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 .screenwavemedia import ScreenwaveMediaIE
60 from .mtv import MTVServicesEmbeddedIE
61 from .pladform import PladformIE
62 from .videomore import VideomoreIE
63 from .webcaster import WebcasterFeedIE
64 from .googledrive import GoogleDriveIE
65 from .jwplatform import JWPlatformIE
66 from .digiteka import DigitekaIE
67 from .arkena import ArkenaIE
68 from .instagram import InstagramIE
69 from .liveleak import LiveLeakIE
70 from .threeqsdn import ThreeQSDNIE
71 from .theplatform import ThePlatformIE
72 from .vessel import VesselIE
73 from .kaltura import KalturaIE
74 from .eagleplatform import EaglePlatformIE
75 from .facebook import FacebookIE
76 from .soundcloud import SoundcloudIE
77 from .vbox7 import Vbox7IE
78 from .dbtv import DBTVIE
81 class GenericIE(InfoExtractor):
82 IE_DESC = 'Generic downloader that works on some sites'
86 # Direct link to a video
88 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
89 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
94 'upload_date': '20100513',
97 # Direct link to media delivered compressed (until Accept-Encoding is *)
99 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
100 'md5': '128c42e68b13950268b648275386fc74',
102 'id': 'FictionJunction-Parallel_Hearts',
104 'title': 'FictionJunction-Parallel_Hearts',
105 'upload_date': '20140522',
107 'expected_warnings': [
108 'URL could be a direct video link, returning it as such.'
110 'skip': 'URL invalid',
112 # Direct download with broken HEAD
114 'url': 'http://ai-radio.org:8000/radio.opus',
121 'skip_download': True, # infinite live stream
123 'expected_warnings': [
124 r'501.*Not Implemented',
128 # Direct link with incorrect MIME type
130 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
131 'md5': '4ccbebe5f36706d85221f204d7eb5913',
133 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
134 'id': '5_Lennart_Poettering_-_Systemd',
136 'title': '5_Lennart_Poettering_-_Systemd',
137 'upload_date': '20141120',
139 'expected_warnings': [
140 'URL could be a direct video link, returning it as such.'
145 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
147 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
148 'title': 'Zero Punctuation',
149 'description': 're:.*groundbreaking video review series.*'
151 'playlist_mincount': 11,
153 # RSS feed with enclosure
155 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
157 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
159 'upload_date': '20150228',
160 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
163 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
165 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
169 'title': 'Automatics, robotics and biocybernetics',
170 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
171 'upload_date': '20130627',
172 'formats': 'mincount:16',
173 'subtitles': 'mincount:1',
176 'force_generic_extractor': True,
177 'skip_download': True,
180 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
182 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
187 'formats': 'mincount:1',
190 'skip_download': True,
193 # SMIL from https://www.restudy.dk/video/play/id/1637
195 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
199 'title': 'video_1637',
200 'formats': 'mincount:3',
203 'skip_download': True,
206 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
208 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
210 'id': 'smil-service',
212 'title': 'smil-service',
213 'formats': 'mincount:1',
216 'skip_download': True,
219 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
221 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
225 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
226 'formats': 'mincount:3',
229 'skip_download': True,
232 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
234 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
236 'id': 'mZlp2ctYIUEB',
238 'title': 'Tikibad ontruimd wegens brand',
239 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
240 'thumbnail': 're:^https?://.*\.jpg$',
244 'skip_download': True,
247 # MPD from http://dash-mse-test.appspot.com/media.html
249 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
250 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
252 'id': 'car-20120827-manifest',
254 'title': 'car-20120827-manifest',
255 'formats': 'mincount:9',
256 'upload_date': '20130904',
259 'format': 'bestvideo',
262 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
264 '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',
269 'formats': 'mincount:8',
273 'skip_download': True,
275 'skip': 'video gone',
277 # m3u8 served with Content-Type: text/plain
279 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
284 'upload_date': '20140720',
285 'formats': 'mincount:11',
289 'skip_download': True,
291 'skip': 'video gone',
295 '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',
299 'upload_date': '20130224',
300 'uploader_id': 'TheVerge',
301 'description': 're:^Chris Ziegler takes a look at the\.*',
302 'uploader': 'The Verge',
303 'title': 'First Firefox OS phones side-by-side',
306 'skip_download': False,
310 # redirect in Refresh HTTP header
311 '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',
315 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
316 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
317 'upload_date': '20150917',
318 'uploader_id': 'brtvofficial',
319 'uploader': 'Boiler Room',
322 'skip_download': False,
326 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
327 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
329 'id': '13601338388002',
331 'uploader': 'www.hodiho.fr',
332 'title': 'R\u00e9gis plante sa Jeep',
335 # bandcamp page with custom domain
337 'add_ie': ['Bandcamp'],
338 'url': 'http://bronyrock.com/track/the-pony-mash',
342 'title': 'The Pony Mash',
343 'uploader': 'M_Pallante',
345 'skip': 'There is a limit of 200 free downloads / month for the test song',
347 # embedded brightcove video
348 # it also tests brightcove videos that need to set the 'Referer' in the
351 'add_ie': ['BrightcoveLegacy'],
352 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
354 'id': '2765128793001',
356 'title': 'Le cours de bourse : l’analyse technique',
357 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
358 'uploader': 'BFM BUSINESS',
361 'skip_download': True,
365 # https://github.com/rg3/youtube-dl/issues/2253
366 'url': 'http://bcove.me/i6nfkrc3',
367 'md5': '0ba9446db037002366bab3b3eb30c88c',
369 'id': '3101154703001',
371 'title': 'Still no power',
372 'uploader': 'thestar.com',
373 '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.',
375 'add_ie': ['BrightcoveLegacy'],
376 'skip': 'video gone',
379 'url': 'http://www.championat.com/video/football/v/87/87499.html',
380 'md5': 'fb973ecf6e4a78a67453647444222983',
382 'id': '3414141473001',
384 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
385 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
386 'uploader': 'Championat',
390 # https://github.com/rg3/youtube-dl/issues/3541
391 'add_ie': ['BrightcoveLegacy'],
392 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
394 'id': '3866516442001',
396 'title': 'Leer mij vrouwen kennen: Aflevering 1',
397 'description': 'Leer mij vrouwen kennen: Aflevering 1',
398 'uploader': 'SBS Broadcasting',
400 'skip': 'Restricted to Netherlands',
402 'skip_download': True, # m3u8 download
407 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
408 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
410 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
412 'title': '2cc213299525360.mov', # that's what we get
415 'add_ie': ['Ooyala'],
418 # ooyala video embedded with http://player.ooyala.com/iframe.js
419 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
421 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
423 'title': '"Steve Jobs: Man in the Machine" trailer',
424 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
428 'skip_download': True,
430 'skip': 'movie expired',
434 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
438 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
439 'upload_date': '20140225',
440 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
441 'uploader': 'Tested',
442 'uploader_id': 'testedcom',
444 # No need to test YoutubeIE here
446 'skip_download': True,
451 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
455 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
456 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
458 # HEAD requests lead to endless 301, while GET is OK
459 'expected_warnings': ['301'],
463 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
467 'title': 'Охотское море стало целиком российским',
468 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
472 'skip_download': True,
477 '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/',
481 'title': 'Дошкольное воспитание',
486 'url': 'http://www.vestifinance.ru/articles/25753',
489 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
494 'title': 'Госзаказ. День 3',
500 'title': 'Госзаказ. День 2',
506 'title': 'Госзаказ. День 1',
512 'skip_download': True,
517 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
519 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
521 'title': 'Ужастики, русский трейлер (2015)',
522 'thumbnail': 're:^https?://.*\.jpg$',
528 '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',
531 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
533 'playlist_mincount': 7,
534 # This forum does not allow <iframe> syntaxes anymore
535 # Now HTML tags are displayed as-is
536 'skip': 'No videos on this page',
540 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
541 'md5': '65fdff94098e4a607385a60c5177c638',
545 'title': 'Hidden miracles of the natural world',
546 'uploader': 'Louie Schwartzberg',
547 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
550 # Embedded Ustream video
552 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
553 'md5': '27b99cdb639c9b12a79bca876a073417',
557 'uploader': 'AU SPA: The NSA and Privacy',
558 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
561 # nowvideo embed hidden behind percent encoding
563 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
564 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
566 'id': '06e53103ca9aa',
568 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
569 'description': 'No description',
574 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
575 'md5': '7653032cbb25bf6c80d80f217055fa43',
577 'id': '048195-004_PLUS7-F',
580 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
581 'upload_date': '20140320',
584 'skip_download': 'Requires rtmpdump'
586 'skip': 'video gone',
590 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
594 'title': 'Alcaline, le concert avec Calogero',
595 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
596 'upload_date': '20150226',
597 'timestamp': 1424989860,
602 'skip_download': True,
604 'expected_warnings': [
610 'url': 'http://www.wired.com/2014/04/honda-asimo/',
611 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
613 'id': '53501be369702d3275860000',
615 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
620 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
621 'md5': '441aeeb82eb72c422c7f14ec533999cd',
623 'id': 'k2mm4bCdJ6CQ2i7c8o2',
625 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
626 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
628 'uploader_id': 'xgditw',
629 'upload_date': '20140425',
630 'timestamp': 1398441542,
632 'add_ie': ['Dailymotion'],
636 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
640 'title': 'The NBL Auction 2014',
641 'uploader': 'BADMINTON England',
642 'uploader_id': 'BADMINTONEvents',
643 'upload_date': '20140603',
644 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
646 'add_ie': ['Youtube'],
648 'skip_download': True,
653 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
654 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
656 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
658 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
659 'description': 'Two valets share their love for movie star Liam Neesons.',
660 'timestamp': 1349922600,
661 'upload_date': '20121011',
664 # YouTube embed via <data-embed-url="">
666 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
670 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
671 'uploader': 'Gameloft',
672 'uploader_id': 'gameloft',
673 'upload_date': '20140828',
674 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
677 'skip_download': True,
682 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
684 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
686 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
687 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
692 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
694 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
695 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
701 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
706 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
707 'md5': '9d65602bf31c6e20014319c7d07fba27',
709 'id': '5123ea6d5e5a7',
712 'uploader': 'www.handjobhub.com',
713 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
716 # Multiple brightcove videos
717 # https://github.com/rg3/youtube-dl/issues/2283
719 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
721 'id': 'always-never',
722 'title': 'Always / Never - The New Yorker',
726 'extract_flat': False,
727 'skip_download': True,
732 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
733 'md5': '96f09a37e44da40dd083e12d9a683327',
737 'title': 'Ump changes call to ball',
738 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
740 'timestamp': 1401537900,
741 'upload_date': '20140531',
742 'thumbnail': 're:^https?://.*\.jpg$',
747 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
748 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
752 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
753 'description': 'a Paywall Videos video from Remilon',
755 'uploader': 'study.com',
756 'timestamp': 1459678540,
757 'upload_date': '20160403',
758 'filesize': 24687186,
762 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
763 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
767 'title': 'Conversation about Hexagonal Rails Part 1',
768 'description': 'a Martin Fowler video from ThoughtWorks',
770 'uploader': 'thoughtworks.wistia.com',
771 'timestamp': 1401832161,
772 'upload_date': '20140603',
775 # Wistia standard embed (async)
777 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
781 'title': 'Drip Brennan Dunn Workshop',
782 'description': 'a JV Webinars video from getdrip-1',
784 'timestamp': 1463607249,
785 'upload_date': '20160518',
788 'skip_download': True,
793 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
797 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
798 'uploader': 'Sophos Security',
799 'title': 'Chet Chat 171 - Oct 29, 2014',
800 'upload_date': '20141029',
803 # Soundcloud multiple embeds
805 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
808 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
810 'playlist_mincount': 7,
814 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
818 'upload_date': '20141112',
819 'title': 'Rosetta #CometLanding webcast HL 10',
822 # Another Livestream embed, without 'new.' in URL
824 'url': 'https://www.freespeech.org/',
828 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
832 'skip_download': True,
837 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
840 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
842 'playlist_mincount': 2,
846 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
850 'upload_date': '20141126',
851 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
856 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
858 'id': '730m_DandD_1901_512k',
860 'uploader': 'www.abc.net.au',
861 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
864 # embedded viddler video
866 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
870 'uploader': 'deadspin',
871 'title': 'WALL-TO-GORTAT',
872 'timestamp': 1422285291,
873 'upload_date': '20150126',
875 'add_ie': ['Viddler'],
879 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
883 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
884 'description': 'md5:601cb790edd05908957dae8aaa866465',
885 'upload_date': '20150220',
887 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
891 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
895 'upload_date': '20150212',
896 'uploader': 'The National Archives UK',
897 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
898 'uploader_id': 'NationalArchives08',
899 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
904 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
905 'playlist_mincount': 5,
907 'id': 'aanslagen-kopenhagen',
908 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
913 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
917 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
920 # Kaltura embed (different embed code)
922 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
926 'upload_date': '20150127',
927 'uploader_id': 'PremierMedia',
929 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
932 # Kaltura embed protected with referrer
934 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
938 'title': 'Violetta - Achter De Schermen - Ruggero',
939 'description': 'Achter de schermen met Ruggero',
940 'timestamp': 1435133761,
941 'upload_date': '20150624',
942 'uploader_id': 'echojecka',
945 # Kaltura embed with single quotes
947 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
952 'timestamp': 1355743100,
953 'upload_date': '20121217',
954 'uploader_id': 'batchUser',
956 'add_ie': ['Kaltura'],
959 # Kaltura embedded via quoted entry_id
960 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
964 'title': '06_matthew_brender_raj_dutt',
965 'timestamp': 1466638791,
966 'upload_date': '20160622',
968 'add_ie': ['Kaltura'],
969 'expected_warnings': [
970 'Could not send HEAD request'
973 'skip_download': True,
976 # Eagle.Platform embed (generic URL)
978 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
979 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
983 'title': 'Навальный вышел на свободу',
984 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
985 'thumbnail': 're:^https?://.*\.jpg$',
991 # ClipYou (Eagle.Platform) embed (custom URL)
993 'url': 'http://muz-tv.ru/play/7129/',
994 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
998 'title': "'O Sole Mio",
999 'thumbnail': 're:^https?://.*\.jpg$',
1006 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1010 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1011 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1012 'thumbnail': 're:^https?://.*\.jpg$',
1019 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1023 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1024 'thumbnail': 're:^https?://.*\.png$',
1030 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1031 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1035 'title': 'Facebook Creates "On This Day" | Crunch Report',
1040 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1044 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1049 # Crooks and Liars embed
1051 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1055 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1056 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1057 'timestamp': 1428207000,
1058 'upload_date': '20150405',
1059 'uploader': 'Heather',
1062 # Crooks and Liars external embed
1064 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1066 'id': 'MTE3MjUtMzQ2MzA',
1068 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1069 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1070 'timestamp': 1265032391,
1071 'upload_date': '20100201',
1072 'uploader': 'Heather',
1075 # NBC Sports vplayer embed
1077 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1079 'id': 'ln7x1qSThw4k',
1081 'title': "PFT Live: New leader in the 'new-look' defense",
1082 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1083 'uploader': 'NBCU-SPORTS',
1084 'upload_date': '20140107',
1085 'timestamp': 1389118457,
1090 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1091 'md5': '1aa589c675898ae6d37a17913cf68d66',
1093 'id': '701714499682',
1095 'title': 'PREVIEW: On Assignment: David Letterman',
1096 '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.',
1101 'url': 'https://video.udn.com/news/300346',
1102 'md5': 'fd2060e988c326991037b9aff9df21a6',
1106 'title': '中一中男師變性 全校師生力挺',
1107 'thumbnail': 're:^https?://.*\.jpg$',
1111 'skip_download': True,
1116 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1118 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1120 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1121 'title': 'This is what separates the Excel masters from the wannabes',
1122 'duration': 191.933,
1126 'skip_download': True,
1129 # Brightcove URL in single quotes
1131 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1132 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1134 'id': '4255764656001',
1136 'title': 'SN Presents: Russell Martin, World Citizen',
1137 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1138 'uploader': 'Rogers Sportsnet',
1139 'uploader_id': '1704050871',
1140 'upload_date': '20150525',
1141 'timestamp': 1432570283,
1144 # Dailymotion Cloud video
1146 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1147 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1151 'title': 'Sauvons les abeilles ! - Le débat',
1152 'description': 'md5:d9082128b1c5277987825d684939ca26',
1153 'thumbnail': 're:^https?://.*\.jpe?g$',
1154 'timestamp': 1434970506,
1155 'upload_date': '20150622',
1156 'uploader': 'Public Sénat',
1157 'uploader_id': 'xa9gza',
1160 # OnionStudios embed
1162 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1166 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1167 'thumbnail': 're:^https?://.*\.jpe?g$',
1168 'uploader': 'ClickHole',
1169 'uploader_id': 'clickhole',
1174 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1176 'id': '74849a00-85a9-11e1-9660-123139220831',
1178 'title': '#whilewewatch',
1181 # AdobeTVVideo embed
1183 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1184 'md5': '43662b577c018ad707a63766462b1e87',
1188 'title': 'New experience with Acrobat DC',
1189 'description': 'New experience with Acrobat DC',
1190 'duration': 248.667,
1193 # ScreenwaveMedia embed
1195 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1196 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1198 'id': 'cinemasnob-55d26273809dd',
1200 'title': 'cinemasnob',
1203 # BrightcoveInPageEmbed embed
1205 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1207 'id': '4238694884001',
1209 'title': 'Tabletop: Dread, Last Thoughts',
1210 'description': 'Tabletop: Dread, Last Thoughts',
1214 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1215 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1217 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1219 'id': '4785848093001',
1221 'title': 'The Cardinal Pell Interview',
1222 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1223 'uploader': 'GlobeCast Australia - GlobeStream',
1224 'uploader_id': '2733773828001',
1225 'upload_date': '20160304',
1226 'timestamp': 1457083087,
1230 'skip_download': True,
1233 # Another form of arte.tv embed
1235 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1236 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1238 'id': '030273-562_PLUS7-F',
1240 'title': 'ARTE Reportage - Nulle part, en France',
1241 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1242 'upload_date': '20160409',
1247 'url': 'http://www.wykop.pl/link/3088787/',
1248 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1250 'id': '874_1459135191',
1252 'title': 'Man shows poor quality of new apartment building',
1253 'description': 'The wall is like a sand pile.',
1254 'uploader': 'Lake8737',
1257 # Duplicated embedded video URLs
1259 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1261 'id': '149298443_480_16c25b74_2',
1263 'title': 'vs. Blue Orange Spring Game',
1264 'uploader': 'www.hudl.com',
1267 # twitter:player:stream embed
1269 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1273 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1274 'uploader': 'www.rtl.be',
1278 'skip_download': True,
1281 # twitter:player embed
1283 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1284 'md5': 'a3e0df96369831de324f0778e126653c',
1286 'id': '4909620399001',
1288 'title': 'What Do Black Holes Sound Like?',
1289 'description': 'what do black holes sound like',
1290 'upload_date': '20160524',
1291 'uploader_id': '29913724001',
1292 'timestamp': 1464107587,
1293 'uploader': 'TheAtlantic',
1295 'add_ie': ['BrightcoveLegacy'],
1297 # Facebook <iframe> embed
1299 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1300 'md5': 'fbcde74f534176ecb015849146dd3aee',
1302 'id': '599637780109885',
1304 'title': 'Facebook video #599637780109885',
1307 # Facebook API embed
1309 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1310 'md5': 'a47372ee61b39a7b90287094d447d94e',
1312 'id': '10153467542406923',
1314 'title': 'Facebook video #10153467542406923',
1317 # Wordpress "YouTube Video Importer" plugin
1319 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1320 'md5': 'd16797741b560b485194eddda8121b48',
1322 'id': 'HNTXWDXV9Is',
1324 'title': 'Blue Devils Drumline Stanford lot 2016',
1325 'upload_date': '20160627',
1326 'uploader_id': 'GENOCIDE8GENERAL10',
1327 'uploader': 'cylus cyrus',
1331 # video stored on custom kaltura server
1332 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1333 'md5': '537617d06e64dfed891fa1593c4b30cc',
1337 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1338 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1339 'uploader_id': 'videos.expansion@el-mundo.net',
1340 'upload_date': '20150429',
1341 'timestamp': 1430303472,
1343 'add_ie': ['Kaltura'],
1346 # Non-standard Vimeo embed
1347 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1348 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1352 'title': 'Understanding the web - Teaser',
1353 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1354 'upload_date': '20151214',
1355 'uploader': 'OpenClassrooms',
1356 'uploader_id': 'openclassrooms',
1358 'add_ie': ['Vimeo'],
1361 # generic vimeo embed that requires original URL passed as Referer
1362 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1363 'only_matching': True,
1366 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1367 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1369 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1371 'title': 'Big Buck Bunny',
1372 'description': 'Royalty free test video',
1373 'timestamp': 1432816365,
1374 'upload_date': '20150528',
1378 'skip_download': True,
1380 'add_ie': [ArkenaIE.ie_key()],
1383 '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/',
1387 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1390 'skip_download': True,
1392 'add_ie': [Vbox7IE.ie_key()],
1396 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1399 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1401 'playlist_mincount': 3,
1404 # # TODO: find another test
1405 # # http://schema.org/VideoObject
1406 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1407 # 'md5': '888dcf08b7ea671381f00fab74692755',
1409 # 'id': 'nyvTSJMKId',
1411 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1412 # 'description': '#love for cats.',
1413 # 'timestamp': 1461244995,
1414 # 'upload_date': '20160421',
1417 # 'force_generic_extractor': True,
1422 def report_following_redirect(self, new_url):
1423 """Report information extraction."""
1424 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1426 def _extract_rss(self, url, video_id, doc):
1427 playlist_title = doc.find('./channel/title').text
1428 playlist_desc_el = doc.find('./channel/description')
1429 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1432 for it in doc.findall('./channel/item'):
1433 next_url = xpath_text(it, 'link', fatal=False)
1435 enclosure_nodes = it.findall('./enclosure')
1436 for e in enclosure_nodes:
1437 next_url = e.attrib.get('url')
1447 'title': it.find('title').text,
1451 '_type': 'playlist',
1453 'title': playlist_title,
1454 'description': playlist_desc,
1458 def _extract_camtasia(self, url, video_id, webpage):
1459 """ Returns None if no camtasia video can be found. """
1461 camtasia_cfg = self._search_regex(
1462 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1463 webpage, 'camtasia configuration file', default=None)
1464 if camtasia_cfg is None:
1467 title = self._html_search_meta('DC.title', webpage, fatal=True)
1469 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1470 camtasia_cfg = self._download_xml(
1471 camtasia_url, video_id,
1472 note='Downloading camtasia configuration',
1473 errnote='Failed to download camtasia configuration')
1474 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1477 for n in fileset_node.getchildren():
1478 url_n = n.find('./uri')
1483 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1484 'title': '%s - %s' % (title, n.tag),
1485 'url': compat_urlparse.urljoin(url, url_n.text),
1486 'duration': float_or_none(n.find('./duration').text),
1490 '_type': 'playlist',
1495 def _real_extract(self, url):
1496 if url.startswith('//'):
1499 'url': self.http_scheme() + url,
1502 parsed_url = compat_urlparse.urlparse(url)
1503 if not parsed_url.scheme:
1504 default_search = self._downloader.params.get('default_search')
1505 if default_search is None:
1506 default_search = 'fixup_error'
1508 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1510 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1511 return self.url_result('http://' + url)
1512 elif default_search != 'fixup_error':
1513 if default_search == 'auto_warning':
1514 if re.match(r'^(?:url|URL)$', url):
1515 raise ExtractorError(
1516 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1519 self._downloader.report_warning(
1520 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1521 return self.url_result('ytsearch:' + url)
1523 if default_search in ('error', 'fixup_error'):
1524 raise ExtractorError(
1525 '%r is not a valid URL. '
1526 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1527 % (url, url), expected=True)
1529 if ':' not in default_search:
1530 default_search += ':'
1531 return self.url_result(default_search + url)
1533 url, smuggled_data = unsmuggle_url(url)
1534 force_videoid = None
1535 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1536 if smuggled_data and 'force_videoid' in smuggled_data:
1537 force_videoid = smuggled_data['force_videoid']
1538 video_id = force_videoid
1540 video_id = self._generic_id(url)
1542 self.to_screen('%s: Requesting header' % video_id)
1544 head_req = HEADRequest(url)
1545 head_response = self._request_webpage(
1547 note=False, errnote='Could not send HEAD request to %s' % url,
1550 if head_response is not False:
1551 # Check for redirect
1552 new_url = head_response.geturl()
1554 self.report_following_redirect(new_url)
1556 new_url = smuggle_url(
1557 new_url, {'force_videoid': force_videoid})
1558 return self.url_result(new_url)
1560 full_response = None
1561 if head_response is False:
1562 request = sanitized_Request(url)
1563 request.add_header('Accept-Encoding', '*')
1564 full_response = self._request_webpage(request, video_id)
1565 head_response = full_response
1569 'title': self._generic_title(url),
1570 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1573 # Check for direct link to a video
1574 content_type = head_response.headers.get('Content-Type', '').lower()
1575 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1577 format_id = m.group('format_id')
1578 if format_id.endswith('mpegurl'):
1579 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1580 elif format_id == 'f4m':
1581 formats = self._extract_f4m_formats(url, video_id)
1584 'format_id': m.group('format_id'),
1586 'vcodec': 'none' if m.group('type') == 'audio' else None
1588 info_dict['direct'] = True
1589 self._sort_formats(formats)
1590 info_dict['formats'] = formats
1593 if not self._downloader.params.get('test', False) and not is_intentional:
1594 force = self._downloader.params.get('force_generic_extractor', False)
1595 self._downloader.report_warning(
1596 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1598 if not full_response:
1599 request = sanitized_Request(url)
1600 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1601 # making it impossible to download only chunk of the file (yet we need only 512kB to
1602 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1603 # that will always result in downloading the whole file that is not desirable.
1604 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1605 # to accept raw bytes and being able to download only a chunk.
1606 # It may probably better to solve this by checking Content-Type for application/octet-stream
1607 # after HEAD request finishes, but not sure if we can rely on this.
1608 request.add_header('Accept-Encoding', '*')
1609 full_response = self._request_webpage(request, video_id)
1611 first_bytes = full_response.read(512)
1613 # Is it an M3U playlist?
1614 if first_bytes.startswith(b'#EXTM3U'):
1615 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1616 self._sort_formats(info_dict['formats'])
1619 # Maybe it's a direct link to a video?
1620 # Be careful not to download the whole thing!
1621 if not is_html(first_bytes):
1622 self._downloader.report_warning(
1623 'URL could be a direct video link, returning it as such.')
1630 webpage = self._webpage_read_content(
1631 full_response, url, video_id, prefix=first_bytes)
1633 self.report_extraction(video_id)
1635 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1637 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1638 if doc.tag == 'rss':
1639 return self._extract_rss(url, video_id, doc)
1640 elif doc.tag == 'SmoothStreamingMedia':
1641 info_dict['formats'] = self._parse_ism_formats(doc, url)
1642 self._sort_formats(info_dict['formats'])
1644 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1645 smil = self._parse_smil(doc, url, video_id)
1646 self._sort_formats(smil['formats'])
1648 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1649 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1650 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1651 info_dict['formats'] = self._parse_mpd_formats(
1653 mpd_base_url=full_response.geturl().rpartition('/')[0],
1655 self._sort_formats(info_dict['formats'])
1657 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1658 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1659 self._sort_formats(info_dict['formats'])
1661 except compat_xml_parse_error:
1664 # Is it a Camtasia project?
1665 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1666 if camtasia_res is not None:
1669 # Sometimes embedded video player is hidden behind percent encoding
1670 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1671 # Unescaping the whole page allows to handle those cases in a generic way
1672 webpage = compat_urllib_parse_unquote(webpage)
1674 # it's tempting to parse this further, but you would
1675 # have to take into account all the variations like
1676 # Video Title - Site Name
1677 # Site Name | Video Title
1678 # Video Title - Tagline | Site Name
1679 # and so on and so forth; it's just not practical
1680 video_title = self._og_search_title(
1681 webpage, default=None) or self._html_search_regex(
1682 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1685 # Try to detect age limit automatically
1686 age_limit = self._rta_search(webpage)
1687 # And then there are the jokers who advertise that they use RTA,
1688 # but actually don't.
1689 AGE_LIMIT_MARKERS = [
1690 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1692 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1695 # video uploader is domain name
1696 video_uploader = self._search_regex(
1697 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1699 video_description = self._og_search_description(webpage, default=None)
1700 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1703 def _playlist_from_matches(matches, getter=None, ie=None):
1705 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1707 return self.playlist_result(
1708 urlrs, playlist_id=video_id, playlist_title=video_title)
1710 # Look for Brightcove Legacy Studio embeds
1711 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1713 self.to_screen('Brightcove video detected.')
1716 'url': smuggle_url(bc_url, {'Referer': url}),
1717 'ie_key': 'BrightcoveLegacy'
1718 } for bc_url in bc_urls]
1721 '_type': 'playlist',
1722 'title': video_title,
1727 # Look for Brightcove New Studio embeds
1728 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1730 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1732 # Look for ThePlatform embeds
1733 tp_urls = ThePlatformIE._extract_urls(webpage)
1735 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1737 # Look for Vessel embeds
1738 vessel_urls = VesselIE._extract_urls(webpage)
1740 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1742 # Look for embedded rtl.nl player
1743 matches = re.findall(
1744 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1747 return _playlist_from_matches(matches, ie='RtlNl')
1749 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1751 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1753 vid_me_embed_url = self._search_regex(
1754 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1755 webpage, 'vid.me embed', default=None)
1756 if vid_me_embed_url is not None:
1757 return self.url_result(vid_me_embed_url, 'Vidme')
1759 # Look for embedded YouTube player
1760 matches = re.findall(r'''(?x)
1769 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1773 return _playlist_from_matches(
1774 matches, lambda m: unescapeHTML(m[1]))
1776 # Look for lazyYT YouTube embed
1777 matches = re.findall(
1778 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1780 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1782 # Look for Wordpress "YouTube Video Importer" plugin
1783 matches = re.findall(r'''(?x)<div[^>]+
1784 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1785 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1787 return _playlist_from_matches(matches, lambda m: m[-1])
1789 matches = DailymotionIE._extract_urls(webpage)
1791 return _playlist_from_matches(matches)
1793 # Look for embedded Dailymotion playlist player (#3822)
1795 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1797 playlists = re.findall(
1798 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1800 return _playlist_from_matches(
1801 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1803 # Look for embedded Wistia player
1805 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1807 embed_url = self._proto_relative_url(
1808 unescapeHTML(match.group('url')))
1810 '_type': 'url_transparent',
1813 'uploader': video_uploader,
1816 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1819 '_type': 'url_transparent',
1820 'url': 'wistia:%s' % match.group('id'),
1822 'uploader': video_uploader,
1827 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1828 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1831 return self.url_result(self._proto_relative_url(
1832 'wistia:%s' % match.group('id')), 'Wistia')
1834 # Look for SVT player
1835 svt_url = SVTIE._extract_url(webpage)
1837 return self.url_result(svt_url, 'SVT')
1839 # Look for embedded condenast player
1840 matches = re.findall(
1841 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1845 '_type': 'playlist',
1848 'ie_key': 'CondeNast',
1850 } for ma in matches],
1851 'title': video_title,
1855 # Look for Bandcamp pages with custom domain
1856 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1857 if mobj is not None:
1858 burl = unescapeHTML(mobj.group(1))
1859 # Don't set the extractor because it can be a track url or an album
1860 return self.url_result(burl)
1862 # Look for embedded Vevo player
1864 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1865 if mobj is not None:
1866 return self.url_result(mobj.group('url'))
1868 # Look for embedded Viddler player
1870 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1872 if mobj is not None:
1873 return self.url_result(mobj.group('url'))
1875 # Look for NYTimes player
1877 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1879 if mobj is not None:
1880 return self.url_result(mobj.group('url'))
1882 # Look for Libsyn player
1884 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1885 if mobj is not None:
1886 return self.url_result(mobj.group('url'))
1888 # Look for Ooyala videos
1889 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1890 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1891 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1892 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1893 if mobj is not None:
1894 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1896 # Look for multiple Ooyala embeds on SBN network websites
1897 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1898 if mobj is not None:
1899 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1901 return _playlist_from_matches(
1902 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1904 # Look for Aparat videos
1905 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1906 if mobj is not None:
1907 return self.url_result(mobj.group(1), 'Aparat')
1909 # Look for MPORA videos
1910 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1911 if mobj is not None:
1912 return self.url_result(mobj.group(1), 'Mpora')
1914 # Look for embedded NovaMov-based player
1916 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1917 (?P<url>http://(?:(?:embed|www)\.)?
1919 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1920 videoweed\.(?:es|com)|
1921 movshare\.(?:net|sx|ag)|
1922 divxstage\.(?:eu|net|ch|co|at|ag))
1923 /embed\.php.+?)\1''', webpage)
1924 if mobj is not None:
1925 return self.url_result(mobj.group('url'))
1927 # Look for embedded Facebook player
1928 facebook_url = FacebookIE._extract_url(webpage)
1929 if facebook_url is not None:
1930 return self.url_result(facebook_url, 'Facebook')
1932 # Look for embedded VK player
1933 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1934 if mobj is not None:
1935 return self.url_result(mobj.group('url'), 'VK')
1937 # Look for embedded Odnoklassniki player
1938 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1939 if mobj is not None:
1940 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1942 # Look for embedded ivi player
1943 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1944 if mobj is not None:
1945 return self.url_result(mobj.group('url'), 'Ivi')
1947 # Look for embedded Huffington Post player
1949 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1950 if mobj is not None:
1951 return self.url_result(mobj.group('url'), 'HuffPost')
1954 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1955 if mobj is not None:
1956 return self.url_result(mobj.group('url'))
1957 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1958 if mobj is not None:
1959 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1961 # Look for funnyordie embed
1962 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1964 return _playlist_from_matches(
1965 matches, getter=unescapeHTML, ie='FunnyOrDie')
1967 # Look for BBC iPlayer embed
1968 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1970 return _playlist_from_matches(matches, ie='BBCCoUk')
1972 # Look for embedded RUTV player
1973 rutv_url = RUTVIE._extract_url(webpage)
1975 return self.url_result(rutv_url, 'RUTV')
1977 # Look for embedded TVC player
1978 tvc_url = TVCIE._extract_url(webpage)
1980 return self.url_result(tvc_url, 'TVC')
1982 # Look for embedded SportBox player
1983 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1985 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1987 # Look for embedded XHamster player
1988 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1990 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1992 # Look for embedded TNAFlixNetwork player
1993 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1995 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1997 # Look for embedded PornHub player
1998 pornhub_urls = PornHubIE._extract_urls(webpage)
2000 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2002 # Look for embedded DrTuber player
2003 drtuber_urls = DrTuberIE._extract_urls(webpage)
2005 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2007 # Look for embedded RedTube player
2008 redtube_urls = RedTubeIE._extract_urls(webpage)
2010 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2012 # Look for embedded Tvigle player
2014 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2015 if mobj is not None:
2016 return self.url_result(mobj.group('url'), 'Tvigle')
2018 # Look for embedded TED player
2020 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2021 if mobj is not None:
2022 return self.url_result(mobj.group('url'), 'TED')
2024 # Look for embedded Ustream videos
2026 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2027 if mobj is not None:
2028 return self.url_result(mobj.group('url'), 'Ustream')
2030 # Look for embedded arte.tv player
2032 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2034 if mobj is not None:
2035 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2037 # Look for embedded francetv player
2039 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2041 if mobj is not None:
2042 return self.url_result(mobj.group('url'))
2044 # Look for embedded smotri.com player
2045 smotri_url = SmotriIE._extract_url(webpage)
2047 return self.url_result(smotri_url, 'Smotri')
2049 # Look for embedded Myvi.ru player
2050 myvi_url = MyviIE._extract_url(webpage)
2052 return self.url_result(myvi_url)
2054 # Look for embedded soundcloud player
2055 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2057 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2059 # Look for embedded mtvservices player
2060 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2062 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2064 # Look for embedded yahoo player
2066 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2068 if mobj is not None:
2069 return self.url_result(mobj.group('url'), 'Yahoo')
2071 # Look for embedded sbs.com.au player
2075 <meta\s+property="og:video"\s+content=|
2078 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2080 if mobj is not None:
2081 return self.url_result(mobj.group('url'), 'SBS')
2083 # Look for embedded Cinchcast player
2085 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2087 if mobj is not None:
2088 return self.url_result(mobj.group('url'), 'Cinchcast')
2091 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2095 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2097 if mobj is not None:
2098 return self.url_result(mobj.group('url'), 'MLB')
2101 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2103 if mobj is not None:
2104 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2107 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2109 if mobj is not None:
2110 return self.url_result(mobj.group('url'), 'Livestream')
2112 # Look for Zapiks embed
2114 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2115 if mobj is not None:
2116 return self.url_result(mobj.group('url'), 'Zapiks')
2118 # Look for Kaltura embeds
2119 kaltura_url = KalturaIE._extract_url(webpage)
2121 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2123 # Look for Eagle.Platform embeds
2124 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2125 if eagleplatform_url:
2126 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2128 # Look for ClipYou (uses Eagle.Platform) embeds
2130 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2131 if mobj is not None:
2132 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2134 # Look for Pladform embeds
2135 pladform_url = PladformIE._extract_url(webpage)
2137 return self.url_result(pladform_url)
2139 # Look for Videomore embeds
2140 videomore_url = VideomoreIE._extract_url(webpage)
2142 return self.url_result(videomore_url)
2144 # Look for Webcaster embeds
2145 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2147 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2149 # Look for Playwire embeds
2151 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2152 if mobj is not None:
2153 return self.url_result(mobj.group('url'))
2155 # Look for 5min embeds
2157 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2158 if mobj is not None:
2159 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2161 # Look for Crooks and Liars embeds
2163 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2164 if mobj is not None:
2165 return self.url_result(mobj.group('url'))
2167 # Look for NBC Sports VPlayer embeds
2168 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2170 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2172 # Look for NBC News embeds
2173 nbc_news_embed_url = re.search(
2174 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2175 if nbc_news_embed_url:
2176 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2178 # Look for Google Drive embeds
2179 google_drive_url = GoogleDriveIE._extract_url(webpage)
2180 if google_drive_url:
2181 return self.url_result(google_drive_url, 'GoogleDrive')
2183 # Look for UDN embeds
2185 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2186 if mobj is not None:
2187 return self.url_result(
2188 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2190 # Look for Senate ISVP iframe
2191 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2193 return self.url_result(senate_isvp_url, 'SenateISVP')
2195 # Look for Dailymotion Cloud videos
2196 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2198 return self.url_result(dmcloud_url, 'DailymotionCloud')
2200 # Look for OnionStudios embeds
2201 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2202 if onionstudios_url:
2203 return self.url_result(onionstudios_url)
2205 # Look for ViewLift embeds
2206 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2208 return self.url_result(viewlift_url)
2210 # Look for JWPlatform embeds
2211 jwplatform_url = JWPlatformIE._extract_url(webpage)
2213 return self.url_result(jwplatform_url, 'JWPlatform')
2215 # Look for ScreenwaveMedia embeds
2216 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2217 if mobj is not None:
2218 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2220 # Look for Digiteka embeds
2221 digiteka_url = DigitekaIE._extract_url(webpage)
2223 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2225 # Look for Arkena embeds
2226 arkena_url = ArkenaIE._extract_url(webpage)
2228 return self.url_result(arkena_url, ArkenaIE.ie_key())
2230 # Look for Limelight embeds
2231 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2235 'Channel': 'channel',
2236 'ChannelList': 'channel_list',
2238 return self.url_result('limelight:%s:%s' % (
2239 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2243 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2245 name=(["\'])flashVars\2[^>]+
2246 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2249 return self.url_result('limelight:media:%s' % mobj.group('id'))
2251 # Look for AdobeTVVideo embeds
2253 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2255 if mobj is not None:
2256 return self.url_result(
2257 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2260 # Look for Vine embeds
2262 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2264 if mobj is not None:
2265 return self.url_result(
2266 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2268 # Look for VODPlatform embeds
2270 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2272 if mobj is not None:
2273 return self.url_result(
2274 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2276 # Look for Mangomolo embeds
2278 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2280 video\?.*?\bid=(?P<video_id>\d+)|
2281 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2282 ).+?)\1''', webpage)
2283 if mobj is not None:
2285 '_type': 'url_transparent',
2286 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2287 'title': video_title,
2288 'description': video_description,
2289 'thumbnail': video_thumbnail,
2290 'uploader': video_uploader,
2292 video_id = mobj.group('video_id')
2295 'ie_key': 'MangomoloVideo',
2300 'ie_key': 'MangomoloLive',
2301 'id': mobj.group('channel_id'),
2305 # Look for Instagram embeds
2306 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2307 if instagram_embed_url is not None:
2308 return self.url_result(
2309 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2311 # Look for LiveLeak embeds
2312 liveleak_url = LiveLeakIE._extract_url(webpage)
2314 return self.url_result(liveleak_url, 'LiveLeak')
2316 # Look for 3Q SDN embeds
2317 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2320 '_type': 'url_transparent',
2321 'ie_key': ThreeQSDNIE.ie_key(),
2322 'url': self._proto_relative_url(threeqsdn_url),
2323 'title': video_title,
2324 'description': video_description,
2325 'thumbnail': video_thumbnail,
2326 'uploader': video_uploader,
2329 # Look for VBOX7 embeds
2330 vbox7_url = Vbox7IE._extract_url(webpage)
2332 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2334 # Look for DBTV embeds
2335 dbtv_urls = DBTVIE._extract_urls(webpage)
2337 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2339 # Looking for http://schema.org/VideoObject
2340 json_ld = self._search_json_ld(
2341 webpage, video_id, default={}, expected_type='VideoObject')
2342 if json_ld.get('url'):
2344 'title': video_title or info_dict['title'],
2345 'description': video_description,
2346 'thumbnail': video_thumbnail,
2347 'age_limit': age_limit
2349 info_dict.update(json_ld)
2352 # Look for HTML5 media
2353 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2355 for entry in entries:
2358 'title': video_title,
2360 self._sort_formats(entry['formats'])
2361 return self.playlist_result(entries)
2363 def check_video(vurl):
2364 if YoutubeIE.suitable(vurl):
2366 vpath = compat_urlparse.urlparse(vurl).path
2367 vext = determine_ext(vpath)
2368 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2370 def filter_video(urls):
2371 return list(filter(check_video, urls))
2373 # Start with something easy: JW Player in SWFObject
2374 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2376 # Look for gorilla-vid style embedding
2377 found = filter_video(re.findall(r'''(?sx)
2381 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2384 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2386 # Broaden the search a little bit
2387 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2389 # Broaden the findall a little bit: JWPlayer JS loader
2390 found = filter_video(re.findall(
2391 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2394 found = filter_video(re.findall(r'''(?xs)
2395 flowplayer\("[^"]+",\s*
2397 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2398 ["']?url["']?\s*:\s*["']([^"']+)["']
2403 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2405 # Try to find twitter cards info
2406 # twitter:player:stream should be checked before twitter:player since
2407 # it is expected to contain a raw stream (see
2408 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2409 found = filter_video(re.findall(
2410 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2412 # We look for Open Graph info:
2413 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2414 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2415 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2416 if m_video_type is not None:
2417 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2419 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2421 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2422 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2425 # Look also in Refresh HTTP header
2426 refresh_header = head_response.headers.get('Refresh')
2428 # In python 2 response HTTP headers are bytestrings
2429 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2430 refresh_header = refresh_header.decode('iso-8859-1')
2431 found = re.search(REDIRECT_REGEX, refresh_header)
2433 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2434 self.report_following_redirect(new_url)
2441 # twitter:player is a https URL to iframe player that may or may not
2442 # be supported by youtube-dl thus this is checked the very last (see
2443 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2444 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2446 return self.url_result(embed_url)
2449 raise UnsupportedError(url)
2452 for video_url in orderedSet(found):
2453 video_url = unescapeHTML(video_url)
2454 video_url = video_url.replace('\\/', '/')
2455 video_url = compat_urlparse.urljoin(url, video_url)
2456 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2458 # Sometimes, jwplayer extraction will result in a YouTube URL
2459 if YoutubeIE.suitable(video_url):
2460 entries.append(self.url_result(video_url, 'Youtube'))
2463 # here's a fun little line of code for you:
2464 video_id = os.path.splitext(video_id)[0]
2468 'uploader': video_uploader,
2469 'title': video_title,
2470 'age_limit': age_limit,
2473 ext = determine_ext(video_url)
2475 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2477 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2479 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2481 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2483 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2484 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2485 # Just matching .ism/manifest is not enough to be reliably sure
2486 # whether it's actually an ISM manifest or some other streaming
2487 # manifest since there are various streaming URL formats
2488 # possible (see [1]) as well as some other shenanigans like
2489 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2491 # Thus the most reasonable way to solve this is to delegate
2492 # to generic extractor in order to look into the contents of
2493 # the manifest itself.
2494 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2495 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2496 entry_info_dict = self.url_result(
2497 smuggle_url(video_url, {'to_generic': True}),
2500 entry_info_dict['url'] = video_url
2502 if entry_info_dict.get('formats'):
2503 self._sort_formats(entry_info_dict['formats'])
2505 entries.append(entry_info_dict)
2507 if len(entries) == 1:
2510 for num, e in enumerate(entries, start=1):
2511 # 'url' results don't have a title
2512 if e.get('title') is not None:
2513 e['title'] = '%s (%d)' % (e['title'], num)
2515 '_type': 'playlist',