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
106 class GenericIE(InfoExtractor):
107 IE_DESC = 'Generic downloader that works on some sites'
111 # Direct link to a video
113 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
114 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
119 'upload_date': '20100513',
122 # Direct link to media delivered compressed (until Accept-Encoding is *)
124 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
125 'md5': '128c42e68b13950268b648275386fc74',
127 'id': 'FictionJunction-Parallel_Hearts',
129 'title': 'FictionJunction-Parallel_Hearts',
130 'upload_date': '20140522',
132 'expected_warnings': [
133 'URL could be a direct video link, returning it as such.'
135 'skip': 'URL invalid',
137 # Direct download with broken HEAD
139 'url': 'http://ai-radio.org:8000/radio.opus',
146 'skip_download': True, # infinite live stream
148 'expected_warnings': [
149 r'501.*Not Implemented',
153 # Direct link with incorrect MIME type
155 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
156 'md5': '4ccbebe5f36706d85221f204d7eb5913',
158 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
159 'id': '5_Lennart_Poettering_-_Systemd',
161 'title': '5_Lennart_Poettering_-_Systemd',
162 'upload_date': '20141120',
164 'expected_warnings': [
165 'URL could be a direct video link, returning it as such.'
170 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
172 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
173 'title': 'Zero Punctuation',
174 'description': 're:.*groundbreaking video review series.*'
176 'playlist_mincount': 11,
178 # RSS feed with enclosure
180 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
182 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
184 'upload_date': '20150228',
185 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
188 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
190 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
194 'title': 'Automatics, robotics and biocybernetics',
195 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
196 'upload_date': '20130627',
197 'formats': 'mincount:16',
198 'subtitles': 'mincount:1',
201 'force_generic_extractor': True,
202 'skip_download': True,
205 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
207 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
212 'formats': 'mincount:1',
215 'skip_download': True,
218 # SMIL from https://www.restudy.dk/video/play/id/1637
220 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
224 'title': 'video_1637',
225 'formats': 'mincount:3',
228 'skip_download': True,
231 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
233 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
235 'id': 'smil-service',
237 'title': 'smil-service',
238 'formats': 'mincount:1',
241 'skip_download': True,
244 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
246 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
250 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
251 'formats': 'mincount:3',
254 'skip_download': True,
257 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
259 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
261 'id': 'mZlp2ctYIUEB',
263 'title': 'Tikibad ontruimd wegens brand',
264 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
265 'thumbnail': r're:^https?://.*\.jpg$',
269 'skip_download': True,
272 # MPD from http://dash-mse-test.appspot.com/media.html
274 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
275 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
277 'id': 'car-20120827-manifest',
279 'title': 'car-20120827-manifest',
280 'formats': 'mincount:9',
281 'upload_date': '20130904',
284 'format': 'bestvideo',
287 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
289 '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',
294 'formats': 'mincount:8',
298 'skip_download': True,
300 'skip': 'video gone',
302 # m3u8 served with Content-Type: text/plain
304 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
309 'upload_date': '20140720',
310 'formats': 'mincount:11',
314 'skip_download': True,
316 'skip': 'video gone',
320 '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',
324 'upload_date': '20130224',
325 'uploader_id': 'TheVerge',
326 'description': r're:^Chris Ziegler takes a look at the\.*',
327 'uploader': 'The Verge',
328 'title': 'First Firefox OS phones side-by-side',
331 'skip_download': False,
335 # redirect in Refresh HTTP header
336 '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',
340 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
341 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
342 'upload_date': '20150917',
343 'uploader_id': 'brtvofficial',
344 'uploader': 'Boiler Room',
347 'skip_download': False,
351 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
352 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
354 'id': '13601338388002',
356 'uploader': 'www.hodiho.fr',
357 'title': 'R\u00e9gis plante sa Jeep',
360 # bandcamp page with custom domain
362 'add_ie': ['Bandcamp'],
363 'url': 'http://bronyrock.com/track/the-pony-mash',
367 'title': 'The Pony Mash',
368 'uploader': 'M_Pallante',
370 'skip': 'There is a limit of 200 free downloads / month for the test song',
373 # embedded brightcove video
374 # it also tests brightcove videos that need to set the 'Referer'
375 # in the http requests
376 'add_ie': ['BrightcoveLegacy'],
377 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
379 'id': '2765128793001',
381 'title': 'Le cours de bourse : l’analyse technique',
382 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
383 'uploader': 'BFM BUSINESS',
386 'skip_download': True,
390 # embedded with itemprop embedURL and video id spelled as `idVideo`
391 'add_id': ['BrightcoveLegacy'],
392 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
394 'id': '5255628253001',
396 'title': 'md5:37c519b1128915607601e75a87995fc0',
397 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
398 'uploader': 'BFM BUSINESS',
399 'uploader_id': '876450612001',
400 'timestamp': 1482255315,
401 'upload_date': '20161220',
404 'skip_download': True,
408 # https://github.com/rg3/youtube-dl/issues/2253
409 'url': 'http://bcove.me/i6nfkrc3',
410 'md5': '0ba9446db037002366bab3b3eb30c88c',
412 'id': '3101154703001',
414 'title': 'Still no power',
415 'uploader': 'thestar.com',
416 '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.',
418 'add_ie': ['BrightcoveLegacy'],
419 'skip': 'video gone',
422 'url': 'http://www.championat.com/video/football/v/87/87499.html',
423 'md5': 'fb973ecf6e4a78a67453647444222983',
425 'id': '3414141473001',
427 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
428 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
429 'uploader': 'Championat',
433 # https://github.com/rg3/youtube-dl/issues/3541
434 'add_ie': ['BrightcoveLegacy'],
435 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
437 'id': '3866516442001',
439 'title': 'Leer mij vrouwen kennen: Aflevering 1',
440 'description': 'Leer mij vrouwen kennen: Aflevering 1',
441 'uploader': 'SBS Broadcasting',
443 'skip': 'Restricted to Netherlands',
445 'skip_download': True, # m3u8 download
449 # Brightcove video in <iframe>
450 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
451 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
453 'id': '5360463607001',
455 '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',
456 '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。',
457 'uploader': 'United Nations',
458 'uploader_id': '1362235914001',
459 'timestamp': 1489593889,
460 'upload_date': '20170315',
462 'add_ie': ['BrightcoveLegacy'],
465 # Brightcove with alternative playerID key
466 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
468 'id': 'nmeth.2062_SV1',
469 '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',
473 'id': '2228375078001',
475 'title': 'nmeth.2062-sv1',
476 'description': 'nmeth.2062-sv1',
477 'timestamp': 1363357591,
478 'upload_date': '20130315',
479 'uploader': 'Nature Publishing Group',
480 'uploader_id': '1964492299001',
485 # Brightcove with UUID in videoPlayer
486 'url': 'http://www8.hp.com/cn/zh/home.html',
488 'id': '5255815316001',
490 'title': 'Sprocket Video - China',
491 'description': 'Sprocket Video - China',
492 'uploader': 'HP-Video Gallery',
493 'timestamp': 1482263210,
494 'upload_date': '20161220',
495 'uploader_id': '1107601872001',
498 'skip_download': True, # m3u8 download
500 'skip': 'video rotates...weekly?',
503 # Brightcove:new type [2].
504 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
505 'md5': '2b35148fcf48da41c9fb4591650784f3',
507 'id': '5348741021001',
509 'upload_date': '20170306',
510 'uploader_id': '4191638492001',
511 'timestamp': 1488769918,
512 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
517 # Alternative brightcove <video> attributes
518 '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/',
520 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
521 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
524 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
526 'id': '5311302538001',
528 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
529 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
530 'timestamp': 1486321708,
531 'upload_date': '20170205',
532 'uploader_id': '800000640001',
534 'only_matching': True,
538 # Brightcove with UUID in videoPlayer
539 'url': 'http://www8.hp.com/cn/zh/home.html',
541 'id': '5255815316001',
543 'title': 'Sprocket Video - China',
544 'description': 'Sprocket Video - China',
545 'uploader': 'HP-Video Gallery',
546 'timestamp': 1482263210,
547 'upload_date': '20161220',
548 'uploader_id': '1107601872001',
551 'skip_download': True, # m3u8 download
556 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
557 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
559 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
561 'title': '2cc213299525360.mov', # that's what we get
564 'add_ie': ['Ooyala'],
567 # ooyala video embedded with http://player.ooyala.com/iframe.js
568 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
570 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
572 'title': '"Steve Jobs: Man in the Machine" trailer',
573 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
577 'skip_download': True,
579 'skip': 'movie expired',
581 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
583 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
585 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
587 'title': 'Steampunk Fest Comes to Honesdale',
591 'skip_download': True,
596 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
600 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
601 'upload_date': '20140225',
602 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
603 'uploader': 'Tested',
604 'uploader_id': 'testedcom',
606 # No need to test YoutubeIE here
608 'skip_download': True,
613 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
617 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
618 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
620 # HEAD requests lead to endless 301, while GET is OK
621 'expected_warnings': ['301'],
625 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
629 'title': 'Охотское море стало целиком российским',
630 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
634 'skip_download': True,
639 '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/',
643 'title': 'Дошкольное воспитание',
648 'url': 'http://www.vestifinance.ru/articles/25753',
651 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
656 'title': 'Госзаказ. День 3',
662 'title': 'Госзаказ. День 2',
668 'title': 'Госзаказ. День 1',
674 'skip_download': True,
679 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
681 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
683 'title': 'Ужастики, русский трейлер (2015)',
684 'thumbnail': r're:^https?://.*\.jpg$',
690 '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',
693 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
695 'playlist_mincount': 7,
696 # This forum does not allow <iframe> syntaxes anymore
697 # Now HTML tags are displayed as-is
698 'skip': 'No videos on this page',
702 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
703 'md5': '65fdff94098e4a607385a60c5177c638',
707 'title': 'Hidden miracles of the natural world',
708 'uploader': 'Louie Schwartzberg',
709 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
712 # nowvideo embed hidden behind percent encoding
714 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
715 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
717 'id': '06e53103ca9aa',
719 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
720 'description': 'No description',
725 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
726 'md5': '7653032cbb25bf6c80d80f217055fa43',
728 'id': '048195-004_PLUS7-F',
731 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
732 'upload_date': '20140320',
735 'skip_download': 'Requires rtmpdump'
737 'skip': 'video gone',
741 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
745 'title': 'Alcaline, le concert avec Calogero',
746 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
747 'upload_date': '20150226',
748 'timestamp': 1424989860,
753 'skip_download': True,
755 'expected_warnings': [
761 'url': 'http://www.wired.com/2014/04/honda-asimo/',
762 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
764 'id': '53501be369702d3275860000',
766 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
771 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
772 'md5': '441aeeb82eb72c422c7f14ec533999cd',
774 'id': 'k2mm4bCdJ6CQ2i7c8o2',
776 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
777 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
779 'uploader_id': 'xgditw',
780 'upload_date': '20140425',
781 'timestamp': 1398441542,
783 'add_ie': ['Dailymotion'],
787 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
791 'title': 'Care worker punches elderly dementia patient in head 11 times',
792 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
794 'add_ie': ['DailyMail'],
796 'skip_download': True,
801 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
805 'title': 'The NBL Auction 2014',
806 'uploader': 'BADMINTON England',
807 'uploader_id': 'BADMINTONEvents',
808 'upload_date': '20140603',
809 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
811 'add_ie': ['Youtube'],
813 'skip_download': True,
818 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
819 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
821 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
823 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
824 'description': 'Two valets share their love for movie star Liam Neesons.',
825 'timestamp': 1349922600,
826 'upload_date': '20121011',
829 # YouTube embed via <data-embed-url="">
831 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
835 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
836 'uploader': 'Gameloft',
837 'uploader_id': 'gameloft',
838 'upload_date': '20140828',
839 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
842 'skip_download': True,
845 # YouTube <object> embed
847 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
848 'md5': '516718101ec834f74318df76259fb3cc',
852 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
853 'upload_date': '20080526',
854 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
855 'uploader': 'Christopher Sykes',
856 'uploader_id': 'ChristopherJSykes',
858 'add_ie': ['Youtube'],
862 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
864 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
866 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
867 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
872 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
874 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
875 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
881 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
886 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
887 'md5': '9d65602bf31c6e20014319c7d07fba27',
889 'id': '5123ea6d5e5a7',
892 'uploader': 'www.handjobhub.com',
893 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
896 # Multiple brightcove videos
897 # https://github.com/rg3/youtube-dl/issues/2283
899 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
901 'id': 'always-never',
902 'title': 'Always / Never - The New Yorker',
906 'extract_flat': False,
907 'skip_download': True,
912 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
913 'md5': '96f09a37e44da40dd083e12d9a683327',
917 'title': 'Ump changes call to ball',
918 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
920 'timestamp': 1401537900,
921 'upload_date': '20140531',
922 'thumbnail': r're:^https?://.*\.jpg$',
927 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
928 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
932 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
933 'description': 'a Paywall Videos video from Remilon',
935 'uploader': 'study.com',
936 'timestamp': 1459678540,
937 'upload_date': '20160403',
938 'filesize': 24687186,
942 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
943 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
947 'title': 'Conversation about Hexagonal Rails Part 1',
948 'description': 'a Martin Fowler video from ThoughtWorks',
950 'uploader': 'thoughtworks.wistia.com',
951 'timestamp': 1401832161,
952 'upload_date': '20140603',
955 # Wistia standard embed (async)
957 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
961 'title': 'Drip Brennan Dunn Workshop',
962 'description': 'a JV Webinars video from getdrip-1',
964 'timestamp': 1463607249,
965 'upload_date': '20160518',
968 'skip_download': True,
973 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
977 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
978 'uploader': 'Sophos Security',
979 'title': 'Chet Chat 171 - Oct 29, 2014',
980 'upload_date': '20141029',
983 # Soundcloud multiple embeds
985 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
988 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
990 'playlist_mincount': 7,
992 # TuneIn station embed
994 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
999 'location': 'Paris, France',
1004 'skip_download': True,
1009 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1013 'upload_date': '20141112',
1014 'title': 'Rosetta #CometLanding webcast HL 10',
1017 # Another Livestream embed, without 'new.' in URL
1019 'url': 'https://www.freespeech.org/',
1023 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1027 'skip_download': True,
1032 'url': 'https://skiplagged.com/',
1035 'title': 'Skiplagged: The smart way to find cheap flights',
1037 'playlist_mincount': 1,
1038 'add_ie': ['Youtube'],
1042 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1046 'upload_date': '20141126',
1047 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1052 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1054 'id': '730m_DandD_1901_512k',
1056 'uploader': 'www.abc.net.au',
1057 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1060 # embedded viddler video
1062 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1066 'uploader': 'deadspin',
1067 'title': 'WALL-TO-GORTAT',
1068 'timestamp': 1422285291,
1069 'upload_date': '20150126',
1071 'add_ie': ['Viddler'],
1075 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1079 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1080 'description': 'md5:601cb790edd05908957dae8aaa866465',
1081 'upload_date': '20150220',
1083 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1087 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1089 'id': 'Mrj4DVp2zeA',
1091 'upload_date': '20150212',
1092 'uploader': 'The National Archives UK',
1093 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1094 'uploader_id': 'NationalArchives08',
1095 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1100 'url': 'http://www.suffolk.edu/sjc/',
1104 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1105 'uploader': 'www.suffolk.edu',
1108 'skip_download': True,
1113 'url': 'http://www.indiedb.com/games/king-machine/videos',
1117 'title': 'king machine trailer 1',
1118 'thumbnail': r're:^https?://.*\.jpg$',
1122 # JWPlayer config passed as variable
1123 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1127 'title': 'ARIELE | Tube Cup',
1128 'uploader': 'www.txxx.com',
1132 'skip_download': True,
1136 # Video.js embed, multiple formats
1137 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1139 'id': 'yygqldloqIk',
1141 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1142 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1143 'upload_date': '20130314',
1144 'uploader': 'PROстое3D',
1145 'uploader_id': 'PROstoe3D',
1148 'skip_download': True,
1152 # Video.js embed, single format
1153 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1157 'title': 'Step 1 - Good Foundation',
1158 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1161 'skip_download': True,
1166 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1167 'playlist_mincount': 5,
1169 'id': 'aanslagen-kopenhagen',
1170 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1175 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1179 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1182 # Kaltura embed (different embed code)
1184 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1188 'upload_date': '20150127',
1189 'uploader_id': 'PremierMedia',
1191 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1194 # Kaltura embed with single quotes
1196 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1201 'timestamp': 1355743100,
1202 'upload_date': '20121217',
1203 'uploader_id': 'batchUser',
1205 'add_ie': ['Kaltura'],
1208 # Kaltura embedded via quoted entry_id
1209 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1213 'title': '06_matthew_brender_raj_dutt',
1214 'timestamp': 1466638791,
1215 'upload_date': '20160622',
1217 'add_ie': ['Kaltura'],
1218 'expected_warnings': [
1219 'Could not send HEAD request'
1222 'skip_download': True,
1226 # Kaltura embedded, some fileExt broken (#11480)
1227 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1231 'title': 'Our "Standard Models" of particle physics and cosmology',
1232 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1233 'timestamp': 1321158993,
1234 'upload_date': '20111113',
1235 'uploader_id': 'kps1',
1237 'add_ie': ['Kaltura'],
1240 # Kaltura iframe embed
1241 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1242 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1246 'title': 'I. M. Pei: A Centennial Celebration',
1247 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1248 'upload_date': '20170403',
1249 'uploader_id': 'batchUser',
1250 'timestamp': 1491232186,
1252 'add_ie': ['Kaltura'],
1254 # EaglePlatform embed (generic URL)
1256 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1257 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1261 'title': 'Навальный вышел на свободу',
1262 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1263 'thumbnail': r're:^https?://.*\.jpg$',
1269 'skip_download': True,
1272 # referrer protected EaglePlatform embed
1274 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1278 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1279 'thumbnail': r're:^https?://.*\.jpg$',
1284 'skip_download': True,
1287 # ClipYou (EaglePlatform) embed (custom URL)
1289 'url': 'http://muz-tv.ru/play/7129/',
1290 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1294 'title': "'O Sole Mio",
1295 'thumbnail': r're:^https?://.*\.jpg$',
1300 'skip_download': True,
1305 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1309 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1310 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1311 'thumbnail': r're:^https?://.*\.jpg$',
1318 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1322 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1323 'thumbnail': r're:^https?://.*\.png$',
1329 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1330 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1334 'title': 'Facebook Creates "On This Day" | Crunch Report',
1339 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1343 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1348 # Crooks and Liars embed
1350 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1354 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1355 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1356 'timestamp': 1428207000,
1357 'upload_date': '20150405',
1358 'uploader': 'Heather',
1361 # Crooks and Liars external embed
1363 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1365 'id': 'MTE3MjUtMzQ2MzA',
1367 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1368 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1369 'timestamp': 1265032391,
1370 'upload_date': '20100201',
1371 'uploader': 'Heather',
1374 # NBC Sports vplayer embed
1376 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1378 'id': 'ln7x1qSThw4k',
1380 'title': "PFT Live: New leader in the 'new-look' defense",
1381 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1382 'uploader': 'NBCU-SPORTS',
1383 'upload_date': '20140107',
1384 'timestamp': 1389118457,
1389 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1390 'md5': '1aa589c675898ae6d37a17913cf68d66',
1392 'id': '701714499682',
1394 'title': 'PREVIEW: On Assignment: David Letterman',
1395 '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.',
1400 'url': 'https://video.udn.com/news/300346',
1401 'md5': 'fd2060e988c326991037b9aff9df21a6',
1405 'title': '中一中男師變性 全校師生力挺',
1406 'thumbnail': r're:^https?://.*\.jpg$',
1410 'skip_download': True,
1415 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1417 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1419 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1420 'title': 'This is what separates the Excel masters from the wannabes',
1421 'duration': 191.933,
1425 'skip_download': True,
1428 # Brightcove URL in single quotes
1430 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1431 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1433 'id': '4255764656001',
1435 'title': 'SN Presents: Russell Martin, World Citizen',
1436 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1437 'uploader': 'Rogers Sportsnet',
1438 'uploader_id': '1704050871',
1439 'upload_date': '20150525',
1440 'timestamp': 1432570283,
1443 # Dailymotion Cloud video
1445 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1446 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1450 'title': 'Sauvons les abeilles ! - Le débat',
1451 'description': 'md5:d9082128b1c5277987825d684939ca26',
1452 'thumbnail': r're:^https?://.*\.jpe?g$',
1453 'timestamp': 1434970506,
1454 'upload_date': '20150622',
1455 'uploader': 'Public Sénat',
1456 'uploader_id': 'xa9gza',
1459 # OnionStudios embed
1461 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1465 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1466 'thumbnail': r're:^https?://.*\.jpe?g$',
1467 'uploader': 'ClickHole',
1468 'uploader_id': 'clickhole',
1473 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1475 'id': '74849a00-85a9-11e1-9660-123139220831',
1477 'title': '#whilewewatch',
1480 # AdobeTVVideo embed
1482 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1483 'md5': '43662b577c018ad707a63766462b1e87',
1487 'title': 'New experience with Acrobat DC',
1488 'description': 'New experience with Acrobat DC',
1489 'duration': 248.667,
1492 # BrightcoveInPageEmbed embed
1494 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1496 'id': '4238694884001',
1498 'title': 'Tabletop: Dread, Last Thoughts',
1499 'description': 'Tabletop: Dread, Last Thoughts',
1503 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1504 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1506 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1508 'id': '4785848093001',
1510 'title': 'The Cardinal Pell Interview',
1511 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1512 'uploader': 'GlobeCast Australia - GlobeStream',
1513 'uploader_id': '2733773828001',
1514 'upload_date': '20160304',
1515 'timestamp': 1457083087,
1519 'skip_download': True,
1523 # Brightcove embed with whitespace around attribute names
1524 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1526 'id': '3167554373001',
1528 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1529 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1530 'uploader_id': '1079349493',
1531 'upload_date': '20140207',
1532 'timestamp': 1391810548,
1535 'skip_download': True,
1538 # Another form of arte.tv embed
1540 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1541 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1543 'id': '030273-562_PLUS7-F',
1545 'title': 'ARTE Reportage - Nulle part, en France',
1546 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1547 'upload_date': '20160409',
1552 'url': 'http://www.wykop.pl/link/3088787/',
1553 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1555 'id': '874_1459135191',
1557 'title': 'Man shows poor quality of new apartment building',
1558 'description': 'The wall is like a sand pile.',
1559 'uploader': 'Lake8737',
1561 'add_ie': [LiveLeakIE.ie_key()],
1563 # Another LiveLeak embed pattern (#13336)
1565 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1567 'id': '2eb_1496309988',
1569 'title': 'Thief robs place where everyone was armed',
1570 'description': 'md5:694d73ee79e535953cf2488562288eee',
1571 'uploader': 'brazilwtf',
1573 'add_ie': [LiveLeakIE.ie_key()],
1575 # Duplicated embedded video URLs
1577 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1579 'id': '149298443_480_16c25b74_2',
1581 'title': 'vs. Blue Orange Spring Game',
1582 'uploader': 'www.hudl.com',
1585 # twitter:player:stream embed
1587 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1591 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1592 'uploader': 'www.rtl.be',
1596 'skip_download': True,
1599 # twitter:player embed
1601 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1602 'md5': 'a3e0df96369831de324f0778e126653c',
1604 'id': '4909620399001',
1606 'title': 'What Do Black Holes Sound Like?',
1607 'description': 'what do black holes sound like',
1608 'upload_date': '20160524',
1609 'uploader_id': '29913724001',
1610 'timestamp': 1464107587,
1611 'uploader': 'TheAtlantic',
1613 'add_ie': ['BrightcoveLegacy'],
1617 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1621 'title': "Yesterday's Jam (OV)",
1622 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1623 'timestamp': 1492594816,
1624 'upload_date': '20170419',
1627 'format': 'bestvideo',
1628 'skip_download': True,
1631 # Facebook <iframe> embed
1633 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1634 'md5': 'fbcde74f534176ecb015849146dd3aee',
1636 'id': '599637780109885',
1638 'title': 'Facebook video #599637780109885',
1641 # Facebook <iframe> embed, plugin video
1643 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1645 'id': '1754168231264132',
1647 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1648 'uploader': 'Tariq Ramadan (official)',
1649 'timestamp': 1496758379,
1650 'upload_date': '20170606',
1653 'skip_download': True,
1656 # Facebook API embed
1658 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1659 'md5': 'a47372ee61b39a7b90287094d447d94e',
1661 'id': '10153467542406923',
1663 'title': 'Facebook video #10153467542406923',
1666 # Wordpress "YouTube Video Importer" plugin
1668 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1669 'md5': 'd16797741b560b485194eddda8121b48',
1671 'id': 'HNTXWDXV9Is',
1673 'title': 'Blue Devils Drumline Stanford lot 2016',
1674 'upload_date': '20160627',
1675 'uploader_id': 'GENOCIDE8GENERAL10',
1676 'uploader': 'cylus cyrus',
1680 # video stored on custom kaltura server
1681 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1682 'md5': '537617d06e64dfed891fa1593c4b30cc',
1686 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1687 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1688 'uploader_id': 'videos.expansion@el-mundo.net',
1689 'upload_date': '20150429',
1690 'timestamp': 1430303472,
1692 'add_ie': ['Kaltura'],
1695 # Non-standard Vimeo embed
1696 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1697 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1701 'title': 'Understanding the web - Teaser',
1702 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1703 'upload_date': '20151214',
1704 'uploader': 'OpenClassrooms',
1705 'uploader_id': 'openclassrooms',
1707 'add_ie': ['Vimeo'],
1710 # generic vimeo embed that requires original URL passed as Referer
1711 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1712 'only_matching': True,
1715 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1716 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1718 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1720 'title': 'Big Buck Bunny',
1721 'description': 'Royalty free test video',
1722 'timestamp': 1432816365,
1723 'upload_date': '20150528',
1727 'skip_download': True,
1729 'add_ie': [ArkenaIE.ie_key()],
1732 '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/',
1736 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1739 'skip_download': True,
1741 'add_ie': [Vbox7IE.ie_key()],
1745 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1748 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1750 'playlist_mincount': 3,
1754 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1756 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1757 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1759 'playlist_mincount': 2,
1763 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1767 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1768 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1771 'skip_download': True,
1773 'add_ie': [TwentyMinutenIE.ie_key()],
1777 'url': 'https://en.support.wordpress.com/videopress/',
1781 'title': 'IMG_5786',
1782 'timestamp': 1435711927,
1783 'upload_date': '20150701',
1786 'skip_download': True,
1788 'add_ie': [VideoPressIE.ie_key()],
1792 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1794 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1796 'title': 'Магаззино: Казань 2',
1797 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1798 'uploader': 'Магаззино',
1799 'upload_date': '20170228',
1800 'uploader_id': '996642',
1803 'skip_download': True,
1805 'add_ie': [RutubeIE.ie_key()],
1808 # ThePlatform embedded with whitespaces in URLs
1809 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1810 'only_matching': True,
1813 # Senate ISVP iframe https
1814 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1815 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1817 'id': 'govtaff020316',
1819 'title': 'Integrated Senate Video Player',
1821 'add_ie': [SenateISVPIE.ie_key()],
1824 # Limelight embeds (1 channel embed + 4 media embeds)
1825 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1827 'id': 'FacilitatorTraining2017',
1828 'title': 'Facilitator Training 2017',
1830 'playlist_mincount': 5,
1833 # Limelight embed (LimelightPlayerUtil.embed)
1834 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1836 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1838 'title': '07448641',
1839 'timestamp': 1499890639,
1840 'upload_date': '20170712',
1843 'skip_download': True,
1845 'add_ie': ['LimelightMedia'],
1848 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1850 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1851 'title': 'Standoff with Walnut Creek murder suspect ends',
1852 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1854 'playlist_mincount': 4,
1857 # WashingtonPost embed
1858 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1860 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1862 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1863 '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.',
1864 'timestamp': 1455216756,
1865 'uploader': 'The Washington Post',
1866 'upload_date': '20160211',
1868 'add_ie': [WashingtonPostIE.ie_key()],
1872 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1876 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1879 'skip_download': True,
1881 'add_ie': [MediasetIE.ie_key()],
1885 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1887 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1888 'title': 'Slovenskom sa prehnala vlna silných búrok',
1890 'playlist_mincount': 5,
1891 'add_ie': [JojIE.ie_key()],
1894 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1895 'url': 'https://tvrain.ru/amp/418921/',
1896 'md5': 'cc00413936695987e8de148b67d14f1d',
1900 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1905 'url': 'http://help.vzaar.com/article/165-embedding-video',
1906 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1910 'title': 'Building A Business Online: Principal Chairs Q & A',
1914 # multiple HTML5 videos on one page
1915 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1917 'id': 'keyscenarios',
1918 'title': 'Rescue Kit 14 Free Edition - Getting started',
1920 'playlist_count': 4,
1923 # # TODO: find another test
1924 # # http://schema.org/VideoObject
1925 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1926 # 'md5': '888dcf08b7ea671381f00fab74692755',
1928 # 'id': 'nyvTSJMKId',
1930 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1931 # 'description': '#love for cats.',
1932 # 'timestamp': 1461244995,
1933 # 'upload_date': '20160421',
1936 # 'force_generic_extractor': True,
1941 def report_following_redirect(self, new_url):
1942 """Report information extraction."""
1943 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1945 def _extract_rss(self, url, video_id, doc):
1946 playlist_title = doc.find('./channel/title').text
1947 playlist_desc_el = doc.find('./channel/description')
1948 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1951 for it in doc.findall('./channel/item'):
1952 next_url = xpath_text(it, 'link', fatal=False)
1954 enclosure_nodes = it.findall('./enclosure')
1955 for e in enclosure_nodes:
1956 next_url = e.attrib.get('url')
1964 '_type': 'url_transparent',
1966 'title': it.find('title').text,
1970 '_type': 'playlist',
1972 'title': playlist_title,
1973 'description': playlist_desc,
1977 def _extract_camtasia(self, url, video_id, webpage):
1978 """ Returns None if no camtasia video can be found. """
1980 camtasia_cfg = self._search_regex(
1981 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1982 webpage, 'camtasia configuration file', default=None)
1983 if camtasia_cfg is None:
1986 title = self._html_search_meta('DC.title', webpage, fatal=True)
1988 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1989 camtasia_cfg = self._download_xml(
1990 camtasia_url, video_id,
1991 note='Downloading camtasia configuration',
1992 errnote='Failed to download camtasia configuration')
1993 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1996 for n in fileset_node.getchildren():
1997 url_n = n.find('./uri')
2002 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2003 'title': '%s - %s' % (title, n.tag),
2004 'url': compat_urlparse.urljoin(url, url_n.text),
2005 'duration': float_or_none(n.find('./duration').text),
2009 '_type': 'playlist',
2014 def _real_extract(self, url):
2015 if url.startswith('//'):
2018 'url': self.http_scheme() + url,
2021 parsed_url = compat_urlparse.urlparse(url)
2022 if not parsed_url.scheme:
2023 default_search = self._downloader.params.get('default_search')
2024 if default_search is None:
2025 default_search = 'fixup_error'
2027 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2029 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2030 return self.url_result('http://' + url)
2031 elif default_search != 'fixup_error':
2032 if default_search == 'auto_warning':
2033 if re.match(r'^(?:url|URL)$', url):
2034 raise ExtractorError(
2035 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2038 self._downloader.report_warning(
2039 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2040 return self.url_result('ytsearch:' + url)
2042 if default_search in ('error', 'fixup_error'):
2043 raise ExtractorError(
2044 '%r is not a valid URL. '
2045 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2046 % (url, url), expected=True)
2048 if ':' not in default_search:
2049 default_search += ':'
2050 return self.url_result(default_search + url)
2052 url, smuggled_data = unsmuggle_url(url)
2053 force_videoid = None
2054 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2055 if smuggled_data and 'force_videoid' in smuggled_data:
2056 force_videoid = smuggled_data['force_videoid']
2057 video_id = force_videoid
2059 video_id = self._generic_id(url)
2061 self.to_screen('%s: Requesting header' % video_id)
2063 head_req = HEADRequest(url)
2064 head_response = self._request_webpage(
2066 note=False, errnote='Could not send HEAD request to %s' % url,
2069 if head_response is not False:
2070 # Check for redirect
2071 new_url = compat_str(head_response.geturl())
2073 self.report_following_redirect(new_url)
2075 new_url = smuggle_url(
2076 new_url, {'force_videoid': force_videoid})
2077 return self.url_result(new_url)
2079 full_response = None
2080 if head_response is False:
2081 request = sanitized_Request(url)
2082 request.add_header('Accept-Encoding', '*')
2083 full_response = self._request_webpage(request, video_id)
2084 head_response = full_response
2088 'title': self._generic_title(url),
2089 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2092 # Check for direct link to a video
2093 content_type = head_response.headers.get('Content-Type', '').lower()
2094 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2096 format_id = compat_str(m.group('format_id'))
2097 if format_id.endswith('mpegurl'):
2098 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2099 elif format_id == 'f4m':
2100 formats = self._extract_f4m_formats(url, video_id)
2103 'format_id': format_id,
2105 'vcodec': 'none' if m.group('type') == 'audio' else None
2107 info_dict['direct'] = True
2108 self._sort_formats(formats)
2109 info_dict['formats'] = formats
2112 if not self._downloader.params.get('test', False) and not is_intentional:
2113 force = self._downloader.params.get('force_generic_extractor', False)
2114 self._downloader.report_warning(
2115 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2117 if not full_response:
2118 request = sanitized_Request(url)
2119 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2120 # making it impossible to download only chunk of the file (yet we need only 512kB to
2121 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2122 # that will always result in downloading the whole file that is not desirable.
2123 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2124 # to accept raw bytes and being able to download only a chunk.
2125 # It may probably better to solve this by checking Content-Type for application/octet-stream
2126 # after HEAD request finishes, but not sure if we can rely on this.
2127 request.add_header('Accept-Encoding', '*')
2128 full_response = self._request_webpage(request, video_id)
2130 first_bytes = full_response.read(512)
2132 # Is it an M3U playlist?
2133 if first_bytes.startswith(b'#EXTM3U'):
2134 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2135 self._sort_formats(info_dict['formats'])
2138 # Maybe it's a direct link to a video?
2139 # Be careful not to download the whole thing!
2140 if not is_html(first_bytes):
2141 self._downloader.report_warning(
2142 'URL could be a direct video link, returning it as such.')
2149 webpage = self._webpage_read_content(
2150 full_response, url, video_id, prefix=first_bytes)
2152 self.report_extraction(video_id)
2154 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2156 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2157 if doc.tag == 'rss':
2158 return self._extract_rss(url, video_id, doc)
2159 elif doc.tag == 'SmoothStreamingMedia':
2160 info_dict['formats'] = self._parse_ism_formats(doc, url)
2161 self._sort_formats(info_dict['formats'])
2163 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2164 smil = self._parse_smil(doc, url, video_id)
2165 self._sort_formats(smil['formats'])
2167 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2168 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2169 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2170 info_dict['formats'] = self._parse_mpd_formats(
2172 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2174 self._sort_formats(info_dict['formats'])
2176 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2177 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2178 self._sort_formats(info_dict['formats'])
2180 except compat_xml_parse_error:
2183 # Is it a Camtasia project?
2184 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2185 if camtasia_res is not None:
2188 # Sometimes embedded video player is hidden behind percent encoding
2189 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2190 # Unescaping the whole page allows to handle those cases in a generic way
2191 webpage = compat_urllib_parse_unquote(webpage)
2193 # it's tempting to parse this further, but you would
2194 # have to take into account all the variations like
2195 # Video Title - Site Name
2196 # Site Name | Video Title
2197 # Video Title - Tagline | Site Name
2198 # and so on and so forth; it's just not practical
2199 video_title = self._og_search_title(
2200 webpage, default=None) or self._html_search_regex(
2201 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2204 # Try to detect age limit automatically
2205 age_limit = self._rta_search(webpage)
2206 # And then there are the jokers who advertise that they use RTA,
2207 # but actually don't.
2208 AGE_LIMIT_MARKERS = [
2209 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2211 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2214 # video uploader is domain name
2215 video_uploader = self._search_regex(
2216 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2218 video_description = self._og_search_description(webpage, default=None)
2219 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2222 'title': video_title,
2223 'description': video_description,
2224 'thumbnail': video_thumbnail,
2225 'age_limit': age_limit,
2228 # Look for Brightcove Legacy Studio embeds
2229 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2233 'url': smuggle_url(bc_url, {'Referer': url}),
2234 'ie_key': 'BrightcoveLegacy'
2235 } for bc_url in bc_urls]
2238 '_type': 'playlist',
2239 'title': video_title,
2244 # Look for Brightcove New Studio embeds
2245 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2247 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2249 # Look for Nexx embeds
2250 nexx_urls = NexxIE._extract_urls(webpage)
2252 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2254 # Look for Nexx iFrame embeds
2255 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2257 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2259 # Look for ThePlatform embeds
2260 tp_urls = ThePlatformIE._extract_urls(webpage)
2262 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2264 # Look for Vessel embeds
2265 vessel_urls = VesselIE._extract_urls(webpage)
2267 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2269 # Look for embedded rtl.nl player
2270 matches = re.findall(
2271 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2274 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2276 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2278 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2280 vid_me_embed_url = self._search_regex(
2281 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2282 webpage, 'vid.me embed', default=None)
2283 if vid_me_embed_url is not None:
2284 return self.url_result(vid_me_embed_url, 'Vidme')
2286 # Look for YouTube embeds
2287 youtube_urls = YoutubeIE._extract_urls(webpage)
2289 return self.playlist_from_matches(
2290 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2292 matches = DailymotionIE._extract_urls(webpage)
2294 return self.playlist_from_matches(matches, video_id, video_title)
2296 # Look for embedded Dailymotion playlist player (#3822)
2298 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2300 playlists = re.findall(
2301 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2303 return self.playlist_from_matches(
2304 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2306 # Look for DailyMail embeds
2307 dailymail_urls = DailyMailIE._extract_urls(webpage)
2309 return self.playlist_from_matches(
2310 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2312 # Look for embedded Wistia player
2313 wistia_url = WistiaIE._extract_url(webpage)
2316 '_type': 'url_transparent',
2317 'url': self._proto_relative_url(wistia_url),
2318 'ie_key': WistiaIE.ie_key(),
2319 'uploader': video_uploader,
2322 # Look for SVT player
2323 svt_url = SVTIE._extract_url(webpage)
2325 return self.url_result(svt_url, 'SVT')
2327 # Look for Bandcamp pages with custom domain
2328 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2329 if mobj is not None:
2330 burl = unescapeHTML(mobj.group(1))
2331 # Don't set the extractor because it can be a track url or an album
2332 return self.url_result(burl)
2334 # Look for embedded Vevo player
2336 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2337 if mobj is not None:
2338 return self.url_result(mobj.group('url'))
2340 # Look for embedded Viddler player
2342 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2344 if mobj is not None:
2345 return self.url_result(mobj.group('url'))
2347 # Look for NYTimes player
2349 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2351 if mobj is not None:
2352 return self.url_result(mobj.group('url'))
2354 # Look for Libsyn player
2356 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2357 if mobj is not None:
2358 return self.url_result(mobj.group('url'))
2360 # Look for Ooyala videos
2361 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2362 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2363 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2364 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2365 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2366 if mobj is not None:
2367 embed_token = self._search_regex(
2368 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2369 webpage, 'ooyala embed token', default=None)
2370 return OoyalaIE._build_url_result(smuggle_url(
2373 'embed_token': embed_token,
2376 # Look for multiple Ooyala embeds on SBN network websites
2377 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2378 if mobj is not None:
2379 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2381 return self.playlist_from_matches(
2382 embeds, video_id, video_title,
2383 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2385 # Look for Aparat videos
2386 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2387 if mobj is not None:
2388 return self.url_result(mobj.group(1), 'Aparat')
2390 # Look for MPORA videos
2391 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2392 if mobj is not None:
2393 return self.url_result(mobj.group(1), 'Mpora')
2395 # Look for embedded NovaMov-based player
2397 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2398 (?P<url>http://(?:(?:embed|www)\.)?
2400 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2401 videoweed\.(?:es|com)|
2402 movshare\.(?:net|sx|ag)|
2403 divxstage\.(?:eu|net|ch|co|at|ag))
2404 /embed\.php.+?)\1''', webpage)
2405 if mobj is not None:
2406 return self.url_result(mobj.group('url'))
2408 # Look for embedded Facebook player
2409 facebook_urls = FacebookIE._extract_urls(webpage)
2411 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2413 # Look for embedded VK player
2414 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2415 if mobj is not None:
2416 return self.url_result(mobj.group('url'), 'VK')
2418 # Look for embedded Odnoklassniki player
2419 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2420 if mobj is not None:
2421 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2423 # Look for embedded ivi player
2424 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2425 if mobj is not None:
2426 return self.url_result(mobj.group('url'), 'Ivi')
2428 # Look for embedded Huffington Post player
2430 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2431 if mobj is not None:
2432 return self.url_result(mobj.group('url'), 'HuffPost')
2435 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2436 if mobj is not None:
2437 return self.url_result(mobj.group('url'))
2438 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2439 if mobj is not None:
2440 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2442 # Look for funnyordie embed
2443 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2445 return self.playlist_from_matches(
2446 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2448 # Look for BBC iPlayer embed
2449 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2451 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2453 # Look for embedded RUTV player
2454 rutv_url = RUTVIE._extract_url(webpage)
2456 return self.url_result(rutv_url, 'RUTV')
2458 # Look for embedded TVC player
2459 tvc_url = TVCIE._extract_url(webpage)
2461 return self.url_result(tvc_url, 'TVC')
2463 # Look for embedded SportBox player
2464 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2466 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2468 # Look for embedded XHamster player
2469 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2471 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2473 # Look for embedded TNAFlixNetwork player
2474 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2476 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2478 # Look for embedded PornHub player
2479 pornhub_urls = PornHubIE._extract_urls(webpage)
2481 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2483 # Look for embedded DrTuber player
2484 drtuber_urls = DrTuberIE._extract_urls(webpage)
2486 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2488 # Look for embedded RedTube player
2489 redtube_urls = RedTubeIE._extract_urls(webpage)
2491 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2493 # Look for embedded Tvigle player
2495 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2496 if mobj is not None:
2497 return self.url_result(mobj.group('url'), 'Tvigle')
2499 # Look for embedded TED player
2501 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2502 if mobj is not None:
2503 return self.url_result(mobj.group('url'), 'TED')
2505 # Look for embedded Ustream videos
2506 ustream_url = UstreamIE._extract_url(webpage)
2508 return self.url_result(ustream_url, UstreamIE.ie_key())
2510 # Look for embedded arte.tv player
2512 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2514 if mobj is not None:
2515 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2517 # Look for embedded francetv player
2519 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2521 if mobj is not None:
2522 return self.url_result(mobj.group('url'))
2524 # Look for embedded smotri.com player
2525 smotri_url = SmotriIE._extract_url(webpage)
2527 return self.url_result(smotri_url, 'Smotri')
2529 # Look for embedded Myvi.ru player
2530 myvi_url = MyviIE._extract_url(webpage)
2532 return self.url_result(myvi_url)
2534 # Look for embedded soundcloud player
2535 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2537 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2539 # Look for tunein player
2540 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2542 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2544 # Look for embedded mtvservices player
2545 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2547 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2549 # Look for embedded yahoo player
2551 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2553 if mobj is not None:
2554 return self.url_result(mobj.group('url'), 'Yahoo')
2556 # Look for embedded sbs.com.au player
2560 <meta\s+property="og:video"\s+content=|
2563 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2565 if mobj is not None:
2566 return self.url_result(mobj.group('url'), 'SBS')
2568 # Look for embedded Cinchcast player
2570 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'Cinchcast')
2576 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2580 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2582 if mobj is not None:
2583 return self.url_result(mobj.group('url'), 'MLB')
2586 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2588 if mobj is not None:
2589 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2592 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2594 if mobj is not None:
2595 return self.url_result(mobj.group('url'), 'Livestream')
2597 # Look for Zapiks embed
2599 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2600 if mobj is not None:
2601 return self.url_result(mobj.group('url'), 'Zapiks')
2603 # Look for Kaltura embeds
2604 kaltura_url = KalturaIE._extract_url(webpage)
2606 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2608 # Look for EaglePlatform embeds
2609 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2610 if eagleplatform_url:
2611 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2613 # Look for ClipYou (uses EaglePlatform) embeds
2615 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2616 if mobj is not None:
2617 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2619 # Look for Pladform embeds
2620 pladform_url = PladformIE._extract_url(webpage)
2622 return self.url_result(pladform_url)
2624 # Look for Videomore embeds
2625 videomore_url = VideomoreIE._extract_url(webpage)
2627 return self.url_result(videomore_url)
2629 # Look for Webcaster embeds
2630 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2632 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2634 # Look for Playwire embeds
2636 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2637 if mobj is not None:
2638 return self.url_result(mobj.group('url'))
2640 # Look for 5min embeds
2642 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2643 if mobj is not None:
2644 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2646 # Look for Crooks and Liars embeds
2648 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2649 if mobj is not None:
2650 return self.url_result(mobj.group('url'))
2652 # Look for NBC Sports VPlayer embeds
2653 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2655 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2657 # Look for NBC News embeds
2658 nbc_news_embed_url = re.search(
2659 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2660 if nbc_news_embed_url:
2661 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2663 # Look for Google Drive embeds
2664 google_drive_url = GoogleDriveIE._extract_url(webpage)
2665 if google_drive_url:
2666 return self.url_result(google_drive_url, 'GoogleDrive')
2668 # Look for UDN embeds
2670 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2671 if mobj is not None:
2672 return self.url_result(
2673 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2675 # Look for Senate ISVP iframe
2676 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2678 return self.url_result(senate_isvp_url, 'SenateISVP')
2680 # Look for Dailymotion Cloud videos
2681 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2683 return self.url_result(dmcloud_url, 'DailymotionCloud')
2685 # Look for OnionStudios embeds
2686 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2687 if onionstudios_url:
2688 return self.url_result(onionstudios_url)
2690 # Look for ViewLift embeds
2691 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2693 return self.url_result(viewlift_url)
2695 # Look for JWPlatform embeds
2696 jwplatform_url = JWPlatformIE._extract_url(webpage)
2698 return self.url_result(jwplatform_url, 'JWPlatform')
2700 # Look for Digiteka embeds
2701 digiteka_url = DigitekaIE._extract_url(webpage)
2703 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2705 # Look for Arkena embeds
2706 arkena_url = ArkenaIE._extract_url(webpage)
2708 return self.url_result(arkena_url, ArkenaIE.ie_key())
2710 # Look for Piksel embeds
2711 piksel_url = PikselIE._extract_url(webpage)
2713 return self.url_result(piksel_url, PikselIE.ie_key())
2715 # Look for Limelight embeds
2716 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2718 return self.playlist_result(
2719 limelight_urls, video_id, video_title, video_description)
2721 # Look for Anvato embeds
2722 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2724 return self.playlist_result(
2725 anvato_urls, video_id, video_title, video_description)
2727 # Look for AdobeTVVideo embeds
2729 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2731 if mobj is not None:
2732 return self.url_result(
2733 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2736 # Look for Vine embeds
2738 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2740 if mobj is not None:
2741 return self.url_result(
2742 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2744 # Look for VODPlatform embeds
2746 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2748 if mobj is not None:
2749 return self.url_result(
2750 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2752 # Look for Mangomolo embeds
2754 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2756 video\?.*?\bid=(?P<video_id>\d+)|
2757 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2758 ).+?)\1''', webpage)
2759 if mobj is not None:
2761 '_type': 'url_transparent',
2762 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2763 'title': video_title,
2764 'description': video_description,
2765 'thumbnail': video_thumbnail,
2766 'uploader': video_uploader,
2768 video_id = mobj.group('video_id')
2771 'ie_key': 'MangomoloVideo',
2776 'ie_key': 'MangomoloLive',
2777 'id': mobj.group('channel_id'),
2781 # Look for Instagram embeds
2782 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2783 if instagram_embed_url is not None:
2784 return self.url_result(
2785 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2787 # Look for LiveLeak embeds
2788 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2790 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2792 # Look for 3Q SDN embeds
2793 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2796 '_type': 'url_transparent',
2797 'ie_key': ThreeQSDNIE.ie_key(),
2798 'url': self._proto_relative_url(threeqsdn_url),
2799 'title': video_title,
2800 'description': video_description,
2801 'thumbnail': video_thumbnail,
2802 'uploader': video_uploader,
2805 # Look for VBOX7 embeds
2806 vbox7_url = Vbox7IE._extract_url(webpage)
2808 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2810 # Look for DBTV embeds
2811 dbtv_urls = DBTVIE._extract_urls(webpage)
2813 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2815 # Look for Videa embeds
2816 videa_urls = VideaIE._extract_urls(webpage)
2818 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2820 # Look for 20 minuten embeds
2821 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2823 return self.playlist_from_matches(
2824 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2826 # Look for Openload embeds
2827 openload_urls = OpenloadIE._extract_urls(webpage)
2829 return self.playlist_from_matches(
2830 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2832 # Look for VideoPress embeds
2833 videopress_urls = VideoPressIE._extract_urls(webpage)
2835 return self.playlist_from_matches(
2836 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2838 # Look for Rutube embeds
2839 rutube_urls = RutubeIE._extract_urls(webpage)
2841 return self.playlist_from_matches(
2842 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2844 # Look for WashingtonPost embeds
2845 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2847 return self.playlist_from_matches(
2848 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2850 # Look for Mediaset embeds
2851 mediaset_urls = MediasetIE._extract_urls(webpage)
2853 return self.playlist_from_matches(
2854 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2856 # Look for JOJ.sk embeds
2857 joj_urls = JojIE._extract_urls(webpage)
2859 return self.playlist_from_matches(
2860 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2862 # Look for megaphone.fm embeds
2863 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2865 return self.playlist_from_matches(
2866 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2868 # Look for vzaar embeds
2869 vzaar_urls = VzaarIE._extract_urls(webpage)
2871 return self.playlist_from_matches(
2872 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2874 def merge_dicts(dict1, dict2):
2876 for k, v in dict1.items():
2879 for k, v in dict2.items():
2882 if (k not in merged or
2883 (isinstance(v, compat_str) and v and
2884 isinstance(merged[k], compat_str) and
2889 # Look for HTML5 media
2890 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2892 if len(entries) == 1:
2895 'title': video_title,
2898 for num, entry in enumerate(entries, start=1):
2900 'id': '%s-%s' % (video_id, num),
2901 'title': '%s (%d)' % (video_title, num),
2903 for entry in entries:
2904 self._sort_formats(entry['formats'])
2905 return self.playlist_result(entries, video_id, video_title)
2907 jwplayer_data = self._find_jwplayer_data(
2908 webpage, video_id, transform_source=js_to_json)
2910 info = self._parse_jwplayer_data(
2911 jwplayer_data, video_id, require_title=False, base_url=url)
2912 return merge_dicts(info, info_dict)
2916 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2918 if mobj is not None:
2919 sources = self._parse_json(
2920 mobj.group(1), video_id, transform_source=js_to_json,
2922 if not isinstance(sources, list):
2925 for source in sources:
2926 src = source.get('src')
2927 if not src or not isinstance(src, compat_str):
2929 src = compat_urlparse.urljoin(url, src)
2930 src_type = source.get('type')
2931 if isinstance(src_type, compat_str):
2932 src_type = src_type.lower()
2933 ext = determine_ext(src).lower()
2934 if src_type == 'video/youtube':
2935 return self.url_result(src, YoutubeIE.ie_key())
2936 if src_type == 'application/dash+xml' or ext == 'mpd':
2937 formats.extend(self._extract_mpd_formats(
2938 src, video_id, mpd_id='dash', fatal=False))
2939 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2940 formats.extend(self._extract_m3u8_formats(
2941 src, video_id, 'mp4', entry_protocol='m3u8_native',
2942 m3u8_id='hls', fatal=False))
2946 'ext': (mimetype2ext(src_type) or
2947 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2950 self._sort_formats(formats)
2951 info_dict['formats'] = formats
2954 # Looking for http://schema.org/VideoObject
2955 json_ld = self._search_json_ld(
2956 webpage, video_id, default={}, expected_type='VideoObject')
2957 if json_ld.get('url'):
2958 return merge_dicts(json_ld, info_dict)
2960 def check_video(vurl):
2961 if YoutubeIE.suitable(vurl):
2963 if RtmpIE.suitable(vurl):
2965 vpath = compat_urlparse.urlparse(vurl).path
2966 vext = determine_ext(vpath)
2967 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2969 def filter_video(urls):
2970 return list(filter(check_video, urls))
2972 # Start with something easy: JW Player in SWFObject
2973 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2975 # Look for gorilla-vid style embedding
2976 found = filter_video(re.findall(r'''(?sx)
2980 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2983 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2985 # Broaden the search a little bit
2986 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2988 # Broaden the findall a little bit: JWPlayer JS loader
2989 found = filter_video(re.findall(
2990 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2993 found = filter_video(re.findall(r'''(?xs)
2994 flowplayer\("[^"]+",\s*
2996 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2997 ["']?url["']?\s*:\s*["']([^"']+)["']
3002 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3004 # Try to find twitter cards info
3005 # twitter:player:stream should be checked before twitter:player since
3006 # it is expected to contain a raw stream (see
3007 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3008 found = filter_video(re.findall(
3009 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3011 # We look for Open Graph info:
3012 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3013 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3014 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3015 if m_video_type is not None:
3016 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3018 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3020 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3021 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3024 # Look also in Refresh HTTP header
3025 refresh_header = head_response.headers.get('Refresh')
3027 # In python 2 response HTTP headers are bytestrings
3028 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3029 refresh_header = refresh_header.decode('iso-8859-1')
3030 found = re.search(REDIRECT_REGEX, refresh_header)
3032 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3034 self.report_following_redirect(new_url)
3043 # twitter:player is a https URL to iframe player that may or may not
3044 # be supported by youtube-dl thus this is checked the very last (see
3045 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3046 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3047 if embed_url and embed_url != url:
3048 return self.url_result(embed_url)
3051 raise UnsupportedError(url)
3054 for video_url in orderedSet(found):
3055 video_url = unescapeHTML(video_url)
3056 video_url = video_url.replace('\\/', '/')
3057 video_url = compat_urlparse.urljoin(url, video_url)
3058 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3060 # Sometimes, jwplayer extraction will result in a YouTube URL
3061 if YoutubeIE.suitable(video_url):
3062 entries.append(self.url_result(video_url, 'Youtube'))
3065 # here's a fun little line of code for you:
3066 video_id = os.path.splitext(video_id)[0]
3070 'uploader': video_uploader,
3071 'title': video_title,
3072 'age_limit': age_limit,
3075 if RtmpIE.suitable(video_url):
3076 entry_info_dict.update({
3077 '_type': 'url_transparent',
3078 'ie_key': RtmpIE.ie_key(),
3081 entries.append(entry_info_dict)
3084 ext = determine_ext(video_url)
3086 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3088 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3090 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3092 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3094 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3095 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3096 # Just matching .ism/manifest is not enough to be reliably sure
3097 # whether it's actually an ISM manifest or some other streaming
3098 # manifest since there are various streaming URL formats
3099 # possible (see [1]) as well as some other shenanigans like
3100 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3102 # Thus the most reasonable way to solve this is to delegate
3103 # to generic extractor in order to look into the contents of
3104 # the manifest itself.
3105 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3106 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3107 entry_info_dict = self.url_result(
3108 smuggle_url(video_url, {'to_generic': True}),
3111 entry_info_dict['url'] = video_url
3113 if entry_info_dict.get('formats'):
3114 self._sort_formats(entry_info_dict['formats'])
3116 entries.append(entry_info_dict)
3118 if len(entries) == 1:
3121 for num, e in enumerate(entries, start=1):
3122 # 'url' results don't have a title
3123 if e.get('title') is not None:
3124 e['title'] = '%s (%d)' % (e['title'], num)
3126 '_type': 'playlist',