3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .vimeo import VimeoIE
62 from .dailymotion import (
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
105 from .vshare import VShareIE
108 class GenericIE(InfoExtractor):
109 IE_DESC = 'Generic downloader that works on some sites'
113 # Direct link to a video
115 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
116 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
121 'upload_date': '20100513',
124 # Direct link to media delivered compressed (until Accept-Encoding is *)
126 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
127 'md5': '128c42e68b13950268b648275386fc74',
129 'id': 'FictionJunction-Parallel_Hearts',
131 'title': 'FictionJunction-Parallel_Hearts',
132 'upload_date': '20140522',
134 'expected_warnings': [
135 'URL could be a direct video link, returning it as such.'
137 'skip': 'URL invalid',
139 # Direct download with broken HEAD
141 'url': 'http://ai-radio.org:8000/radio.opus',
148 'skip_download': True, # infinite live stream
150 'expected_warnings': [
151 r'501.*Not Implemented',
155 # Direct link with incorrect MIME type
157 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
158 'md5': '4ccbebe5f36706d85221f204d7eb5913',
160 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
161 'id': '5_Lennart_Poettering_-_Systemd',
163 'title': '5_Lennart_Poettering_-_Systemd',
164 'upload_date': '20141120',
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
172 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
174 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
175 'title': 'Zero Punctuation',
176 'description': 're:.*groundbreaking video review series.*'
178 'playlist_mincount': 11,
180 # RSS feed with enclosure
182 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
184 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 'upload_date': '20150228',
187 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
190 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
192 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
196 'title': 'Automatics, robotics and biocybernetics',
197 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
198 'upload_date': '20130627',
199 'formats': 'mincount:16',
200 'subtitles': 'mincount:1',
203 'force_generic_extractor': True,
204 'skip_download': True,
207 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
209 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
214 'formats': 'mincount:1',
217 'skip_download': True,
220 # SMIL from https://www.restudy.dk/video/play/id/1637
222 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
226 'title': 'video_1637',
227 'formats': 'mincount:3',
230 'skip_download': True,
233 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
235 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
237 'id': 'smil-service',
239 'title': 'smil-service',
240 'formats': 'mincount:1',
243 'skip_download': True,
246 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
248 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
252 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
253 'formats': 'mincount:3',
256 'skip_download': True,
259 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
261 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
263 'id': 'mZlp2ctYIUEB',
265 'title': 'Tikibad ontruimd wegens brand',
266 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
267 'thumbnail': r're:^https?://.*\.jpg$',
271 'skip_download': True,
274 # MPD from http://dash-mse-test.appspot.com/media.html
276 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
277 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
279 'id': 'car-20120827-manifest',
281 'title': 'car-20120827-manifest',
282 'formats': 'mincount:9',
283 'upload_date': '20130904',
286 'format': 'bestvideo',
289 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
291 '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',
296 'formats': 'mincount:8',
300 'skip_download': True,
302 'skip': 'video gone',
304 # m3u8 served with Content-Type: text/plain
306 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
311 'upload_date': '20140720',
312 'formats': 'mincount:11',
316 'skip_download': True,
318 'skip': 'video gone',
322 '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',
326 'upload_date': '20130224',
327 'uploader_id': 'TheVerge',
328 'description': r're:^Chris Ziegler takes a look at the\.*',
329 'uploader': 'The Verge',
330 'title': 'First Firefox OS phones side-by-side',
333 'skip_download': False,
337 # redirect in Refresh HTTP header
338 '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',
342 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
343 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
344 'upload_date': '20150917',
345 'uploader_id': 'brtvofficial',
346 'uploader': 'Boiler Room',
349 'skip_download': False,
353 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
354 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
356 'id': '13601338388002',
358 'uploader': 'www.hodiho.fr',
359 'title': 'R\u00e9gis plante sa Jeep',
362 # bandcamp page with custom domain
364 'add_ie': ['Bandcamp'],
365 'url': 'http://bronyrock.com/track/the-pony-mash',
369 'title': 'The Pony Mash',
370 'uploader': 'M_Pallante',
372 'skip': 'There is a limit of 200 free downloads / month for the test song',
375 # embedded brightcove video
376 # it also tests brightcove videos that need to set the 'Referer'
377 # in the http requests
378 'add_ie': ['BrightcoveLegacy'],
379 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
381 'id': '2765128793001',
383 'title': 'Le cours de bourse : l’analyse technique',
384 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
385 'uploader': 'BFM BUSINESS',
388 'skip_download': True,
392 # embedded with itemprop embedURL and video id spelled as `idVideo`
393 'add_id': ['BrightcoveLegacy'],
394 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
396 'id': '5255628253001',
398 'title': 'md5:37c519b1128915607601e75a87995fc0',
399 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
400 'uploader': 'BFM BUSINESS',
401 'uploader_id': '876450612001',
402 'timestamp': 1482255315,
403 'upload_date': '20161220',
406 'skip_download': True,
410 # https://github.com/rg3/youtube-dl/issues/2253
411 'url': 'http://bcove.me/i6nfkrc3',
412 'md5': '0ba9446db037002366bab3b3eb30c88c',
414 'id': '3101154703001',
416 'title': 'Still no power',
417 'uploader': 'thestar.com',
418 '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.',
420 'add_ie': ['BrightcoveLegacy'],
421 'skip': 'video gone',
424 'url': 'http://www.championat.com/video/football/v/87/87499.html',
425 'md5': 'fb973ecf6e4a78a67453647444222983',
427 'id': '3414141473001',
429 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
430 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
431 'uploader': 'Championat',
435 # https://github.com/rg3/youtube-dl/issues/3541
436 'add_ie': ['BrightcoveLegacy'],
437 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
439 'id': '3866516442001',
441 'title': 'Leer mij vrouwen kennen: Aflevering 1',
442 'description': 'Leer mij vrouwen kennen: Aflevering 1',
443 'uploader': 'SBS Broadcasting',
445 'skip': 'Restricted to Netherlands',
447 'skip_download': True, # m3u8 download
451 # Brightcove video in <iframe>
452 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
453 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
455 'id': '5360463607001',
457 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
458 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
459 'uploader': 'United Nations',
460 'uploader_id': '1362235914001',
461 'timestamp': 1489593889,
462 'upload_date': '20170315',
464 'add_ie': ['BrightcoveLegacy'],
467 # Brightcove with alternative playerID key
468 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
470 'id': 'nmeth.2062_SV1',
471 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
475 'id': '2228375078001',
477 'title': 'nmeth.2062-sv1',
478 'description': 'nmeth.2062-sv1',
479 'timestamp': 1363357591,
480 'upload_date': '20130315',
481 'uploader': 'Nature Publishing Group',
482 'uploader_id': '1964492299001',
487 # Brightcove with UUID in videoPlayer
488 'url': 'http://www8.hp.com/cn/zh/home.html',
490 'id': '5255815316001',
492 'title': 'Sprocket Video - China',
493 'description': 'Sprocket Video - China',
494 'uploader': 'HP-Video Gallery',
495 'timestamp': 1482263210,
496 'upload_date': '20161220',
497 'uploader_id': '1107601872001',
500 'skip_download': True, # m3u8 download
502 'skip': 'video rotates...weekly?',
505 # Brightcove:new type [2].
506 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
507 'md5': '2b35148fcf48da41c9fb4591650784f3',
509 'id': '5348741021001',
511 'upload_date': '20170306',
512 'uploader_id': '4191638492001',
513 'timestamp': 1488769918,
514 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
519 # Alternative brightcove <video> attributes
520 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
522 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
523 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
526 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
528 'id': '5311302538001',
530 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
531 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
532 'timestamp': 1486321708,
533 'upload_date': '20170205',
534 'uploader_id': '800000640001',
536 'only_matching': True,
540 # Brightcove with UUID in videoPlayer
541 'url': 'http://www8.hp.com/cn/zh/home.html',
543 'id': '5255815316001',
545 'title': 'Sprocket Video - China',
546 'description': 'Sprocket Video - China',
547 'uploader': 'HP-Video Gallery',
548 'timestamp': 1482263210,
549 'upload_date': '20161220',
550 'uploader_id': '1107601872001',
553 'skip_download': True, # m3u8 download
558 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
559 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
561 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
563 'title': '2cc213299525360.mov', # that's what we get
566 'add_ie': ['Ooyala'],
569 # ooyala video embedded with http://player.ooyala.com/iframe.js
570 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
572 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
574 'title': '"Steve Jobs: Man in the Machine" trailer',
575 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
579 'skip_download': True,
581 'skip': 'movie expired',
583 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
585 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
587 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
589 'title': 'Steampunk Fest Comes to Honesdale',
593 'skip_download': True,
598 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
602 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
603 'upload_date': '20140225',
604 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
605 'uploader': 'Tested',
606 'uploader_id': 'testedcom',
608 # No need to test YoutubeIE here
610 'skip_download': True,
615 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
619 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
620 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
622 # HEAD requests lead to endless 301, while GET is OK
623 'expected_warnings': ['301'],
627 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
631 'title': 'Охотское море стало целиком российским',
632 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
636 'skip_download': True,
641 '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/',
645 'title': 'Дошкольное воспитание',
650 'url': 'http://www.vestifinance.ru/articles/25753',
653 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
658 'title': 'Госзаказ. День 3',
664 'title': 'Госзаказ. День 2',
670 'title': 'Госзаказ. День 1',
676 'skip_download': True,
681 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
683 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
685 'title': 'Ужастики, русский трейлер (2015)',
686 'thumbnail': r're:^https?://.*\.jpg$',
692 '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',
695 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
697 'playlist_mincount': 7,
698 # This forum does not allow <iframe> syntaxes anymore
699 # Now HTML tags are displayed as-is
700 'skip': 'No videos on this page',
704 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
705 'md5': '65fdff94098e4a607385a60c5177c638',
709 'title': 'Hidden miracles of the natural world',
710 'uploader': 'Louie Schwartzberg',
711 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
714 # nowvideo embed hidden behind percent encoding
716 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
717 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
719 'id': '06e53103ca9aa',
721 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
722 'description': 'No description',
727 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
728 'md5': '7653032cbb25bf6c80d80f217055fa43',
730 'id': '048195-004_PLUS7-F',
733 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
734 'upload_date': '20140320',
737 'skip_download': 'Requires rtmpdump'
739 'skip': 'video gone',
743 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
747 'title': 'Alcaline, le concert avec Calogero',
748 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
749 'upload_date': '20150226',
750 'timestamp': 1424989860,
755 'skip_download': True,
757 'expected_warnings': [
763 'url': 'http://www.wired.com/2014/04/honda-asimo/',
764 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
766 'id': '53501be369702d3275860000',
768 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
773 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
774 'md5': '441aeeb82eb72c422c7f14ec533999cd',
776 'id': 'k2mm4bCdJ6CQ2i7c8o2',
778 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
779 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
781 'uploader_id': 'xgditw',
782 'upload_date': '20140425',
783 'timestamp': 1398441542,
785 'add_ie': ['Dailymotion'],
789 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
793 'title': 'Care worker punches elderly dementia patient in head 11 times',
794 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
796 'add_ie': ['DailyMail'],
798 'skip_download': True,
803 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
807 'title': 'The NBL Auction 2014',
808 'uploader': 'BADMINTON England',
809 'uploader_id': 'BADMINTONEvents',
810 'upload_date': '20140603',
811 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
813 'add_ie': ['Youtube'],
815 'skip_download': True,
820 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
821 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
823 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
825 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
826 'description': 'Two valets share their love for movie star Liam Neesons.',
827 'timestamp': 1349922600,
828 'upload_date': '20121011',
831 # YouTube embed via <data-embed-url="">
833 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
837 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
838 'uploader': 'Gameloft',
839 'uploader_id': 'gameloft',
840 'upload_date': '20140828',
841 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
844 'skip_download': True,
847 # YouTube <object> embed
849 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
850 'md5': '516718101ec834f74318df76259fb3cc',
854 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
855 'upload_date': '20080526',
856 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
857 'uploader': 'Christopher Sykes',
858 'uploader_id': 'ChristopherJSykes',
860 'add_ie': ['Youtube'],
864 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
866 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
868 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
869 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
874 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
876 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
877 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
883 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
888 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
889 'md5': '9d65602bf31c6e20014319c7d07fba27',
891 'id': '5123ea6d5e5a7',
894 'uploader': 'www.handjobhub.com',
895 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
898 # Multiple brightcove videos
899 # https://github.com/rg3/youtube-dl/issues/2283
901 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
903 'id': 'always-never',
904 'title': 'Always / Never - The New Yorker',
908 'extract_flat': False,
909 'skip_download': True,
914 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
915 'md5': '96f09a37e44da40dd083e12d9a683327',
919 'title': 'Ump changes call to ball',
920 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
922 'timestamp': 1401537900,
923 'upload_date': '20140531',
924 'thumbnail': r're:^https?://.*\.jpg$',
929 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
930 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
934 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
935 'description': 'a Paywall Videos video from Remilon',
937 'uploader': 'study.com',
938 'timestamp': 1459678540,
939 'upload_date': '20160403',
940 'filesize': 24687186,
944 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
945 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
949 'title': 'Conversation about Hexagonal Rails Part 1',
950 'description': 'a Martin Fowler video from ThoughtWorks',
952 'uploader': 'thoughtworks.wistia.com',
953 'timestamp': 1401832161,
954 'upload_date': '20140603',
957 # Wistia standard embed (async)
959 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
963 'title': 'Drip Brennan Dunn Workshop',
964 'description': 'a JV Webinars video from getdrip-1',
966 'timestamp': 1463607249,
967 'upload_date': '20160518',
970 'skip_download': True,
975 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
979 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
980 'uploader': 'Sophos Security',
981 'title': 'Chet Chat 171 - Oct 29, 2014',
982 'upload_date': '20141029',
985 # Soundcloud multiple embeds
987 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
990 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
992 'playlist_mincount': 7,
994 # TuneIn station embed
996 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1001 'location': 'Paris, France',
1006 'skip_download': True,
1011 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1015 'upload_date': '20141112',
1016 'title': 'Rosetta #CometLanding webcast HL 10',
1019 # Another Livestream embed, without 'new.' in URL
1021 'url': 'https://www.freespeech.org/',
1025 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1029 'skip_download': True,
1034 'url': 'https://skiplagged.com/',
1037 'title': 'Skiplagged: The smart way to find cheap flights',
1039 'playlist_mincount': 1,
1040 'add_ie': ['Youtube'],
1044 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1048 'upload_date': '20141126',
1049 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1054 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1056 'id': '730m_DandD_1901_512k',
1058 'uploader': 'www.abc.net.au',
1059 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1062 # embedded viddler video
1064 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1068 'uploader': 'deadspin',
1069 'title': 'WALL-TO-GORTAT',
1070 'timestamp': 1422285291,
1071 'upload_date': '20150126',
1073 'add_ie': ['Viddler'],
1077 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1081 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1082 'description': 'md5:601cb790edd05908957dae8aaa866465',
1083 'upload_date': '20150220',
1085 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1089 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1091 'id': 'Mrj4DVp2zeA',
1093 'upload_date': '20150212',
1094 'uploader': 'The National Archives UK',
1095 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1096 'uploader_id': 'NationalArchives08',
1097 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1102 'url': 'http://www.suffolk.edu/sjc/',
1106 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1107 'uploader': 'www.suffolk.edu',
1110 'skip_download': True,
1112 'skip': 'does not contain a video anymore',
1116 'url': 'http://www.indiedb.com/games/king-machine/videos',
1120 'title': 'king machine trailer 1',
1121 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1122 'thumbnail': r're:^https?://.*\.jpg$',
1126 # JWPlayer config passed as variable
1127 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1131 'title': 'ARIELE | Tube Cup',
1132 'uploader': 'www.txxx.com',
1136 'skip_download': True,
1140 # Video.js embed, multiple formats
1141 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1143 'id': 'yygqldloqIk',
1145 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1146 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1147 'upload_date': '20130314',
1148 'uploader': 'PROстое3D',
1149 'uploader_id': 'PROstoe3D',
1152 'skip_download': True,
1156 # Video.js embed, single format
1157 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1161 'title': 'Step 1 - Good Foundation',
1162 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1165 'skip_download': True,
1170 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1171 'playlist_mincount': 5,
1173 'id': 'aanslagen-kopenhagen',
1174 'title': 'Aanslagen Kopenhagen',
1179 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1183 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1186 # Kaltura embed (different embed code)
1188 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1192 'upload_date': '20150127',
1193 'uploader_id': 'PremierMedia',
1195 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1198 # Kaltura embed with single quotes
1200 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1205 'timestamp': 1355743100,
1206 'upload_date': '20121217',
1207 'uploader_id': 'batchUser',
1209 'add_ie': ['Kaltura'],
1212 # Kaltura embedded via quoted entry_id
1213 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1217 'title': '06_matthew_brender_raj_dutt',
1218 'timestamp': 1466638791,
1219 'upload_date': '20160622',
1221 'add_ie': ['Kaltura'],
1222 'expected_warnings': [
1223 'Could not send HEAD request'
1226 'skip_download': True,
1230 # Kaltura embedded, some fileExt broken (#11480)
1231 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1235 'title': 'Our "Standard Models" of particle physics and cosmology',
1236 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1237 'timestamp': 1321158993,
1238 'upload_date': '20111113',
1239 'uploader_id': 'kps1',
1241 'add_ie': ['Kaltura'],
1244 # Kaltura iframe embed
1245 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1246 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1250 'title': 'I. M. Pei: A Centennial Celebration',
1251 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1252 'upload_date': '20170403',
1253 'uploader_id': 'batchUser',
1254 'timestamp': 1491232186,
1256 'add_ie': ['Kaltura'],
1258 # EaglePlatform embed (generic URL)
1260 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1261 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1265 'title': 'Навальный вышел на свободу',
1266 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1267 'thumbnail': r're:^https?://.*\.jpg$',
1273 'skip_download': True,
1276 # referrer protected EaglePlatform embed
1278 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1282 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1283 'thumbnail': r're:^https?://.*\.jpg$',
1288 'skip_download': True,
1291 # ClipYou (EaglePlatform) embed (custom URL)
1293 'url': 'http://muz-tv.ru/play/7129/',
1294 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1298 'title': "'O Sole Mio",
1299 'thumbnail': r're:^https?://.*\.jpg$',
1304 'skip_download': True,
1306 'skip': 'This video is unavailable.',
1310 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1314 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1315 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1316 'thumbnail': r're:^https?://.*\.jpg$',
1320 'skip': 'HTTP Error 404: Not Found',
1324 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1328 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1329 'thumbnail': r're:^https?://.*\.png$',
1335 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1336 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1340 'title': 'Facebook Creates "On This Day" | Crunch Report',
1341 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1342 'timestamp': 1427237531,
1343 'uploader': 'Crunch Report',
1344 'upload_date': '20150324',
1348 'skip_download': True,
1353 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1357 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1362 # Crooks and Liars embed
1364 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1368 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1369 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1370 'timestamp': 1428207000,
1371 'upload_date': '20150405',
1372 'uploader': 'Heather',
1375 # Crooks and Liars external embed
1377 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1379 'id': 'MTE3MjUtMzQ2MzA',
1381 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1382 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1383 'timestamp': 1265032391,
1384 'upload_date': '20100201',
1385 'uploader': 'Heather',
1388 # NBC Sports vplayer embed
1390 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1392 'id': 'ln7x1qSThw4k',
1394 'title': "PFT Live: New leader in the 'new-look' defense",
1395 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1396 'uploader': 'NBCU-SPORTS',
1397 'upload_date': '20140107',
1398 'timestamp': 1389118457,
1400 'skip': 'Invalid Page URL',
1404 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1405 'md5': '1aa589c675898ae6d37a17913cf68d66',
1407 'id': 'x_dtl_oa_LettermanliftPR_160608',
1409 'title': 'David Letterman: A Preview',
1410 '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.',
1411 'upload_date': '20160609',
1412 'timestamp': 1465431544,
1413 'uploader': 'NBCU-NEWS',
1418 'url': 'https://video.udn.com/news/300346',
1419 'md5': 'fd2060e988c326991037b9aff9df21a6',
1423 'title': '中一中男師變性 全校師生力挺',
1424 'thumbnail': r're:^https?://.*\.jpg$',
1428 'skip_download': True,
1430 'expected_warnings': ['Failed to parse JSON Expecting value'],
1434 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1436 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1438 'description': 'Index/Match versus VLOOKUP.',
1439 'title': 'This is what separates the Excel masters from the wannabes',
1440 'duration': 191.933,
1444 'skip_download': True,
1447 # Brightcove URL in single quotes
1449 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1450 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1452 'id': '4255764656001',
1454 'title': 'SN Presents: Russell Martin, World Citizen',
1455 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1456 'uploader': 'Rogers Sportsnet',
1457 'uploader_id': '1704050871',
1458 'upload_date': '20150525',
1459 'timestamp': 1432570283,
1462 # Dailymotion Cloud video
1464 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1465 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1469 'title': 'Sauvons les abeilles ! - Le débat',
1470 'description': 'md5:d9082128b1c5277987825d684939ca26',
1471 'thumbnail': r're:^https?://.*\.jpe?g$',
1472 'timestamp': 1434970506,
1473 'upload_date': '20150622',
1474 'uploader': 'Public Sénat',
1475 'uploader_id': 'xa9gza',
1477 'skip': 'File not found.',
1479 # OnionStudios embed
1481 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1485 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1486 'thumbnail': r're:^https?://.*\.jpe?g$',
1487 'uploader': 'ClickHole',
1488 'uploader_id': 'clickhole',
1493 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1495 'id': '74849a00-85a9-11e1-9660-123139220831',
1497 'title': '#whilewewatch',
1500 # AdobeTVVideo embed
1502 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1503 'md5': '43662b577c018ad707a63766462b1e87',
1507 'title': 'New experience with Acrobat DC',
1508 'description': 'New experience with Acrobat DC',
1509 'duration': 248.667,
1512 # BrightcoveInPageEmbed embed
1514 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1516 'id': '4238694884001',
1518 'title': 'Tabletop: Dread, Last Thoughts',
1519 'description': 'Tabletop: Dread, Last Thoughts',
1523 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1524 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1526 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1528 'id': '4785848093001',
1530 'title': 'The Cardinal Pell Interview',
1531 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1532 'uploader': 'GlobeCast Australia - GlobeStream',
1533 'uploader_id': '2733773828001',
1534 'upload_date': '20160304',
1535 'timestamp': 1457083087,
1539 'skip_download': True,
1543 # Brightcove embed with whitespace around attribute names
1544 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1546 'id': '3167554373001',
1548 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1549 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1550 'uploader_id': '1079349493',
1551 'upload_date': '20140207',
1552 'timestamp': 1391810548,
1555 'skip_download': True,
1558 # Another form of arte.tv embed
1560 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1561 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1563 'id': '030273-562_PLUS7-F',
1565 'title': 'ARTE Reportage - Nulle part, en France',
1566 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1567 'upload_date': '20160409',
1572 'url': 'http://www.wykop.pl/link/3088787/',
1573 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1575 'id': '874_1459135191',
1577 'title': 'Man shows poor quality of new apartment building',
1578 'description': 'The wall is like a sand pile.',
1579 'uploader': 'Lake8737',
1581 'add_ie': [LiveLeakIE.ie_key()],
1583 # Another LiveLeak embed pattern (#13336)
1585 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1587 'id': '2eb_1496309988',
1589 'title': 'Thief robs place where everyone was armed',
1590 'description': 'md5:694d73ee79e535953cf2488562288eee',
1591 'uploader': 'brazilwtf',
1593 'add_ie': [LiveLeakIE.ie_key()],
1595 # Duplicated embedded video URLs
1597 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1599 'id': '149298443_480_16c25b74_2',
1601 'title': 'vs. Blue Orange Spring Game',
1602 'uploader': 'www.hudl.com',
1605 # twitter:player:stream embed
1607 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1611 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1612 'uploader': 'www.rtl.be',
1616 'skip_download': True,
1619 # twitter:player embed
1621 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1622 'md5': 'a3e0df96369831de324f0778e126653c',
1624 'id': '4909620399001',
1626 'title': 'What Do Black Holes Sound Like?',
1627 'description': 'what do black holes sound like',
1628 'upload_date': '20160524',
1629 'uploader_id': '29913724001',
1630 'timestamp': 1464107587,
1631 'uploader': 'TheAtlantic',
1633 'add_ie': ['BrightcoveLegacy'],
1635 # Facebook <iframe> embed
1637 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1638 'md5': 'fbcde74f534176ecb015849146dd3aee',
1640 'id': '599637780109885',
1642 'title': 'Facebook video #599637780109885',
1645 # Facebook <iframe> embed, plugin video
1647 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1649 'id': '1754168231264132',
1651 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1652 'uploader': 'Tariq Ramadan (official)',
1653 'timestamp': 1496758379,
1654 'upload_date': '20170606',
1657 'skip_download': True,
1660 # Facebook API embed
1662 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1663 'md5': 'a47372ee61b39a7b90287094d447d94e',
1665 'id': '10153467542406923',
1667 'title': 'Facebook video #10153467542406923',
1670 # Wordpress "YouTube Video Importer" plugin
1672 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1673 'md5': 'd16797741b560b485194eddda8121b48',
1675 'id': 'HNTXWDXV9Is',
1677 'title': 'Blue Devils Drumline Stanford lot 2016',
1678 'upload_date': '20160627',
1679 'uploader_id': 'GENOCIDE8GENERAL10',
1680 'uploader': 'cylus cyrus',
1684 # video stored on custom kaltura server
1685 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1686 'md5': '537617d06e64dfed891fa1593c4b30cc',
1690 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1691 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1692 'uploader_id': 'videos.expansion@el-mundo.net',
1693 'upload_date': '20150429',
1694 'timestamp': 1430303472,
1696 'add_ie': ['Kaltura'],
1699 # Non-standard Vimeo embed
1700 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1701 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1705 'title': 'Understanding the web - Teaser',
1706 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1707 'upload_date': '20151214',
1708 'uploader': 'OpenClassrooms',
1709 'uploader_id': 'openclassrooms',
1711 'add_ie': ['Vimeo'],
1714 # generic vimeo embed that requires original URL passed as Referer
1715 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1716 'only_matching': True,
1719 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1720 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1722 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1724 'title': 'Big Buck Bunny',
1725 'description': 'Royalty free test video',
1726 'timestamp': 1432816365,
1727 'upload_date': '20150528',
1731 'skip_download': True,
1733 'add_ie': [ArkenaIE.ie_key()],
1736 '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/',
1740 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1743 'skip_download': True,
1745 'add_ie': [Vbox7IE.ie_key()],
1749 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1752 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1754 'playlist_mincount': 3,
1758 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1760 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1761 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1763 'playlist_mincount': 2,
1767 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1771 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1772 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1775 'skip_download': True,
1777 'add_ie': [TwentyMinutenIE.ie_key()],
1781 'url': 'https://en.support.wordpress.com/videopress/',
1785 'title': 'IMG_5786',
1786 'timestamp': 1435711927,
1787 'upload_date': '20150701',
1790 'skip_download': True,
1792 'add_ie': [VideoPressIE.ie_key()],
1796 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1798 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1800 'title': 'Магаззино: Казань 2',
1801 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1802 'uploader': 'Магаззино',
1803 'upload_date': '20170228',
1804 'uploader_id': '996642',
1807 'skip_download': True,
1809 'add_ie': [RutubeIE.ie_key()],
1812 # ThePlatform embedded with whitespaces in URLs
1813 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1814 'only_matching': True,
1817 # Senate ISVP iframe https
1818 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1819 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1821 'id': 'govtaff020316',
1823 'title': 'Integrated Senate Video Player',
1825 'add_ie': [SenateISVPIE.ie_key()],
1828 # Limelight embeds (1 channel embed + 4 media embeds)
1829 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1831 'id': 'FacilitatorTraining2017',
1832 'title': 'Facilitator Training 2017',
1834 'playlist_mincount': 5,
1837 # Limelight embed (LimelightPlayerUtil.embed)
1838 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1840 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1842 'title': '07448641',
1843 'timestamp': 1499890639,
1844 'upload_date': '20170712',
1847 'skip_download': True,
1849 'add_ie': ['LimelightMedia'],
1852 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1854 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1855 'title': 'Standoff with Walnut Creek murder suspect ends',
1856 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1858 'playlist_mincount': 4,
1861 # WashingtonPost embed
1862 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1864 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1866 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1867 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1868 'timestamp': 1455216756,
1869 'uploader': 'The Washington Post',
1870 'upload_date': '20160211',
1872 'add_ie': [WashingtonPostIE.ie_key()],
1876 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1880 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1883 'skip_download': True,
1885 'add_ie': [MediasetIE.ie_key()],
1889 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1891 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1892 'title': 'Slovenskom sa prehnala vlna silných búrok',
1894 'playlist_mincount': 5,
1895 'add_ie': [JojIE.ie_key()],
1898 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1899 'url': 'https://tvrain.ru/amp/418921/',
1900 'md5': 'cc00413936695987e8de148b67d14f1d',
1904 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1909 'url': 'http://help.vzaar.com/article/165-embedding-video',
1910 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1914 'title': 'Building A Business Online: Principal Chairs Q & A',
1918 # multiple HTML5 videos on one page
1919 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1921 'id': 'keyscenarios',
1922 'title': 'Rescue Kit 14 Free Edition - Getting started',
1924 'playlist_count': 4,
1928 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1929 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1932 'title': 'vl14062007715967',
1937 # # TODO: find another test
1938 # # http://schema.org/VideoObject
1939 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1940 # 'md5': '888dcf08b7ea671381f00fab74692755',
1942 # 'id': 'nyvTSJMKId',
1944 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1945 # 'description': '#love for cats.',
1946 # 'timestamp': 1461244995,
1947 # 'upload_date': '20160421',
1950 # 'force_generic_extractor': True,
1955 def report_following_redirect(self, new_url):
1956 """Report information extraction."""
1957 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1959 def _extract_rss(self, url, video_id, doc):
1960 playlist_title = doc.find('./channel/title').text
1961 playlist_desc_el = doc.find('./channel/description')
1962 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1965 for it in doc.findall('./channel/item'):
1966 next_url = xpath_text(it, 'link', fatal=False)
1968 enclosure_nodes = it.findall('./enclosure')
1969 for e in enclosure_nodes:
1970 next_url = e.attrib.get('url')
1978 '_type': 'url_transparent',
1980 'title': it.find('title').text,
1984 '_type': 'playlist',
1986 'title': playlist_title,
1987 'description': playlist_desc,
1991 def _extract_camtasia(self, url, video_id, webpage):
1992 """ Returns None if no camtasia video can be found. """
1994 camtasia_cfg = self._search_regex(
1995 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1996 webpage, 'camtasia configuration file', default=None)
1997 if camtasia_cfg is None:
2000 title = self._html_search_meta('DC.title', webpage, fatal=True)
2002 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2003 camtasia_cfg = self._download_xml(
2004 camtasia_url, video_id,
2005 note='Downloading camtasia configuration',
2006 errnote='Failed to download camtasia configuration')
2007 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2010 for n in fileset_node.getchildren():
2011 url_n = n.find('./uri')
2016 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2017 'title': '%s - %s' % (title, n.tag),
2018 'url': compat_urlparse.urljoin(url, url_n.text),
2019 'duration': float_or_none(n.find('./duration').text),
2023 '_type': 'playlist',
2028 def _real_extract(self, url):
2029 if url.startswith('//'):
2032 'url': self.http_scheme() + url,
2035 parsed_url = compat_urlparse.urlparse(url)
2036 if not parsed_url.scheme:
2037 default_search = self._downloader.params.get('default_search')
2038 if default_search is None:
2039 default_search = 'fixup_error'
2041 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2043 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2044 return self.url_result('http://' + url)
2045 elif default_search != 'fixup_error':
2046 if default_search == 'auto_warning':
2047 if re.match(r'^(?:url|URL)$', url):
2048 raise ExtractorError(
2049 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2052 self._downloader.report_warning(
2053 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2054 return self.url_result('ytsearch:' + url)
2056 if default_search in ('error', 'fixup_error'):
2057 raise ExtractorError(
2058 '%r is not a valid URL. '
2059 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2060 % (url, url), expected=True)
2062 if ':' not in default_search:
2063 default_search += ':'
2064 return self.url_result(default_search + url)
2066 url, smuggled_data = unsmuggle_url(url)
2067 force_videoid = None
2068 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2069 if smuggled_data and 'force_videoid' in smuggled_data:
2070 force_videoid = smuggled_data['force_videoid']
2071 video_id = force_videoid
2073 video_id = self._generic_id(url)
2075 self.to_screen('%s: Requesting header' % video_id)
2077 head_req = HEADRequest(url)
2078 head_response = self._request_webpage(
2080 note=False, errnote='Could not send HEAD request to %s' % url,
2083 if head_response is not False:
2084 # Check for redirect
2085 new_url = compat_str(head_response.geturl())
2087 self.report_following_redirect(new_url)
2089 new_url = smuggle_url(
2090 new_url, {'force_videoid': force_videoid})
2091 return self.url_result(new_url)
2093 full_response = None
2094 if head_response is False:
2095 request = sanitized_Request(url)
2096 request.add_header('Accept-Encoding', '*')
2097 full_response = self._request_webpage(request, video_id)
2098 head_response = full_response
2102 'title': self._generic_title(url),
2103 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2106 # Check for direct link to a video
2107 content_type = head_response.headers.get('Content-Type', '').lower()
2108 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2110 format_id = compat_str(m.group('format_id'))
2111 if format_id.endswith('mpegurl'):
2112 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2113 elif format_id == 'f4m':
2114 formats = self._extract_f4m_formats(url, video_id)
2117 'format_id': format_id,
2119 'vcodec': 'none' if m.group('type') == 'audio' else None
2121 info_dict['direct'] = True
2122 self._sort_formats(formats)
2123 info_dict['formats'] = formats
2126 if not self._downloader.params.get('test', False) and not is_intentional:
2127 force = self._downloader.params.get('force_generic_extractor', False)
2128 self._downloader.report_warning(
2129 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2131 if not full_response:
2132 request = sanitized_Request(url)
2133 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2134 # making it impossible to download only chunk of the file (yet we need only 512kB to
2135 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2136 # that will always result in downloading the whole file that is not desirable.
2137 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2138 # to accept raw bytes and being able to download only a chunk.
2139 # It may probably better to solve this by checking Content-Type for application/octet-stream
2140 # after HEAD request finishes, but not sure if we can rely on this.
2141 request.add_header('Accept-Encoding', '*')
2142 full_response = self._request_webpage(request, video_id)
2144 first_bytes = full_response.read(512)
2146 # Is it an M3U playlist?
2147 if first_bytes.startswith(b'#EXTM3U'):
2148 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2149 self._sort_formats(info_dict['formats'])
2152 # Maybe it's a direct link to a video?
2153 # Be careful not to download the whole thing!
2154 if not is_html(first_bytes):
2155 self._downloader.report_warning(
2156 'URL could be a direct video link, returning it as such.')
2163 webpage = self._webpage_read_content(
2164 full_response, url, video_id, prefix=first_bytes)
2166 self.report_extraction(video_id)
2168 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2170 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2171 if doc.tag == 'rss':
2172 return self._extract_rss(url, video_id, doc)
2173 elif doc.tag == 'SmoothStreamingMedia':
2174 info_dict['formats'] = self._parse_ism_formats(doc, url)
2175 self._sort_formats(info_dict['formats'])
2177 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2178 smil = self._parse_smil(doc, url, video_id)
2179 self._sort_formats(smil['formats'])
2181 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2182 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2183 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2184 info_dict['formats'] = self._parse_mpd_formats(
2186 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2188 self._sort_formats(info_dict['formats'])
2190 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2191 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2192 self._sort_formats(info_dict['formats'])
2194 except compat_xml_parse_error:
2197 # Is it a Camtasia project?
2198 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2199 if camtasia_res is not None:
2202 # Sometimes embedded video player is hidden behind percent encoding
2203 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2204 # Unescaping the whole page allows to handle those cases in a generic way
2205 webpage = compat_urllib_parse_unquote(webpage)
2207 # it's tempting to parse this further, but you would
2208 # have to take into account all the variations like
2209 # Video Title - Site Name
2210 # Site Name | Video Title
2211 # Video Title - Tagline | Site Name
2212 # and so on and so forth; it's just not practical
2213 video_title = self._og_search_title(
2214 webpage, default=None) or self._html_search_regex(
2215 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2218 # Try to detect age limit automatically
2219 age_limit = self._rta_search(webpage)
2220 # And then there are the jokers who advertise that they use RTA,
2221 # but actually don't.
2222 AGE_LIMIT_MARKERS = [
2223 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2225 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2228 # video uploader is domain name
2229 video_uploader = self._search_regex(
2230 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2232 video_description = self._og_search_description(webpage, default=None)
2233 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2236 'title': video_title,
2237 'description': video_description,
2238 'thumbnail': video_thumbnail,
2239 'age_limit': age_limit,
2242 # Look for Brightcove Legacy Studio embeds
2243 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2247 'url': smuggle_url(bc_url, {'Referer': url}),
2248 'ie_key': 'BrightcoveLegacy'
2249 } for bc_url in bc_urls]
2252 '_type': 'playlist',
2253 'title': video_title,
2258 # Look for Brightcove New Studio embeds
2259 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2261 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2263 # Look for Nexx embeds
2264 nexx_urls = NexxIE._extract_urls(webpage)
2266 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2268 # Look for Nexx iFrame embeds
2269 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2271 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2273 # Look for ThePlatform embeds
2274 tp_urls = ThePlatformIE._extract_urls(webpage)
2276 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2278 # Look for Vessel embeds
2279 vessel_urls = VesselIE._extract_urls(webpage)
2281 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2283 # Look for embedded rtl.nl player
2284 matches = re.findall(
2285 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2288 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2290 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2292 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2294 vid_me_embed_url = self._search_regex(
2295 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2296 webpage, 'vid.me embed', default=None)
2297 if vid_me_embed_url is not None:
2298 return self.url_result(vid_me_embed_url, 'Vidme')
2300 # Look for YouTube embeds
2301 youtube_urls = YoutubeIE._extract_urls(webpage)
2303 return self.playlist_from_matches(
2304 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2306 matches = DailymotionIE._extract_urls(webpage)
2308 return self.playlist_from_matches(matches, video_id, video_title)
2310 # Look for embedded Dailymotion playlist player (#3822)
2312 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2314 playlists = re.findall(
2315 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2317 return self.playlist_from_matches(
2318 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2320 # Look for DailyMail embeds
2321 dailymail_urls = DailyMailIE._extract_urls(webpage)
2323 return self.playlist_from_matches(
2324 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2326 # Look for embedded Wistia player
2327 wistia_url = WistiaIE._extract_url(webpage)
2330 '_type': 'url_transparent',
2331 'url': self._proto_relative_url(wistia_url),
2332 'ie_key': WistiaIE.ie_key(),
2333 'uploader': video_uploader,
2336 # Look for SVT player
2337 svt_url = SVTIE._extract_url(webpage)
2339 return self.url_result(svt_url, 'SVT')
2341 # Look for Bandcamp pages with custom domain
2342 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2343 if mobj is not None:
2344 burl = unescapeHTML(mobj.group(1))
2345 # Don't set the extractor because it can be a track url or an album
2346 return self.url_result(burl)
2348 # Look for embedded Vevo player
2350 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2351 if mobj is not None:
2352 return self.url_result(mobj.group('url'))
2354 # Look for embedded Viddler player
2356 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2358 if mobj is not None:
2359 return self.url_result(mobj.group('url'))
2361 # Look for NYTimes player
2363 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2365 if mobj is not None:
2366 return self.url_result(mobj.group('url'))
2368 # Look for Libsyn player
2370 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2371 if mobj is not None:
2372 return self.url_result(mobj.group('url'))
2374 # Look for Ooyala videos
2375 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2376 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2377 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2378 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2379 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2380 if mobj is not None:
2381 embed_token = self._search_regex(
2382 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2383 webpage, 'ooyala embed token', default=None)
2384 return OoyalaIE._build_url_result(smuggle_url(
2387 'embed_token': embed_token,
2390 # Look for multiple Ooyala embeds on SBN network websites
2391 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2392 if mobj is not None:
2393 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2395 return self.playlist_from_matches(
2396 embeds, video_id, video_title,
2397 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2399 # Look for Aparat videos
2400 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2401 if mobj is not None:
2402 return self.url_result(mobj.group(1), 'Aparat')
2404 # Look for MPORA videos
2405 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2406 if mobj is not None:
2407 return self.url_result(mobj.group(1), 'Mpora')
2409 # Look for embedded NovaMov-based player
2411 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2412 (?P<url>http://(?:(?:embed|www)\.)?
2414 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2415 videoweed\.(?:es|com)|
2416 movshare\.(?:net|sx|ag)|
2417 divxstage\.(?:eu|net|ch|co|at|ag))
2418 /embed\.php.+?)\1''', webpage)
2419 if mobj is not None:
2420 return self.url_result(mobj.group('url'))
2422 # Look for embedded Facebook player
2423 facebook_urls = FacebookIE._extract_urls(webpage)
2425 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2427 # Look for embedded VK player
2428 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2429 if mobj is not None:
2430 return self.url_result(mobj.group('url'), 'VK')
2432 # Look for embedded Odnoklassniki player
2433 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2434 if mobj is not None:
2435 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2437 # Look for embedded ivi player
2438 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2439 if mobj is not None:
2440 return self.url_result(mobj.group('url'), 'Ivi')
2442 # Look for embedded Huffington Post player
2444 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2445 if mobj is not None:
2446 return self.url_result(mobj.group('url'), 'HuffPost')
2449 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2450 if mobj is not None:
2451 return self.url_result(mobj.group('url'))
2452 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2453 if mobj is not None:
2454 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2456 # Look for funnyordie embed
2457 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2459 return self.playlist_from_matches(
2460 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2462 # Look for BBC iPlayer embed
2463 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2465 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2467 # Look for embedded RUTV player
2468 rutv_url = RUTVIE._extract_url(webpage)
2470 return self.url_result(rutv_url, 'RUTV')
2472 # Look for embedded TVC player
2473 tvc_url = TVCIE._extract_url(webpage)
2475 return self.url_result(tvc_url, 'TVC')
2477 # Look for embedded SportBox player
2478 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2480 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2482 # Look for embedded XHamster player
2483 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2485 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2487 # Look for embedded TNAFlixNetwork player
2488 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2490 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2492 # Look for embedded PornHub player
2493 pornhub_urls = PornHubIE._extract_urls(webpage)
2495 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2497 # Look for embedded DrTuber player
2498 drtuber_urls = DrTuberIE._extract_urls(webpage)
2500 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2502 # Look for embedded RedTube player
2503 redtube_urls = RedTubeIE._extract_urls(webpage)
2505 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2507 # Look for embedded Tvigle player
2509 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2510 if mobj is not None:
2511 return self.url_result(mobj.group('url'), 'Tvigle')
2513 # Look for embedded TED player
2515 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2516 if mobj is not None:
2517 return self.url_result(mobj.group('url'), 'TED')
2519 # Look for embedded Ustream videos
2520 ustream_url = UstreamIE._extract_url(webpage)
2522 return self.url_result(ustream_url, UstreamIE.ie_key())
2524 # Look for embedded arte.tv player
2526 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2531 # Look for embedded francetv player
2533 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2535 if mobj is not None:
2536 return self.url_result(mobj.group('url'))
2538 # Look for embedded smotri.com player
2539 smotri_url = SmotriIE._extract_url(webpage)
2541 return self.url_result(smotri_url, 'Smotri')
2543 # Look for embedded Myvi.ru player
2544 myvi_url = MyviIE._extract_url(webpage)
2546 return self.url_result(myvi_url)
2548 # Look for embedded soundcloud player
2549 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2551 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2553 # Look for tunein player
2554 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2556 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2558 # Look for embedded mtvservices player
2559 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2561 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2563 # Look for embedded yahoo player
2565 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2567 if mobj is not None:
2568 return self.url_result(mobj.group('url'), 'Yahoo')
2570 # Look for embedded sbs.com.au player
2574 <meta\s+property="og:video"\s+content=|
2577 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2579 if mobj is not None:
2580 return self.url_result(mobj.group('url'), 'SBS')
2582 # Look for embedded Cinchcast player
2584 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2586 if mobj is not None:
2587 return self.url_result(mobj.group('url'), 'Cinchcast')
2590 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2594 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2596 if mobj is not None:
2597 return self.url_result(mobj.group('url'), 'MLB')
2600 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2602 if mobj is not None:
2603 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2606 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2608 if mobj is not None:
2609 return self.url_result(mobj.group('url'), 'Livestream')
2611 # Look for Zapiks embed
2613 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2614 if mobj is not None:
2615 return self.url_result(mobj.group('url'), 'Zapiks')
2617 # Look for Kaltura embeds
2618 kaltura_url = KalturaIE._extract_url(webpage)
2620 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2622 # Look for EaglePlatform embeds
2623 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2624 if eagleplatform_url:
2625 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2627 # Look for ClipYou (uses EaglePlatform) embeds
2629 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2630 if mobj is not None:
2631 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2633 # Look for Pladform embeds
2634 pladform_url = PladformIE._extract_url(webpage)
2636 return self.url_result(pladform_url)
2638 # Look for Videomore embeds
2639 videomore_url = VideomoreIE._extract_url(webpage)
2641 return self.url_result(videomore_url)
2643 # Look for Webcaster embeds
2644 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2646 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2648 # Look for Playwire embeds
2650 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2651 if mobj is not None:
2652 return self.url_result(mobj.group('url'))
2654 # Look for 5min embeds
2656 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2657 if mobj is not None:
2658 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2660 # Look for Crooks and Liars embeds
2662 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2663 if mobj is not None:
2664 return self.url_result(mobj.group('url'))
2666 # Look for NBC Sports VPlayer embeds
2667 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2669 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2671 # Look for NBC News embeds
2672 nbc_news_embed_url = re.search(
2673 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2674 if nbc_news_embed_url:
2675 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2677 # Look for Google Drive embeds
2678 google_drive_url = GoogleDriveIE._extract_url(webpage)
2679 if google_drive_url:
2680 return self.url_result(google_drive_url, 'GoogleDrive')
2682 # Look for UDN embeds
2684 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2685 if mobj is not None:
2686 return self.url_result(
2687 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2689 # Look for Senate ISVP iframe
2690 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2692 return self.url_result(senate_isvp_url, 'SenateISVP')
2694 # Look for Dailymotion Cloud videos
2695 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2697 return self.url_result(dmcloud_url, 'DailymotionCloud')
2699 # Look for OnionStudios embeds
2700 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2701 if onionstudios_url:
2702 return self.url_result(onionstudios_url)
2704 # Look for ViewLift embeds
2705 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2707 return self.url_result(viewlift_url)
2709 # Look for JWPlatform embeds
2710 jwplatform_url = JWPlatformIE._extract_url(webpage)
2712 return self.url_result(jwplatform_url, 'JWPlatform')
2714 # Look for Digiteka embeds
2715 digiteka_url = DigitekaIE._extract_url(webpage)
2717 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2719 # Look for Arkena embeds
2720 arkena_url = ArkenaIE._extract_url(webpage)
2722 return self.url_result(arkena_url, ArkenaIE.ie_key())
2724 # Look for Piksel embeds
2725 piksel_url = PikselIE._extract_url(webpage)
2727 return self.url_result(piksel_url, PikselIE.ie_key())
2729 # Look for Limelight embeds
2730 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2732 return self.playlist_result(
2733 limelight_urls, video_id, video_title, video_description)
2735 # Look for Anvato embeds
2736 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2738 return self.playlist_result(
2739 anvato_urls, video_id, video_title, video_description)
2741 # Look for AdobeTVVideo embeds
2743 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2745 if mobj is not None:
2746 return self.url_result(
2747 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2750 # Look for Vine embeds
2752 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2754 if mobj is not None:
2755 return self.url_result(
2756 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2758 # Look for VODPlatform embeds
2760 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2762 if mobj is not None:
2763 return self.url_result(
2764 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2766 # Look for Mangomolo embeds
2768 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2770 video\?.*?\bid=(?P<video_id>\d+)|
2771 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2772 ).+?)\1''', webpage)
2773 if mobj is not None:
2775 '_type': 'url_transparent',
2776 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2777 'title': video_title,
2778 'description': video_description,
2779 'thumbnail': video_thumbnail,
2780 'uploader': video_uploader,
2782 video_id = mobj.group('video_id')
2785 'ie_key': 'MangomoloVideo',
2790 'ie_key': 'MangomoloLive',
2791 'id': mobj.group('channel_id'),
2795 # Look for Instagram embeds
2796 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2797 if instagram_embed_url is not None:
2798 return self.url_result(
2799 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2801 # Look for LiveLeak embeds
2802 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2804 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2806 # Look for 3Q SDN embeds
2807 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2810 '_type': 'url_transparent',
2811 'ie_key': ThreeQSDNIE.ie_key(),
2812 'url': self._proto_relative_url(threeqsdn_url),
2813 'title': video_title,
2814 'description': video_description,
2815 'thumbnail': video_thumbnail,
2816 'uploader': video_uploader,
2819 # Look for VBOX7 embeds
2820 vbox7_url = Vbox7IE._extract_url(webpage)
2822 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2824 # Look for DBTV embeds
2825 dbtv_urls = DBTVIE._extract_urls(webpage)
2827 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2829 # Look for Videa embeds
2830 videa_urls = VideaIE._extract_urls(webpage)
2832 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2834 # Look for 20 minuten embeds
2835 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2837 return self.playlist_from_matches(
2838 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2840 # Look for Openload embeds
2841 openload_urls = OpenloadIE._extract_urls(webpage)
2843 return self.playlist_from_matches(
2844 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2846 # Look for VideoPress embeds
2847 videopress_urls = VideoPressIE._extract_urls(webpage)
2849 return self.playlist_from_matches(
2850 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2852 # Look for Rutube embeds
2853 rutube_urls = RutubeIE._extract_urls(webpage)
2855 return self.playlist_from_matches(
2856 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2858 # Look for WashingtonPost embeds
2859 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2861 return self.playlist_from_matches(
2862 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2864 # Look for Mediaset embeds
2865 mediaset_urls = MediasetIE._extract_urls(webpage)
2867 return self.playlist_from_matches(
2868 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2870 # Look for JOJ.sk embeds
2871 joj_urls = JojIE._extract_urls(webpage)
2873 return self.playlist_from_matches(
2874 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2876 # Look for megaphone.fm embeds
2877 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2879 return self.playlist_from_matches(
2880 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2882 # Look for vzaar embeds
2883 vzaar_urls = VzaarIE._extract_urls(webpage)
2885 return self.playlist_from_matches(
2886 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2888 channel9_urls = Channel9IE._extract_urls(webpage)
2890 return self.playlist_from_matches(
2891 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2893 vshare_urls = VShareIE._extract_urls(webpage)
2895 return self.playlist_from_matches(
2896 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2898 def merge_dicts(dict1, dict2):
2900 for k, v in dict1.items():
2903 for k, v in dict2.items():
2906 if (k not in merged or
2907 (isinstance(v, compat_str) and v and
2908 isinstance(merged[k], compat_str) and
2913 # Look for HTML5 media
2914 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2916 if len(entries) == 1:
2919 'title': video_title,
2922 for num, entry in enumerate(entries, start=1):
2924 'id': '%s-%s' % (video_id, num),
2925 'title': '%s (%d)' % (video_title, num),
2927 for entry in entries:
2928 self._sort_formats(entry['formats'])
2929 return self.playlist_result(entries, video_id, video_title)
2931 jwplayer_data = self._find_jwplayer_data(
2932 webpage, video_id, transform_source=js_to_json)
2934 info = self._parse_jwplayer_data(
2935 jwplayer_data, video_id, require_title=False, base_url=url)
2936 return merge_dicts(info, info_dict)
2940 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2942 if mobj is not None:
2943 sources = self._parse_json(
2944 mobj.group(1), video_id, transform_source=js_to_json,
2946 if not isinstance(sources, list):
2949 for source in sources:
2950 src = source.get('src')
2951 if not src or not isinstance(src, compat_str):
2953 src = compat_urlparse.urljoin(url, src)
2954 src_type = source.get('type')
2955 if isinstance(src_type, compat_str):
2956 src_type = src_type.lower()
2957 ext = determine_ext(src).lower()
2958 if src_type == 'video/youtube':
2959 return self.url_result(src, YoutubeIE.ie_key())
2960 if src_type == 'application/dash+xml' or ext == 'mpd':
2961 formats.extend(self._extract_mpd_formats(
2962 src, video_id, mpd_id='dash', fatal=False))
2963 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2964 formats.extend(self._extract_m3u8_formats(
2965 src, video_id, 'mp4', entry_protocol='m3u8_native',
2966 m3u8_id='hls', fatal=False))
2970 'ext': (mimetype2ext(src_type) or
2971 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2974 self._sort_formats(formats)
2975 info_dict['formats'] = formats
2978 # Looking for http://schema.org/VideoObject
2979 json_ld = self._search_json_ld(
2980 webpage, video_id, default={}, expected_type='VideoObject')
2981 if json_ld.get('url'):
2982 return merge_dicts(json_ld, info_dict)
2984 def check_video(vurl):
2985 if YoutubeIE.suitable(vurl):
2987 if RtmpIE.suitable(vurl):
2989 vpath = compat_urlparse.urlparse(vurl).path
2990 vext = determine_ext(vpath)
2991 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2993 def filter_video(urls):
2994 return list(filter(check_video, urls))
2996 # Start with something easy: JW Player in SWFObject
2997 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2999 # Look for gorilla-vid style embedding
3000 found = filter_video(re.findall(r'''(?sx)
3004 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3007 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3009 # Broaden the search a little bit
3010 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3012 # Broaden the findall a little bit: JWPlayer JS loader
3013 found = filter_video(re.findall(
3014 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3017 found = filter_video(re.findall(r'''(?xs)
3018 flowplayer\("[^"]+",\s*
3020 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3021 ["']?url["']?\s*:\s*["']([^"']+)["']
3026 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3028 # Try to find twitter cards info
3029 # twitter:player:stream should be checked before twitter:player since
3030 # it is expected to contain a raw stream (see
3031 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3032 found = filter_video(re.findall(
3033 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3035 # We look for Open Graph info:
3036 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3037 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3038 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3039 if m_video_type is not None:
3040 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3042 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3044 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3045 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3048 # Look also in Refresh HTTP header
3049 refresh_header = head_response.headers.get('Refresh')
3051 # In python 2 response HTTP headers are bytestrings
3052 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3053 refresh_header = refresh_header.decode('iso-8859-1')
3054 found = re.search(REDIRECT_REGEX, refresh_header)
3056 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3058 self.report_following_redirect(new_url)
3067 # twitter:player is a https URL to iframe player that may or may not
3068 # be supported by youtube-dl thus this is checked the very last (see
3069 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3070 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3071 if embed_url and embed_url != url:
3072 return self.url_result(embed_url)
3075 raise UnsupportedError(url)
3078 for video_url in orderedSet(found):
3079 video_url = unescapeHTML(video_url)
3080 video_url = video_url.replace('\\/', '/')
3081 video_url = compat_urlparse.urljoin(url, video_url)
3082 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3084 # Sometimes, jwplayer extraction will result in a YouTube URL
3085 if YoutubeIE.suitable(video_url):
3086 entries.append(self.url_result(video_url, 'Youtube'))
3089 # here's a fun little line of code for you:
3090 video_id = os.path.splitext(video_id)[0]
3094 'uploader': video_uploader,
3095 'title': video_title,
3096 'age_limit': age_limit,
3099 if RtmpIE.suitable(video_url):
3100 entry_info_dict.update({
3101 '_type': 'url_transparent',
3102 'ie_key': RtmpIE.ie_key(),
3105 entries.append(entry_info_dict)
3108 ext = determine_ext(video_url)
3110 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3112 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3114 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3116 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3118 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3119 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3120 # Just matching .ism/manifest is not enough to be reliably sure
3121 # whether it's actually an ISM manifest or some other streaming
3122 # manifest since there are various streaming URL formats
3123 # possible (see [1]) as well as some other shenanigans like
3124 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3126 # Thus the most reasonable way to solve this is to delegate
3127 # to generic extractor in order to look into the contents of
3128 # the manifest itself.
3129 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3130 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3131 entry_info_dict = self.url_result(
3132 smuggle_url(video_url, {'to_generic': True}),
3135 entry_info_dict['url'] = video_url
3137 if entry_info_dict.get('formats'):
3138 self._sort_formats(entry_info_dict['formats'])
3140 entries.append(entry_info_dict)
3142 if len(entries) == 1:
3145 for num, e in enumerate(entries, start=1):
3146 # 'url' results don't have a title
3147 if e.get('title') is not None:
3148 e['title'] = '%s (%d)' % (e['title'], num)
3150 '_type': 'playlist',