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 (
39 from .nbc import NBCSportsVPlayerIE
40 from .ooyala import OoyalaIE
41 from .rutv import RUTVIE
42 from .tvc import TVCIE
43 from .sportbox import SportBoxEmbedIE
44 from .smotri import SmotriIE
45 from .myvi import MyviIE
46 from .condenast import CondeNastIE
47 from .udn import UDNEmbedIE
48 from .senateisvp import SenateISVPIE
49 from .svt import SVTIE
50 from .pornhub import PornHubIE
51 from .xhamster import XHamsterEmbedIE
52 from .tnaflix import TNAFlixNetworkEmbedIE
53 from .drtuber import DrTuberIE
54 from .redtube import RedTubeIE
55 from .vimeo import VimeoIE
56 from .dailymotion import (
60 from .onionstudios import OnionStudiosIE
61 from .viewlift import ViewLiftEmbedIE
62 from .mtv import MTVServicesEmbeddedIE
63 from .pladform import PladformIE
64 from .videomore import VideomoreIE
65 from .webcaster import WebcasterFeedIE
66 from .googledrive import GoogleDriveIE
67 from .jwplatform import JWPlatformIE
68 from .digiteka import DigitekaIE
69 from .arkena import ArkenaIE
70 from .instagram import InstagramIE
71 from .liveleak import LiveLeakIE
72 from .threeqsdn import ThreeQSDNIE
73 from .theplatform import ThePlatformIE
74 from .vessel import VesselIE
75 from .kaltura import KalturaIE
76 from .eagleplatform import EaglePlatformIE
77 from .facebook import FacebookIE
78 from .soundcloud import SoundcloudIE
79 from .tunein import TuneInBaseIE
80 from .vbox7 import Vbox7IE
81 from .dbtv import DBTVIE
82 from .piksel import PikselIE
83 from .videa import VideaIE
84 from .twentymin import TwentyMinutenIE
85 from .ustream import UstreamIE
86 from .openload import OpenloadIE
87 from .videopress import VideoPressIE
88 from .rutube import RutubeIE
89 from .limelight import LimelightBaseIE
90 from .anvato import AnvatoIE
91 from .washingtonpost import WashingtonPostIE
92 from .wistia import WistiaIE
93 from .mediaset import MediasetIE
96 class GenericIE(InfoExtractor):
97 IE_DESC = 'Generic downloader that works on some sites'
101 # Direct link to a video
103 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
104 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
109 'upload_date': '20100513',
112 # Direct link to media delivered compressed (until Accept-Encoding is *)
114 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
115 'md5': '128c42e68b13950268b648275386fc74',
117 'id': 'FictionJunction-Parallel_Hearts',
119 'title': 'FictionJunction-Parallel_Hearts',
120 'upload_date': '20140522',
122 'expected_warnings': [
123 'URL could be a direct video link, returning it as such.'
125 'skip': 'URL invalid',
127 # Direct download with broken HEAD
129 'url': 'http://ai-radio.org:8000/radio.opus',
136 'skip_download': True, # infinite live stream
138 'expected_warnings': [
139 r'501.*Not Implemented',
143 # Direct link with incorrect MIME type
145 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
146 'md5': '4ccbebe5f36706d85221f204d7eb5913',
148 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
149 'id': '5_Lennart_Poettering_-_Systemd',
151 'title': '5_Lennart_Poettering_-_Systemd',
152 'upload_date': '20141120',
154 'expected_warnings': [
155 'URL could be a direct video link, returning it as such.'
160 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
162 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
163 'title': 'Zero Punctuation',
164 'description': 're:.*groundbreaking video review series.*'
166 'playlist_mincount': 11,
168 # RSS feed with enclosure
170 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
172 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
174 'upload_date': '20150228',
175 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
178 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
180 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
184 'title': 'Automatics, robotics and biocybernetics',
185 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
186 'upload_date': '20130627',
187 'formats': 'mincount:16',
188 'subtitles': 'mincount:1',
191 'force_generic_extractor': True,
192 'skip_download': True,
195 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
197 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
202 'formats': 'mincount:1',
205 'skip_download': True,
208 # SMIL from https://www.restudy.dk/video/play/id/1637
210 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
214 'title': 'video_1637',
215 'formats': 'mincount:3',
218 'skip_download': True,
221 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
223 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
225 'id': 'smil-service',
227 'title': 'smil-service',
228 'formats': 'mincount:1',
231 'skip_download': True,
234 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
236 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
240 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
241 'formats': 'mincount:3',
244 'skip_download': True,
247 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
249 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
251 'id': 'mZlp2ctYIUEB',
253 'title': 'Tikibad ontruimd wegens brand',
254 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
255 'thumbnail': r're:^https?://.*\.jpg$',
259 'skip_download': True,
262 # MPD from http://dash-mse-test.appspot.com/media.html
264 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
265 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
267 'id': 'car-20120827-manifest',
269 'title': 'car-20120827-manifest',
270 'formats': 'mincount:9',
271 'upload_date': '20130904',
274 'format': 'bestvideo',
277 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
279 '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',
284 'formats': 'mincount:8',
288 'skip_download': True,
290 'skip': 'video gone',
292 # m3u8 served with Content-Type: text/plain
294 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
299 'upload_date': '20140720',
300 'formats': 'mincount:11',
304 'skip_download': True,
306 'skip': 'video gone',
310 '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',
314 'upload_date': '20130224',
315 'uploader_id': 'TheVerge',
316 'description': r're:^Chris Ziegler takes a look at the\.*',
317 'uploader': 'The Verge',
318 'title': 'First Firefox OS phones side-by-side',
321 'skip_download': False,
325 # redirect in Refresh HTTP header
326 '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',
330 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
331 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
332 'upload_date': '20150917',
333 'uploader_id': 'brtvofficial',
334 'uploader': 'Boiler Room',
337 'skip_download': False,
341 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
342 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
344 'id': '13601338388002',
346 'uploader': 'www.hodiho.fr',
347 'title': 'R\u00e9gis plante sa Jeep',
350 # bandcamp page with custom domain
352 'add_ie': ['Bandcamp'],
353 'url': 'http://bronyrock.com/track/the-pony-mash',
357 'title': 'The Pony Mash',
358 'uploader': 'M_Pallante',
360 'skip': 'There is a limit of 200 free downloads / month for the test song',
363 # embedded brightcove video
364 # it also tests brightcove videos that need to set the 'Referer'
365 # in the http requests
366 'add_ie': ['BrightcoveLegacy'],
367 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
369 'id': '2765128793001',
371 'title': 'Le cours de bourse : l’analyse technique',
372 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
373 'uploader': 'BFM BUSINESS',
376 'skip_download': True,
380 # embedded with itemprop embedURL and video id spelled as `idVideo`
381 'add_id': ['BrightcoveLegacy'],
382 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
384 'id': '5255628253001',
386 'title': 'md5:37c519b1128915607601e75a87995fc0',
387 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
388 'uploader': 'BFM BUSINESS',
389 'uploader_id': '876450612001',
390 'timestamp': 1482255315,
391 'upload_date': '20161220',
394 'skip_download': True,
398 # https://github.com/rg3/youtube-dl/issues/2253
399 'url': 'http://bcove.me/i6nfkrc3',
400 'md5': '0ba9446db037002366bab3b3eb30c88c',
402 'id': '3101154703001',
404 'title': 'Still no power',
405 'uploader': 'thestar.com',
406 '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.',
408 'add_ie': ['BrightcoveLegacy'],
409 'skip': 'video gone',
412 'url': 'http://www.championat.com/video/football/v/87/87499.html',
413 'md5': 'fb973ecf6e4a78a67453647444222983',
415 'id': '3414141473001',
417 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
418 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
419 'uploader': 'Championat',
423 # https://github.com/rg3/youtube-dl/issues/3541
424 'add_ie': ['BrightcoveLegacy'],
425 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
427 'id': '3866516442001',
429 'title': 'Leer mij vrouwen kennen: Aflevering 1',
430 'description': 'Leer mij vrouwen kennen: Aflevering 1',
431 'uploader': 'SBS Broadcasting',
433 'skip': 'Restricted to Netherlands',
435 'skip_download': True, # m3u8 download
439 # Brightcove video in <iframe>
440 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
441 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
443 'id': '5360463607001',
445 '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',
446 '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。',
447 'uploader': 'United Nations',
448 'uploader_id': '1362235914001',
449 'timestamp': 1489593889,
450 'upload_date': '20170315',
452 'add_ie': ['BrightcoveLegacy'],
455 # Brightcove with alternative playerID key
456 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
458 'id': 'nmeth.2062_SV1',
459 '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',
463 'id': '2228375078001',
465 'title': 'nmeth.2062-sv1',
466 'description': 'nmeth.2062-sv1',
467 'timestamp': 1363357591,
468 'upload_date': '20130315',
469 'uploader': 'Nature Publishing Group',
470 'uploader_id': '1964492299001',
475 # Brightcove with UUID in videoPlayer
476 'url': 'http://www8.hp.com/cn/zh/home.html',
478 'id': '5255815316001',
480 'title': 'Sprocket Video - China',
481 'description': 'Sprocket Video - China',
482 'uploader': 'HP-Video Gallery',
483 'timestamp': 1482263210,
484 'upload_date': '20161220',
485 'uploader_id': '1107601872001',
488 'skip_download': True, # m3u8 download
490 'skip': 'video rotates...weekly?',
493 # Brightcove:new type [2].
494 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
495 'md5': '2b35148fcf48da41c9fb4591650784f3',
497 'id': '5348741021001',
499 'upload_date': '20170306',
500 'uploader_id': '4191638492001',
501 'timestamp': 1488769918,
502 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
507 # Alternative brightcove <video> attributes
508 '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/',
510 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
511 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
514 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
516 'id': '5311302538001',
518 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
519 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
520 'timestamp': 1486321708,
521 'upload_date': '20170205',
522 'uploader_id': '800000640001',
524 'only_matching': True,
528 # Brightcove with UUID in videoPlayer
529 'url': 'http://www8.hp.com/cn/zh/home.html',
531 'id': '5255815316001',
533 'title': 'Sprocket Video - China',
534 'description': 'Sprocket Video - China',
535 'uploader': 'HP-Video Gallery',
536 'timestamp': 1482263210,
537 'upload_date': '20161220',
538 'uploader_id': '1107601872001',
541 'skip_download': True, # m3u8 download
546 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
547 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
549 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
551 'title': '2cc213299525360.mov', # that's what we get
554 'add_ie': ['Ooyala'],
557 # ooyala video embedded with http://player.ooyala.com/iframe.js
558 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
560 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
562 'title': '"Steve Jobs: Man in the Machine" trailer',
563 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
567 'skip_download': True,
569 'skip': 'movie expired',
573 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
577 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
578 'upload_date': '20140225',
579 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
580 'uploader': 'Tested',
581 'uploader_id': 'testedcom',
583 # No need to test YoutubeIE here
585 'skip_download': True,
590 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
594 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
595 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
597 # HEAD requests lead to endless 301, while GET is OK
598 'expected_warnings': ['301'],
602 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
606 'title': 'Охотское море стало целиком российским',
607 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
611 'skip_download': True,
616 '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/',
620 'title': 'Дошкольное воспитание',
625 'url': 'http://www.vestifinance.ru/articles/25753',
628 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
633 'title': 'Госзаказ. День 3',
639 'title': 'Госзаказ. День 2',
645 'title': 'Госзаказ. День 1',
651 'skip_download': True,
656 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
658 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
660 'title': 'Ужастики, русский трейлер (2015)',
661 'thumbnail': r're:^https?://.*\.jpg$',
667 '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',
670 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
672 'playlist_mincount': 7,
673 # This forum does not allow <iframe> syntaxes anymore
674 # Now HTML tags are displayed as-is
675 'skip': 'No videos on this page',
679 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
680 'md5': '65fdff94098e4a607385a60c5177c638',
684 'title': 'Hidden miracles of the natural world',
685 'uploader': 'Louie Schwartzberg',
686 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
689 # nowvideo embed hidden behind percent encoding
691 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
692 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
694 'id': '06e53103ca9aa',
696 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
697 'description': 'No description',
702 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
703 'md5': '7653032cbb25bf6c80d80f217055fa43',
705 'id': '048195-004_PLUS7-F',
708 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
709 'upload_date': '20140320',
712 'skip_download': 'Requires rtmpdump'
714 'skip': 'video gone',
718 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
722 'title': 'Alcaline, le concert avec Calogero',
723 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
724 'upload_date': '20150226',
725 'timestamp': 1424989860,
730 'skip_download': True,
732 'expected_warnings': [
738 'url': 'http://www.wired.com/2014/04/honda-asimo/',
739 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
741 'id': '53501be369702d3275860000',
743 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
748 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
749 'md5': '441aeeb82eb72c422c7f14ec533999cd',
751 'id': 'k2mm4bCdJ6CQ2i7c8o2',
753 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
754 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
756 'uploader_id': 'xgditw',
757 'upload_date': '20140425',
758 'timestamp': 1398441542,
760 'add_ie': ['Dailymotion'],
764 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
768 'title': 'The NBL Auction 2014',
769 'uploader': 'BADMINTON England',
770 'uploader_id': 'BADMINTONEvents',
771 'upload_date': '20140603',
772 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
774 'add_ie': ['Youtube'],
776 'skip_download': True,
781 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
782 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
784 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
786 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
787 'description': 'Two valets share their love for movie star Liam Neesons.',
788 'timestamp': 1349922600,
789 'upload_date': '20121011',
792 # YouTube embed via <data-embed-url="">
794 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
798 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
799 'uploader': 'Gameloft',
800 'uploader_id': 'gameloft',
801 'upload_date': '20140828',
802 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
805 'skip_download': True,
808 # YouTube <object> embed
810 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
811 'md5': '516718101ec834f74318df76259fb3cc',
815 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
816 'upload_date': '20080526',
817 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
818 'uploader': 'Christopher Sykes',
819 'uploader_id': 'ChristopherJSykes',
821 'add_ie': ['Youtube'],
825 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
827 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
829 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
830 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
835 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
837 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
838 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
844 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
849 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
850 'md5': '9d65602bf31c6e20014319c7d07fba27',
852 'id': '5123ea6d5e5a7',
855 'uploader': 'www.handjobhub.com',
856 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
859 # Multiple brightcove videos
860 # https://github.com/rg3/youtube-dl/issues/2283
862 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
864 'id': 'always-never',
865 'title': 'Always / Never - The New Yorker',
869 'extract_flat': False,
870 'skip_download': True,
875 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
876 'md5': '96f09a37e44da40dd083e12d9a683327',
880 'title': 'Ump changes call to ball',
881 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
883 'timestamp': 1401537900,
884 'upload_date': '20140531',
885 'thumbnail': r're:^https?://.*\.jpg$',
890 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
891 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
895 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
896 'description': 'a Paywall Videos video from Remilon',
898 'uploader': 'study.com',
899 'timestamp': 1459678540,
900 'upload_date': '20160403',
901 'filesize': 24687186,
905 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
906 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
910 'title': 'Conversation about Hexagonal Rails Part 1',
911 'description': 'a Martin Fowler video from ThoughtWorks',
913 'uploader': 'thoughtworks.wistia.com',
914 'timestamp': 1401832161,
915 'upload_date': '20140603',
918 # Wistia standard embed (async)
920 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
924 'title': 'Drip Brennan Dunn Workshop',
925 'description': 'a JV Webinars video from getdrip-1',
927 'timestamp': 1463607249,
928 'upload_date': '20160518',
931 'skip_download': True,
936 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
940 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
941 'uploader': 'Sophos Security',
942 'title': 'Chet Chat 171 - Oct 29, 2014',
943 'upload_date': '20141029',
946 # Soundcloud multiple embeds
948 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
951 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
953 'playlist_mincount': 7,
955 # TuneIn station embed
957 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
962 'location': 'Paris, France',
967 'skip_download': True,
972 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
976 'upload_date': '20141112',
977 'title': 'Rosetta #CometLanding webcast HL 10',
980 # Another Livestream embed, without 'new.' in URL
982 'url': 'https://www.freespeech.org/',
986 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
990 'skip_download': True,
995 'url': 'https://skiplagged.com/',
998 'title': 'Skiplagged: The smart way to find cheap flights',
1000 'playlist_mincount': 1,
1001 'add_ie': ['Youtube'],
1005 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1009 'upload_date': '20141126',
1010 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1015 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1017 'id': '730m_DandD_1901_512k',
1019 'uploader': 'www.abc.net.au',
1020 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1023 # embedded viddler video
1025 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1029 'uploader': 'deadspin',
1030 'title': 'WALL-TO-GORTAT',
1031 'timestamp': 1422285291,
1032 'upload_date': '20150126',
1034 'add_ie': ['Viddler'],
1038 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1042 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1043 'description': 'md5:601cb790edd05908957dae8aaa866465',
1044 'upload_date': '20150220',
1046 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1050 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1052 'id': 'Mrj4DVp2zeA',
1054 'upload_date': '20150212',
1055 'uploader': 'The National Archives UK',
1056 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1057 'uploader_id': 'NationalArchives08',
1058 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1063 'url': 'http://www.suffolk.edu/sjc/',
1067 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1068 'uploader': 'www.suffolk.edu',
1071 'skip_download': True,
1076 'url': 'http://www.indiedb.com/games/king-machine/videos',
1080 'title': 'king machine trailer 1',
1081 'thumbnail': r're:^https?://.*\.jpg$',
1085 # JWPlayer config passed as variable
1086 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1090 'title': 'ARIELE | Tube Cup',
1091 'uploader': 'www.txxx.com',
1095 'skip_download': True,
1100 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1101 'playlist_mincount': 5,
1103 'id': 'aanslagen-kopenhagen',
1104 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1109 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1113 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1116 # Kaltura embed (different embed code)
1118 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1122 'upload_date': '20150127',
1123 'uploader_id': 'PremierMedia',
1125 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1128 # Kaltura embed with single quotes
1130 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1135 'timestamp': 1355743100,
1136 'upload_date': '20121217',
1137 'uploader_id': 'batchUser',
1139 'add_ie': ['Kaltura'],
1142 # Kaltura embedded via quoted entry_id
1143 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1147 'title': '06_matthew_brender_raj_dutt',
1148 'timestamp': 1466638791,
1149 'upload_date': '20160622',
1151 'add_ie': ['Kaltura'],
1152 'expected_warnings': [
1153 'Could not send HEAD request'
1156 'skip_download': True,
1160 # Kaltura embedded, some fileExt broken (#11480)
1161 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1165 'title': 'Our "Standard Models" of particle physics and cosmology',
1166 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1167 'timestamp': 1321158993,
1168 'upload_date': '20111113',
1169 'uploader_id': 'kps1',
1171 'add_ie': ['Kaltura'],
1174 # Kaltura iframe embed
1175 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1176 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1180 'title': 'I. M. Pei: A Centennial Celebration',
1181 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1182 'upload_date': '20170403',
1183 'uploader_id': 'batchUser',
1184 'timestamp': 1491232186,
1186 'add_ie': ['Kaltura'],
1188 # Eagle.Platform embed (generic URL)
1190 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1191 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1195 'title': 'Навальный вышел на свободу',
1196 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1197 'thumbnail': r're:^https?://.*\.jpg$',
1203 # ClipYou (Eagle.Platform) embed (custom URL)
1205 'url': 'http://muz-tv.ru/play/7129/',
1206 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1210 'title': "'O Sole Mio",
1211 'thumbnail': r're:^https?://.*\.jpg$',
1218 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1222 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1223 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1224 'thumbnail': r're:^https?://.*\.jpg$',
1231 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1235 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1236 'thumbnail': r're:^https?://.*\.png$',
1242 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1243 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1247 'title': 'Facebook Creates "On This Day" | Crunch Report',
1252 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1256 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1261 # Crooks and Liars embed
1263 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1267 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1268 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1269 'timestamp': 1428207000,
1270 'upload_date': '20150405',
1271 'uploader': 'Heather',
1274 # Crooks and Liars external embed
1276 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1278 'id': 'MTE3MjUtMzQ2MzA',
1280 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1281 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1282 'timestamp': 1265032391,
1283 'upload_date': '20100201',
1284 'uploader': 'Heather',
1287 # NBC Sports vplayer embed
1289 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1291 'id': 'ln7x1qSThw4k',
1293 'title': "PFT Live: New leader in the 'new-look' defense",
1294 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1295 'uploader': 'NBCU-SPORTS',
1296 'upload_date': '20140107',
1297 'timestamp': 1389118457,
1302 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1303 'md5': '1aa589c675898ae6d37a17913cf68d66',
1305 'id': '701714499682',
1307 'title': 'PREVIEW: On Assignment: David Letterman',
1308 '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.',
1313 'url': 'https://video.udn.com/news/300346',
1314 'md5': 'fd2060e988c326991037b9aff9df21a6',
1318 'title': '中一中男師變性 全校師生力挺',
1319 'thumbnail': r're:^https?://.*\.jpg$',
1323 'skip_download': True,
1328 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1330 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1332 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1333 'title': 'This is what separates the Excel masters from the wannabes',
1334 'duration': 191.933,
1338 'skip_download': True,
1341 # Brightcove URL in single quotes
1343 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1344 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1346 'id': '4255764656001',
1348 'title': 'SN Presents: Russell Martin, World Citizen',
1349 '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.',
1350 'uploader': 'Rogers Sportsnet',
1351 'uploader_id': '1704050871',
1352 'upload_date': '20150525',
1353 'timestamp': 1432570283,
1356 # Dailymotion Cloud video
1358 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1359 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1363 'title': 'Sauvons les abeilles ! - Le débat',
1364 'description': 'md5:d9082128b1c5277987825d684939ca26',
1365 'thumbnail': r're:^https?://.*\.jpe?g$',
1366 'timestamp': 1434970506,
1367 'upload_date': '20150622',
1368 'uploader': 'Public Sénat',
1369 'uploader_id': 'xa9gza',
1372 # OnionStudios embed
1374 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1378 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1379 'thumbnail': r're:^https?://.*\.jpe?g$',
1380 'uploader': 'ClickHole',
1381 'uploader_id': 'clickhole',
1386 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1388 'id': '74849a00-85a9-11e1-9660-123139220831',
1390 'title': '#whilewewatch',
1393 # AdobeTVVideo embed
1395 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1396 'md5': '43662b577c018ad707a63766462b1e87',
1400 'title': 'New experience with Acrobat DC',
1401 'description': 'New experience with Acrobat DC',
1402 'duration': 248.667,
1405 # BrightcoveInPageEmbed embed
1407 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1409 'id': '4238694884001',
1411 'title': 'Tabletop: Dread, Last Thoughts',
1412 'description': 'Tabletop: Dread, Last Thoughts',
1416 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1417 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1419 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1421 'id': '4785848093001',
1423 'title': 'The Cardinal Pell Interview',
1424 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1425 'uploader': 'GlobeCast Australia - GlobeStream',
1426 'uploader_id': '2733773828001',
1427 'upload_date': '20160304',
1428 'timestamp': 1457083087,
1432 'skip_download': True,
1436 # Brightcove embed with whitespace around attribute names
1437 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1439 'id': '3167554373001',
1441 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1442 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1443 'uploader_id': '1079349493',
1444 'upload_date': '20140207',
1445 'timestamp': 1391810548,
1448 'skip_download': True,
1451 # Another form of arte.tv embed
1453 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1454 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1456 'id': '030273-562_PLUS7-F',
1458 'title': 'ARTE Reportage - Nulle part, en France',
1459 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1460 'upload_date': '20160409',
1465 'url': 'http://www.wykop.pl/link/3088787/',
1466 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1468 'id': '874_1459135191',
1470 'title': 'Man shows poor quality of new apartment building',
1471 'description': 'The wall is like a sand pile.',
1472 'uploader': 'Lake8737',
1475 # Duplicated embedded video URLs
1477 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1479 'id': '149298443_480_16c25b74_2',
1481 'title': 'vs. Blue Orange Spring Game',
1482 'uploader': 'www.hudl.com',
1485 # twitter:player:stream embed
1487 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1491 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1492 'uploader': 'www.rtl.be',
1496 'skip_download': True,
1499 # twitter:player embed
1501 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1502 'md5': 'a3e0df96369831de324f0778e126653c',
1504 'id': '4909620399001',
1506 'title': 'What Do Black Holes Sound Like?',
1507 'description': 'what do black holes sound like',
1508 'upload_date': '20160524',
1509 'uploader_id': '29913724001',
1510 'timestamp': 1464107587,
1511 'uploader': 'TheAtlantic',
1513 'add_ie': ['BrightcoveLegacy'],
1515 # Facebook <iframe> embed
1517 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1518 'md5': 'fbcde74f534176ecb015849146dd3aee',
1520 'id': '599637780109885',
1522 'title': 'Facebook video #599637780109885',
1525 # Facebook API embed
1527 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1528 'md5': 'a47372ee61b39a7b90287094d447d94e',
1530 'id': '10153467542406923',
1532 'title': 'Facebook video #10153467542406923',
1535 # Wordpress "YouTube Video Importer" plugin
1537 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1538 'md5': 'd16797741b560b485194eddda8121b48',
1540 'id': 'HNTXWDXV9Is',
1542 'title': 'Blue Devils Drumline Stanford lot 2016',
1543 'upload_date': '20160627',
1544 'uploader_id': 'GENOCIDE8GENERAL10',
1545 'uploader': 'cylus cyrus',
1549 # video stored on custom kaltura server
1550 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1551 'md5': '537617d06e64dfed891fa1593c4b30cc',
1555 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1556 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1557 'uploader_id': 'videos.expansion@el-mundo.net',
1558 'upload_date': '20150429',
1559 'timestamp': 1430303472,
1561 'add_ie': ['Kaltura'],
1564 # Non-standard Vimeo embed
1565 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1566 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1570 'title': 'Understanding the web - Teaser',
1571 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1572 'upload_date': '20151214',
1573 'uploader': 'OpenClassrooms',
1574 'uploader_id': 'openclassrooms',
1576 'add_ie': ['Vimeo'],
1579 # generic vimeo embed that requires original URL passed as Referer
1580 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1581 'only_matching': True,
1584 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1585 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1587 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1589 'title': 'Big Buck Bunny',
1590 'description': 'Royalty free test video',
1591 'timestamp': 1432816365,
1592 'upload_date': '20150528',
1596 'skip_download': True,
1598 'add_ie': [ArkenaIE.ie_key()],
1601 '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/',
1605 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1608 'skip_download': True,
1610 'add_ie': [Vbox7IE.ie_key()],
1614 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1617 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1619 'playlist_mincount': 3,
1623 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1625 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1626 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1628 'playlist_mincount': 2,
1632 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1636 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1637 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1640 'skip_download': True,
1642 'add_ie': [TwentyMinutenIE.ie_key()],
1646 'url': 'https://en.support.wordpress.com/videopress/',
1650 'title': 'IMG_5786',
1651 'timestamp': 1435711927,
1652 'upload_date': '20150701',
1655 'skip_download': True,
1657 'add_ie': [VideoPressIE.ie_key()],
1661 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1663 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1665 'title': 'Магаззино: Казань 2',
1666 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1667 'uploader': 'Магаззино',
1668 'upload_date': '20170228',
1669 'uploader_id': '996642',
1672 'skip_download': True,
1674 'add_ie': [RutubeIE.ie_key()],
1677 # ThePlatform embedded with whitespaces in URLs
1678 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1679 'only_matching': True,
1682 # Senate ISVP iframe https
1683 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1684 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1686 'id': 'govtaff020316',
1688 'title': 'Integrated Senate Video Player',
1690 'add_ie': [SenateISVPIE.ie_key()],
1693 # Limelight embeds (1 channel embed + 4 media embeds)
1694 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1696 'id': 'FacilitatorTraining2017',
1697 'title': 'Facilitator Training 2017',
1699 'playlist_mincount': 5,
1702 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1704 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1705 'title': 'Standoff with Walnut Creek murder suspect ends',
1706 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1708 'playlist_mincount': 4,
1711 # WashingtonPost embed
1712 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1714 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1716 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1717 '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.',
1718 'timestamp': 1455216756,
1719 'uploader': 'The Washington Post',
1720 'upload_date': '20160211',
1722 'add_ie': [WashingtonPostIE.ie_key()],
1726 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1730 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1733 'skip_download': True,
1735 'add_ie': [MediasetIE.ie_key()],
1738 # # TODO: find another test
1739 # # http://schema.org/VideoObject
1740 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1741 # 'md5': '888dcf08b7ea671381f00fab74692755',
1743 # 'id': 'nyvTSJMKId',
1745 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1746 # 'description': '#love for cats.',
1747 # 'timestamp': 1461244995,
1748 # 'upload_date': '20160421',
1751 # 'force_generic_extractor': True,
1756 def report_following_redirect(self, new_url):
1757 """Report information extraction."""
1758 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1760 def _extract_rss(self, url, video_id, doc):
1761 playlist_title = doc.find('./channel/title').text
1762 playlist_desc_el = doc.find('./channel/description')
1763 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1766 for it in doc.findall('./channel/item'):
1767 next_url = xpath_text(it, 'link', fatal=False)
1769 enclosure_nodes = it.findall('./enclosure')
1770 for e in enclosure_nodes:
1771 next_url = e.attrib.get('url')
1779 '_type': 'url_transparent',
1781 'title': it.find('title').text,
1785 '_type': 'playlist',
1787 'title': playlist_title,
1788 'description': playlist_desc,
1792 def _extract_camtasia(self, url, video_id, webpage):
1793 """ Returns None if no camtasia video can be found. """
1795 camtasia_cfg = self._search_regex(
1796 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1797 webpage, 'camtasia configuration file', default=None)
1798 if camtasia_cfg is None:
1801 title = self._html_search_meta('DC.title', webpage, fatal=True)
1803 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1804 camtasia_cfg = self._download_xml(
1805 camtasia_url, video_id,
1806 note='Downloading camtasia configuration',
1807 errnote='Failed to download camtasia configuration')
1808 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1811 for n in fileset_node.getchildren():
1812 url_n = n.find('./uri')
1817 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1818 'title': '%s - %s' % (title, n.tag),
1819 'url': compat_urlparse.urljoin(url, url_n.text),
1820 'duration': float_or_none(n.find('./duration').text),
1824 '_type': 'playlist',
1829 def _real_extract(self, url):
1830 if url.startswith('//'):
1833 'url': self.http_scheme() + url,
1836 parsed_url = compat_urlparse.urlparse(url)
1837 if not parsed_url.scheme:
1838 default_search = self._downloader.params.get('default_search')
1839 if default_search is None:
1840 default_search = 'fixup_error'
1842 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1844 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1845 return self.url_result('http://' + url)
1846 elif default_search != 'fixup_error':
1847 if default_search == 'auto_warning':
1848 if re.match(r'^(?:url|URL)$', url):
1849 raise ExtractorError(
1850 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1853 self._downloader.report_warning(
1854 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1855 return self.url_result('ytsearch:' + url)
1857 if default_search in ('error', 'fixup_error'):
1858 raise ExtractorError(
1859 '%r is not a valid URL. '
1860 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1861 % (url, url), expected=True)
1863 if ':' not in default_search:
1864 default_search += ':'
1865 return self.url_result(default_search + url)
1867 url, smuggled_data = unsmuggle_url(url)
1868 force_videoid = None
1869 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1870 if smuggled_data and 'force_videoid' in smuggled_data:
1871 force_videoid = smuggled_data['force_videoid']
1872 video_id = force_videoid
1874 video_id = self._generic_id(url)
1876 self.to_screen('%s: Requesting header' % video_id)
1878 head_req = HEADRequest(url)
1879 head_response = self._request_webpage(
1881 note=False, errnote='Could not send HEAD request to %s' % url,
1884 if head_response is not False:
1885 # Check for redirect
1886 new_url = head_response.geturl()
1888 self.report_following_redirect(new_url)
1890 new_url = smuggle_url(
1891 new_url, {'force_videoid': force_videoid})
1892 return self.url_result(new_url)
1894 full_response = None
1895 if head_response is False:
1896 request = sanitized_Request(url)
1897 request.add_header('Accept-Encoding', '*')
1898 full_response = self._request_webpage(request, video_id)
1899 head_response = full_response
1903 'title': self._generic_title(url),
1904 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1907 # Check for direct link to a video
1908 content_type = head_response.headers.get('Content-Type', '').lower()
1909 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1911 format_id = compat_str(m.group('format_id'))
1912 if format_id.endswith('mpegurl'):
1913 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1914 elif format_id == 'f4m':
1915 formats = self._extract_f4m_formats(url, video_id)
1918 'format_id': format_id,
1920 'vcodec': 'none' if m.group('type') == 'audio' else None
1922 info_dict['direct'] = True
1923 self._sort_formats(formats)
1924 info_dict['formats'] = formats
1927 if not self._downloader.params.get('test', False) and not is_intentional:
1928 force = self._downloader.params.get('force_generic_extractor', False)
1929 self._downloader.report_warning(
1930 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1932 if not full_response:
1933 request = sanitized_Request(url)
1934 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1935 # making it impossible to download only chunk of the file (yet we need only 512kB to
1936 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1937 # that will always result in downloading the whole file that is not desirable.
1938 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1939 # to accept raw bytes and being able to download only a chunk.
1940 # It may probably better to solve this by checking Content-Type for application/octet-stream
1941 # after HEAD request finishes, but not sure if we can rely on this.
1942 request.add_header('Accept-Encoding', '*')
1943 full_response = self._request_webpage(request, video_id)
1945 first_bytes = full_response.read(512)
1947 # Is it an M3U playlist?
1948 if first_bytes.startswith(b'#EXTM3U'):
1949 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1950 self._sort_formats(info_dict['formats'])
1953 # Maybe it's a direct link to a video?
1954 # Be careful not to download the whole thing!
1955 if not is_html(first_bytes):
1956 self._downloader.report_warning(
1957 'URL could be a direct video link, returning it as such.')
1964 webpage = self._webpage_read_content(
1965 full_response, url, video_id, prefix=first_bytes)
1967 self.report_extraction(video_id)
1969 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1971 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1972 if doc.tag == 'rss':
1973 return self._extract_rss(url, video_id, doc)
1974 elif doc.tag == 'SmoothStreamingMedia':
1975 info_dict['formats'] = self._parse_ism_formats(doc, url)
1976 self._sort_formats(info_dict['formats'])
1978 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1979 smil = self._parse_smil(doc, url, video_id)
1980 self._sort_formats(smil['formats'])
1982 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1983 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1984 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1985 info_dict['formats'] = self._parse_mpd_formats(
1987 mpd_base_url=full_response.geturl().rpartition('/')[0],
1989 self._sort_formats(info_dict['formats'])
1991 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1992 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1993 self._sort_formats(info_dict['formats'])
1995 except compat_xml_parse_error:
1998 # Is it a Camtasia project?
1999 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2000 if camtasia_res is not None:
2003 # Sometimes embedded video player is hidden behind percent encoding
2004 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2005 # Unescaping the whole page allows to handle those cases in a generic way
2006 webpage = compat_urllib_parse_unquote(webpage)
2008 # it's tempting to parse this further, but you would
2009 # have to take into account all the variations like
2010 # Video Title - Site Name
2011 # Site Name | Video Title
2012 # Video Title - Tagline | Site Name
2013 # and so on and so forth; it's just not practical
2014 video_title = self._og_search_title(
2015 webpage, default=None) or self._html_search_regex(
2016 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2019 # Try to detect age limit automatically
2020 age_limit = self._rta_search(webpage)
2021 # And then there are the jokers who advertise that they use RTA,
2022 # but actually don't.
2023 AGE_LIMIT_MARKERS = [
2024 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2026 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2029 # video uploader is domain name
2030 video_uploader = self._search_regex(
2031 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2033 video_description = self._og_search_description(webpage, default=None)
2034 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2036 # Look for Brightcove Legacy Studio embeds
2037 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2041 'url': smuggle_url(bc_url, {'Referer': url}),
2042 'ie_key': 'BrightcoveLegacy'
2043 } for bc_url in bc_urls]
2046 '_type': 'playlist',
2047 'title': video_title,
2052 # Look for Brightcove New Studio embeds
2053 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2055 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2057 # Look for ThePlatform embeds
2058 tp_urls = ThePlatformIE._extract_urls(webpage)
2060 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2062 # Look for Vessel embeds
2063 vessel_urls = VesselIE._extract_urls(webpage)
2065 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2067 # Look for embedded rtl.nl player
2068 matches = re.findall(
2069 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2072 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2074 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2076 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2078 vid_me_embed_url = self._search_regex(
2079 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2080 webpage, 'vid.me embed', default=None)
2081 if vid_me_embed_url is not None:
2082 return self.url_result(vid_me_embed_url, 'Vidme')
2084 # Look for embedded YouTube player
2085 matches = re.findall(r'''(?x)
2095 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2099 return self.playlist_from_matches(
2100 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2102 # Look for lazyYT YouTube embed
2103 matches = re.findall(
2104 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2106 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2108 # Look for Wordpress "YouTube Video Importer" plugin
2109 matches = re.findall(r'''(?x)<div[^>]+
2110 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2111 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2113 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2115 matches = DailymotionIE._extract_urls(webpage)
2117 return self.playlist_from_matches(matches, video_id, video_title)
2119 # Look for embedded Dailymotion playlist player (#3822)
2121 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2123 playlists = re.findall(
2124 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2126 return self.playlist_from_matches(
2127 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2129 # Look for embedded Wistia player
2130 wistia_url = WistiaIE._extract_url(webpage)
2133 '_type': 'url_transparent',
2134 'url': self._proto_relative_url(wistia_url),
2135 'ie_key': WistiaIE.ie_key(),
2136 'uploader': video_uploader,
2139 # Look for SVT player
2140 svt_url = SVTIE._extract_url(webpage)
2142 return self.url_result(svt_url, 'SVT')
2144 # Look for Bandcamp pages with custom domain
2145 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2146 if mobj is not None:
2147 burl = unescapeHTML(mobj.group(1))
2148 # Don't set the extractor because it can be a track url or an album
2149 return self.url_result(burl)
2151 # Look for embedded Vevo player
2153 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2154 if mobj is not None:
2155 return self.url_result(mobj.group('url'))
2157 # Look for embedded Viddler player
2159 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2161 if mobj is not None:
2162 return self.url_result(mobj.group('url'))
2164 # Look for NYTimes player
2166 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2168 if mobj is not None:
2169 return self.url_result(mobj.group('url'))
2171 # Look for Libsyn player
2173 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2174 if mobj is not None:
2175 return self.url_result(mobj.group('url'))
2177 # Look for Ooyala videos
2178 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2179 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2180 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2181 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2182 if mobj is not None:
2183 embed_token = self._search_regex(
2184 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2185 webpage, 'ooyala embed token', default=None)
2186 return OoyalaIE._build_url_result(smuggle_url(
2189 'embed_token': embed_token,
2192 # Look for multiple Ooyala embeds on SBN network websites
2193 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2194 if mobj is not None:
2195 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2197 return self.playlist_from_matches(
2198 embeds, video_id, video_title,
2199 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2201 # Look for Aparat videos
2202 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2203 if mobj is not None:
2204 return self.url_result(mobj.group(1), 'Aparat')
2206 # Look for MPORA videos
2207 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2208 if mobj is not None:
2209 return self.url_result(mobj.group(1), 'Mpora')
2211 # Look for embedded NovaMov-based player
2213 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2214 (?P<url>http://(?:(?:embed|www)\.)?
2216 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2217 videoweed\.(?:es|com)|
2218 movshare\.(?:net|sx|ag)|
2219 divxstage\.(?:eu|net|ch|co|at|ag))
2220 /embed\.php.+?)\1''', webpage)
2221 if mobj is not None:
2222 return self.url_result(mobj.group('url'))
2224 # Look for embedded Facebook player
2225 facebook_urls = FacebookIE._extract_urls(webpage)
2227 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2229 # Look for embedded VK player
2230 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2231 if mobj is not None:
2232 return self.url_result(mobj.group('url'), 'VK')
2234 # Look for embedded Odnoklassniki player
2235 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2236 if mobj is not None:
2237 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2239 # Look for embedded ivi player
2240 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2241 if mobj is not None:
2242 return self.url_result(mobj.group('url'), 'Ivi')
2244 # Look for embedded Huffington Post player
2246 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2247 if mobj is not None:
2248 return self.url_result(mobj.group('url'), 'HuffPost')
2251 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2252 if mobj is not None:
2253 return self.url_result(mobj.group('url'))
2254 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2255 if mobj is not None:
2256 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2258 # Look for funnyordie embed
2259 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2261 return self.playlist_from_matches(
2262 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2264 # Look for BBC iPlayer embed
2265 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2267 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2269 # Look for embedded RUTV player
2270 rutv_url = RUTVIE._extract_url(webpage)
2272 return self.url_result(rutv_url, 'RUTV')
2274 # Look for embedded TVC player
2275 tvc_url = TVCIE._extract_url(webpage)
2277 return self.url_result(tvc_url, 'TVC')
2279 # Look for embedded SportBox player
2280 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2282 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2284 # Look for embedded XHamster player
2285 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2287 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2289 # Look for embedded TNAFlixNetwork player
2290 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2292 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2294 # Look for embedded PornHub player
2295 pornhub_urls = PornHubIE._extract_urls(webpage)
2297 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2299 # Look for embedded DrTuber player
2300 drtuber_urls = DrTuberIE._extract_urls(webpage)
2302 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2304 # Look for embedded RedTube player
2305 redtube_urls = RedTubeIE._extract_urls(webpage)
2307 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2309 # Look for embedded Tvigle player
2311 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2312 if mobj is not None:
2313 return self.url_result(mobj.group('url'), 'Tvigle')
2315 # Look for embedded TED player
2317 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2318 if mobj is not None:
2319 return self.url_result(mobj.group('url'), 'TED')
2321 # Look for embedded Ustream videos
2322 ustream_url = UstreamIE._extract_url(webpage)
2324 return self.url_result(ustream_url, UstreamIE.ie_key())
2326 # Look for embedded arte.tv player
2328 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2330 if mobj is not None:
2331 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2333 # Look for embedded francetv player
2335 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2337 if mobj is not None:
2338 return self.url_result(mobj.group('url'))
2340 # Look for embedded smotri.com player
2341 smotri_url = SmotriIE._extract_url(webpage)
2343 return self.url_result(smotri_url, 'Smotri')
2345 # Look for embedded Myvi.ru player
2346 myvi_url = MyviIE._extract_url(webpage)
2348 return self.url_result(myvi_url)
2350 # Look for embedded soundcloud player
2351 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2353 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2355 # Look for tunein player
2356 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2358 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2360 # Look for embedded mtvservices player
2361 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2363 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2365 # Look for embedded yahoo player
2367 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2369 if mobj is not None:
2370 return self.url_result(mobj.group('url'), 'Yahoo')
2372 # Look for embedded sbs.com.au player
2376 <meta\s+property="og:video"\s+content=|
2379 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2381 if mobj is not None:
2382 return self.url_result(mobj.group('url'), 'SBS')
2384 # Look for embedded Cinchcast player
2386 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2388 if mobj is not None:
2389 return self.url_result(mobj.group('url'), 'Cinchcast')
2392 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2396 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2398 if mobj is not None:
2399 return self.url_result(mobj.group('url'), 'MLB')
2402 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2404 if mobj is not None:
2405 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2408 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2410 if mobj is not None:
2411 return self.url_result(mobj.group('url'), 'Livestream')
2413 # Look for Zapiks embed
2415 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2416 if mobj is not None:
2417 return self.url_result(mobj.group('url'), 'Zapiks')
2419 # Look for Kaltura embeds
2420 kaltura_url = KalturaIE._extract_url(webpage)
2422 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2424 # Look for Eagle.Platform embeds
2425 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2426 if eagleplatform_url:
2427 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2429 # Look for ClipYou (uses Eagle.Platform) embeds
2431 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2432 if mobj is not None:
2433 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2435 # Look for Pladform embeds
2436 pladform_url = PladformIE._extract_url(webpage)
2438 return self.url_result(pladform_url)
2440 # Look for Videomore embeds
2441 videomore_url = VideomoreIE._extract_url(webpage)
2443 return self.url_result(videomore_url)
2445 # Look for Webcaster embeds
2446 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2448 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2450 # Look for Playwire embeds
2452 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2453 if mobj is not None:
2454 return self.url_result(mobj.group('url'))
2456 # Look for 5min embeds
2458 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2459 if mobj is not None:
2460 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2462 # Look for Crooks and Liars embeds
2464 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2465 if mobj is not None:
2466 return self.url_result(mobj.group('url'))
2468 # Look for NBC Sports VPlayer embeds
2469 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2471 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2473 # Look for NBC News embeds
2474 nbc_news_embed_url = re.search(
2475 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2476 if nbc_news_embed_url:
2477 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2479 # Look for Google Drive embeds
2480 google_drive_url = GoogleDriveIE._extract_url(webpage)
2481 if google_drive_url:
2482 return self.url_result(google_drive_url, 'GoogleDrive')
2484 # Look for UDN embeds
2486 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2487 if mobj is not None:
2488 return self.url_result(
2489 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2491 # Look for Senate ISVP iframe
2492 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2494 return self.url_result(senate_isvp_url, 'SenateISVP')
2496 # Look for Dailymotion Cloud videos
2497 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2499 return self.url_result(dmcloud_url, 'DailymotionCloud')
2501 # Look for OnionStudios embeds
2502 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2503 if onionstudios_url:
2504 return self.url_result(onionstudios_url)
2506 # Look for ViewLift embeds
2507 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2509 return self.url_result(viewlift_url)
2511 # Look for JWPlatform embeds
2512 jwplatform_url = JWPlatformIE._extract_url(webpage)
2514 return self.url_result(jwplatform_url, 'JWPlatform')
2516 # Look for Digiteka embeds
2517 digiteka_url = DigitekaIE._extract_url(webpage)
2519 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2521 # Look for Arkena embeds
2522 arkena_url = ArkenaIE._extract_url(webpage)
2524 return self.url_result(arkena_url, ArkenaIE.ie_key())
2526 # Look for Piksel embeds
2527 piksel_url = PikselIE._extract_url(webpage)
2529 return self.url_result(piksel_url, PikselIE.ie_key())
2531 # Look for Limelight embeds
2532 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2534 return self.playlist_result(
2535 limelight_urls, video_id, video_title, video_description)
2537 # Look for Anvato embeds
2538 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2540 return self.playlist_result(
2541 anvato_urls, video_id, video_title, video_description)
2543 # Look for AdobeTVVideo embeds
2545 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2547 if mobj is not None:
2548 return self.url_result(
2549 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2552 # Look for Vine embeds
2554 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2556 if mobj is not None:
2557 return self.url_result(
2558 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2560 # Look for VODPlatform embeds
2562 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2564 if mobj is not None:
2565 return self.url_result(
2566 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2568 # Look for Mangomolo embeds
2570 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2572 video\?.*?\bid=(?P<video_id>\d+)|
2573 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2574 ).+?)\1''', webpage)
2575 if mobj is not None:
2577 '_type': 'url_transparent',
2578 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2579 'title': video_title,
2580 'description': video_description,
2581 'thumbnail': video_thumbnail,
2582 'uploader': video_uploader,
2584 video_id = mobj.group('video_id')
2587 'ie_key': 'MangomoloVideo',
2592 'ie_key': 'MangomoloLive',
2593 'id': mobj.group('channel_id'),
2597 # Look for Instagram embeds
2598 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2599 if instagram_embed_url is not None:
2600 return self.url_result(
2601 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2603 # Look for LiveLeak embeds
2604 liveleak_url = LiveLeakIE._extract_url(webpage)
2606 return self.url_result(liveleak_url, 'LiveLeak')
2608 # Look for 3Q SDN embeds
2609 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2612 '_type': 'url_transparent',
2613 'ie_key': ThreeQSDNIE.ie_key(),
2614 'url': self._proto_relative_url(threeqsdn_url),
2615 'title': video_title,
2616 'description': video_description,
2617 'thumbnail': video_thumbnail,
2618 'uploader': video_uploader,
2621 # Look for VBOX7 embeds
2622 vbox7_url = Vbox7IE._extract_url(webpage)
2624 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2626 # Look for DBTV embeds
2627 dbtv_urls = DBTVIE._extract_urls(webpage)
2629 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2631 # Look for Videa embeds
2632 videa_urls = VideaIE._extract_urls(webpage)
2634 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2636 # Look for 20 minuten embeds
2637 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2639 return self.playlist_from_matches(
2640 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2642 # Look for Openload embeds
2643 openload_urls = OpenloadIE._extract_urls(webpage)
2645 return self.playlist_from_matches(
2646 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2648 # Look for VideoPress embeds
2649 videopress_urls = VideoPressIE._extract_urls(webpage)
2651 return self.playlist_from_matches(
2652 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2654 # Look for Rutube embeds
2655 rutube_urls = RutubeIE._extract_urls(webpage)
2657 return self.playlist_from_matches(
2658 rutube_urls, ie=RutubeIE.ie_key())
2660 # Look for WashingtonPost embeds
2661 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2663 return self.playlist_from_matches(
2664 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2666 # Look for Mediaset embeds
2667 mediaset_urls = MediasetIE._extract_urls(webpage)
2669 return self.playlist_from_matches(
2670 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2672 # Looking for http://schema.org/VideoObject
2673 json_ld = self._search_json_ld(
2674 webpage, video_id, default={}, expected_type='VideoObject')
2675 if json_ld.get('url'):
2677 'title': video_title or info_dict['title'],
2678 'description': video_description,
2679 'thumbnail': video_thumbnail,
2680 'age_limit': age_limit
2682 info_dict.update(json_ld)
2685 # Look for HTML5 media
2686 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2688 for entry in entries:
2691 'title': video_title,
2693 self._sort_formats(entry['formats'])
2694 return self.playlist_result(entries)
2696 jwplayer_data = self._find_jwplayer_data(
2697 webpage, video_id, transform_source=js_to_json)
2699 info = self._parse_jwplayer_data(
2700 jwplayer_data, video_id, require_title=False, base_url=url)
2701 if not info.get('title'):
2702 info['title'] = video_title
2705 def check_video(vurl):
2706 if YoutubeIE.suitable(vurl):
2708 if RtmpIE.suitable(vurl):
2710 vpath = compat_urlparse.urlparse(vurl).path
2711 vext = determine_ext(vpath)
2712 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2714 def filter_video(urls):
2715 return list(filter(check_video, urls))
2717 # Start with something easy: JW Player in SWFObject
2718 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2720 # Look for gorilla-vid style embedding
2721 found = filter_video(re.findall(r'''(?sx)
2725 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2728 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2730 # Broaden the search a little bit
2731 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2733 # Broaden the findall a little bit: JWPlayer JS loader
2734 found = filter_video(re.findall(
2735 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2738 found = filter_video(re.findall(r'''(?xs)
2739 flowplayer\("[^"]+",\s*
2741 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2742 ["']?url["']?\s*:\s*["']([^"']+)["']
2747 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2749 # Try to find twitter cards info
2750 # twitter:player:stream should be checked before twitter:player since
2751 # it is expected to contain a raw stream (see
2752 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2753 found = filter_video(re.findall(
2754 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2756 # We look for Open Graph info:
2757 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2758 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2759 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2760 if m_video_type is not None:
2761 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2763 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2765 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2766 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2769 # Look also in Refresh HTTP header
2770 refresh_header = head_response.headers.get('Refresh')
2772 # In python 2 response HTTP headers are bytestrings
2773 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2774 refresh_header = refresh_header.decode('iso-8859-1')
2775 found = re.search(REDIRECT_REGEX, refresh_header)
2777 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2779 self.report_following_redirect(new_url)
2788 # twitter:player is a https URL to iframe player that may or may not
2789 # be supported by youtube-dl thus this is checked the very last (see
2790 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2791 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2793 return self.url_result(embed_url)
2796 raise UnsupportedError(url)
2799 for video_url in orderedSet(found):
2800 video_url = unescapeHTML(video_url)
2801 video_url = video_url.replace('\\/', '/')
2802 video_url = compat_urlparse.urljoin(url, video_url)
2803 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2805 # Sometimes, jwplayer extraction will result in a YouTube URL
2806 if YoutubeIE.suitable(video_url):
2807 entries.append(self.url_result(video_url, 'Youtube'))
2810 # here's a fun little line of code for you:
2811 video_id = os.path.splitext(video_id)[0]
2815 'uploader': video_uploader,
2816 'title': video_title,
2817 'age_limit': age_limit,
2820 if RtmpIE.suitable(video_url):
2821 entry_info_dict.update({
2822 '_type': 'url_transparent',
2823 'ie_key': RtmpIE.ie_key(),
2826 entries.append(entry_info_dict)
2829 ext = determine_ext(video_url)
2831 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2833 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2835 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2837 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2839 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2840 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2841 # Just matching .ism/manifest is not enough to be reliably sure
2842 # whether it's actually an ISM manifest or some other streaming
2843 # manifest since there are various streaming URL formats
2844 # possible (see [1]) as well as some other shenanigans like
2845 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2847 # Thus the most reasonable way to solve this is to delegate
2848 # to generic extractor in order to look into the contents of
2849 # the manifest itself.
2850 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2851 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2852 entry_info_dict = self.url_result(
2853 smuggle_url(video_url, {'to_generic': True}),
2856 entry_info_dict['url'] = video_url
2858 if entry_info_dict.get('formats'):
2859 self._sort_formats(entry_info_dict['formats'])
2861 entries.append(entry_info_dict)
2863 if len(entries) == 1:
2866 for num, e in enumerate(entries, start=1):
2867 # 'url' results don't have a title
2868 if e.get('title') is not None:
2869 e['title'] = '%s (%d)' % (e['title'], num)
2871 '_type': 'playlist',