy'],
371 'url': 'http://www.championat.com/video/football/v/87/87499.html',
372 'md5': 'fb973ecf6e4a78a67453647444222983',
374 'id': '3414141473001',
376 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
377 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
378 'uploader': 'Championat',
382 # https://github.com/rg3/youtube-dl/issues/3541
383 'add_ie': ['BrightcoveLegacy'],
384 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
386 'id': '3866516442001',
388 'title': 'Leer mij vrouwen kennen: Aflevering 1',
389 'description': 'Leer mij vrouwen kennen: Aflevering 1',
390 'uploader': 'SBS Broadcasting',
392 'skip': 'Restricted to Netherlands',
394 'skip_download': True, # m3u8 download
399 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
400 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
402 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
404 'title': '2cc213299525360.mov', # that's what we get
407 'add_ie': ['Ooyala'],
410 # ooyala video embedded with http://player.ooyala.com/iframe.js
411 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
413 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
415 'title': '"Steve Jobs: Man in the Machine" trailer',
416 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
420 'skip_download': True,
425 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
429 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
430 'upload_date': '20140225',
431 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
432 'uploader': 'Tested',
433 'uploader_id': 'testedcom',
435 # No need to test YoutubeIE here
437 'skip_download': True,
442 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
446 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
447 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
452 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
456 'title': 'Охотское море стало целиком российским',
457 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
461 'skip_download': True,
466 '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/',
470 'title': 'Дошкольное воспитание',
475 'url': 'http://www.vestifinance.ru/articles/25753',
478 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
483 'title': 'Госзаказ. День 3',
489 'title': 'Госзаказ. День 2',
495 'title': 'Госзаказ. День 1',
501 'skip_download': True,
506 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
508 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
510 'title': 'Ужастики, русский трейлер (2015)',
511 'thumbnail': 're:^https?://.*\.jpg$',
517 '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',
520 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
522 'playlist_mincount': 7,
526 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
527 'md5': '65fdff94098e4a607385a60c5177c638',
531 'title': 'Hidden miracles of the natural world',
532 'uploader': 'Louie Schwartzberg',
533 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
536 # Embedded Ustream video
538 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
539 'md5': '27b99cdb639c9b12a79bca876a073417',
543 'uploader': 'AU SPA: The NSA and Privacy',
544 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
547 # nowvideo embed hidden behind percent encoding
549 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
550 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
552 'id': '06e53103ca9aa',
554 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
555 'description': 'No description',
560 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
561 'md5': '7653032cbb25bf6c80d80f217055fa43',
563 'id': '048195-004_PLUS7-F',
566 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
567 'upload_date': '20140320',
570 'skip_download': 'Requires rtmpdump'
575 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
579 'title': 'Alcaline, le concert avec Calogero',
580 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
581 'upload_date': '20150226',
582 'timestamp': 1424989860,
587 'skip_download': True,
589 'expected_warnings': [
595 'url': 'http://www.wired.com/2014/04/honda-asimo/',
596 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
598 'id': '53501be369702d3275860000',
600 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
605 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
606 'md5': '441aeeb82eb72c422c7f14ec533999cd',
608 'id': 'k2mm4bCdJ6CQ2i7c8o2',
610 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
611 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
613 'uploader_id': 'xgditw',
614 'upload_date': '20140425',
615 'timestamp': 1398441542,
617 'add_ie': ['Dailymotion'],
621 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
625 'title': 'The NBL Auction 2014',
626 'uploader': 'BADMINTON England',
627 'uploader_id': 'BADMINTONEvents',
628 'upload_date': '20140603',
629 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
631 'add_ie': ['Youtube'],
633 'skip_download': True,
638 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
639 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
641 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
643 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
644 'description': 'Two valets share their love for movie star Liam Neesons.',
645 'timestamp': 1349922600,
646 'upload_date': '20121011',
649 # YouTube embed via <data-embed-url="">
651 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
655 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
656 'uploader': 'Gameloft',
657 'uploader_id': 'gameloft',
658 'upload_date': '20140828',
659 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
662 'skip_download': True,
667 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
669 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
671 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
672 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
677 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
679 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
680 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
686 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
691 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
692 'md5': '9d65602bf31c6e20014319c7d07fba27',
694 'id': '5123ea6d5e5a7',
697 'uploader': 'www.handjobhub.com',
698 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
701 # Multiple brightcove videos
702 # https://github.com/rg3/youtube-dl/issues/2283
704 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
706 'id': 'always-never',
707 'title': 'Always / Never - The New Yorker',
711 'extract_flat': False,
712 'skip_download': True,
717 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
718 'md5': '96f09a37e44da40dd083e12d9a683327',
722 'title': 'Ump changes call to ball',
723 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
725 'timestamp': 1401537900,
726 'upload_date': '20140531',
727 'thumbnail': 're:^https?://.*\.jpg$',
732 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
733 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
737 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
738 'description': 'a Paywall Videos video from Remilon',
740 'uploader': 'study.com',
741 'timestamp': 1459678540,
742 'upload_date': '20160403',
743 'filesize': 24687186,
747 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
748 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
752 'title': 'Conversation about Hexagonal Rails Part 1',
753 'description': 'a Martin Fowler video from ThoughtWorks',
755 'uploader': 'thoughtworks.wistia.com',
756 'timestamp': 1401832161,
757 'upload_date': '20140603',
760 # Wistia standard embed (async)
762 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
766 'title': 'Drip Brennan Dunn Workshop',
767 'description': 'a JV Webinars video from getdrip-1',
769 'timestamp': 1463607249,
770 'upload_date': '20160518',
773 'skip_download': True,
778 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
782 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
783 'uploader': 'Sophos Security',
784 'title': 'Chet Chat 171 - Oct 29, 2014',
785 'upload_date': '20141029',
790 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
794 'upload_date': '20141112',
795 'title': 'Rosetta #CometLanding webcast HL 10',
798 # Another Livestream embed, without 'new.' in URL
800 'url': 'https://www.freespeech.org/',
804 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
808 'skip_download': True,
813 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
816 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
818 'playlist_mincount': 2,
822 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
826 'upload_date': '20141126',
827 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
832 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
834 'id': '730m_DandD_1901_512k',
836 'uploader': 'www.abc.net.au',
837 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
840 # embedded viddler video
842 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
846 'uploader': 'deadspin',
847 'title': 'WALL-TO-GORTAT',
848 'timestamp': 1422285291,
849 'upload_date': '20150126',
851 'add_ie': ['Viddler'],
855 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
859 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
860 'description': 'md5:601cb790edd05908957dae8aaa866465',
861 'upload_date': '20150220',
863 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
867 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
871 'upload_date': '20150212',
872 'uploader': 'The National Archives UK',
873 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
874 'uploader_id': 'NationalArchives08',
875 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
880 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
881 'playlist_mincount': 5,
883 'id': 'aanslagen-kopenhagen',
884 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
889 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
893 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
896 # Kaltura embed (different embed code)
898 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
902 'upload_date': '20150127',
903 'uploader_id': 'PremierMedia',
905 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
908 # Kaltura embed protected with referrer
910 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
914 'title': 'Violetta - Achter De Schermen - Ruggero',
915 'description': 'Achter de schermen met Ruggero',
916 'timestamp': 1435133761,
917 'upload_date': '20150624',
918 'uploader_id': 'echojecka',
921 # Kaltura embed with single quotes
923 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
928 'timestamp': 1355743100,
929 'upload_date': '20121217',
930 'uploader_id': 'batchUser',
932 'add_ie': ['Kaltura'],
935 # Kaltura embedded via quoted entry_id
936 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
940 'title': '06_matthew_brender_raj_dutt',
941 'timestamp': 1466638791,
942 'upload_date': '20160622',
944 'add_ie': ['Kaltura'],
945 'expected_warnings': [
946 'Could not send HEAD request'
949 'skip_download': True,
952 # Eagle.Platform embed (generic URL)
954 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
955 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
959 'title': 'Навальный вышел на свободу',
960 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
961 'thumbnail': 're:^https?://.*\.jpg$',
967 # ClipYou (Eagle.Platform) embed (custom URL)
969 'url': 'http://muz-tv.ru/play/7129/',
970 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
974 'title': "'O Sole Mio",
975 'thumbnail': 're:^https?://.*\.jpg$',
982 'url': 'http://muz-tv.ru/kinozal/view/7400/',
986 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
987 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
988 'thumbnail': 're:^https?://.*\.jpg$',
995 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
999 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1000 'thumbnail': 're:^https?://.*\.png$',
1006 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1007 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1011 'title': 'Facebook Creates "On This Day" | Crunch Report',
1016 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1020 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1025 # Crooks and Liars embed
1027 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1031 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1032 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1033 'timestamp': 1428207000,
1034 'upload_date': '20150405',
1035 'uploader': 'Heather',
1038 # Crooks and Liars external embed
1040 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1042 'id': 'MTE3MjUtMzQ2MzA',
1044 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1045 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1046 'timestamp': 1265032391,
1047 'upload_date': '20100201',
1048 'uploader': 'Heather',
1051 # NBC Sports vplayer embed
1053 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1055 'id': 'ln7x1qSThw4k',
1057 'title': "PFT Live: New leader in the 'new-look' defense",
1058 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1059 'uploader': 'NBCU-SPORTS',
1060 'upload_date': '20140107',
1061 'timestamp': 1389118457,
1066 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1067 'md5': '1aa589c675898ae6d37a17913cf68d66',
1069 'id': '701714499682',
1071 'title': 'PREVIEW: On Assignment: David Letterman',
1072 '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.',
1077 'url': 'https://video.udn.com/news/300346',
1078 'md5': 'fd2060e988c326991037b9aff9df21a6',
1082 'title': '中一中男師變性 全校師生力挺',
1083 'thumbnail': 're:^https?://.*\.jpg$',
1087 'skip_download': True,
1092 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1094 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1096 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1097 'title': 'This is what separates the Excel masters from the wannabes',
1098 'duration': 191.933,
1102 'skip_download': True,
1105 # Brightcove URL in single quotes
1107 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1108 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1110 'id': '4255764656001',
1112 'title': 'SN Presents: Russell Martin, World Citizen',
1113 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1114 'uploader': 'Rogers Sportsnet',
1115 'uploader_id': '1704050871',
1116 'upload_date': '20150525',
1117 'timestamp': 1432570283,
1120 # Dailymotion Cloud video
1122 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1123 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1127 'title': 'Sauvons les abeilles ! - Le débat',
1128 'description': 'md5:d9082128b1c5277987825d684939ca26',
1129 'thumbnail': 're:^https?://.*\.jpe?g$',
1130 'timestamp': 1434970506,
1131 'upload_date': '20150622',
1132 'uploader': 'Public Sénat',
1133 'uploader_id': 'xa9gza',
1136 # OnionStudios embed
1138 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1142 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1143 'thumbnail': 're:^https?://.*\.jpe?g$',
1144 'uploader': 'ClickHole',
1145 'uploader_id': 'clickhole',
1150 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1152 'id': '74849a00-85a9-11e1-9660-123139220831',
1154 'title': '#whilewewatch',
1157 # AdobeTVVideo embed
1159 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1160 'md5': '43662b577c018ad707a63766462b1e87',
1164 'title': 'New experience with Acrobat DC',
1165 'description': 'New experience with Acrobat DC',
1166 'duration': 248.667,
1169 # ScreenwaveMedia embed
1171 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1172 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1174 'id': 'cinemasnob-55d26273809dd',
1176 'title': 'cinemasnob',
1179 # BrightcoveInPageEmbed embed
1181 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1183 'id': '4238694884001',
1185 'title': 'Tabletop: Dread, Last Thoughts',
1186 'description': 'Tabletop: Dread, Last Thoughts',
1190 # JWPlayer with M3U8
1192 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1196 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1197 'uploader': 'ren.tv',
1201 'skip_download': True,
1204 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1205 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1207 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1209 'id': '4785848093001',
1211 'title': 'The Cardinal Pell Interview',
1212 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1213 'uploader': 'GlobeCast Australia - GlobeStream',
1214 'uploader_id': '2733773828001',
1215 'upload_date': '20160304',
1216 'timestamp': 1457083087,
1220 'skip_download': True,
1223 # Another form of arte.tv embed
1225 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1226 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1228 'id': '030273-562_PLUS7-F',
1230 'title': 'ARTE Reportage - Nulle part, en France',
1231 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1232 'upload_date': '20160409',
1237 'url': 'http://www.wykop.pl/link/3088787/',
1238 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1240 'id': '874_1459135191',
1242 'title': 'Man shows poor quality of new apartment building',
1243 'description': 'The wall is like a sand pile.',
1244 'uploader': 'Lake8737',
1247 # Duplicated embedded video URLs
1249 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1251 'id': '149298443_480_16c25b74_2',
1253 'title': 'vs. Blue Orange Spring Game',
1254 'uploader': 'www.hudl.com',
1257 # twitter:player:stream embed
1259 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1263 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1264 'uploader': 'www.rtl.be',
1268 'skip_download': True,
1271 # twitter:player embed
1273 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1274 'md5': 'a3e0df96369831de324f0778e126653c',
1276 'id': '4909620399001',
1278 'title': 'What Do Black Holes Sound Like?',
1279 'description': 'what do black holes sound like',
1280 'upload_date': '20160524',
1281 'uploader_id': '29913724001',
1282 'timestamp': 1464107587,
1283 'uploader': 'TheAtlantic',
1285 'add_ie': ['BrightcoveLegacy'],
1287 # Facebook <iframe> embed
1289 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1290 'md5': 'fbcde74f534176ecb015849146dd3aee',
1292 'id': '599637780109885',
1294 'title': 'Facebook video #599637780109885',
1297 # Facebook API embed
1299 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1300 'md5': 'a47372ee61b39a7b90287094d447d94e',
1302 'id': '10153467542406923',
1304 'title': 'Facebook video #10153467542406923',
1307 # Wordpress "YouTube Video Importer" plugin
1309 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1310 'md5': 'd16797741b560b485194eddda8121b48',
1312 'id': 'HNTXWDXV9Is',
1314 'title': 'Blue Devils Drumline Stanford lot 2016',
1315 'upload_date': '20160627',
1316 'uploader_id': 'GENOCIDE8GENERAL10',
1317 'uploader': 'cylus cyrus',
1321 # video stored on custom kaltura server
1322 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1323 'md5': '537617d06e64dfed891fa1593c4b30cc',
1327 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1328 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1329 'uploader_id': 'videos.expansion@el-mundo.net',
1330 'upload_date': '20150429',
1331 'timestamp': 1430303472,
1333 'add_ie': ['Kaltura'],
1336 # Non-standard Vimeo embed
1337 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1338 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1342 'title': 'Understanding the web - Teaser',
1343 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1344 'upload_date': '20151214',
1345 'uploader': 'OpenClassrooms',
1346 'uploader_id': 'openclassrooms',
1348 'add_ie': ['Vimeo'],
1351 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1352 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1354 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1356 'title': 'Big Buck Bunny',
1357 'description': 'Royalty free test video',
1358 'timestamp': 1432816365,
1359 'upload_date': '20150528',
1363 'skip_download': True,
1365 'add_ie': [ArkenaIE.ie_key()],
1368 # # TODO: find another test
1369 # # http://schema.org/VideoObject
1370 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1371 # 'md5': '888dcf08b7ea671381f00fab74692755',
1373 # 'id': 'nyvTSJMKId',
1375 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1376 # 'description': '#love for cats.',
1377 # 'timestamp': 1461244995,
1378 # 'upload_date': '20160421',
1381 # 'force_generic_extractor': True,
1386 def report_following_redirect(self, new_url):
1387 """Report information extraction."""
1388 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1390 def _extract_rss(self, url, video_id, doc):
1391 playlist_title = doc.find('./channel/title').text
1392 playlist_desc_el = doc.find('./channel/description')
1393 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1396 for it in doc.findall('./channel/item'):
1397 next_url = xpath_text(it, 'link', fatal=False)
1399 enclosure_nodes = it.findall('./enclosure')
1400 for e in enclosure_nodes:
1401 next_url = e.attrib.get('url')
1411 'title': it.find('title').text,
1415 '_type': 'playlist',
1417 'title': playlist_title,
1418 'description': playlist_desc,
1422 def _extract_camtasia(self, url, video_id, webpage):
1423 """ Returns None if no camtasia video can be found. """
1425 camtasia_cfg = self._search_regex(
1426 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1427 webpage, 'camtasia configuration file', default=None)
1428 if camtasia_cfg is None:
1431 title = self._html_search_meta('DC.title', webpage, fatal=True)
1433 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1434 camtasia_cfg = self._download_xml(
1435 camtasia_url, video_id,
1436 note='Downloading camtasia configuration',
1437 errnote='Failed to download camtasia configuration')
1438 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1441 for n in fileset_node.getchildren():
1442 url_n = n.find('./uri')
1447 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1448 'title': '%s - %s' % (title, n.tag),
1449 'url': compat_urlparse.urljoin(url, url_n.text),
1450 'duration': float_or_none(n.find('./duration').text),
1454 '_type': 'playlist',
1459 def _real_extract(self, url):
1460 if url.startswith('//'):
1463 'url': self.http_scheme() + url,
1466 parsed_url = compat_urlparse.urlparse(url)
1467 if not parsed_url.scheme:
1468 default_search = self._downloader.params.get('default_search')
1469 if default_search is None:
1470 default_search = 'fixup_error'
1472 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1474 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1475 return self.url_result('http://' + url)
1476 elif default_search != 'fixup_error':
1477 if default_search == 'auto_warning':
1478 if re.match(r'^(?:url|URL)$', url):
1479 raise ExtractorError(
1480 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1483 self._downloader.report_warning(
1484 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1485 return self.url_result('ytsearch:' + url)
1487 if default_search in ('error', 'fixup_error'):
1488 raise ExtractorError(
1489 '%r is not a valid URL. '
1490 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1491 % (url, url), expected=True)
1493 if ':' not in default_search:
1494 default_search += ':'
1495 return self.url_result(default_search + url)
1497 url, smuggled_data = unsmuggle_url(url)
1498 force_videoid = None
1499 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1500 if smuggled_data and 'force_videoid' in smuggled_data:
1501 force_videoid = smuggled_data['force_videoid']
1502 video_id = force_videoid
1504 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1506 self.to_screen('%s: Requesting header' % video_id)
1508 head_req = HEADRequest(url)
1509 head_response = self._request_webpage(
1511 note=False, errnote='Could not send HEAD request to %s' % url,
1514 if head_response is not False:
1515 # Check for redirect
1516 new_url = head_response.geturl()
1518 self.report_following_redirect(new_url)
1520 new_url = smuggle_url(
1521 new_url, {'force_videoid': force_videoid})
1522 return self.url_result(new_url)
1524 full_response = None
1525 if head_response is False:
1526 request = sanitized_Request(url)
1527 request.add_header('Accept-Encoding', '*')
1528 full_response = self._request_webpage(request, video_id)
1529 head_response = full_response
1533 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1534 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1537 # Check for direct link to a video
1538 content_type = head_response.headers.get('Content-Type', '').lower()
1539 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1541 format_id = m.group('format_id')
1542 if format_id.endswith('mpegurl'):
1543 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1544 elif format_id == 'f4m':
1545 formats = self._extract_f4m_formats(url, video_id)
1548 'format_id': m.group('format_id'),
1550 'vcodec': 'none' if m.group('type') == 'audio' else None
1552 info_dict['direct'] = True
1553 self._sort_formats(formats)
1554 info_dict['formats'] = formats
1557 if not self._downloader.params.get('test', False) and not is_intentional:
1558 force = self._downloader.params.get('force_generic_extractor', False)
1559 self._downloader.report_warning(
1560 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1562 if not full_response:
1563 request = sanitized_Request(url)
1564 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1565 # making it impossible to download only chunk of the file (yet we need only 512kB to
1566 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1567 # that will always result in downloading the whole file that is not desirable.
1568 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1569 # to accept raw bytes and being able to download only a chunk.
1570 # It may probably better to solve this by checking Content-Type for application/octet-stream
1571 # after HEAD request finishes, but not sure if we can rely on this.
1572 request.add_header('Accept-Encoding', '*')
1573 full_response = self._request_webpage(request, video_id)
1575 first_bytes = full_response.read(512)
1577 # Is it an M3U playlist?
1578 if first_bytes.startswith(b'#EXTM3U'):
1579 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1580 self._sort_formats(info_dict['formats'])
1583 # Maybe it's a direct link to a video?
1584 # Be careful not to download the whole thing!
1585 if not is_html(first_bytes):
1586 self._downloader.report_warning(
1587 'URL could be a direct video link, returning it as such.')
1594 webpage = self._webpage_read_content(
1595 full_response, url, video_id, prefix=first_bytes)
1597 self.report_extraction(video_id)
1599 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1601 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1602 if doc.tag == 'rss':
1603 return self._extract_rss(url, video_id, doc)
1604 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1605 smil = self._parse_smil(doc, url, video_id)
1606 self._sort_formats(smil['formats'])
1608 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1609 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1610 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1611 info_dict['formats'] = self._parse_mpd_formats(
1612 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1613 self._sort_formats(info_dict['formats'])
1615 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1616 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1617 self._sort_formats(info_dict['formats'])
1619 except compat_xml_parse_error:
1622 # Is it a Camtasia project?
1623 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1624 if camtasia_res is not None:
1627 # Sometimes embedded video player is hidden behind percent encoding
1628 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1629 # Unescaping the whole page allows to handle those cases in a generic way
1630 webpage = compat_urllib_parse_unquote(webpage)
1632 # it's tempting to parse this further, but you would
1633 # have to take into account all the variations like
1634 # Video Title - Site Name
1635 # Site Name | Video Title
1636 # Video Title - Tagline | Site Name
1637 # and so on and so forth; it's just not practical
1638 video_title = self._og_search_title(
1639 webpage, default=None) or self._html_search_regex(
1640 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1643 # Try to detect age limit automatically
1644 age_limit = self._rta_search(webpage)
1645 # And then there are the jokers who advertise that they use RTA,
1646 # but actually don't.
1647 AGE_LIMIT_MARKERS = [
1648 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1650 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1653 # video uploader is domain name
1654 video_uploader = self._search_regex(
1655 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1657 video_description = self._og_search_description(webpage, default=None)
1658 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1661 def _playlist_from_matches(matches, getter=None, ie=None):
1663 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1665 return self.playlist_result(
1666 urlrs, playlist_id=video_id, playlist_title=video_title)
1668 # Look for Brightcove Legacy Studio embeds
1669 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1671 self.to_screen('Brightcove video detected.')
1674 'url': smuggle_url(bc_url, {'Referer': url}),
1675 'ie_key': 'BrightcoveLegacy'
1676 } for bc_url in bc_urls]
1679 '_type': 'playlist',
1680 'title': video_title,
1685 # Look for Brightcove New Studio embeds
1686 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1688 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1690 # Look for ThePlatform embeds
1691 tp_urls = ThePlatformIE._extract_urls(webpage)
1693 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1695 # Look for Vessel embeds
1696 vessel_urls = VesselIE._extract_urls(webpage)
1698 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1700 # Look for embedded rtl.nl player
1701 matches = re.findall(
1702 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1705 return _playlist_from_matches(matches, ie='RtlNl')
1707 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1708 if vimeo_url is not None:
1709 return self.url_result(vimeo_url)
1711 vid_me_embed_url = self._search_regex(
1712 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1713 webpage, 'vid.me embed', default=None)
1714 if vid_me_embed_url is not None:
1715 return self.url_result(vid_me_embed_url, 'Vidme')
1717 # Look for embedded YouTube player
1718 matches = re.findall(r'''(?x)
1727 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1731 return _playlist_from_matches(
1732 matches, lambda m: unescapeHTML(m[1]))
1734 # Look for lazyYT YouTube embed
1735 matches = re.findall(
1736 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1738 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1740 # Look for Wordpress "YouTube Video Importer" plugin
1741 matches = re.findall(r'''(?x)<div[^>]+
1742 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1743 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1745 return _playlist_from_matches(matches, lambda m: m[-1])
1747 matches = DailymotionIE._extract_urls(webpage)
1749 return _playlist_from_matches(matches)
1751 # Look for embedded Dailymotion playlist player (#3822)
1753 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1755 playlists = re.findall(
1756 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1758 return _playlist_from_matches(
1759 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1761 # Look for embedded Wistia player
1763 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1765 embed_url = self._proto_relative_url(
1766 unescapeHTML(match.group('url')))
1768 '_type': 'url_transparent',
1771 'uploader': video_uploader,
1774 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1777 '_type': 'url_transparent',
1778 'url': 'wistia:%s' % match.group('id'),
1780 'uploader': video_uploader,
1785 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1786 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1789 return self.url_result(self._proto_relative_url(
1790 'wistia:%s' % match.group('id')), 'Wistia')
1792 # Look for SVT player
1793 svt_url = SVTIE._extract_url(webpage)
1795 return self.url_result(svt_url, 'SVT')
1797 # Look for embedded condenast player
1798 matches = re.findall(
1799 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1803 '_type': 'playlist',
1806 'ie_key': 'CondeNast',
1808 } for ma in matches],
1809 'title': video_title,
1813 # Look for Bandcamp pages with custom domain
1814 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1815 if mobj is not None:
1816 burl = unescapeHTML(mobj.group(1))
1817 # Don't set the extractor because it can be a track url or an album
1818 return self.url_result(burl)
1820 # Look for embedded Vevo player
1822 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1823 if mobj is not None:
1824 return self.url_result(mobj.group('url'))
1826 # Look for embedded Viddler player
1828 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1830 if mobj is not None:
1831 return self.url_result(mobj.group('url'))
1833 # Look for NYTimes player
1835 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1837 if mobj is not None:
1838 return self.url_result(mobj.group('url'))
1840 # Look for Libsyn player
1842 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1843 if mobj is not None:
1844 return self.url_result(mobj.group('url'))
1846 # Look for Ooyala videos
1847 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1848 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1849 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1850 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1851 if mobj is not None:
1852 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1854 # Look for multiple Ooyala embeds on SBN network websites
1855 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1856 if mobj is not None:
1857 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1859 return _playlist_from_matches(
1860 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1862 # Look for Aparat videos
1863 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1864 if mobj is not None:
1865 return self.url_result(mobj.group(1), 'Aparat')
1867 # Look for MPORA videos
1868 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1869 if mobj is not None:
1870 return self.url_result(mobj.group(1), 'Mpora')
1872 # Look for embedded NovaMov-based player
1874 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1875 (?P<url>http://(?:(?:embed|www)\.)?
1877 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1878 videoweed\.(?:es|com)|
1879 movshare\.(?:net|sx|ag)|
1880 divxstage\.(?:eu|net|ch|co|at|ag))
1881 /embed\.php.+?)\1''', webpage)
1882 if mobj is not None:
1883 return self.url_result(mobj.group('url'))
1885 # Look for embedded Facebook player
1886 facebook_url = FacebookIE._extract_url(webpage)
1887 if facebook_url is not None:
1888 return self.url_result(facebook_url, 'Facebook')
1890 # Look for embedded VK player
1891 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1892 if mobj is not None:
1893 return self.url_result(mobj.group('url'), 'VK')
1895 # Look for embedded Odnoklassniki player
1896 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1897 if mobj is not None:
1898 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1900 # Look for embedded ivi player
1901 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1902 if mobj is not None:
1903 return self.url_result(mobj.group('url'), 'Ivi')
1905 # Look for embedded Huffington Post player
1907 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1908 if mobj is not None:
1909 return self.url_result(mobj.group('url'), 'HuffPost')
1912 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1913 if mobj is not None:
1914 return self.url_result(mobj.group('url'))
1915 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1916 if mobj is not None:
1917 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1919 # Look for funnyordie embed
1920 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1922 return _playlist_from_matches(
1923 matches, getter=unescapeHTML, ie='FunnyOrDie')
1925 # Look for BBC iPlayer embed
1926 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1928 return _playlist_from_matches(matches, ie='BBCCoUk')
1930 # Look for embedded RUTV player
1931 rutv_url = RUTVIE._extract_url(webpage)
1933 return self.url_result(rutv_url, 'RUTV')
1935 # Look for embedded TVC player
1936 tvc_url = TVCIE._extract_url(webpage)
1938 return self.url_result(tvc_url, 'TVC')
1940 # Look for embedded SportBox player
1941 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1943 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1945 # Look for embedded PornHub player
1946 pornhub_url = PornHubIE._extract_url(webpage)
1948 return self.url_result(pornhub_url, 'PornHub')
1950 # Look for embedded XHamster player
1951 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1953 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1955 # Look for embedded TNAFlixNetwork player
1956 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1958 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1960 # Look for embedded Tvigle player
1962 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1963 if mobj is not None:
1964 return self.url_result(mobj.group('url'), 'Tvigle')
1966 # Look for embedded TED player
1968 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1969 if mobj is not None:
1970 return self.url_result(mobj.group('url'), 'TED')
1972 # Look for embedded Ustream videos
1974 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1975 if mobj is not None:
1976 return self.url_result(mobj.group('url'), 'Ustream')
1978 # Look for embedded arte.tv player
1980 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1982 if mobj is not None:
1983 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1985 # Look for embedded francetv player
1987 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1989 if mobj is not None:
1990 return self.url_result(mobj.group('url'))
1992 # Look for embedded smotri.com player
1993 smotri_url = SmotriIE._extract_url(webpage)
1995 return self.url_result(smotri_url, 'Smotri')
1997 # Look for embedded Myvi.ru player
1998 myvi_url = MyviIE._extract_url(webpage)
2000 return self.url_result(myvi_url)
2002 # Look for embedded soundcloud player
2003 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2005 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2007 # Look for embedded mtvservices player
2008 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2010 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2012 # Look for embedded yahoo player
2014 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2016 if mobj is not None:
2017 return self.url_result(mobj.group('url'), 'Yahoo')
2019 # Look for embedded sbs.com.au player
2023 <meta\s+property="og:video"\s+content=|
2026 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2028 if mobj is not None:
2029 return self.url_result(mobj.group('url'), 'SBS')
2031 # Look for embedded Cinchcast player
2033 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2035 if mobj is not None:
2036 return self.url_result(mobj.group('url'), 'Cinchcast')
2039 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2043 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2045 if mobj is not None:
2046 return self.url_result(mobj.group('url'), 'MLB')
2049 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2051 if mobj is not None:
2052 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2055 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2057 if mobj is not None:
2058 return self.url_result(mobj.group('url'), 'Livestream')
2060 # Look for Zapiks embed
2062 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2063 if mobj is not None:
2064 return self.url_result(mobj.group('url'), 'Zapiks')
2066 # Look for Kaltura embeds
2067 kaltura_url = KalturaIE._extract_url(webpage)
2069 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2071 # Look for Eagle.Platform embeds
2072 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2073 if eagleplatform_url:
2074 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2076 # Look for ClipYou (uses Eagle.Platform) embeds
2078 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2079 if mobj is not None:
2080 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2082 # Look for Pladform embeds
2083 pladform_url = PladformIE._extract_url(webpage)
2085 return self.url_result(pladform_url)
2087 # Look for Videomore embeds
2088 videomore_url = VideomoreIE._extract_url(webpage)
2090 return self.url_result(videomore_url)
2092 # Look for Playwire embeds
2094 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2095 if mobj is not None:
2096 return self.url_result(mobj.group('url'))
2098 # Look for 5min embeds
2100 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2101 if mobj is not None:
2102 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2104 # Look for Crooks and Liars embeds
2106 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2107 if mobj is not None:
2108 return self.url_result(mobj.group('url'))
2110 # Look for NBC Sports VPlayer embeds
2111 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2113 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2115 # Look for NBC News embeds
2116 nbc_news_embed_url = re.search(
2117 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2118 if nbc_news_embed_url:
2119 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2121 # Look for Google Drive embeds
2122 google_drive_url = GoogleDriveIE._extract_url(webpage)
2123 if google_drive_url:
2124 return self.url_result(google_drive_url, 'GoogleDrive')
2126 # Look for UDN embeds
2128 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2129 if mobj is not None:
2130 return self.url_result(
2131 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2133 # Look for Senate ISVP iframe
2134 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2136 return self.url_result(senate_isvp_url, 'SenateISVP')
2138 # Look for Dailymotion Cloud videos
2139 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2141 return self.url_result(dmcloud_url, 'DailymotionCloud')
2143 # Look for OnionStudios embeds
2144 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2145 if onionstudios_url:
2146 return self.url_result(onionstudios_url)
2148 # Look for ViewLift embeds
2149 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2151 return self.url_result(viewlift_url)
2153 # Look for JWPlatform embeds
2154 jwplatform_url = JWPlatformIE._extract_url(webpage)
2156 return self.url_result(jwplatform_url, 'JWPlatform')
2158 # Look for ScreenwaveMedia embeds
2159 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2160 if mobj is not None:
2161 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2163 # Look for Digiteka embeds
2164 digiteka_url = DigitekaIE._extract_url(webpage)
2166 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2168 # Look for Arkena embeds
2169 arkena_url = ArkenaIE._extract_url(webpage)
2171 return self.url_result(arkena_url, ArkenaIE.ie_key())
2173 # Look for Limelight embeds
2174 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2178 'Channel': 'channel',
2179 'ChannelList': 'channel_list',
2181 return self.url_result('limelight:%s:%s' % (
2182 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2184 # Look for AdobeTVVideo embeds
2186 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2188 if mobj is not None:
2189 return self.url_result(
2190 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2193 # Look for Vine embeds
2195 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2197 if mobj is not None:
2198 return self.url_result(
2199 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2201 # Look for Instagram embeds
2202 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2203 if instagram_embed_url is not None:
2204 return self.url_result(
2205 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2207 # Look for LiveLeak embeds
2208 liveleak_url = LiveLeakIE._extract_url(webpage)
2210 return self.url_result(liveleak_url, 'LiveLeak')
2212 # Look for 3Q SDN embeds
2213 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2216 '_type': 'url_transparent',
2217 'ie_key': ThreeQSDNIE.ie_key(),
2218 'url': self._proto_relative_url(threeqsdn_url),
2219 'title': video_title,
2220 'description': video_description,
2221 'thumbnail': video_thumbnail,
2222 'uploader': video_uploader,
2225 # Looking for http://schema.org/VideoObject
2226 json_ld = self._search_json_ld(
2227 webpage, video_id, default=None, expected_type='VideoObject')
2228 if json_ld and json_ld.get('url'):
2230 'title': video_title or info_dict['title'],
2231 'description': video_description,
2232 'thumbnail': video_thumbnail,
2233 'age_limit': age_limit
2235 info_dict.update(json_ld)
2238 def check_video(vurl):
2239 if YoutubeIE.suitable(vurl):
2241 vpath = compat_urlparse.urlparse(vurl).path
2242 vext = determine_ext(vpath)
2243 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2245 def filter_video(urls):
2246 return list(filter(check_video, urls))
2248 # Start with something easy: JW Player in SWFObject
2249 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2251 # Look for gorilla-vid style embedding
2252 found = filter_video(re.findall(r'''(?sx)
2256 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2259 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2261 # Broaden the search a little bit
2262 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2264 # Broaden the findall a little bit: JWPlayer JS loader
2265 found = filter_video(re.findall(
2266 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2269 found = filter_video(re.findall(r'''(?xs)
2270 flowplayer\("[^"]+",\s*
2272 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2273 ["']?url["']?\s*:\s*["']([^"']+)["']
2278 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2280 # Try to find twitter cards info
2281 # twitter:player:stream should be checked before twitter:player since
2282 # it is expected to contain a raw stream (see
2283 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2284 found = filter_video(re.findall(
2285 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2287 # We look for Open Graph info:
2288 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2289 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2290 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2291 if m_video_type is not None:
2292 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2295 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2297 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2299 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2300 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2303 # Look also in Refresh HTTP header
2304 refresh_header = head_response.headers.get('Refresh')
2306 # In python 2 response HTTP headers are bytestrings
2307 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2308 refresh_header = refresh_header.decode('iso-8859-1')
2309 found = re.search(REDIRECT_REGEX, refresh_header)
2311 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2312 self.report_following_redirect(new_url)
2319 # twitter:player is a https URL to iframe player that may or may not
2320 # be supported by youtube-dl thus this is checked the very last (see
2321 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2322 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2324 return self.url_result(embed_url)
2327 raise UnsupportedError(url)
2330 for video_url in orderedSet(found):
2331 video_url = unescapeHTML(video_url)
2332 video_url = video_url.replace('\\/', '/')
2333 video_url = compat_urlparse.urljoin(url, video_url)
2334 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2336 # Sometimes, jwplayer extraction will result in a YouTube URL
2337 if YoutubeIE.suitable(video_url):
2338 entries.append(self.url_result(video_url, 'Youtube'))
2341 # here's a fun little line of code for you:
2342 video_id = os.path.splitext(video_id)[0]
2346 'uploader': video_uploader,
2347 'title': video_title,
2348 'age_limit': age_limit,
2351 ext = determine_ext(video_url)
2353 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2355 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2357 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2359 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2361 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2363 entry_info_dict['url'] = video_url
2365 if entry_info_dict.get('formats'):
2366 self._sort_formats(entry_info_dict['formats'])
2368 entries.append(entry_info_dict)
2370 if len(entries) == 1:
2373 for num, e in enumerate(entries, start=1):
2374 # 'url' results don't have a title
2375 if e.get('title') is not None:
2376 e['title'] = '%s (%d)' % (e['title'], num)
2378 '_type': 'playlist',