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,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .drtuber import DrTuberIE
51 from .redtube import RedTubeIE
52 from .vimeo import VimeoIE
53 from .dailymotion import (
57 from .onionstudios import OnionStudiosIE
58 from .viewlift import ViewLiftEmbedIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .webcaster import WebcasterFeedIE
63 from .googledrive import GoogleDriveIE
64 from .jwplatform import JWPlatformIE
65 from .digiteka import DigitekaIE
66 from .arkena import ArkenaIE
67 from .instagram import InstagramIE
68 from .liveleak import LiveLeakIE
69 from .threeqsdn import ThreeQSDNIE
70 from .theplatform import ThePlatformIE
71 from .vessel import VesselIE
72 from .kaltura import KalturaIE
73 from .eagleplatform import EaglePlatformIE
74 from .facebook import FacebookIE
75 from .soundcloud import SoundcloudIE
76 from .tunein import TuneInBaseIE
77 from .vbox7 import Vbox7IE
78 from .dbtv import DBTVIE
79 from .piksel import PikselIE
80 from .videa import VideaIE
83 class GenericIE(InfoExtractor):
84 IE_DESC = 'Generic downloader that works on some sites'
88 # Direct link to a video
90 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
91 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
96 'upload_date': '20100513',
99 # Direct link to media delivered compressed (until Accept-Encoding is *)
101 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
102 'md5': '128c42e68b13950268b648275386fc74',
104 'id': 'FictionJunction-Parallel_Hearts',
106 'title': 'FictionJunction-Parallel_Hearts',
107 'upload_date': '20140522',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
112 'skip': 'URL invalid',
114 # Direct download with broken HEAD
116 'url': 'http://ai-radio.org:8000/radio.opus',
123 'skip_download': True, # infinite live stream
125 'expected_warnings': [
126 r'501.*Not Implemented',
130 # Direct link with incorrect MIME type
132 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
133 'md5': '4ccbebe5f36706d85221f204d7eb5913',
135 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
136 'id': '5_Lennart_Poettering_-_Systemd',
138 'title': '5_Lennart_Poettering_-_Systemd',
139 'upload_date': '20141120',
141 'expected_warnings': [
142 'URL could be a direct video link, returning it as such.'
147 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
149 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
150 'title': 'Zero Punctuation',
151 'description': 're:.*groundbreaking video review series.*'
153 'playlist_mincount': 11,
155 # RSS feed with enclosure
157 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
159 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
161 'upload_date': '20150228',
162 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
165 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
167 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
171 'title': 'Automatics, robotics and biocybernetics',
172 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
173 'upload_date': '20130627',
174 'formats': 'mincount:16',
175 'subtitles': 'mincount:1',
178 'force_generic_extractor': True,
179 'skip_download': True,
182 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
184 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
189 'formats': 'mincount:1',
192 'skip_download': True,
195 # SMIL from https://www.restudy.dk/video/play/id/1637
197 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
201 'title': 'video_1637',
202 'formats': 'mincount:3',
205 'skip_download': True,
208 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
210 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
212 'id': 'smil-service',
214 'title': 'smil-service',
215 'formats': 'mincount:1',
218 'skip_download': True,
221 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
223 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
227 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
228 'formats': 'mincount:3',
231 'skip_download': True,
234 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
236 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
238 'id': 'mZlp2ctYIUEB',
240 'title': 'Tikibad ontruimd wegens brand',
241 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
242 'thumbnail': r're:^https?://.*\.jpg$',
246 'skip_download': True,
249 # MPD from http://dash-mse-test.appspot.com/media.html
251 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
252 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
254 'id': 'car-20120827-manifest',
256 'title': 'car-20120827-manifest',
257 'formats': 'mincount:9',
258 'upload_date': '20130904',
261 'format': 'bestvideo',
264 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
266 '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',
271 'formats': 'mincount:8',
275 'skip_download': True,
277 'skip': 'video gone',
279 # m3u8 served with Content-Type: text/plain
281 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
286 'upload_date': '20140720',
287 'formats': 'mincount:11',
291 'skip_download': True,
293 'skip': 'video gone',
297 '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',
301 'upload_date': '20130224',
302 'uploader_id': 'TheVerge',
303 'description': r're:^Chris Ziegler takes a look at the\.*',
304 'uploader': 'The Verge',
305 'title': 'First Firefox OS phones side-by-side',
308 'skip_download': False,
312 # redirect in Refresh HTTP header
313 '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',
317 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
318 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
319 'upload_date': '20150917',
320 'uploader_id': 'brtvofficial',
321 'uploader': 'Boiler Room',
324 'skip_download': False,
328 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
329 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
331 'id': '13601338388002',
333 'uploader': 'www.hodiho.fr',
334 'title': 'R\u00e9gis plante sa Jeep',
337 # bandcamp page with custom domain
339 'add_ie': ['Bandcamp'],
340 'url': 'http://bronyrock.com/track/the-pony-mash',
344 'title': 'The Pony Mash',
345 'uploader': 'M_Pallante',
347 'skip': 'There is a limit of 200 free downloads / month for the test song',
350 # embedded brightcove video
351 # it also tests brightcove videos that need to set the 'Referer'
352 # in the http requests
353 'add_ie': ['BrightcoveLegacy'],
354 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
356 'id': '2765128793001',
358 'title': 'Le cours de bourse : l’analyse technique',
359 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
360 'uploader': 'BFM BUSINESS',
363 'skip_download': True,
367 # embedded with itemprop embedURL and video id spelled as `idVideo`
368 'add_id': ['BrightcoveLegacy'],
369 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
371 'id': '5255628253001',
373 'title': 'md5:37c519b1128915607601e75a87995fc0',
374 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
375 'uploader': 'BFM BUSINESS',
376 'uploader_id': '876450612001',
377 'timestamp': 1482255315,
378 'upload_date': '20161220',
381 'skip_download': True,
385 # https://github.com/rg3/youtube-dl/issues/2253
386 'url': 'http://bcove.me/i6nfkrc3',
387 'md5': '0ba9446db037002366bab3b3eb30c88c',
389 'id': '3101154703001',
391 'title': 'Still no power',
392 'uploader': 'thestar.com',
393 '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.',
395 'add_ie': ['BrightcoveLegacy'],
396 'skip': 'video gone',
399 'url': 'http://www.championat.com/video/football/v/87/87499.html',
400 'md5': 'fb973ecf6e4a78a67453647444222983',
402 'id': '3414141473001',
404 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
405 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
406 'uploader': 'Championat',
410 # https://github.com/rg3/youtube-dl/issues/3541
411 'add_ie': ['BrightcoveLegacy'],
412 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
414 'id': '3866516442001',
416 'title': 'Leer mij vrouwen kennen: Aflevering 1',
417 'description': 'Leer mij vrouwen kennen: Aflevering 1',
418 'uploader': 'SBS Broadcasting',
420 'skip': 'Restricted to Netherlands',
422 'skip_download': True, # m3u8 download
427 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
428 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
430 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
432 'title': '2cc213299525360.mov', # that's what we get
435 'add_ie': ['Ooyala'],
438 # ooyala video embedded with http://player.ooyala.com/iframe.js
439 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
441 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
443 'title': '"Steve Jobs: Man in the Machine" trailer',
444 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
448 'skip_download': True,
450 'skip': 'movie expired',
454 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
458 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
459 'upload_date': '20140225',
460 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
461 'uploader': 'Tested',
462 'uploader_id': 'testedcom',
464 # No need to test YoutubeIE here
466 'skip_download': True,
471 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
475 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
476 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
478 # HEAD requests lead to endless 301, while GET is OK
479 'expected_warnings': ['301'],
483 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
487 'title': 'Охотское море стало целиком российским',
488 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
492 'skip_download': True,
497 '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/',
501 'title': 'Дошкольное воспитание',
506 'url': 'http://www.vestifinance.ru/articles/25753',
509 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
514 'title': 'Госзаказ. День 3',
520 'title': 'Госзаказ. День 2',
526 'title': 'Госзаказ. День 1',
532 'skip_download': True,
537 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
539 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
541 'title': 'Ужастики, русский трейлер (2015)',
542 'thumbnail': r're:^https?://.*\.jpg$',
548 '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',
551 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
553 'playlist_mincount': 7,
554 # This forum does not allow <iframe> syntaxes anymore
555 # Now HTML tags are displayed as-is
556 'skip': 'No videos on this page',
560 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
561 'md5': '65fdff94098e4a607385a60c5177c638',
565 'title': 'Hidden miracles of the natural world',
566 'uploader': 'Louie Schwartzberg',
567 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
570 # Embedded Ustream video
572 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
573 'md5': '27b99cdb639c9b12a79bca876a073417',
577 'uploader': 'AU SPA: The NSA and Privacy',
578 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
581 # nowvideo embed hidden behind percent encoding
583 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
584 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
586 'id': '06e53103ca9aa',
588 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
589 'description': 'No description',
594 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
595 'md5': '7653032cbb25bf6c80d80f217055fa43',
597 'id': '048195-004_PLUS7-F',
600 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
601 'upload_date': '20140320',
604 'skip_download': 'Requires rtmpdump'
606 'skip': 'video gone',
610 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
614 'title': 'Alcaline, le concert avec Calogero',
615 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
616 'upload_date': '20150226',
617 'timestamp': 1424989860,
622 'skip_download': True,
624 'expected_warnings': [
630 'url': 'http://www.wired.com/2014/04/honda-asimo/',
631 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
633 'id': '53501be369702d3275860000',
635 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
640 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
641 'md5': '441aeeb82eb72c422c7f14ec533999cd',
643 'id': 'k2mm4bCdJ6CQ2i7c8o2',
645 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
646 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
648 'uploader_id': 'xgditw',
649 'upload_date': '20140425',
650 'timestamp': 1398441542,
652 'add_ie': ['Dailymotion'],
656 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
660 'title': 'The NBL Auction 2014',
661 'uploader': 'BADMINTON England',
662 'uploader_id': 'BADMINTONEvents',
663 'upload_date': '20140603',
664 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
666 'add_ie': ['Youtube'],
668 'skip_download': True,
673 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
674 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
676 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
678 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
679 'description': 'Two valets share their love for movie star Liam Neesons.',
680 'timestamp': 1349922600,
681 'upload_date': '20121011',
684 # YouTube embed via <data-embed-url="">
686 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
690 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
691 'uploader': 'Gameloft',
692 'uploader_id': 'gameloft',
693 'upload_date': '20140828',
694 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
697 'skip_download': True,
702 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
704 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
706 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
707 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
712 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
714 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
715 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
721 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
726 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
727 'md5': '9d65602bf31c6e20014319c7d07fba27',
729 'id': '5123ea6d5e5a7',
732 'uploader': 'www.handjobhub.com',
733 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
736 # Multiple brightcove videos
737 # https://github.com/rg3/youtube-dl/issues/2283
739 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
741 'id': 'always-never',
742 'title': 'Always / Never - The New Yorker',
746 'extract_flat': False,
747 'skip_download': True,
752 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
753 'md5': '96f09a37e44da40dd083e12d9a683327',
757 'title': 'Ump changes call to ball',
758 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
760 'timestamp': 1401537900,
761 'upload_date': '20140531',
762 'thumbnail': r're:^https?://.*\.jpg$',
767 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
768 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
772 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
773 'description': 'a Paywall Videos video from Remilon',
775 'uploader': 'study.com',
776 'timestamp': 1459678540,
777 'upload_date': '20160403',
778 'filesize': 24687186,
782 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
783 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
787 'title': 'Conversation about Hexagonal Rails Part 1',
788 'description': 'a Martin Fowler video from ThoughtWorks',
790 'uploader': 'thoughtworks.wistia.com',
791 'timestamp': 1401832161,
792 'upload_date': '20140603',
795 # Wistia standard embed (async)
797 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
801 'title': 'Drip Brennan Dunn Workshop',
802 'description': 'a JV Webinars video from getdrip-1',
804 'timestamp': 1463607249,
805 'upload_date': '20160518',
808 'skip_download': True,
813 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
817 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
818 'uploader': 'Sophos Security',
819 'title': 'Chet Chat 171 - Oct 29, 2014',
820 'upload_date': '20141029',
823 # Soundcloud multiple embeds
825 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
828 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
830 'playlist_mincount': 7,
832 # TuneIn station embed
834 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
839 'location': 'Paris, France',
844 'skip_download': True,
849 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
853 'upload_date': '20141112',
854 'title': 'Rosetta #CometLanding webcast HL 10',
857 # Another Livestream embed, without 'new.' in URL
859 'url': 'https://www.freespeech.org/',
863 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
867 'skip_download': True,
872 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
875 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
877 'playlist_mincount': 2,
881 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
885 'upload_date': '20141126',
886 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
891 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
893 'id': '730m_DandD_1901_512k',
895 'uploader': 'www.abc.net.au',
896 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
899 # embedded viddler video
901 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
905 'uploader': 'deadspin',
906 'title': 'WALL-TO-GORTAT',
907 'timestamp': 1422285291,
908 'upload_date': '20150126',
910 'add_ie': ['Viddler'],
914 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
918 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
919 'description': 'md5:601cb790edd05908957dae8aaa866465',
920 'upload_date': '20150220',
922 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
926 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
930 'upload_date': '20150212',
931 'uploader': 'The National Archives UK',
932 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
933 'uploader_id': 'NationalArchives08',
934 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
939 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
940 'playlist_mincount': 5,
942 'id': 'aanslagen-kopenhagen',
943 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
948 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
952 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
955 # Kaltura embed (different embed code)
957 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
961 'upload_date': '20150127',
962 'uploader_id': 'PremierMedia',
964 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
967 # Kaltura embed protected with referrer
969 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
973 'title': 'Violetta - Achter De Schermen - Ruggero',
974 'description': 'Achter de schermen met Ruggero',
975 'timestamp': 1435133761,
976 'upload_date': '20150624',
977 'uploader_id': 'echojecka',
980 # Kaltura embed with single quotes
982 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
987 'timestamp': 1355743100,
988 'upload_date': '20121217',
989 'uploader_id': 'batchUser',
991 'add_ie': ['Kaltura'],
994 # Kaltura embedded via quoted entry_id
995 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
999 'title': '06_matthew_brender_raj_dutt',
1000 'timestamp': 1466638791,
1001 'upload_date': '20160622',
1003 'add_ie': ['Kaltura'],
1004 'expected_warnings': [
1005 'Could not send HEAD request'
1008 'skip_download': True,
1012 # Kaltura embedded, some fileExt broken (#11480)
1013 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1017 'title': 'Our "Standard Models" of particle physics and cosmology',
1018 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1019 'timestamp': 1321158993,
1020 'upload_date': '20111113',
1021 'uploader_id': 'kps1',
1023 'add_ie': ['Kaltura'],
1025 # Eagle.Platform embed (generic URL)
1027 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1028 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1032 'title': 'Навальный вышел на свободу',
1033 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1034 'thumbnail': r're:^https?://.*\.jpg$',
1040 # ClipYou (Eagle.Platform) embed (custom URL)
1042 'url': 'http://muz-tv.ru/play/7129/',
1043 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1047 'title': "'O Sole Mio",
1048 'thumbnail': r're:^https?://.*\.jpg$',
1055 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1059 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1060 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1061 'thumbnail': r're:^https?://.*\.jpg$',
1068 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1072 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1073 'thumbnail': r're:^https?://.*\.png$',
1079 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1080 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1084 'title': 'Facebook Creates "On This Day" | Crunch Report',
1089 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1093 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1098 # Crooks and Liars embed
1100 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1104 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1105 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1106 'timestamp': 1428207000,
1107 'upload_date': '20150405',
1108 'uploader': 'Heather',
1111 # Crooks and Liars external embed
1113 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1115 'id': 'MTE3MjUtMzQ2MzA',
1117 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1118 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1119 'timestamp': 1265032391,
1120 'upload_date': '20100201',
1121 'uploader': 'Heather',
1124 # NBC Sports vplayer embed
1126 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1128 'id': 'ln7x1qSThw4k',
1130 'title': "PFT Live: New leader in the 'new-look' defense",
1131 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1132 'uploader': 'NBCU-SPORTS',
1133 'upload_date': '20140107',
1134 'timestamp': 1389118457,
1139 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1140 'md5': '1aa589c675898ae6d37a17913cf68d66',
1142 'id': '701714499682',
1144 'title': 'PREVIEW: On Assignment: David Letterman',
1145 '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.',
1150 'url': 'https://video.udn.com/news/300346',
1151 'md5': 'fd2060e988c326991037b9aff9df21a6',
1155 'title': '中一中男師變性 全校師生力挺',
1156 'thumbnail': r're:^https?://.*\.jpg$',
1160 'skip_download': True,
1165 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1167 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1169 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1170 'title': 'This is what separates the Excel masters from the wannabes',
1171 'duration': 191.933,
1175 'skip_download': True,
1178 # Brightcove URL in single quotes
1180 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1181 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1183 'id': '4255764656001',
1185 'title': 'SN Presents: Russell Martin, World Citizen',
1186 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1187 'uploader': 'Rogers Sportsnet',
1188 'uploader_id': '1704050871',
1189 'upload_date': '20150525',
1190 'timestamp': 1432570283,
1193 # Dailymotion Cloud video
1195 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1196 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1200 'title': 'Sauvons les abeilles ! - Le débat',
1201 'description': 'md5:d9082128b1c5277987825d684939ca26',
1202 'thumbnail': r're:^https?://.*\.jpe?g$',
1203 'timestamp': 1434970506,
1204 'upload_date': '20150622',
1205 'uploader': 'Public Sénat',
1206 'uploader_id': 'xa9gza',
1209 # OnionStudios embed
1211 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1215 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1216 'thumbnail': r're:^https?://.*\.jpe?g$',
1217 'uploader': 'ClickHole',
1218 'uploader_id': 'clickhole',
1223 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1225 'id': '74849a00-85a9-11e1-9660-123139220831',
1227 'title': '#whilewewatch',
1230 # AdobeTVVideo embed
1232 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1233 'md5': '43662b577c018ad707a63766462b1e87',
1237 'title': 'New experience with Acrobat DC',
1238 'description': 'New experience with Acrobat DC',
1239 'duration': 248.667,
1242 # BrightcoveInPageEmbed embed
1244 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1246 'id': '4238694884001',
1248 'title': 'Tabletop: Dread, Last Thoughts',
1249 'description': 'Tabletop: Dread, Last Thoughts',
1253 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1254 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1256 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1258 'id': '4785848093001',
1260 'title': 'The Cardinal Pell Interview',
1261 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1262 'uploader': 'GlobeCast Australia - GlobeStream',
1263 'uploader_id': '2733773828001',
1264 'upload_date': '20160304',
1265 'timestamp': 1457083087,
1269 'skip_download': True,
1272 # Another form of arte.tv embed
1274 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1275 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1277 'id': '030273-562_PLUS7-F',
1279 'title': 'ARTE Reportage - Nulle part, en France',
1280 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1281 'upload_date': '20160409',
1286 'url': 'http://www.wykop.pl/link/3088787/',
1287 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1289 'id': '874_1459135191',
1291 'title': 'Man shows poor quality of new apartment building',
1292 'description': 'The wall is like a sand pile.',
1293 'uploader': 'Lake8737',
1296 # Duplicated embedded video URLs
1298 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1300 'id': '149298443_480_16c25b74_2',
1302 'title': 'vs. Blue Orange Spring Game',
1303 'uploader': 'www.hudl.com',
1306 # twitter:player:stream embed
1308 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1312 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1313 'uploader': 'www.rtl.be',
1317 'skip_download': True,
1320 # twitter:player embed
1322 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1323 'md5': 'a3e0df96369831de324f0778e126653c',
1325 'id': '4909620399001',
1327 'title': 'What Do Black Holes Sound Like?',
1328 'description': 'what do black holes sound like',
1329 'upload_date': '20160524',
1330 'uploader_id': '29913724001',
1331 'timestamp': 1464107587,
1332 'uploader': 'TheAtlantic',
1334 'add_ie': ['BrightcoveLegacy'],
1336 # Facebook <iframe> embed
1338 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1339 'md5': 'fbcde74f534176ecb015849146dd3aee',
1341 'id': '599637780109885',
1343 'title': 'Facebook video #599637780109885',
1346 # Facebook API embed
1348 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1349 'md5': 'a47372ee61b39a7b90287094d447d94e',
1351 'id': '10153467542406923',
1353 'title': 'Facebook video #10153467542406923',
1356 # Wordpress "YouTube Video Importer" plugin
1358 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1359 'md5': 'd16797741b560b485194eddda8121b48',
1361 'id': 'HNTXWDXV9Is',
1363 'title': 'Blue Devils Drumline Stanford lot 2016',
1364 'upload_date': '20160627',
1365 'uploader_id': 'GENOCIDE8GENERAL10',
1366 'uploader': 'cylus cyrus',
1370 # video stored on custom kaltura server
1371 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1372 'md5': '537617d06e64dfed891fa1593c4b30cc',
1376 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1377 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1378 'uploader_id': 'videos.expansion@el-mundo.net',
1379 'upload_date': '20150429',
1380 'timestamp': 1430303472,
1382 'add_ie': ['Kaltura'],
1385 # Non-standard Vimeo embed
1386 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1387 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1391 'title': 'Understanding the web - Teaser',
1392 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1393 'upload_date': '20151214',
1394 'uploader': 'OpenClassrooms',
1395 'uploader_id': 'openclassrooms',
1397 'add_ie': ['Vimeo'],
1400 # generic vimeo embed that requires original URL passed as Referer
1401 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1402 'only_matching': True,
1405 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1406 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1408 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1410 'title': 'Big Buck Bunny',
1411 'description': 'Royalty free test video',
1412 'timestamp': 1432816365,
1413 'upload_date': '20150528',
1417 'skip_download': True,
1419 'add_ie': [ArkenaIE.ie_key()],
1422 '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/',
1426 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1429 'skip_download': True,
1431 'add_ie': [Vbox7IE.ie_key()],
1435 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1438 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1440 'playlist_mincount': 3,
1444 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1446 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1447 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1449 'playlist_mincount': 2,
1452 # # TODO: find another test
1453 # # http://schema.org/VideoObject
1454 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1455 # 'md5': '888dcf08b7ea671381f00fab74692755',
1457 # 'id': 'nyvTSJMKId',
1459 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1460 # 'description': '#love for cats.',
1461 # 'timestamp': 1461244995,
1462 # 'upload_date': '20160421',
1465 # 'force_generic_extractor': True,
1470 def report_following_redirect(self, new_url):
1471 """Report information extraction."""
1472 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1474 def _extract_rss(self, url, video_id, doc):
1475 playlist_title = doc.find('./channel/title').text
1476 playlist_desc_el = doc.find('./channel/description')
1477 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1480 for it in doc.findall('./channel/item'):
1481 next_url = xpath_text(it, 'link', fatal=False)
1483 enclosure_nodes = it.findall('./enclosure')
1484 for e in enclosure_nodes:
1485 next_url = e.attrib.get('url')
1495 'title': it.find('title').text,
1499 '_type': 'playlist',
1501 'title': playlist_title,
1502 'description': playlist_desc,
1506 def _extract_camtasia(self, url, video_id, webpage):
1507 """ Returns None if no camtasia video can be found. """
1509 camtasia_cfg = self._search_regex(
1510 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1511 webpage, 'camtasia configuration file', default=None)
1512 if camtasia_cfg is None:
1515 title = self._html_search_meta('DC.title', webpage, fatal=True)
1517 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1518 camtasia_cfg = self._download_xml(
1519 camtasia_url, video_id,
1520 note='Downloading camtasia configuration',
1521 errnote='Failed to download camtasia configuration')
1522 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1525 for n in fileset_node.getchildren():
1526 url_n = n.find('./uri')
1531 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1532 'title': '%s - %s' % (title, n.tag),
1533 'url': compat_urlparse.urljoin(url, url_n.text),
1534 'duration': float_or_none(n.find('./duration').text),
1538 '_type': 'playlist',
1543 def _real_extract(self, url):
1544 if url.startswith('//'):
1547 'url': self.http_scheme() + url,
1550 parsed_url = compat_urlparse.urlparse(url)
1551 if not parsed_url.scheme:
1552 default_search = self._downloader.params.get('default_search')
1553 if default_search is None:
1554 default_search = 'fixup_error'
1556 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1558 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1559 return self.url_result('http://' + url)
1560 elif default_search != 'fixup_error':
1561 if default_search == 'auto_warning':
1562 if re.match(r'^(?:url|URL)$', url):
1563 raise ExtractorError(
1564 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1567 self._downloader.report_warning(
1568 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1569 return self.url_result('ytsearch:' + url)
1571 if default_search in ('error', 'fixup_error'):
1572 raise ExtractorError(
1573 '%r is not a valid URL. '
1574 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1575 % (url, url), expected=True)
1577 if ':' not in default_search:
1578 default_search += ':'
1579 return self.url_result(default_search + url)
1581 url, smuggled_data = unsmuggle_url(url)
1582 force_videoid = None
1583 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1584 if smuggled_data and 'force_videoid' in smuggled_data:
1585 force_videoid = smuggled_data['force_videoid']
1586 video_id = force_videoid
1588 video_id = self._generic_id(url)
1590 self.to_screen('%s: Requesting header' % video_id)
1592 head_req = HEADRequest(url)
1593 head_response = self._request_webpage(
1595 note=False, errnote='Could not send HEAD request to %s' % url,
1598 if head_response is not False:
1599 # Check for redirect
1600 new_url = head_response.geturl()
1602 self.report_following_redirect(new_url)
1604 new_url = smuggle_url(
1605 new_url, {'force_videoid': force_videoid})
1606 return self.url_result(new_url)
1608 full_response = None
1609 if head_response is False:
1610 request = sanitized_Request(url)
1611 request.add_header('Accept-Encoding', '*')
1612 full_response = self._request_webpage(request, video_id)
1613 head_response = full_response
1617 'title': self._generic_title(url),
1618 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1621 # Check for direct link to a video
1622 content_type = head_response.headers.get('Content-Type', '').lower()
1623 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1625 format_id = m.group('format_id')
1626 if format_id.endswith('mpegurl'):
1627 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1628 elif format_id == 'f4m':
1629 formats = self._extract_f4m_formats(url, video_id)
1632 'format_id': m.group('format_id'),
1634 'vcodec': 'none' if m.group('type') == 'audio' else None
1636 info_dict['direct'] = True
1637 self._sort_formats(formats)
1638 info_dict['formats'] = formats
1641 if not self._downloader.params.get('test', False) and not is_intentional:
1642 force = self._downloader.params.get('force_generic_extractor', False)
1643 self._downloader.report_warning(
1644 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1646 if not full_response:
1647 request = sanitized_Request(url)
1648 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1649 # making it impossible to download only chunk of the file (yet we need only 512kB to
1650 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1651 # that will always result in downloading the whole file that is not desirable.
1652 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1653 # to accept raw bytes and being able to download only a chunk.
1654 # It may probably better to solve this by checking Content-Type for application/octet-stream
1655 # after HEAD request finishes, but not sure if we can rely on this.
1656 request.add_header('Accept-Encoding', '*')
1657 full_response = self._request_webpage(request, video_id)
1659 first_bytes = full_response.read(512)
1661 # Is it an M3U playlist?
1662 if first_bytes.startswith(b'#EXTM3U'):
1663 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1664 self._sort_formats(info_dict['formats'])
1667 # Maybe it's a direct link to a video?
1668 # Be careful not to download the whole thing!
1669 if not is_html(first_bytes):
1670 self._downloader.report_warning(
1671 'URL could be a direct video link, returning it as such.')
1678 webpage = self._webpage_read_content(
1679 full_response, url, video_id, prefix=first_bytes)
1681 self.report_extraction(video_id)
1683 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1685 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1686 if doc.tag == 'rss':
1687 return self._extract_rss(url, video_id, doc)
1688 elif doc.tag == 'SmoothStreamingMedia':
1689 info_dict['formats'] = self._parse_ism_formats(doc, url)
1690 self._sort_formats(info_dict['formats'])
1692 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1693 smil = self._parse_smil(doc, url, video_id)
1694 self._sort_formats(smil['formats'])
1696 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1697 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1698 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1699 info_dict['formats'] = self._parse_mpd_formats(
1701 mpd_base_url=full_response.geturl().rpartition('/')[0],
1703 self._sort_formats(info_dict['formats'])
1705 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1706 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1707 self._sort_formats(info_dict['formats'])
1709 except compat_xml_parse_error:
1712 # Is it a Camtasia project?
1713 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1714 if camtasia_res is not None:
1717 # Sometimes embedded video player is hidden behind percent encoding
1718 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1719 # Unescaping the whole page allows to handle those cases in a generic way
1720 webpage = compat_urllib_parse_unquote(webpage)
1722 # it's tempting to parse this further, but you would
1723 # have to take into account all the variations like
1724 # Video Title - Site Name
1725 # Site Name | Video Title
1726 # Video Title - Tagline | Site Name
1727 # and so on and so forth; it's just not practical
1728 video_title = self._og_search_title(
1729 webpage, default=None) or self._html_search_regex(
1730 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1733 # Try to detect age limit automatically
1734 age_limit = self._rta_search(webpage)
1735 # And then there are the jokers who advertise that they use RTA,
1736 # but actually don't.
1737 AGE_LIMIT_MARKERS = [
1738 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1740 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1743 # video uploader is domain name
1744 video_uploader = self._search_regex(
1745 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1747 video_description = self._og_search_description(webpage, default=None)
1748 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1751 def _playlist_from_matches(matches, getter=None, ie=None):
1753 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1755 return self.playlist_result(
1756 urlrs, playlist_id=video_id, playlist_title=video_title)
1758 # Look for Brightcove Legacy Studio embeds
1759 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1761 self.to_screen('Brightcove video detected.')
1764 'url': smuggle_url(bc_url, {'Referer': url}),
1765 'ie_key': 'BrightcoveLegacy'
1766 } for bc_url in bc_urls]
1769 '_type': 'playlist',
1770 'title': video_title,
1775 # Look for Brightcove New Studio embeds
1776 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1778 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1780 # Look for ThePlatform embeds
1781 tp_urls = ThePlatformIE._extract_urls(webpage)
1783 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1785 # Look for Vessel embeds
1786 vessel_urls = VesselIE._extract_urls(webpage)
1788 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1790 # Look for embedded rtl.nl player
1791 matches = re.findall(
1792 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1795 return _playlist_from_matches(matches, ie='RtlNl')
1797 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1799 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1801 vid_me_embed_url = self._search_regex(
1802 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1803 webpage, 'vid.me embed', default=None)
1804 if vid_me_embed_url is not None:
1805 return self.url_result(vid_me_embed_url, 'Vidme')
1807 # Look for embedded YouTube player
1808 matches = re.findall(r'''(?x)
1817 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1821 return _playlist_from_matches(
1822 matches, lambda m: unescapeHTML(m[1]))
1824 # Look for lazyYT YouTube embed
1825 matches = re.findall(
1826 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1828 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1830 # Look for Wordpress "YouTube Video Importer" plugin
1831 matches = re.findall(r'''(?x)<div[^>]+
1832 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1833 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1835 return _playlist_from_matches(matches, lambda m: m[-1])
1837 matches = DailymotionIE._extract_urls(webpage)
1839 return _playlist_from_matches(matches)
1841 # Look for embedded Dailymotion playlist player (#3822)
1843 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1845 playlists = re.findall(
1846 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1848 return _playlist_from_matches(
1849 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1851 # Look for embedded Wistia player
1853 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1855 embed_url = self._proto_relative_url(
1856 unescapeHTML(match.group('url')))
1858 '_type': 'url_transparent',
1861 'uploader': video_uploader,
1864 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1867 '_type': 'url_transparent',
1868 'url': 'wistia:%s' % match.group('id'),
1870 'uploader': video_uploader,
1875 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1876 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1879 return self.url_result(self._proto_relative_url(
1880 'wistia:%s' % match.group('id')), 'Wistia')
1882 # Look for SVT player
1883 svt_url = SVTIE._extract_url(webpage)
1885 return self.url_result(svt_url, 'SVT')
1887 # Look for embedded condenast player
1888 matches = re.findall(
1889 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1893 '_type': 'playlist',
1896 'ie_key': 'CondeNast',
1898 } for ma in matches],
1899 'title': video_title,
1903 # Look for Bandcamp pages with custom domain
1904 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1905 if mobj is not None:
1906 burl = unescapeHTML(mobj.group(1))
1907 # Don't set the extractor because it can be a track url or an album
1908 return self.url_result(burl)
1910 # Look for embedded Vevo player
1912 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1913 if mobj is not None:
1914 return self.url_result(mobj.group('url'))
1916 # Look for embedded Viddler player
1918 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1920 if mobj is not None:
1921 return self.url_result(mobj.group('url'))
1923 # Look for NYTimes player
1925 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1927 if mobj is not None:
1928 return self.url_result(mobj.group('url'))
1930 # Look for Libsyn player
1932 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1933 if mobj is not None:
1934 return self.url_result(mobj.group('url'))
1936 # Look for Ooyala videos
1937 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1938 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1939 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1940 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1941 if mobj is not None:
1942 embed_token = self._search_regex(
1943 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1944 webpage, 'ooyala embed token', default=None)
1945 return OoyalaIE._build_url_result(smuggle_url(
1948 'embed_token': embed_token,
1951 # Look for multiple Ooyala embeds on SBN network websites
1952 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1953 if mobj is not None:
1954 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1956 return _playlist_from_matches(
1957 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1959 # Look for Aparat videos
1960 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1961 if mobj is not None:
1962 return self.url_result(mobj.group(1), 'Aparat')
1964 # Look for MPORA videos
1965 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1966 if mobj is not None:
1967 return self.url_result(mobj.group(1), 'Mpora')
1969 # Look for embedded NovaMov-based player
1971 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1972 (?P<url>http://(?:(?:embed|www)\.)?
1974 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1975 videoweed\.(?:es|com)|
1976 movshare\.(?:net|sx|ag)|
1977 divxstage\.(?:eu|net|ch|co|at|ag))
1978 /embed\.php.+?)\1''', webpage)
1979 if mobj is not None:
1980 return self.url_result(mobj.group('url'))
1982 # Look for embedded Facebook player
1983 facebook_url = FacebookIE._extract_url(webpage)
1984 if facebook_url is not None:
1985 return self.url_result(facebook_url, 'Facebook')
1987 # Look for embedded VK player
1988 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1989 if mobj is not None:
1990 return self.url_result(mobj.group('url'), 'VK')
1992 # Look for embedded Odnoklassniki player
1993 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1994 if mobj is not None:
1995 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1997 # Look for embedded ivi player
1998 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1999 if mobj is not None:
2000 return self.url_result(mobj.group('url'), 'Ivi')
2002 # Look for embedded Huffington Post player
2004 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2005 if mobj is not None:
2006 return self.url_result(mobj.group('url'), 'HuffPost')
2009 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2010 if mobj is not None:
2011 return self.url_result(mobj.group('url'))
2012 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2013 if mobj is not None:
2014 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2016 # Look for funnyordie embed
2017 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2019 return _playlist_from_matches(
2020 matches, getter=unescapeHTML, ie='FunnyOrDie')
2022 # Look for BBC iPlayer embed
2023 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2025 return _playlist_from_matches(matches, ie='BBCCoUk')
2027 # Look for embedded RUTV player
2028 rutv_url = RUTVIE._extract_url(webpage)
2030 return self.url_result(rutv_url, 'RUTV')
2032 # Look for embedded TVC player
2033 tvc_url = TVCIE._extract_url(webpage)
2035 return self.url_result(tvc_url, 'TVC')
2037 # Look for embedded SportBox player
2038 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2040 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2042 # Look for embedded XHamster player
2043 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2045 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2047 # Look for embedded TNAFlixNetwork player
2048 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2050 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2052 # Look for embedded PornHub player
2053 pornhub_urls = PornHubIE._extract_urls(webpage)
2055 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2057 # Look for embedded DrTuber player
2058 drtuber_urls = DrTuberIE._extract_urls(webpage)
2060 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2062 # Look for embedded RedTube player
2063 redtube_urls = RedTubeIE._extract_urls(webpage)
2065 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2067 # Look for embedded Tvigle player
2069 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2070 if mobj is not None:
2071 return self.url_result(mobj.group('url'), 'Tvigle')
2073 # Look for embedded TED player
2075 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2076 if mobj is not None:
2077 return self.url_result(mobj.group('url'), 'TED')
2079 # Look for embedded Ustream videos
2081 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2082 if mobj is not None:
2083 return self.url_result(mobj.group('url'), 'Ustream')
2085 # Look for embedded arte.tv player
2087 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2089 if mobj is not None:
2090 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2092 # Look for embedded francetv player
2094 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2096 if mobj is not None:
2097 return self.url_result(mobj.group('url'))
2099 # Look for embedded smotri.com player
2100 smotri_url = SmotriIE._extract_url(webpage)
2102 return self.url_result(smotri_url, 'Smotri')
2104 # Look for embedded Myvi.ru player
2105 myvi_url = MyviIE._extract_url(webpage)
2107 return self.url_result(myvi_url)
2109 # Look for embedded soundcloud player
2110 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2112 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2114 # Look for tunein player
2115 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2117 return _playlist_from_matches(tunein_urls)
2119 # Look for embedded mtvservices player
2120 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2122 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2124 # Look for embedded yahoo player
2126 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2128 if mobj is not None:
2129 return self.url_result(mobj.group('url'), 'Yahoo')
2131 # Look for embedded sbs.com.au player
2135 <meta\s+property="og:video"\s+content=|
2138 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2140 if mobj is not None:
2141 return self.url_result(mobj.group('url'), 'SBS')
2143 # Look for embedded Cinchcast player
2145 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2147 if mobj is not None:
2148 return self.url_result(mobj.group('url'), 'Cinchcast')
2151 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2155 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2157 if mobj is not None:
2158 return self.url_result(mobj.group('url'), 'MLB')
2161 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2163 if mobj is not None:
2164 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2167 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2169 if mobj is not None:
2170 return self.url_result(mobj.group('url'), 'Livestream')
2172 # Look for Zapiks embed
2174 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2175 if mobj is not None:
2176 return self.url_result(mobj.group('url'), 'Zapiks')
2178 # Look for Kaltura embeds
2179 kaltura_url = KalturaIE._extract_url(webpage)
2181 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2183 # Look for Eagle.Platform embeds
2184 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2185 if eagleplatform_url:
2186 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2188 # Look for ClipYou (uses Eagle.Platform) embeds
2190 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2191 if mobj is not None:
2192 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2194 # Look for Pladform embeds
2195 pladform_url = PladformIE._extract_url(webpage)
2197 return self.url_result(pladform_url)
2199 # Look for Videomore embeds
2200 videomore_url = VideomoreIE._extract_url(webpage)
2202 return self.url_result(videomore_url)
2204 # Look for Webcaster embeds
2205 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2207 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2209 # Look for Playwire embeds
2211 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2212 if mobj is not None:
2213 return self.url_result(mobj.group('url'))
2215 # Look for 5min embeds
2217 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2218 if mobj is not None:
2219 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2221 # Look for Crooks and Liars embeds
2223 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2224 if mobj is not None:
2225 return self.url_result(mobj.group('url'))
2227 # Look for NBC Sports VPlayer embeds
2228 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2230 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2232 # Look for NBC News embeds
2233 nbc_news_embed_url = re.search(
2234 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2235 if nbc_news_embed_url:
2236 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2238 # Look for Google Drive embeds
2239 google_drive_url = GoogleDriveIE._extract_url(webpage)
2240 if google_drive_url:
2241 return self.url_result(google_drive_url, 'GoogleDrive')
2243 # Look for UDN embeds
2245 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2246 if mobj is not None:
2247 return self.url_result(
2248 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2250 # Look for Senate ISVP iframe
2251 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2253 return self.url_result(senate_isvp_url, 'SenateISVP')
2255 # Look for Dailymotion Cloud videos
2256 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2258 return self.url_result(dmcloud_url, 'DailymotionCloud')
2260 # Look for OnionStudios embeds
2261 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2262 if onionstudios_url:
2263 return self.url_result(onionstudios_url)
2265 # Look for ViewLift embeds
2266 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2268 return self.url_result(viewlift_url)
2270 # Look for JWPlatform embeds
2271 jwplatform_url = JWPlatformIE._extract_url(webpage)
2273 return self.url_result(jwplatform_url, 'JWPlatform')
2275 # Look for Digiteka embeds
2276 digiteka_url = DigitekaIE._extract_url(webpage)
2278 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2280 # Look for Arkena embeds
2281 arkena_url = ArkenaIE._extract_url(webpage)
2283 return self.url_result(arkena_url, ArkenaIE.ie_key())
2285 # Look for Piksel embeds
2286 piksel_url = PikselIE._extract_url(webpage)
2288 return self.url_result(piksel_url, PikselIE.ie_key())
2290 # Look for Limelight embeds
2291 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2295 'Channel': 'channel',
2296 'ChannelList': 'channel_list',
2298 return self.url_result('limelight:%s:%s' % (
2299 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2303 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2305 name=(["\'])flashVars\2[^>]+
2306 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2309 return self.url_result('limelight:media:%s' % mobj.group('id'))
2311 # Look for AdobeTVVideo embeds
2313 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2315 if mobj is not None:
2316 return self.url_result(
2317 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2320 # Look for Vine embeds
2322 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2324 if mobj is not None:
2325 return self.url_result(
2326 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2328 # Look for VODPlatform embeds
2330 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2332 if mobj is not None:
2333 return self.url_result(
2334 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2336 # Look for Mangomolo embeds
2338 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2340 video\?.*?\bid=(?P<video_id>\d+)|
2341 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2342 ).+?)\1''', webpage)
2343 if mobj is not None:
2345 '_type': 'url_transparent',
2346 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2347 'title': video_title,
2348 'description': video_description,
2349 'thumbnail': video_thumbnail,
2350 'uploader': video_uploader,
2352 video_id = mobj.group('video_id')
2355 'ie_key': 'MangomoloVideo',
2360 'ie_key': 'MangomoloLive',
2361 'id': mobj.group('channel_id'),
2365 # Look for Instagram embeds
2366 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2367 if instagram_embed_url is not None:
2368 return self.url_result(
2369 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2371 # Look for LiveLeak embeds
2372 liveleak_url = LiveLeakIE._extract_url(webpage)
2374 return self.url_result(liveleak_url, 'LiveLeak')
2376 # Look for 3Q SDN embeds
2377 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2380 '_type': 'url_transparent',
2381 'ie_key': ThreeQSDNIE.ie_key(),
2382 'url': self._proto_relative_url(threeqsdn_url),
2383 'title': video_title,
2384 'description': video_description,
2385 'thumbnail': video_thumbnail,
2386 'uploader': video_uploader,
2389 # Look for VBOX7 embeds
2390 vbox7_url = Vbox7IE._extract_url(webpage)
2392 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2394 # Look for DBTV embeds
2395 dbtv_urls = DBTVIE._extract_urls(webpage)
2397 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2399 # Look for Videa embeds
2400 videa_urls = VideaIE._extract_urls(webpage)
2402 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2404 # Looking for http://schema.org/VideoObject
2405 json_ld = self._search_json_ld(
2406 webpage, video_id, default={}, expected_type='VideoObject')
2407 if json_ld.get('url'):
2409 'title': video_title or info_dict['title'],
2410 'description': video_description,
2411 'thumbnail': video_thumbnail,
2412 'age_limit': age_limit
2414 info_dict.update(json_ld)
2417 # Look for HTML5 media
2418 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2420 for entry in entries:
2423 'title': video_title,
2425 self._sort_formats(entry['formats'])
2426 return self.playlist_result(entries)
2428 def check_video(vurl):
2429 if YoutubeIE.suitable(vurl):
2431 vpath = compat_urlparse.urlparse(vurl).path
2432 vext = determine_ext(vpath)
2433 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2435 def filter_video(urls):
2436 return list(filter(check_video, urls))
2438 # Start with something easy: JW Player in SWFObject
2439 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2441 # Look for gorilla-vid style embedding
2442 found = filter_video(re.findall(r'''(?sx)
2446 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2449 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2451 # Broaden the search a little bit
2452 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2454 # Broaden the findall a little bit: JWPlayer JS loader
2455 found = filter_video(re.findall(
2456 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2459 found = filter_video(re.findall(r'''(?xs)
2460 flowplayer\("[^"]+",\s*
2462 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2463 ["']?url["']?\s*:\s*["']([^"']+)["']
2468 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2470 # Try to find twitter cards info
2471 # twitter:player:stream should be checked before twitter:player since
2472 # it is expected to contain a raw stream (see
2473 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2474 found = filter_video(re.findall(
2475 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2477 # We look for Open Graph info:
2478 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2479 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2480 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2481 if m_video_type is not None:
2482 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2484 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2486 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2487 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2490 # Look also in Refresh HTTP header
2491 refresh_header = head_response.headers.get('Refresh')
2493 # In python 2 response HTTP headers are bytestrings
2494 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2495 refresh_header = refresh_header.decode('iso-8859-1')
2496 found = re.search(REDIRECT_REGEX, refresh_header)
2498 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2499 self.report_following_redirect(new_url)
2506 # twitter:player is a https URL to iframe player that may or may not
2507 # be supported by youtube-dl thus this is checked the very last (see
2508 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2509 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2511 return self.url_result(embed_url)
2514 raise UnsupportedError(url)
2517 for video_url in orderedSet(found):
2518 video_url = unescapeHTML(video_url)
2519 video_url = video_url.replace('\\/', '/')
2520 video_url = compat_urlparse.urljoin(url, video_url)
2521 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2523 # Sometimes, jwplayer extraction will result in a YouTube URL
2524 if YoutubeIE.suitable(video_url):
2525 entries.append(self.url_result(video_url, 'Youtube'))
2528 # here's a fun little line of code for you:
2529 video_id = os.path.splitext(video_id)[0]
2533 'uploader': video_uploader,
2534 'title': video_title,
2535 'age_limit': age_limit,
2538 ext = determine_ext(video_url)
2540 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2542 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2544 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2546 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2548 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2549 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2550 # Just matching .ism/manifest is not enough to be reliably sure
2551 # whether it's actually an ISM manifest or some other streaming
2552 # manifest since there are various streaming URL formats
2553 # possible (see [1]) as well as some other shenanigans like
2554 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2556 # Thus the most reasonable way to solve this is to delegate
2557 # to generic extractor in order to look into the contents of
2558 # the manifest itself.
2559 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2560 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2561 entry_info_dict = self.url_result(
2562 smuggle_url(video_url, {'to_generic': True}),
2565 entry_info_dict['url'] = video_url
2567 if entry_info_dict.get('formats'):
2568 self._sort_formats(entry_info_dict['formats'])
2570 entries.append(entry_info_dict)
2572 if len(entries) == 1:
2575 for num, e in enumerate(entries, start=1):
2576 # 'url' results don't have a title
2577 if e.get('title') is not None:
2578 e['title'] = '%s (%d)' % (e['title'], num)
2580 '_type': 'playlist',