3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
43 from .nbc import NBCSportsVPlayerIE
44 from .ooyala import OoyalaIE
45 from .rutv import RUTVIE
46 from .tvc import TVCIE
47 from .sportbox import SportBoxEmbedIE
48 from .smotri import SmotriIE
49 from .myvi import MyviIE
50 from .condenast import CondeNastIE
51 from .udn import UDNEmbedIE
52 from .senateisvp import SenateISVPIE
53 from .svt import SVTIE
54 from .pornhub import PornHubIE
55 from .xhamster import XHamsterEmbedIE
56 from .tnaflix import TNAFlixNetworkEmbedIE
57 from .drtuber import DrTuberIE
58 from .redtube import RedTubeIE
59 from .vimeo import VimeoIE
60 from .dailymotion import (
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
101 from .vzaar import VzaarIE
104 class GenericIE(InfoExtractor):
105 IE_DESC = 'Generic downloader that works on some sites'
109 # Direct link to a video
111 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
112 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
117 'upload_date': '20100513',
120 # Direct link to media delivered compressed (until Accept-Encoding is *)
122 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
123 'md5': '128c42e68b13950268b648275386fc74',
125 'id': 'FictionJunction-Parallel_Hearts',
127 'title': 'FictionJunction-Parallel_Hearts',
128 'upload_date': '20140522',
130 'expected_warnings': [
131 'URL could be a direct video link, returning it as such.'
133 'skip': 'URL invalid',
135 # Direct download with broken HEAD
137 'url': 'http://ai-radio.org:8000/radio.opus',
144 'skip_download': True, # infinite live stream
146 'expected_warnings': [
147 r'501.*Not Implemented',
151 # Direct link with incorrect MIME type
153 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
154 'md5': '4ccbebe5f36706d85221f204d7eb5913',
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'id': '5_Lennart_Poettering_-_Systemd',
159 'title': '5_Lennart_Poettering_-_Systemd',
160 'upload_date': '20141120',
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
168 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
170 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'title': 'Zero Punctuation',
172 'description': 're:.*groundbreaking video review series.*'
174 'playlist_mincount': 11,
176 # RSS feed with enclosure
178 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
180 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
182 'upload_date': '20150228',
183 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
188 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
192 'title': 'Automatics, robotics and biocybernetics',
193 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
194 'upload_date': '20130627',
195 'formats': 'mincount:16',
196 'subtitles': 'mincount:1',
199 'force_generic_extractor': True,
200 'skip_download': True,
203 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
205 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
210 'formats': 'mincount:1',
213 'skip_download': True,
216 # SMIL from https://www.restudy.dk/video/play/id/1637
218 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
222 'title': 'video_1637',
223 'formats': 'mincount:3',
226 'skip_download': True,
229 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
231 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
233 'id': 'smil-service',
235 'title': 'smil-service',
236 'formats': 'mincount:1',
239 'skip_download': True,
242 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
244 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
248 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
249 'formats': 'mincount:3',
252 'skip_download': True,
255 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
257 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
259 'id': 'mZlp2ctYIUEB',
261 'title': 'Tikibad ontruimd wegens brand',
262 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
263 'thumbnail': r're:^https?://.*\.jpg$',
267 'skip_download': True,
270 # MPD from http://dash-mse-test.appspot.com/media.html
272 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
273 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
275 'id': 'car-20120827-manifest',
277 'title': 'car-20120827-manifest',
278 'formats': 'mincount:9',
279 'upload_date': '20130904',
282 'format': 'bestvideo',
285 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
287 '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',
292 'formats': 'mincount:8',
296 'skip_download': True,
298 'skip': 'video gone',
300 # m3u8 served with Content-Type: text/plain
302 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
307 'upload_date': '20140720',
308 'formats': 'mincount:11',
312 'skip_download': True,
314 'skip': 'video gone',
318 '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',
322 'upload_date': '20130224',
323 'uploader_id': 'TheVerge',
324 'description': r're:^Chris Ziegler takes a look at the\.*',
325 'uploader': 'The Verge',
326 'title': 'First Firefox OS phones side-by-side',
329 'skip_download': False,
333 # redirect in Refresh HTTP header
334 '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',
338 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
339 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
340 'upload_date': '20150917',
341 'uploader_id': 'brtvofficial',
342 'uploader': 'Boiler Room',
345 'skip_download': False,
349 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
350 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
352 'id': '13601338388002',
354 'uploader': 'www.hodiho.fr',
355 'title': 'R\u00e9gis plante sa Jeep',
358 # bandcamp page with custom domain
360 'add_ie': ['Bandcamp'],
361 'url': 'http://bronyrock.com/track/the-pony-mash',
365 'title': 'The Pony Mash',
366 'uploader': 'M_Pallante',
368 'skip': 'There is a limit of 200 free downloads / month for the test song',
371 # embedded brightcove video
372 # it also tests brightcove videos that need to set the 'Referer'
373 # in the http requests
374 'add_ie': ['BrightcoveLegacy'],
375 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
377 'id': '2765128793001',
379 'title': 'Le cours de bourse : l’analyse technique',
380 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
381 'uploader': 'BFM BUSINESS',
384 'skip_download': True,
388 # embedded with itemprop embedURL and video id spelled as `idVideo`
389 'add_id': ['BrightcoveLegacy'],
390 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
392 'id': '5255628253001',
394 'title': 'md5:37c519b1128915607601e75a87995fc0',
395 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
396 'uploader': 'BFM BUSINESS',
397 'uploader_id': '876450612001',
398 'timestamp': 1482255315,
399 'upload_date': '20161220',
402 'skip_download': True,
406 # https://github.com/rg3/youtube-dl/issues/2253
407 'url': 'http://bcove.me/i6nfkrc3',
408 'md5': '0ba9446db037002366bab3b3eb30c88c',
410 'id': '3101154703001',
412 'title': 'Still no power',
413 'uploader': 'thestar.com',
414 '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.',
416 'add_ie': ['BrightcoveLegacy'],
417 'skip': 'video gone',
420 'url': 'http://www.championat.com/video/football/v/87/87499.html',
421 'md5': 'fb973ecf6e4a78a67453647444222983',
423 'id': '3414141473001',
425 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
426 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
427 'uploader': 'Championat',
431 # https://github.com/rg3/youtube-dl/issues/3541
432 'add_ie': ['BrightcoveLegacy'],
433 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
435 'id': '3866516442001',
437 'title': 'Leer mij vrouwen kennen: Aflevering 1',
438 'description': 'Leer mij vrouwen kennen: Aflevering 1',
439 'uploader': 'SBS Broadcasting',
441 'skip': 'Restricted to Netherlands',
443 'skip_download': True, # m3u8 download
447 # Brightcove video in <iframe>
448 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
449 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
451 'id': '5360463607001',
453 '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',
454 '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。',
455 'uploader': 'United Nations',
456 'uploader_id': '1362235914001',
457 'timestamp': 1489593889,
458 'upload_date': '20170315',
460 'add_ie': ['BrightcoveLegacy'],
463 # Brightcove with alternative playerID key
464 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
466 'id': 'nmeth.2062_SV1',
467 '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',
471 'id': '2228375078001',
473 'title': 'nmeth.2062-sv1',
474 'description': 'nmeth.2062-sv1',
475 'timestamp': 1363357591,
476 'upload_date': '20130315',
477 'uploader': 'Nature Publishing Group',
478 'uploader_id': '1964492299001',
483 # Brightcove with UUID in videoPlayer
484 'url': 'http://www8.hp.com/cn/zh/home.html',
486 'id': '5255815316001',
488 'title': 'Sprocket Video - China',
489 'description': 'Sprocket Video - China',
490 'uploader': 'HP-Video Gallery',
491 'timestamp': 1482263210,
492 'upload_date': '20161220',
493 'uploader_id': '1107601872001',
496 'skip_download': True, # m3u8 download
498 'skip': 'video rotates...weekly?',
501 # Brightcove:new type [2].
502 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
503 'md5': '2b35148fcf48da41c9fb4591650784f3',
505 'id': '5348741021001',
507 'upload_date': '20170306',
508 'uploader_id': '4191638492001',
509 'timestamp': 1488769918,
510 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
515 # Alternative brightcove <video> attributes
516 '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/',
518 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
519 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
522 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
524 'id': '5311302538001',
526 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
527 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
528 'timestamp': 1486321708,
529 'upload_date': '20170205',
530 'uploader_id': '800000640001',
532 'only_matching': True,
536 # Brightcove with UUID in videoPlayer
537 'url': 'http://www8.hp.com/cn/zh/home.html',
539 'id': '5255815316001',
541 'title': 'Sprocket Video - China',
542 'description': 'Sprocket Video - China',
543 'uploader': 'HP-Video Gallery',
544 'timestamp': 1482263210,
545 'upload_date': '20161220',
546 'uploader_id': '1107601872001',
549 'skip_download': True, # m3u8 download
554 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
555 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
557 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
559 'title': '2cc213299525360.mov', # that's what we get
562 'add_ie': ['Ooyala'],
565 # ooyala video embedded with http://player.ooyala.com/iframe.js
566 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
568 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
570 'title': '"Steve Jobs: Man in the Machine" trailer',
571 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
575 'skip_download': True,
577 'skip': 'movie expired',
579 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
581 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
583 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
585 'title': 'Steampunk Fest Comes to Honesdale',
589 'skip_download': True,
594 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
598 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
599 'upload_date': '20140225',
600 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
601 'uploader': 'Tested',
602 'uploader_id': 'testedcom',
604 # No need to test YoutubeIE here
606 'skip_download': True,
611 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
615 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
616 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
618 # HEAD requests lead to endless 301, while GET is OK
619 'expected_warnings': ['301'],
623 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
627 'title': 'Охотское море стало целиком российским',
628 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
632 'skip_download': True,
637 '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/',
641 'title': 'Дошкольное воспитание',
646 'url': 'http://www.vestifinance.ru/articles/25753',
649 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
654 'title': 'Госзаказ. День 3',
660 'title': 'Госзаказ. День 2',
666 'title': 'Госзаказ. День 1',
672 'skip_download': True,
677 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
679 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
681 'title': 'Ужастики, русский трейлер (2015)',
682 'thumbnail': r're:^https?://.*\.jpg$',
688 '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',
691 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
693 'playlist_mincount': 7,
694 # This forum does not allow <iframe> syntaxes anymore
695 # Now HTML tags are displayed as-is
696 'skip': 'No videos on this page',
700 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
701 'md5': '65fdff94098e4a607385a60c5177c638',
705 'title': 'Hidden miracles of the natural world',
706 'uploader': 'Louie Schwartzberg',
707 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
710 # nowvideo embed hidden behind percent encoding
712 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
713 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
715 'id': '06e53103ca9aa',
717 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
718 'description': 'No description',
723 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
724 'md5': '7653032cbb25bf6c80d80f217055fa43',
726 'id': '048195-004_PLUS7-F',
729 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
730 'upload_date': '20140320',
733 'skip_download': 'Requires rtmpdump'
735 'skip': 'video gone',
739 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
743 'title': 'Alcaline, le concert avec Calogero',
744 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
745 'upload_date': '20150226',
746 'timestamp': 1424989860,
751 'skip_download': True,
753 'expected_warnings': [
759 'url': 'http://www.wired.com/2014/04/honda-asimo/',
760 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
762 'id': '53501be369702d3275860000',
764 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
769 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
770 'md5': '441aeeb82eb72c422c7f14ec533999cd',
772 'id': 'k2mm4bCdJ6CQ2i7c8o2',
774 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
775 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
777 'uploader_id': 'xgditw',
778 'upload_date': '20140425',
779 'timestamp': 1398441542,
781 'add_ie': ['Dailymotion'],
785 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
789 'title': 'Care worker punches elderly dementia patient in head 11 times',
790 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
792 'add_ie': ['DailyMail'],
794 'skip_download': True,
799 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
803 'title': 'The NBL Auction 2014',
804 'uploader': 'BADMINTON England',
805 'uploader_id': 'BADMINTONEvents',
806 'upload_date': '20140603',
807 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
809 'add_ie': ['Youtube'],
811 'skip_download': True,
816 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
817 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
819 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
821 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
822 'description': 'Two valets share their love for movie star Liam Neesons.',
823 'timestamp': 1349922600,
824 'upload_date': '20121011',
827 # YouTube embed via <data-embed-url="">
829 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
833 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
834 'uploader': 'Gameloft',
835 'uploader_id': 'gameloft',
836 'upload_date': '20140828',
837 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
840 'skip_download': True,
843 # YouTube <object> embed
845 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
846 'md5': '516718101ec834f74318df76259fb3cc',
850 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
851 'upload_date': '20080526',
852 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
853 'uploader': 'Christopher Sykes',
854 'uploader_id': 'ChristopherJSykes',
856 'add_ie': ['Youtube'],
860 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
862 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
864 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
865 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
870 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
872 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
873 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
879 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
884 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
885 'md5': '9d65602bf31c6e20014319c7d07fba27',
887 'id': '5123ea6d5e5a7',
890 'uploader': 'www.handjobhub.com',
891 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
894 # Multiple brightcove videos
895 # https://github.com/rg3/youtube-dl/issues/2283
897 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
899 'id': 'always-never',
900 'title': 'Always / Never - The New Yorker',
904 'extract_flat': False,
905 'skip_download': True,
910 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
911 'md5': '96f09a37e44da40dd083e12d9a683327',
915 'title': 'Ump changes call to ball',
916 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
918 'timestamp': 1401537900,
919 'upload_date': '20140531',
920 'thumbnail': r're:^https?://.*\.jpg$',
925 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
926 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
930 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
931 'description': 'a Paywall Videos video from Remilon',
933 'uploader': 'study.com',
934 'timestamp': 1459678540,
935 'upload_date': '20160403',
936 'filesize': 24687186,
940 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
941 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
945 'title': 'Conversation about Hexagonal Rails Part 1',
946 'description': 'a Martin Fowler video from ThoughtWorks',
948 'uploader': 'thoughtworks.wistia.com',
949 'timestamp': 1401832161,
950 'upload_date': '20140603',
953 # Wistia standard embed (async)
955 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
959 'title': 'Drip Brennan Dunn Workshop',
960 'description': 'a JV Webinars video from getdrip-1',
962 'timestamp': 1463607249,
963 'upload_date': '20160518',
966 'skip_download': True,
971 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
975 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
976 'uploader': 'Sophos Security',
977 'title': 'Chet Chat 171 - Oct 29, 2014',
978 'upload_date': '20141029',
981 # Soundcloud multiple embeds
983 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
986 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
988 'playlist_mincount': 7,
990 # TuneIn station embed
992 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
997 'location': 'Paris, France',
1002 'skip_download': True,
1007 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1011 'upload_date': '20141112',
1012 'title': 'Rosetta #CometLanding webcast HL 10',
1015 # Another Livestream embed, without 'new.' in URL
1017 'url': 'https://www.freespeech.org/',
1021 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1025 'skip_download': True,
1030 'url': 'https://skiplagged.com/',
1033 'title': 'Skiplagged: The smart way to find cheap flights',
1035 'playlist_mincount': 1,
1036 'add_ie': ['Youtube'],
1040 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1044 'upload_date': '20141126',
1045 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1050 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1052 'id': '730m_DandD_1901_512k',
1054 'uploader': 'www.abc.net.au',
1055 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1058 # embedded viddler video
1060 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1064 'uploader': 'deadspin',
1065 'title': 'WALL-TO-GORTAT',
1066 'timestamp': 1422285291,
1067 'upload_date': '20150126',
1069 'add_ie': ['Viddler'],
1073 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1077 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1078 'description': 'md5:601cb790edd05908957dae8aaa866465',
1079 'upload_date': '20150220',
1081 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1085 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1087 'id': 'Mrj4DVp2zeA',
1089 'upload_date': '20150212',
1090 'uploader': 'The National Archives UK',
1091 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1092 'uploader_id': 'NationalArchives08',
1093 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1098 'url': 'http://www.suffolk.edu/sjc/',
1102 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1103 'uploader': 'www.suffolk.edu',
1106 'skip_download': True,
1111 'url': 'http://www.indiedb.com/games/king-machine/videos',
1115 'title': 'king machine trailer 1',
1116 'thumbnail': r're:^https?://.*\.jpg$',
1120 # JWPlayer config passed as variable
1121 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1125 'title': 'ARIELE | Tube Cup',
1126 'uploader': 'www.txxx.com',
1130 'skip_download': True,
1135 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1136 'playlist_mincount': 5,
1138 'id': 'aanslagen-kopenhagen',
1139 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1144 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1148 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1151 # Kaltura embed (different embed code)
1153 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1157 'upload_date': '20150127',
1158 'uploader_id': 'PremierMedia',
1160 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1163 # Kaltura embed with single quotes
1165 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1170 'timestamp': 1355743100,
1171 'upload_date': '20121217',
1172 'uploader_id': 'batchUser',
1174 'add_ie': ['Kaltura'],
1177 # Kaltura embedded via quoted entry_id
1178 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1182 'title': '06_matthew_brender_raj_dutt',
1183 'timestamp': 1466638791,
1184 'upload_date': '20160622',
1186 'add_ie': ['Kaltura'],
1187 'expected_warnings': [
1188 'Could not send HEAD request'
1191 'skip_download': True,
1195 # Kaltura embedded, some fileExt broken (#11480)
1196 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1200 'title': 'Our "Standard Models" of particle physics and cosmology',
1201 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1202 'timestamp': 1321158993,
1203 'upload_date': '20111113',
1204 'uploader_id': 'kps1',
1206 'add_ie': ['Kaltura'],
1209 # Kaltura iframe embed
1210 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1211 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1215 'title': 'I. M. Pei: A Centennial Celebration',
1216 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1217 'upload_date': '20170403',
1218 'uploader_id': 'batchUser',
1219 'timestamp': 1491232186,
1221 'add_ie': ['Kaltura'],
1223 # EaglePlatform embed (generic URL)
1225 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1226 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1230 'title': 'Навальный вышел на свободу',
1231 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1232 'thumbnail': r're:^https?://.*\.jpg$',
1238 'skip_download': True,
1241 # referrer protected EaglePlatform embed
1243 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1247 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1248 'thumbnail': r're:^https?://.*\.jpg$',
1253 'skip_download': True,
1256 # ClipYou (EaglePlatform) embed (custom URL)
1258 'url': 'http://muz-tv.ru/play/7129/',
1259 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1263 'title': "'O Sole Mio",
1264 'thumbnail': r're:^https?://.*\.jpg$',
1269 'skip_download': True,
1274 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1278 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1279 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1280 'thumbnail': r're:^https?://.*\.jpg$',
1287 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1291 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1292 'thumbnail': r're:^https?://.*\.png$',
1298 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1299 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1303 'title': 'Facebook Creates "On This Day" | Crunch Report',
1308 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1312 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1317 # Crooks and Liars embed
1319 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1323 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1324 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1325 'timestamp': 1428207000,
1326 'upload_date': '20150405',
1327 'uploader': 'Heather',
1330 # Crooks and Liars external embed
1332 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1334 'id': 'MTE3MjUtMzQ2MzA',
1336 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1337 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1338 'timestamp': 1265032391,
1339 'upload_date': '20100201',
1340 'uploader': 'Heather',
1343 # NBC Sports vplayer embed
1345 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1347 'id': 'ln7x1qSThw4k',
1349 'title': "PFT Live: New leader in the 'new-look' defense",
1350 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1351 'uploader': 'NBCU-SPORTS',
1352 'upload_date': '20140107',
1353 'timestamp': 1389118457,
1358 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1359 'md5': '1aa589c675898ae6d37a17913cf68d66',
1361 'id': '701714499682',
1363 'title': 'PREVIEW: On Assignment: David Letterman',
1364 '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.',
1369 'url': 'https://video.udn.com/news/300346',
1370 'md5': 'fd2060e988c326991037b9aff9df21a6',
1374 'title': '中一中男師變性 全校師生力挺',
1375 'thumbnail': r're:^https?://.*\.jpg$',
1379 'skip_download': True,
1384 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1386 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1388 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1389 'title': 'This is what separates the Excel masters from the wannabes',
1390 'duration': 191.933,
1394 'skip_download': True,
1397 # Brightcove URL in single quotes
1399 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1400 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1402 'id': '4255764656001',
1404 'title': 'SN Presents: Russell Martin, World Citizen',
1405 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1406 'uploader': 'Rogers Sportsnet',
1407 'uploader_id': '1704050871',
1408 'upload_date': '20150525',
1409 'timestamp': 1432570283,
1412 # Dailymotion Cloud video
1414 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1415 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1419 'title': 'Sauvons les abeilles ! - Le débat',
1420 'description': 'md5:d9082128b1c5277987825d684939ca26',
1421 'thumbnail': r're:^https?://.*\.jpe?g$',
1422 'timestamp': 1434970506,
1423 'upload_date': '20150622',
1424 'uploader': 'Public Sénat',
1425 'uploader_id': 'xa9gza',
1428 # OnionStudios embed
1430 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1434 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1435 'thumbnail': r're:^https?://.*\.jpe?g$',
1436 'uploader': 'ClickHole',
1437 'uploader_id': 'clickhole',
1442 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1444 'id': '74849a00-85a9-11e1-9660-123139220831',
1446 'title': '#whilewewatch',
1449 # AdobeTVVideo embed
1451 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1452 'md5': '43662b577c018ad707a63766462b1e87',
1456 'title': 'New experience with Acrobat DC',
1457 'description': 'New experience with Acrobat DC',
1458 'duration': 248.667,
1461 # BrightcoveInPageEmbed embed
1463 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1465 'id': '4238694884001',
1467 'title': 'Tabletop: Dread, Last Thoughts',
1468 'description': 'Tabletop: Dread, Last Thoughts',
1472 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1473 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1475 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1477 'id': '4785848093001',
1479 'title': 'The Cardinal Pell Interview',
1480 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1481 'uploader': 'GlobeCast Australia - GlobeStream',
1482 'uploader_id': '2733773828001',
1483 'upload_date': '20160304',
1484 'timestamp': 1457083087,
1488 'skip_download': True,
1492 # Brightcove embed with whitespace around attribute names
1493 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1495 'id': '3167554373001',
1497 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1498 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1499 'uploader_id': '1079349493',
1500 'upload_date': '20140207',
1501 'timestamp': 1391810548,
1504 'skip_download': True,
1507 # Another form of arte.tv embed
1509 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1510 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1512 'id': '030273-562_PLUS7-F',
1514 'title': 'ARTE Reportage - Nulle part, en France',
1515 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1516 'upload_date': '20160409',
1521 'url': 'http://www.wykop.pl/link/3088787/',
1522 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1524 'id': '874_1459135191',
1526 'title': 'Man shows poor quality of new apartment building',
1527 'description': 'The wall is like a sand pile.',
1528 'uploader': 'Lake8737',
1530 'add_ie': [LiveLeakIE.ie_key()],
1532 # Another LiveLeak embed pattern (#13336)
1534 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1536 'id': '2eb_1496309988',
1538 'title': 'Thief robs place where everyone was armed',
1539 'description': 'md5:694d73ee79e535953cf2488562288eee',
1540 'uploader': 'brazilwtf',
1542 'add_ie': [LiveLeakIE.ie_key()],
1544 # Duplicated embedded video URLs
1546 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1548 'id': '149298443_480_16c25b74_2',
1550 'title': 'vs. Blue Orange Spring Game',
1551 'uploader': 'www.hudl.com',
1554 # twitter:player:stream embed
1556 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1560 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1561 'uploader': 'www.rtl.be',
1565 'skip_download': True,
1568 # twitter:player embed
1570 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1571 'md5': 'a3e0df96369831de324f0778e126653c',
1573 'id': '4909620399001',
1575 'title': 'What Do Black Holes Sound Like?',
1576 'description': 'what do black holes sound like',
1577 'upload_date': '20160524',
1578 'uploader_id': '29913724001',
1579 'timestamp': 1464107587,
1580 'uploader': 'TheAtlantic',
1582 'add_ie': ['BrightcoveLegacy'],
1586 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1590 'title': "Yesterday's Jam (OV)",
1591 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1592 'timestamp': 1492594816,
1593 'upload_date': '20170419',
1596 'format': 'bestvideo',
1597 'skip_download': True,
1600 # Facebook <iframe> embed
1602 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1603 'md5': 'fbcde74f534176ecb015849146dd3aee',
1605 'id': '599637780109885',
1607 'title': 'Facebook video #599637780109885',
1610 # Facebook <iframe> embed, plugin video
1612 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1614 'id': '1754168231264132',
1616 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1617 'uploader': 'Tariq Ramadan (official)',
1618 'timestamp': 1496758379,
1619 'upload_date': '20170606',
1622 'skip_download': True,
1625 # Facebook API embed
1627 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1628 'md5': 'a47372ee61b39a7b90287094d447d94e',
1630 'id': '10153467542406923',
1632 'title': 'Facebook video #10153467542406923',
1635 # Wordpress "YouTube Video Importer" plugin
1637 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1638 'md5': 'd16797741b560b485194eddda8121b48',
1640 'id': 'HNTXWDXV9Is',
1642 'title': 'Blue Devils Drumline Stanford lot 2016',
1643 'upload_date': '20160627',
1644 'uploader_id': 'GENOCIDE8GENERAL10',
1645 'uploader': 'cylus cyrus',
1649 # video stored on custom kaltura server
1650 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1651 'md5': '537617d06e64dfed891fa1593c4b30cc',
1655 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1656 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1657 'uploader_id': 'videos.expansion@el-mundo.net',
1658 'upload_date': '20150429',
1659 'timestamp': 1430303472,
1661 'add_ie': ['Kaltura'],
1664 # Non-standard Vimeo embed
1665 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1666 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1670 'title': 'Understanding the web - Teaser',
1671 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1672 'upload_date': '20151214',
1673 'uploader': 'OpenClassrooms',
1674 'uploader_id': 'openclassrooms',
1676 'add_ie': ['Vimeo'],
1679 # generic vimeo embed that requires original URL passed as Referer
1680 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1681 'only_matching': True,
1684 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1685 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1687 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1689 'title': 'Big Buck Bunny',
1690 'description': 'Royalty free test video',
1691 'timestamp': 1432816365,
1692 'upload_date': '20150528',
1696 'skip_download': True,
1698 'add_ie': [ArkenaIE.ie_key()],
1701 '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/',
1705 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1708 'skip_download': True,
1710 'add_ie': [Vbox7IE.ie_key()],
1714 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1717 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1719 'playlist_mincount': 3,
1723 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1725 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1726 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1728 'playlist_mincount': 2,
1732 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1736 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1737 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1740 'skip_download': True,
1742 'add_ie': [TwentyMinutenIE.ie_key()],
1746 'url': 'https://en.support.wordpress.com/videopress/',
1750 'title': 'IMG_5786',
1751 'timestamp': 1435711927,
1752 'upload_date': '20150701',
1755 'skip_download': True,
1757 'add_ie': [VideoPressIE.ie_key()],
1761 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1763 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1765 'title': 'Магаззино: Казань 2',
1766 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1767 'uploader': 'Магаззино',
1768 'upload_date': '20170228',
1769 'uploader_id': '996642',
1772 'skip_download': True,
1774 'add_ie': [RutubeIE.ie_key()],
1777 # ThePlatform embedded with whitespaces in URLs
1778 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1779 'only_matching': True,
1782 # Senate ISVP iframe https
1783 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1784 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1786 'id': 'govtaff020316',
1788 'title': 'Integrated Senate Video Player',
1790 'add_ie': [SenateISVPIE.ie_key()],
1793 # Limelight embeds (1 channel embed + 4 media embeds)
1794 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1796 'id': 'FacilitatorTraining2017',
1797 'title': 'Facilitator Training 2017',
1799 'playlist_mincount': 5,
1802 # Limelight embed (LimelightPlayerUtil.embed)
1803 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1805 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1807 'title': '07448641',
1808 'timestamp': 1499890639,
1809 'upload_date': '20170712',
1812 'skip_download': True,
1814 'add_ie': ['LimelightMedia'],
1817 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1819 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1820 'title': 'Standoff with Walnut Creek murder suspect ends',
1821 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1823 'playlist_mincount': 4,
1826 # WashingtonPost embed
1827 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1829 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1831 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1832 '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.',
1833 'timestamp': 1455216756,
1834 'uploader': 'The Washington Post',
1835 'upload_date': '20160211',
1837 'add_ie': [WashingtonPostIE.ie_key()],
1841 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1845 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1848 'skip_download': True,
1850 'add_ie': [MediasetIE.ie_key()],
1854 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1856 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1857 'title': 'Slovenskom sa prehnala vlna silných búrok',
1859 'playlist_mincount': 5,
1860 'add_ie': [JojIE.ie_key()],
1863 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1864 'url': 'https://tvrain.ru/amp/418921/',
1865 'md5': 'cc00413936695987e8de148b67d14f1d',
1869 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1874 'url': 'http://help.vzaar.com/article/165-embedding-video',
1875 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1879 'title': 'Building A Business Online: Principal Chairs Q & A',
1883 # # TODO: find another test
1884 # # http://schema.org/VideoObject
1885 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1886 # 'md5': '888dcf08b7ea671381f00fab74692755',
1888 # 'id': 'nyvTSJMKId',
1890 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1891 # 'description': '#love for cats.',
1892 # 'timestamp': 1461244995,
1893 # 'upload_date': '20160421',
1896 # 'force_generic_extractor': True,
1901 def report_following_redirect(self, new_url):
1902 """Report information extraction."""
1903 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1905 def _extract_rss(self, url, video_id, doc):
1906 playlist_title = doc.find('./channel/title').text
1907 playlist_desc_el = doc.find('./channel/description')
1908 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1911 for it in doc.findall('./channel/item'):
1912 next_url = xpath_text(it, 'link', fatal=False)
1914 enclosure_nodes = it.findall('./enclosure')
1915 for e in enclosure_nodes:
1916 next_url = e.attrib.get('url')
1924 '_type': 'url_transparent',
1926 'title': it.find('title').text,
1930 '_type': 'playlist',
1932 'title': playlist_title,
1933 'description': playlist_desc,
1937 def _extract_camtasia(self, url, video_id, webpage):
1938 """ Returns None if no camtasia video can be found. """
1940 camtasia_cfg = self._search_regex(
1941 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1942 webpage, 'camtasia configuration file', default=None)
1943 if camtasia_cfg is None:
1946 title = self._html_search_meta('DC.title', webpage, fatal=True)
1948 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1949 camtasia_cfg = self._download_xml(
1950 camtasia_url, video_id,
1951 note='Downloading camtasia configuration',
1952 errnote='Failed to download camtasia configuration')
1953 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1956 for n in fileset_node.getchildren():
1957 url_n = n.find('./uri')
1962 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1963 'title': '%s - %s' % (title, n.tag),
1964 'url': compat_urlparse.urljoin(url, url_n.text),
1965 'duration': float_or_none(n.find('./duration').text),
1969 '_type': 'playlist',
1974 def _real_extract(self, url):
1975 if url.startswith('//'):
1978 'url': self.http_scheme() + url,
1981 parsed_url = compat_urlparse.urlparse(url)
1982 if not parsed_url.scheme:
1983 default_search = self._downloader.params.get('default_search')
1984 if default_search is None:
1985 default_search = 'fixup_error'
1987 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1989 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1990 return self.url_result('http://' + url)
1991 elif default_search != 'fixup_error':
1992 if default_search == 'auto_warning':
1993 if re.match(r'^(?:url|URL)$', url):
1994 raise ExtractorError(
1995 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1998 self._downloader.report_warning(
1999 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2000 return self.url_result('ytsearch:' + url)
2002 if default_search in ('error', 'fixup_error'):
2003 raise ExtractorError(
2004 '%r is not a valid URL. '
2005 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2006 % (url, url), expected=True)
2008 if ':' not in default_search:
2009 default_search += ':'
2010 return self.url_result(default_search + url)
2012 url, smuggled_data = unsmuggle_url(url)
2013 force_videoid = None
2014 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2015 if smuggled_data and 'force_videoid' in smuggled_data:
2016 force_videoid = smuggled_data['force_videoid']
2017 video_id = force_videoid
2019 video_id = self._generic_id(url)
2021 self.to_screen('%s: Requesting header' % video_id)
2023 head_req = HEADRequest(url)
2024 head_response = self._request_webpage(
2026 note=False, errnote='Could not send HEAD request to %s' % url,
2029 if head_response is not False:
2030 # Check for redirect
2031 new_url = compat_str(head_response.geturl())
2033 self.report_following_redirect(new_url)
2035 new_url = smuggle_url(
2036 new_url, {'force_videoid': force_videoid})
2037 return self.url_result(new_url)
2039 full_response = None
2040 if head_response is False:
2041 request = sanitized_Request(url)
2042 request.add_header('Accept-Encoding', '*')
2043 full_response = self._request_webpage(request, video_id)
2044 head_response = full_response
2048 'title': self._generic_title(url),
2049 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2052 # Check for direct link to a video
2053 content_type = head_response.headers.get('Content-Type', '').lower()
2054 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2056 format_id = compat_str(m.group('format_id'))
2057 if format_id.endswith('mpegurl'):
2058 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2059 elif format_id == 'f4m':
2060 formats = self._extract_f4m_formats(url, video_id)
2063 'format_id': format_id,
2065 'vcodec': 'none' if m.group('type') == 'audio' else None
2067 info_dict['direct'] = True
2068 self._sort_formats(formats)
2069 info_dict['formats'] = formats
2072 if not self._downloader.params.get('test', False) and not is_intentional:
2073 force = self._downloader.params.get('force_generic_extractor', False)
2074 self._downloader.report_warning(
2075 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2077 if not full_response:
2078 request = sanitized_Request(url)
2079 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2080 # making it impossible to download only chunk of the file (yet we need only 512kB to
2081 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2082 # that will always result in downloading the whole file that is not desirable.
2083 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2084 # to accept raw bytes and being able to download only a chunk.
2085 # It may probably better to solve this by checking Content-Type for application/octet-stream
2086 # after HEAD request finishes, but not sure if we can rely on this.
2087 request.add_header('Accept-Encoding', '*')
2088 full_response = self._request_webpage(request, video_id)
2090 first_bytes = full_response.read(512)
2092 # Is it an M3U playlist?
2093 if first_bytes.startswith(b'#EXTM3U'):
2094 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2095 self._sort_formats(info_dict['formats'])
2098 # Maybe it's a direct link to a video?
2099 # Be careful not to download the whole thing!
2100 if not is_html(first_bytes):
2101 self._downloader.report_warning(
2102 'URL could be a direct video link, returning it as such.')
2109 webpage = self._webpage_read_content(
2110 full_response, url, video_id, prefix=first_bytes)
2112 self.report_extraction(video_id)
2114 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2116 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2117 if doc.tag == 'rss':
2118 return self._extract_rss(url, video_id, doc)
2119 elif doc.tag == 'SmoothStreamingMedia':
2120 info_dict['formats'] = self._parse_ism_formats(doc, url)
2121 self._sort_formats(info_dict['formats'])
2123 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2124 smil = self._parse_smil(doc, url, video_id)
2125 self._sort_formats(smil['formats'])
2127 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2128 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2129 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2130 info_dict['formats'] = self._parse_mpd_formats(
2132 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2134 self._sort_formats(info_dict['formats'])
2136 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2137 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2138 self._sort_formats(info_dict['formats'])
2140 except compat_xml_parse_error:
2143 # Is it a Camtasia project?
2144 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2145 if camtasia_res is not None:
2148 # Sometimes embedded video player is hidden behind percent encoding
2149 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2150 # Unescaping the whole page allows to handle those cases in a generic way
2151 webpage = compat_urllib_parse_unquote(webpage)
2153 # it's tempting to parse this further, but you would
2154 # have to take into account all the variations like
2155 # Video Title - Site Name
2156 # Site Name | Video Title
2157 # Video Title - Tagline | Site Name
2158 # and so on and so forth; it's just not practical
2159 video_title = self._og_search_title(
2160 webpage, default=None) or self._html_search_regex(
2161 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2164 # Try to detect age limit automatically
2165 age_limit = self._rta_search(webpage)
2166 # And then there are the jokers who advertise that they use RTA,
2167 # but actually don't.
2168 AGE_LIMIT_MARKERS = [
2169 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2171 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2174 # video uploader is domain name
2175 video_uploader = self._search_regex(
2176 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2178 video_description = self._og_search_description(webpage, default=None)
2179 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2182 'title': video_title,
2183 'description': video_description,
2184 'thumbnail': video_thumbnail,
2185 'age_limit': age_limit,
2188 # Look for Brightcove Legacy Studio embeds
2189 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2193 'url': smuggle_url(bc_url, {'Referer': url}),
2194 'ie_key': 'BrightcoveLegacy'
2195 } for bc_url in bc_urls]
2198 '_type': 'playlist',
2199 'title': video_title,
2204 # Look for Brightcove New Studio embeds
2205 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2207 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2209 # Look for Nexx embeds
2210 nexx_urls = NexxIE._extract_urls(webpage)
2212 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2214 # Look for Nexx iFrame embeds
2215 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2217 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2219 # Look for ThePlatform embeds
2220 tp_urls = ThePlatformIE._extract_urls(webpage)
2222 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2224 # Look for Vessel embeds
2225 vessel_urls = VesselIE._extract_urls(webpage)
2227 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2229 # Look for embedded rtl.nl player
2230 matches = re.findall(
2231 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2234 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2236 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2238 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2240 vid_me_embed_url = self._search_regex(
2241 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2242 webpage, 'vid.me embed', default=None)
2243 if vid_me_embed_url is not None:
2244 return self.url_result(vid_me_embed_url, 'Vidme')
2246 # Look for YouTube embeds
2247 youtube_urls = YoutubeIE._extract_urls(webpage)
2249 return self.playlist_from_matches(
2250 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2252 matches = DailymotionIE._extract_urls(webpage)
2254 return self.playlist_from_matches(matches, video_id, video_title)
2256 # Look for embedded Dailymotion playlist player (#3822)
2258 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2260 playlists = re.findall(
2261 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2263 return self.playlist_from_matches(
2264 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2266 # Look for DailyMail embeds
2267 dailymail_urls = DailyMailIE._extract_urls(webpage)
2269 return self.playlist_from_matches(
2270 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2272 # Look for embedded Wistia player
2273 wistia_url = WistiaIE._extract_url(webpage)
2276 '_type': 'url_transparent',
2277 'url': self._proto_relative_url(wistia_url),
2278 'ie_key': WistiaIE.ie_key(),
2279 'uploader': video_uploader,
2282 # Look for SVT player
2283 svt_url = SVTIE._extract_url(webpage)
2285 return self.url_result(svt_url, 'SVT')
2287 # Look for Bandcamp pages with custom domain
2288 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2289 if mobj is not None:
2290 burl = unescapeHTML(mobj.group(1))
2291 # Don't set the extractor because it can be a track url or an album
2292 return self.url_result(burl)
2294 # Look for embedded Vevo player
2296 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2297 if mobj is not None:
2298 return self.url_result(mobj.group('url'))
2300 # Look for embedded Viddler player
2302 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2304 if mobj is not None:
2305 return self.url_result(mobj.group('url'))
2307 # Look for NYTimes player
2309 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2311 if mobj is not None:
2312 return self.url_result(mobj.group('url'))
2314 # Look for Libsyn player
2316 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2317 if mobj is not None:
2318 return self.url_result(mobj.group('url'))
2320 # Look for Ooyala videos
2321 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2322 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2323 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2324 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2325 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2326 if mobj is not None:
2327 embed_token = self._search_regex(
2328 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2329 webpage, 'ooyala embed token', default=None)
2330 return OoyalaIE._build_url_result(smuggle_url(
2333 'embed_token': embed_token,
2336 # Look for multiple Ooyala embeds on SBN network websites
2337 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2338 if mobj is not None:
2339 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2341 return self.playlist_from_matches(
2342 embeds, video_id, video_title,
2343 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2345 # Look for Aparat videos
2346 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2347 if mobj is not None:
2348 return self.url_result(mobj.group(1), 'Aparat')
2350 # Look for MPORA videos
2351 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2352 if mobj is not None:
2353 return self.url_result(mobj.group(1), 'Mpora')
2355 # Look for embedded NovaMov-based player
2357 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2358 (?P<url>http://(?:(?:embed|www)\.)?
2360 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2361 videoweed\.(?:es|com)|
2362 movshare\.(?:net|sx|ag)|
2363 divxstage\.(?:eu|net|ch|co|at|ag))
2364 /embed\.php.+?)\1''', webpage)
2365 if mobj is not None:
2366 return self.url_result(mobj.group('url'))
2368 # Look for embedded Facebook player
2369 facebook_urls = FacebookIE._extract_urls(webpage)
2371 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2373 # Look for embedded VK player
2374 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2375 if mobj is not None:
2376 return self.url_result(mobj.group('url'), 'VK')
2378 # Look for embedded Odnoklassniki player
2379 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2380 if mobj is not None:
2381 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2383 # Look for embedded ivi player
2384 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2385 if mobj is not None:
2386 return self.url_result(mobj.group('url'), 'Ivi')
2388 # Look for embedded Huffington Post player
2390 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2391 if mobj is not None:
2392 return self.url_result(mobj.group('url'), 'HuffPost')
2395 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2396 if mobj is not None:
2397 return self.url_result(mobj.group('url'))
2398 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2399 if mobj is not None:
2400 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2402 # Look for funnyordie embed
2403 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2405 return self.playlist_from_matches(
2406 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2408 # Look for BBC iPlayer embed
2409 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2411 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2413 # Look for embedded RUTV player
2414 rutv_url = RUTVIE._extract_url(webpage)
2416 return self.url_result(rutv_url, 'RUTV')
2418 # Look for embedded TVC player
2419 tvc_url = TVCIE._extract_url(webpage)
2421 return self.url_result(tvc_url, 'TVC')
2423 # Look for embedded SportBox player
2424 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2426 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2428 # Look for embedded XHamster player
2429 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2431 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2433 # Look for embedded TNAFlixNetwork player
2434 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2436 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2438 # Look for embedded PornHub player
2439 pornhub_urls = PornHubIE._extract_urls(webpage)
2441 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2443 # Look for embedded DrTuber player
2444 drtuber_urls = DrTuberIE._extract_urls(webpage)
2446 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2448 # Look for embedded RedTube player
2449 redtube_urls = RedTubeIE._extract_urls(webpage)
2451 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2453 # Look for embedded Tvigle player
2455 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2456 if mobj is not None:
2457 return self.url_result(mobj.group('url'), 'Tvigle')
2459 # Look for embedded TED player
2461 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2462 if mobj is not None:
2463 return self.url_result(mobj.group('url'), 'TED')
2465 # Look for embedded Ustream videos
2466 ustream_url = UstreamIE._extract_url(webpage)
2468 return self.url_result(ustream_url, UstreamIE.ie_key())
2470 # Look for embedded arte.tv player
2472 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2474 if mobj is not None:
2475 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2477 # Look for embedded francetv player
2479 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2481 if mobj is not None:
2482 return self.url_result(mobj.group('url'))
2484 # Look for embedded smotri.com player
2485 smotri_url = SmotriIE._extract_url(webpage)
2487 return self.url_result(smotri_url, 'Smotri')
2489 # Look for embedded Myvi.ru player
2490 myvi_url = MyviIE._extract_url(webpage)
2492 return self.url_result(myvi_url)
2494 # Look for embedded soundcloud player
2495 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2497 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2499 # Look for tunein player
2500 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2502 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2504 # Look for embedded mtvservices player
2505 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2507 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2509 # Look for embedded yahoo player
2511 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2513 if mobj is not None:
2514 return self.url_result(mobj.group('url'), 'Yahoo')
2516 # Look for embedded sbs.com.au player
2520 <meta\s+property="og:video"\s+content=|
2523 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2525 if mobj is not None:
2526 return self.url_result(mobj.group('url'), 'SBS')
2528 # Look for embedded Cinchcast player
2530 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'), 'Cinchcast')
2536 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2540 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'), 'MLB')
2546 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2548 if mobj is not None:
2549 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2552 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2554 if mobj is not None:
2555 return self.url_result(mobj.group('url'), 'Livestream')
2557 # Look for Zapiks embed
2559 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2560 if mobj is not None:
2561 return self.url_result(mobj.group('url'), 'Zapiks')
2563 # Look for Kaltura embeds
2564 kaltura_url = KalturaIE._extract_url(webpage)
2566 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2568 # Look for EaglePlatform embeds
2569 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2570 if eagleplatform_url:
2571 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2573 # Look for ClipYou (uses EaglePlatform) embeds
2575 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2576 if mobj is not None:
2577 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2579 # Look for Pladform embeds
2580 pladform_url = PladformIE._extract_url(webpage)
2582 return self.url_result(pladform_url)
2584 # Look for Videomore embeds
2585 videomore_url = VideomoreIE._extract_url(webpage)
2587 return self.url_result(videomore_url)
2589 # Look for Webcaster embeds
2590 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2592 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2594 # Look for Playwire embeds
2596 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2597 if mobj is not None:
2598 return self.url_result(mobj.group('url'))
2600 # Look for 5min embeds
2602 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2603 if mobj is not None:
2604 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2606 # Look for Crooks and Liars embeds
2608 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2609 if mobj is not None:
2610 return self.url_result(mobj.group('url'))
2612 # Look for NBC Sports VPlayer embeds
2613 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2615 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2617 # Look for NBC News embeds
2618 nbc_news_embed_url = re.search(
2619 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2620 if nbc_news_embed_url:
2621 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2623 # Look for Google Drive embeds
2624 google_drive_url = GoogleDriveIE._extract_url(webpage)
2625 if google_drive_url:
2626 return self.url_result(google_drive_url, 'GoogleDrive')
2628 # Look for UDN embeds
2630 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2631 if mobj is not None:
2632 return self.url_result(
2633 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2635 # Look for Senate ISVP iframe
2636 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2638 return self.url_result(senate_isvp_url, 'SenateISVP')
2640 # Look for Dailymotion Cloud videos
2641 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2643 return self.url_result(dmcloud_url, 'DailymotionCloud')
2645 # Look for OnionStudios embeds
2646 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2647 if onionstudios_url:
2648 return self.url_result(onionstudios_url)
2650 # Look for ViewLift embeds
2651 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2653 return self.url_result(viewlift_url)
2655 # Look for JWPlatform embeds
2656 jwplatform_url = JWPlatformIE._extract_url(webpage)
2658 return self.url_result(jwplatform_url, 'JWPlatform')
2660 # Look for Digiteka embeds
2661 digiteka_url = DigitekaIE._extract_url(webpage)
2663 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2665 # Look for Arkena embeds
2666 arkena_url = ArkenaIE._extract_url(webpage)
2668 return self.url_result(arkena_url, ArkenaIE.ie_key())
2670 # Look for Piksel embeds
2671 piksel_url = PikselIE._extract_url(webpage)
2673 return self.url_result(piksel_url, PikselIE.ie_key())
2675 # Look for Limelight embeds
2676 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2678 return self.playlist_result(
2679 limelight_urls, video_id, video_title, video_description)
2681 # Look for Anvato embeds
2682 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2684 return self.playlist_result(
2685 anvato_urls, video_id, video_title, video_description)
2687 # Look for AdobeTVVideo embeds
2689 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2691 if mobj is not None:
2692 return self.url_result(
2693 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2696 # Look for Vine embeds
2698 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2700 if mobj is not None:
2701 return self.url_result(
2702 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2704 # Look for VODPlatform embeds
2706 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2708 if mobj is not None:
2709 return self.url_result(
2710 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2712 # Look for Mangomolo embeds
2714 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2716 video\?.*?\bid=(?P<video_id>\d+)|
2717 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2718 ).+?)\1''', webpage)
2719 if mobj is not None:
2721 '_type': 'url_transparent',
2722 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2723 'title': video_title,
2724 'description': video_description,
2725 'thumbnail': video_thumbnail,
2726 'uploader': video_uploader,
2728 video_id = mobj.group('video_id')
2731 'ie_key': 'MangomoloVideo',
2736 'ie_key': 'MangomoloLive',
2737 'id': mobj.group('channel_id'),
2741 # Look for Instagram embeds
2742 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2743 if instagram_embed_url is not None:
2744 return self.url_result(
2745 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2747 # Look for LiveLeak embeds
2748 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2750 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2752 # Look for 3Q SDN embeds
2753 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2756 '_type': 'url_transparent',
2757 'ie_key': ThreeQSDNIE.ie_key(),
2758 'url': self._proto_relative_url(threeqsdn_url),
2759 'title': video_title,
2760 'description': video_description,
2761 'thumbnail': video_thumbnail,
2762 'uploader': video_uploader,
2765 # Look for VBOX7 embeds
2766 vbox7_url = Vbox7IE._extract_url(webpage)
2768 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2770 # Look for DBTV embeds
2771 dbtv_urls = DBTVIE._extract_urls(webpage)
2773 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2775 # Look for Videa embeds
2776 videa_urls = VideaIE._extract_urls(webpage)
2778 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2780 # Look for 20 minuten embeds
2781 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2783 return self.playlist_from_matches(
2784 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2786 # Look for Openload embeds
2787 openload_urls = OpenloadIE._extract_urls(webpage)
2789 return self.playlist_from_matches(
2790 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2792 # Look for VideoPress embeds
2793 videopress_urls = VideoPressIE._extract_urls(webpage)
2795 return self.playlist_from_matches(
2796 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2798 # Look for Rutube embeds
2799 rutube_urls = RutubeIE._extract_urls(webpage)
2801 return self.playlist_from_matches(
2802 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2804 # Look for WashingtonPost embeds
2805 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2807 return self.playlist_from_matches(
2808 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2810 # Look for Mediaset embeds
2811 mediaset_urls = MediasetIE._extract_urls(webpage)
2813 return self.playlist_from_matches(
2814 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2816 # Look for JOJ.sk embeds
2817 joj_urls = JojIE._extract_urls(webpage)
2819 return self.playlist_from_matches(
2820 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2822 # Look for megaphone.fm embeds
2823 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2825 return self.playlist_from_matches(
2826 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2828 # Look for vzaar embeds
2829 vzaar_urls = VzaarIE._extract_urls(webpage)
2831 return self.playlist_from_matches(
2832 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2834 def merge_dicts(dict1, dict2):
2836 for k, v in dict1.items():
2839 for k, v in dict2.items():
2842 if (k not in merged or
2843 (isinstance(v, compat_str) and v and
2844 isinstance(merged[k], compat_str) and
2849 # Look for HTML5 media
2850 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2852 for entry in entries:
2855 'title': video_title,
2857 self._sort_formats(entry['formats'])
2858 return self.playlist_result(entries)
2860 jwplayer_data = self._find_jwplayer_data(
2861 webpage, video_id, transform_source=js_to_json)
2863 info = self._parse_jwplayer_data(
2864 jwplayer_data, video_id, require_title=False, base_url=url)
2865 return merge_dicts(info, info_dict)
2867 # Looking for http://schema.org/VideoObject
2868 json_ld = self._search_json_ld(
2869 webpage, video_id, default={}, expected_type='VideoObject')
2870 if json_ld.get('url'):
2871 return merge_dicts(json_ld, info_dict)
2873 def check_video(vurl):
2874 if YoutubeIE.suitable(vurl):
2876 if RtmpIE.suitable(vurl):
2878 vpath = compat_urlparse.urlparse(vurl).path
2879 vext = determine_ext(vpath)
2880 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2882 def filter_video(urls):
2883 return list(filter(check_video, urls))
2885 # Start with something easy: JW Player in SWFObject
2886 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2888 # Look for gorilla-vid style embedding
2889 found = filter_video(re.findall(r'''(?sx)
2893 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2896 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2898 # Broaden the search a little bit
2899 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2901 # Broaden the findall a little bit: JWPlayer JS loader
2902 found = filter_video(re.findall(
2903 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2906 found = filter_video(re.findall(r'''(?xs)
2907 flowplayer\("[^"]+",\s*
2909 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2910 ["']?url["']?\s*:\s*["']([^"']+)["']
2915 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2917 # Try to find twitter cards info
2918 # twitter:player:stream should be checked before twitter:player since
2919 # it is expected to contain a raw stream (see
2920 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2921 found = filter_video(re.findall(
2922 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2924 # We look for Open Graph info:
2925 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2926 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2927 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2928 if m_video_type is not None:
2929 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2931 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2933 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2934 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2937 # Look also in Refresh HTTP header
2938 refresh_header = head_response.headers.get('Refresh')
2940 # In python 2 response HTTP headers are bytestrings
2941 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2942 refresh_header = refresh_header.decode('iso-8859-1')
2943 found = re.search(REDIRECT_REGEX, refresh_header)
2945 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2947 self.report_following_redirect(new_url)
2956 # twitter:player is a https URL to iframe player that may or may not
2957 # be supported by youtube-dl thus this is checked the very last (see
2958 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2959 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2961 return self.url_result(embed_url)
2964 raise UnsupportedError(url)
2967 for video_url in orderedSet(found):
2968 video_url = unescapeHTML(video_url)
2969 video_url = video_url.replace('\\/', '/')
2970 video_url = compat_urlparse.urljoin(url, video_url)
2971 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2973 # Sometimes, jwplayer extraction will result in a YouTube URL
2974 if YoutubeIE.suitable(video_url):
2975 entries.append(self.url_result(video_url, 'Youtube'))
2978 # here's a fun little line of code for you:
2979 video_id = os.path.splitext(video_id)[0]
2983 'uploader': video_uploader,
2984 'title': video_title,
2985 'age_limit': age_limit,
2988 if RtmpIE.suitable(video_url):
2989 entry_info_dict.update({
2990 '_type': 'url_transparent',
2991 'ie_key': RtmpIE.ie_key(),
2994 entries.append(entry_info_dict)
2997 ext = determine_ext(video_url)
2999 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3001 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3003 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3005 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3007 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3008 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3009 # Just matching .ism/manifest is not enough to be reliably sure
3010 # whether it's actually an ISM manifest or some other streaming
3011 # manifest since there are various streaming URL formats
3012 # possible (see [1]) as well as some other shenanigans like
3013 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3015 # Thus the most reasonable way to solve this is to delegate
3016 # to generic extractor in order to look into the contents of
3017 # the manifest itself.
3018 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3019 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3020 entry_info_dict = self.url_result(
3021 smuggle_url(video_url, {'to_generic': True}),
3024 entry_info_dict['url'] = video_url
3026 if entry_info_dict.get('formats'):
3027 self._sort_formats(entry_info_dict['formats'])
3029 entries.append(entry_info_dict)
3031 if len(entries) == 1:
3034 for num, e in enumerate(entries, start=1):
3035 # 'url' results don't have a title
3036 if e.get('title') is not None:
3037 e['title'] = '%s (%d)' % (e['title'], num)
3039 '_type': 'playlist',