3 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from .youtube
import YoutubeIE
11 from ..compat
import (
12 compat_etree_fromstring
,
13 compat_urllib_parse_unquote
,
15 compat_xml_parse_error
,
33 from .commonprotocols
import RtmpIE
34 from .brightcove
import (
38 from .nbc
import NBCSportsVPlayerIE
39 from .ooyala
import OoyalaIE
40 from .rutv
import RUTVIE
41 from .tvc
import TVCIE
42 from .sportbox
import SportBoxEmbedIE
43 from .smotri
import SmotriIE
44 from .myvi
import MyviIE
45 from .condenast
import CondeNastIE
46 from .udn
import UDNEmbedIE
47 from .senateisvp
import SenateISVPIE
48 from .svt
import SVTIE
49 from .pornhub
import PornHubIE
50 from .xhamster
import XHamsterEmbedIE
51 from .tnaflix
import TNAFlixNetworkEmbedIE
52 from .drtuber
import DrTuberIE
53 from .redtube
import RedTubeIE
54 from .vimeo
import VimeoIE
55 from .dailymotion
import (
59 from .onionstudios
import OnionStudiosIE
60 from .viewlift
import ViewLiftEmbedIE
61 from .mtv
import MTVServicesEmbeddedIE
62 from .pladform
import PladformIE
63 from .videomore
import VideomoreIE
64 from .webcaster
import WebcasterFeedIE
65 from .googledrive
import GoogleDriveIE
66 from .jwplatform
import JWPlatformIE
67 from .digiteka
import DigitekaIE
68 from .arkena
import ArkenaIE
69 from .instagram
import InstagramIE
70 from .liveleak
import LiveLeakIE
71 from .threeqsdn
import ThreeQSDNIE
72 from .theplatform
import ThePlatformIE
73 from .vessel
import VesselIE
74 from .kaltura
import KalturaIE
75 from .eagleplatform
import EaglePlatformIE
76 from .facebook
import FacebookIE
77 from .soundcloud
import SoundcloudIE
78 from .tunein
import TuneInBaseIE
79 from .vbox7
import Vbox7IE
80 from .dbtv
import DBTVIE
81 from .piksel
import PikselIE
82 from .videa
import VideaIE
83 from .twentymin
import TwentyMinutenIE
84 from .ustream
import UstreamIE
85 from .openload
import OpenloadIE
86 from .videopress
import VideoPressIE
87 from .rutube
import RutubeIE
90 class GenericIE(InfoExtractor
):
91 IE_DESC
= 'Generic downloader that works on some sites'
95 # Direct link to a video
97 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
98 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
103 'upload_date': '20100513',
106 # Direct link to media delivered compressed (until Accept-Encoding is *)
108 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
109 'md5': '128c42e68b13950268b648275386fc74',
111 'id': 'FictionJunction-Parallel_Hearts',
113 'title': 'FictionJunction-Parallel_Hearts',
114 'upload_date': '20140522',
116 'expected_warnings': [
117 'URL could be a direct video link, returning it as such.'
119 'skip': 'URL invalid',
121 # Direct download with broken HEAD
123 'url': 'http://ai-radio.org:8000/radio.opus',
130 'skip_download': True, # infinite live stream
132 'expected_warnings': [
133 r
'501.*Not Implemented',
137 # Direct link with incorrect MIME type
139 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
140 'md5': '4ccbebe5f36706d85221f204d7eb5913',
142 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
143 'id': '5_Lennart_Poettering_-_Systemd',
145 'title': '5_Lennart_Poettering_-_Systemd',
146 'upload_date': '20141120',
148 'expected_warnings': [
149 'URL could be a direct video link, returning it as such.'
154 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
156 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'title': 'Zero Punctuation',
158 'description': 're:.*groundbreaking video review series.*'
160 'playlist_mincount': 11,
162 # RSS feed with enclosure
164 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
166 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
168 'upload_date': '20150228',
169 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
172 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
174 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
178 'title': 'Automatics, robotics and biocybernetics',
179 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
180 'upload_date': '20130627',
181 'formats': 'mincount:16',
182 'subtitles': 'mincount:1',
185 'force_generic_extractor': True,
186 'skip_download': True,
189 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
191 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
196 'formats': 'mincount:1',
199 'skip_download': True,
202 # SMIL from https://www.restudy.dk/video/play/id/1637
204 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
208 'title': 'video_1637',
209 'formats': 'mincount:3',
212 'skip_download': True,
215 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
217 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
219 'id': 'smil-service',
221 'title': 'smil-service',
222 'formats': 'mincount:1',
225 'skip_download': True,
228 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
230 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
234 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
235 'formats': 'mincount:3',
238 'skip_download': True,
241 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
243 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
245 'id': 'mZlp2ctYIUEB',
247 'title': 'Tikibad ontruimd wegens brand',
248 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
249 'thumbnail': r
're:^https?://.*\.jpg$',
253 'skip_download': True,
256 # MPD from http://dash-mse-test.appspot.com/media.html
258 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
259 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
261 'id': 'car-20120827-manifest',
263 'title': 'car-20120827-manifest',
264 'formats': 'mincount:9',
265 'upload_date': '20130904',
268 'format': 'bestvideo',
271 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
273 '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',
278 'formats': 'mincount:8',
282 'skip_download': True,
284 'skip': 'video gone',
286 # m3u8 served with Content-Type: text/plain
288 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
293 'upload_date': '20140720',
294 'formats': 'mincount:11',
298 'skip_download': True,
300 'skip': 'video gone',
304 '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',
308 'upload_date': '20130224',
309 'uploader_id': 'TheVerge',
310 'description': r
're:^Chris Ziegler takes a look at the\.*',
311 'uploader': 'The Verge',
312 'title': 'First Firefox OS phones side-by-side',
315 'skip_download': False,
319 # redirect in Refresh HTTP header
320 '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',
324 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
325 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
326 'upload_date': '20150917',
327 'uploader_id': 'brtvofficial',
328 'uploader': 'Boiler Room',
331 'skip_download': False,
335 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
336 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
338 'id': '13601338388002',
340 'uploader': 'www.hodiho.fr',
341 'title': 'R\u00e9gis plante sa Jeep',
344 # bandcamp page with custom domain
346 'add_ie': ['Bandcamp'],
347 'url': 'http://bronyrock.com/track/the-pony-mash',
351 'title': 'The Pony Mash',
352 'uploader': 'M_Pallante',
354 'skip': 'There is a limit of 200 free downloads / month for the test song',
357 # embedded brightcove video
358 # it also tests brightcove videos that need to set the 'Referer'
359 # in the http requests
360 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
363 'id': '2765128793001',
365 'title': 'Le cours de bourse : l’analyse technique',
366 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
367 'uploader': 'BFM BUSINESS',
370 'skip_download': True,
374 # embedded with itemprop embedURL and video id spelled as `idVideo`
375 'add_id': ['BrightcoveLegacy'],
376 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
378 'id': '5255628253001',
380 'title': 'md5:37c519b1128915607601e75a87995fc0',
381 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
382 'uploader': 'BFM BUSINESS',
383 'uploader_id': '876450612001',
384 'timestamp': 1482255315,
385 'upload_date': '20161220',
388 'skip_download': True,
392 # https://github.com/rg3/youtube-dl/issues/2253
393 'url': 'http://bcove.me/i6nfkrc3',
394 'md5': '0ba9446db037002366bab3b3eb30c88c',
396 'id': '3101154703001',
398 'title': 'Still no power',
399 'uploader': 'thestar.com',
400 '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.',
402 'add_ie': ['BrightcoveLegacy'],
403 'skip': 'video gone',
406 'url': 'http://www.championat.com/video/football/v/87/87499.html',
407 'md5': 'fb973ecf6e4a78a67453647444222983',
409 'id': '3414141473001',
411 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
412 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
413 'uploader': 'Championat',
417 # https://github.com/rg3/youtube-dl/issues/3541
418 'add_ie': ['BrightcoveLegacy'],
419 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
421 'id': '3866516442001',
423 'title': 'Leer mij vrouwen kennen: Aflevering 1',
424 'description': 'Leer mij vrouwen kennen: Aflevering 1',
425 'uploader': 'SBS Broadcasting',
427 'skip': 'Restricted to Netherlands',
429 'skip_download': True, # m3u8 download
433 # Brightcove with alternative playerID key
434 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
436 'id': 'nmeth.2062_SV1',
437 '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',
441 'id': '2228375078001',
443 'title': 'nmeth.2062-sv1',
444 'description': 'nmeth.2062-sv1',
445 'timestamp': 1363357591,
446 'upload_date': '20130315',
447 'uploader': 'Nature Publishing Group',
448 'uploader_id': '1964492299001',
453 # Brightcove with UUID in videoPlayer
454 'url': 'http://www8.hp.com/cn/zh/home.html',
456 'id': '5255815316001',
458 'title': 'Sprocket Video - China',
459 'description': 'Sprocket Video - China',
460 'uploader': 'HP-Video Gallery',
461 'timestamp': 1482263210,
462 'upload_date': '20161220',
463 'uploader_id': '1107601872001',
466 'skip_download': True, # m3u8 download
471 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
472 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
474 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
476 'title': '2cc213299525360.mov', # that's what we get
479 'add_ie': ['Ooyala'],
482 # ooyala video embedded with http://player.ooyala.com/iframe.js
483 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
485 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
487 'title': '"Steve Jobs: Man in the Machine" trailer',
488 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
492 'skip_download': True,
494 'skip': 'movie expired',
498 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
502 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
503 'upload_date': '20140225',
504 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
505 'uploader': 'Tested',
506 'uploader_id': 'testedcom',
508 # No need to test YoutubeIE here
510 'skip_download': True,
515 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
519 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
520 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
522 # HEAD requests lead to endless 301, while GET is OK
523 'expected_warnings': ['301'],
527 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
531 'title': 'Охотское море стало целиком российским',
532 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
536 'skip_download': True,
541 '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/',
545 'title': 'Дошкольное воспитание',
550 'url': 'http://www.vestifinance.ru/articles/25753',
553 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
558 'title': 'Госзаказ. День 3',
564 'title': 'Госзаказ. День 2',
570 'title': 'Госзаказ. День 1',
576 'skip_download': True,
581 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
583 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
585 'title': 'Ужастики, русский трейлер (2015)',
586 'thumbnail': r
're:^https?://.*\.jpg$',
592 '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',
595 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
597 'playlist_mincount': 7,
598 # This forum does not allow <iframe> syntaxes anymore
599 # Now HTML tags are displayed as-is
600 'skip': 'No videos on this page',
604 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
605 'md5': '65fdff94098e4a607385a60c5177c638',
609 'title': 'Hidden miracles of the natural world',
610 'uploader': 'Louie Schwartzberg',
611 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
614 # nowvideo embed hidden behind percent encoding
616 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
617 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
619 'id': '06e53103ca9aa',
621 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
622 'description': 'No description',
627 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
628 'md5': '7653032cbb25bf6c80d80f217055fa43',
630 'id': '048195-004_PLUS7-F',
633 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
634 'upload_date': '20140320',
637 'skip_download': 'Requires rtmpdump'
639 'skip': 'video gone',
643 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
647 'title': 'Alcaline, le concert avec Calogero',
648 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
649 'upload_date': '20150226',
650 'timestamp': 1424989860,
655 'skip_download': True,
657 'expected_warnings': [
663 'url': 'http://www.wired.com/2014/04/honda-asimo/',
664 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
666 'id': '53501be369702d3275860000',
668 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
673 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
674 'md5': '441aeeb82eb72c422c7f14ec533999cd',
676 'id': 'k2mm4bCdJ6CQ2i7c8o2',
678 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
679 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
681 'uploader_id': 'xgditw',
682 'upload_date': '20140425',
683 'timestamp': 1398441542,
685 'add_ie': ['Dailymotion'],
689 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
693 'title': 'The NBL Auction 2014',
694 'uploader': 'BADMINTON England',
695 'uploader_id': 'BADMINTONEvents',
696 'upload_date': '20140603',
697 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
699 'add_ie': ['Youtube'],
701 'skip_download': True,
706 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
707 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
709 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
711 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
712 'description': 'Two valets share their love for movie star Liam Neesons.',
713 'timestamp': 1349922600,
714 'upload_date': '20121011',
717 # YouTube embed via <data-embed-url="">
719 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
723 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
724 'uploader': 'Gameloft',
725 'uploader_id': 'gameloft',
726 'upload_date': '20140828',
727 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
730 'skip_download': True,
735 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
737 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
739 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
740 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
745 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
747 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
748 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
754 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
759 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
760 'md5': '9d65602bf31c6e20014319c7d07fba27',
762 'id': '5123ea6d5e5a7',
765 'uploader': 'www.handjobhub.com',
766 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
769 # Multiple brightcove videos
770 # https://github.com/rg3/youtube-dl/issues/2283
772 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
774 'id': 'always-never',
775 'title': 'Always / Never - The New Yorker',
779 'extract_flat': False,
780 'skip_download': True,
785 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
786 'md5': '96f09a37e44da40dd083e12d9a683327',
790 'title': 'Ump changes call to ball',
791 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
793 'timestamp': 1401537900,
794 'upload_date': '20140531',
795 'thumbnail': r
're:^https?://.*\.jpg$',
800 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
801 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
805 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
806 'description': 'a Paywall Videos video from Remilon',
808 'uploader': 'study.com',
809 'timestamp': 1459678540,
810 'upload_date': '20160403',
811 'filesize': 24687186,
815 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
816 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
820 'title': 'Conversation about Hexagonal Rails Part 1',
821 'description': 'a Martin Fowler video from ThoughtWorks',
823 'uploader': 'thoughtworks.wistia.com',
824 'timestamp': 1401832161,
825 'upload_date': '20140603',
828 # Wistia standard embed (async)
830 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
834 'title': 'Drip Brennan Dunn Workshop',
835 'description': 'a JV Webinars video from getdrip-1',
837 'timestamp': 1463607249,
838 'upload_date': '20160518',
841 'skip_download': True,
846 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
850 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
851 'uploader': 'Sophos Security',
852 'title': 'Chet Chat 171 - Oct 29, 2014',
853 'upload_date': '20141029',
856 # Soundcloud multiple embeds
858 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
861 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
863 'playlist_mincount': 7,
865 # TuneIn station embed
867 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
872 'location': 'Paris, France',
877 'skip_download': True,
882 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
886 'upload_date': '20141112',
887 'title': 'Rosetta #CometLanding webcast HL 10',
890 # Another Livestream embed, without 'new.' in URL
892 'url': 'https://www.freespeech.org/',
896 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
900 'skip_download': True,
905 'url': 'https://skiplagged.com/',
908 'title': 'Skiplagged: The smart way to find cheap flights',
910 'playlist_mincount': 1,
911 'add_ie': ['Youtube'],
915 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
919 'upload_date': '20141126',
920 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
925 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
927 'id': '730m_DandD_1901_512k',
929 'uploader': 'www.abc.net.au',
930 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
933 # embedded viddler video
935 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
939 'uploader': 'deadspin',
940 'title': 'WALL-TO-GORTAT',
941 'timestamp': 1422285291,
942 'upload_date': '20150126',
944 'add_ie': ['Viddler'],
948 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
952 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
953 'description': 'md5:601cb790edd05908957dae8aaa866465',
954 'upload_date': '20150220',
956 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
960 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
964 'upload_date': '20150212',
965 'uploader': 'The National Archives UK',
966 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
967 'uploader_id': 'NationalArchives08',
968 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
973 'url': 'http://www.suffolk.edu/sjc/',
977 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
978 'uploader': 'www.suffolk.edu',
981 'skip_download': True,
986 'url': 'http://www.indiedb.com/games/king-machine/videos',
990 'title': 'king machine trailer 1',
991 'thumbnail': r
're:^https?://.*\.jpg$',
996 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
997 'playlist_mincount': 5,
999 'id': 'aanslagen-kopenhagen',
1000 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1005 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1009 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1012 # Kaltura embed (different embed code)
1014 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1018 'upload_date': '20150127',
1019 'uploader_id': 'PremierMedia',
1021 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1024 # Kaltura embed with single quotes
1026 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1031 'timestamp': 1355743100,
1032 'upload_date': '20121217',
1033 'uploader_id': 'batchUser',
1035 'add_ie': ['Kaltura'],
1038 # Kaltura embedded via quoted entry_id
1039 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1043 'title': '06_matthew_brender_raj_dutt',
1044 'timestamp': 1466638791,
1045 'upload_date': '20160622',
1047 'add_ie': ['Kaltura'],
1048 'expected_warnings': [
1049 'Could not send HEAD request'
1052 'skip_download': True,
1056 # Kaltura embedded, some fileExt broken (#11480)
1057 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1061 'title': 'Our "Standard Models" of particle physics and cosmology',
1062 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1063 'timestamp': 1321158993,
1064 'upload_date': '20111113',
1065 'uploader_id': 'kps1',
1067 'add_ie': ['Kaltura'],
1069 # Eagle.Platform embed (generic URL)
1071 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1072 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1076 'title': 'Навальный вышел на свободу',
1077 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1078 'thumbnail': r
're:^https?://.*\.jpg$',
1084 # ClipYou (Eagle.Platform) embed (custom URL)
1086 'url': 'http://muz-tv.ru/play/7129/',
1087 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1091 'title': "'O Sole Mio",
1092 'thumbnail': r
're:^https?://.*\.jpg$',
1099 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1103 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1104 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1105 'thumbnail': r
're:^https?://.*\.jpg$',
1112 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1116 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1117 'thumbnail': r
're:^https?://.*\.png$',
1123 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1124 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1128 'title': 'Facebook Creates "On This Day" | Crunch Report',
1133 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1137 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1142 # Crooks and Liars embed
1144 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1148 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1149 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1150 'timestamp': 1428207000,
1151 'upload_date': '20150405',
1152 'uploader': 'Heather',
1155 # Crooks and Liars external embed
1157 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1159 'id': 'MTE3MjUtMzQ2MzA',
1161 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1162 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1163 'timestamp': 1265032391,
1164 'upload_date': '20100201',
1165 'uploader': 'Heather',
1168 # NBC Sports vplayer embed
1170 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1172 'id': 'ln7x1qSThw4k',
1174 'title': "PFT Live: New leader in the 'new-look' defense",
1175 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1176 'uploader': 'NBCU-SPORTS',
1177 'upload_date': '20140107',
1178 'timestamp': 1389118457,
1183 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1184 'md5': '1aa589c675898ae6d37a17913cf68d66',
1186 'id': '701714499682',
1188 'title': 'PREVIEW: On Assignment: David Letterman',
1189 '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.',
1194 'url': 'https://video.udn.com/news/300346',
1195 'md5': 'fd2060e988c326991037b9aff9df21a6',
1199 'title': '中一中男師變性 全校師生力挺',
1200 'thumbnail': r
're:^https?://.*\.jpg$',
1204 'skip_download': True,
1209 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1211 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1213 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1214 'title': 'This is what separates the Excel masters from the wannabes',
1215 'duration': 191.933,
1219 'skip_download': True,
1222 # Brightcove URL in single quotes
1224 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1225 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1227 'id': '4255764656001',
1229 'title': 'SN Presents: Russell Martin, World Citizen',
1230 '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.',
1231 'uploader': 'Rogers Sportsnet',
1232 'uploader_id': '1704050871',
1233 'upload_date': '20150525',
1234 'timestamp': 1432570283,
1237 # Dailymotion Cloud video
1239 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1240 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1244 'title': 'Sauvons les abeilles ! - Le débat',
1245 'description': 'md5:d9082128b1c5277987825d684939ca26',
1246 'thumbnail': r
're:^https?://.*\.jpe?g$',
1247 'timestamp': 1434970506,
1248 'upload_date': '20150622',
1249 'uploader': 'Public Sénat',
1250 'uploader_id': 'xa9gza',
1253 # OnionStudios embed
1255 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1259 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1260 'thumbnail': r
're:^https?://.*\.jpe?g$',
1261 'uploader': 'ClickHole',
1262 'uploader_id': 'clickhole',
1267 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1269 'id': '74849a00-85a9-11e1-9660-123139220831',
1271 'title': '#whilewewatch',
1274 # AdobeTVVideo embed
1276 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1277 'md5': '43662b577c018ad707a63766462b1e87',
1281 'title': 'New experience with Acrobat DC',
1282 'description': 'New experience with Acrobat DC',
1283 'duration': 248.667,
1286 # BrightcoveInPageEmbed embed
1288 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1290 'id': '4238694884001',
1292 'title': 'Tabletop: Dread, Last Thoughts',
1293 'description': 'Tabletop: Dread, Last Thoughts',
1297 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1298 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1300 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1302 'id': '4785848093001',
1304 'title': 'The Cardinal Pell Interview',
1305 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1306 'uploader': 'GlobeCast Australia - GlobeStream',
1307 'uploader_id': '2733773828001',
1308 'upload_date': '20160304',
1309 'timestamp': 1457083087,
1313 'skip_download': True,
1316 # Another form of arte.tv embed
1318 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1319 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1321 'id': '030273-562_PLUS7-F',
1323 'title': 'ARTE Reportage - Nulle part, en France',
1324 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1325 'upload_date': '20160409',
1330 'url': 'http://www.wykop.pl/link/3088787/',
1331 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1333 'id': '874_1459135191',
1335 'title': 'Man shows poor quality of new apartment building',
1336 'description': 'The wall is like a sand pile.',
1337 'uploader': 'Lake8737',
1340 # Duplicated embedded video URLs
1342 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1344 'id': '149298443_480_16c25b74_2',
1346 'title': 'vs. Blue Orange Spring Game',
1347 'uploader': 'www.hudl.com',
1350 # twitter:player:stream embed
1352 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1356 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1357 'uploader': 'www.rtl.be',
1361 'skip_download': True,
1364 # twitter:player embed
1366 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1367 'md5': 'a3e0df96369831de324f0778e126653c',
1369 'id': '4909620399001',
1371 'title': 'What Do Black Holes Sound Like?',
1372 'description': 'what do black holes sound like',
1373 'upload_date': '20160524',
1374 'uploader_id': '29913724001',
1375 'timestamp': 1464107587,
1376 'uploader': 'TheAtlantic',
1378 'add_ie': ['BrightcoveLegacy'],
1380 # Facebook <iframe> embed
1382 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1383 'md5': 'fbcde74f534176ecb015849146dd3aee',
1385 'id': '599637780109885',
1387 'title': 'Facebook video #599637780109885',
1390 # Facebook API embed
1392 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1393 'md5': 'a47372ee61b39a7b90287094d447d94e',
1395 'id': '10153467542406923',
1397 'title': 'Facebook video #10153467542406923',
1400 # Wordpress "YouTube Video Importer" plugin
1402 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1403 'md5': 'd16797741b560b485194eddda8121b48',
1405 'id': 'HNTXWDXV9Is',
1407 'title': 'Blue Devils Drumline Stanford lot 2016',
1408 'upload_date': '20160627',
1409 'uploader_id': 'GENOCIDE8GENERAL10',
1410 'uploader': 'cylus cyrus',
1414 # video stored on custom kaltura server
1415 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1416 'md5': '537617d06e64dfed891fa1593c4b30cc',
1420 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1421 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1422 'uploader_id': 'videos.expansion@el-mundo.net',
1423 'upload_date': '20150429',
1424 'timestamp': 1430303472,
1426 'add_ie': ['Kaltura'],
1429 # Non-standard Vimeo embed
1430 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1431 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1435 'title': 'Understanding the web - Teaser',
1436 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1437 'upload_date': '20151214',
1438 'uploader': 'OpenClassrooms',
1439 'uploader_id': 'openclassrooms',
1441 'add_ie': ['Vimeo'],
1444 # generic vimeo embed that requires original URL passed as Referer
1445 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1446 'only_matching': True,
1449 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1450 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1452 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1454 'title': 'Big Buck Bunny',
1455 'description': 'Royalty free test video',
1456 'timestamp': 1432816365,
1457 'upload_date': '20150528',
1461 'skip_download': True,
1463 'add_ie': [ArkenaIE
.ie_key()],
1466 '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/',
1470 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1473 'skip_download': True,
1475 'add_ie': [Vbox7IE
.ie_key()],
1479 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1482 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1484 'playlist_mincount': 3,
1488 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1490 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1491 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1493 'playlist_mincount': 2,
1497 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1501 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1502 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1505 'skip_download': True,
1507 'add_ie': [TwentyMinutenIE
.ie_key()],
1511 'url': 'https://en.support.wordpress.com/videopress/',
1515 'title': 'IMG_5786',
1516 'timestamp': 1435711927,
1517 'upload_date': '20150701',
1520 'skip_download': True,
1522 'add_ie': [VideoPressIE
.ie_key()],
1526 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1528 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1530 'title': 'Магаззино: Казань 2',
1531 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1532 'uploader': 'Магаззино',
1533 'upload_date': '20170228',
1534 'uploader_id': '996642',
1537 'skip_download': True,
1539 'add_ie': [RutubeIE
.ie_key()],
1542 # ThePlatform embedded with whitespaces in URLs
1543 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1544 'only_matching': True,
1547 # Senate ISVP iframe https
1548 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1549 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1551 'id': 'govtaff020316',
1553 'title': 'Integrated Senate Video Player',
1555 'add_ie': [SenateISVPIE
.ie_key()],
1558 # # TODO: find another test
1559 # # http://schema.org/VideoObject
1560 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1561 # 'md5': '888dcf08b7ea671381f00fab74692755',
1563 # 'id': 'nyvTSJMKId',
1565 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1566 # 'description': '#love for cats.',
1567 # 'timestamp': 1461244995,
1568 # 'upload_date': '20160421',
1571 # 'force_generic_extractor': True,
1576 def report_following_redirect(self
, new_url
):
1577 """Report information extraction."""
1578 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
1580 def _extract_rss(self
, url
, video_id
, doc
):
1581 playlist_title
= doc
.find('./channel/title').text
1582 playlist_desc_el
= doc
.find('./channel/description')
1583 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
1586 for it
in doc
.findall('./channel/item'):
1587 next_url
= xpath_text(it
, 'link', fatal
=False)
1589 enclosure_nodes
= it
.findall('./enclosure')
1590 for e
in enclosure_nodes
:
1591 next_url
= e
.attrib
.get('url')
1601 'title': it
.find('title').text
,
1605 '_type': 'playlist',
1607 'title': playlist_title
,
1608 'description': playlist_desc
,
1612 def _extract_camtasia(self
, url
, video_id
, webpage
):
1613 """ Returns None if no camtasia video can be found. """
1615 camtasia_cfg
= self
._search
_regex
(
1616 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1617 webpage
, 'camtasia configuration file', default
=None)
1618 if camtasia_cfg
is None:
1621 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
1623 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
1624 camtasia_cfg
= self
._download
_xml
(
1625 camtasia_url
, video_id
,
1626 note
='Downloading camtasia configuration',
1627 errnote
='Failed to download camtasia configuration')
1628 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
1631 for n
in fileset_node
.getchildren():
1632 url_n
= n
.find('./uri')
1637 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
1638 'title': '%s - %s' % (title
, n
.tag
),
1639 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
1640 'duration': float_or_none(n
.find('./duration').text
),
1644 '_type': 'playlist',
1649 def _real_extract(self
, url
):
1650 if url
.startswith('//'):
1653 'url': self
.http_scheme() + url
,
1656 parsed_url
= compat_urlparse
.urlparse(url
)
1657 if not parsed_url
.scheme
:
1658 default_search
= self
._downloader
.params
.get('default_search')
1659 if default_search
is None:
1660 default_search
= 'fixup_error'
1662 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
1664 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
1665 return self
.url_result('http://' + url
)
1666 elif default_search
!= 'fixup_error':
1667 if default_search
== 'auto_warning':
1668 if re
.match(r
'^(?:url|URL)$', url
):
1669 raise ExtractorError(
1670 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
1673 self
._downloader
.report_warning(
1674 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
1675 return self
.url_result('ytsearch:' + url
)
1677 if default_search
in ('error', 'fixup_error'):
1678 raise ExtractorError(
1679 '%r is not a valid URL. '
1680 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1681 % (url
, url
), expected
=True)
1683 if ':' not in default_search
:
1684 default_search
+= ':'
1685 return self
.url_result(default_search
+ url
)
1687 url
, smuggled_data
= unsmuggle_url(url
)
1688 force_videoid
= None
1689 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
1690 if smuggled_data
and 'force_videoid' in smuggled_data
:
1691 force_videoid
= smuggled_data
['force_videoid']
1692 video_id
= force_videoid
1694 video_id
= self
._generic
_id
(url
)
1696 self
.to_screen('%s: Requesting header' % video_id
)
1698 head_req
= HEADRequest(url
)
1699 head_response
= self
._request
_webpage
(
1701 note
=False, errnote
='Could not send HEAD request to %s' % url
,
1704 if head_response
is not False:
1705 # Check for redirect
1706 new_url
= head_response
.geturl()
1708 self
.report_following_redirect(new_url
)
1710 new_url
= smuggle_url(
1711 new_url
, {'force_videoid': force_videoid}
)
1712 return self
.url_result(new_url
)
1714 full_response
= None
1715 if head_response
is False:
1716 request
= sanitized_Request(url
)
1717 request
.add_header('Accept-Encoding', '*')
1718 full_response
= self
._request
_webpage
(request
, video_id
)
1719 head_response
= full_response
1723 'title': self
._generic
_title
(url
),
1724 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
1727 # Check for direct link to a video
1728 content_type
= head_response
.headers
.get('Content-Type', '').lower()
1729 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
1731 format_id
= m
.group('format_id')
1732 if format_id
.endswith('mpegurl'):
1733 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1734 elif format_id
== 'f4m':
1735 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
1738 'format_id': m
.group('format_id'),
1740 'vcodec': 'none' if m
.group('type') == 'audio' else None
1742 info_dict
['direct'] = True
1743 self
._sort
_formats
(formats
)
1744 info_dict
['formats'] = formats
1747 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
1748 force
= self
._downloader
.params
.get('force_generic_extractor', False)
1749 self
._downloader
.report_warning(
1750 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
1752 if not full_response
:
1753 request
= sanitized_Request(url
)
1754 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1755 # making it impossible to download only chunk of the file (yet we need only 512kB to
1756 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1757 # that will always result in downloading the whole file that is not desirable.
1758 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1759 # to accept raw bytes and being able to download only a chunk.
1760 # It may probably better to solve this by checking Content-Type for application/octet-stream
1761 # after HEAD request finishes, but not sure if we can rely on this.
1762 request
.add_header('Accept-Encoding', '*')
1763 full_response
= self
._request
_webpage
(request
, video_id
)
1765 first_bytes
= full_response
.read(512)
1767 # Is it an M3U playlist?
1768 if first_bytes
.startswith(b
'#EXTM3U'):
1769 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
1770 self
._sort
_formats
(info_dict
['formats'])
1773 # Maybe it's a direct link to a video?
1774 # Be careful not to download the whole thing!
1775 if not is_html(first_bytes
):
1776 self
._downloader
.report_warning(
1777 'URL could be a direct video link, returning it as such.')
1784 webpage
= self
._webpage
_read
_content
(
1785 full_response
, url
, video_id
, prefix
=first_bytes
)
1787 self
.report_extraction(video_id
)
1789 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1791 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
1792 if doc
.tag
== 'rss':
1793 return self
._extract
_rss
(url
, video_id
, doc
)
1794 elif doc
.tag
== 'SmoothStreamingMedia':
1795 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
1796 self
._sort
_formats
(info_dict
['formats'])
1798 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
1799 smil
= self
._parse
_smil
(doc
, url
, video_id
)
1800 self
._sort
_formats
(smil
['formats'])
1802 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
1803 return self
.playlist_result(self
._parse
_xspf
(doc
, video_id
), video_id
)
1804 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
1805 info_dict
['formats'] = self
._parse
_mpd
_formats
(
1807 mpd_base_url
=full_response
.geturl().rpartition('/')[0],
1809 self
._sort
_formats
(info_dict
['formats'])
1811 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
1812 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
1813 self
._sort
_formats
(info_dict
['formats'])
1815 except compat_xml_parse_error
:
1818 # Is it a Camtasia project?
1819 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
1820 if camtasia_res
is not None:
1823 # Sometimes embedded video player is hidden behind percent encoding
1824 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1825 # Unescaping the whole page allows to handle those cases in a generic way
1826 webpage
= compat_urllib_parse_unquote(webpage
)
1828 # it's tempting to parse this further, but you would
1829 # have to take into account all the variations like
1830 # Video Title - Site Name
1831 # Site Name | Video Title
1832 # Video Title - Tagline | Site Name
1833 # and so on and so forth; it's just not practical
1834 video_title
= self
._og
_search
_title
(
1835 webpage
, default
=None) or self
._html
_search
_regex
(
1836 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
1839 # Try to detect age limit automatically
1840 age_limit
= self
._rta
_search
(webpage
)
1841 # And then there are the jokers who advertise that they use RTA,
1842 # but actually don't.
1843 AGE_LIMIT_MARKERS
= [
1844 r
'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1846 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
1849 # video uploader is domain name
1850 video_uploader
= self
._search
_regex
(
1851 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
1853 video_description
= self
._og
_search
_description
(webpage
, default
=None)
1854 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
1856 # Look for Brightcove Legacy Studio embeds
1857 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
1859 self
.to_screen('Brightcove video detected.')
1862 'url': smuggle_url(bc_url
, {'Referer': url}
),
1863 'ie_key': 'BrightcoveLegacy'
1864 } for bc_url
in bc_urls
]
1867 '_type': 'playlist',
1868 'title': video_title
,
1873 # Look for Brightcove New Studio embeds
1874 bc_urls
= BrightcoveNewIE
._extract
_urls
(webpage
)
1876 return self
.playlist_from_matches(bc_urls
, video_id
, video_title
, ie
='BrightcoveNew')
1878 # Look for ThePlatform embeds
1879 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
1881 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
1883 # Look for Vessel embeds
1884 vessel_urls
= VesselIE
._extract
_urls
(webpage
)
1886 return self
.playlist_from_matches(vessel_urls
, video_id
, video_title
, ie
=VesselIE
.ie_key())
1888 # Look for embedded rtl.nl player
1889 matches
= re
.findall(
1890 r
'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1893 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
1895 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
1897 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
1899 vid_me_embed_url
= self
._search
_regex
(
1900 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1901 webpage, 'vid.me embed', default=None)
1902 if vid_me_embed_url is not None:
1903 return self.url_result(vid_me_embed_url, 'Vidme')
1905 # Look for embedded YouTube player
1906 matches = re.findall(r'''(?x)
1915 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1919 return self.playlist_from_matches(
1920 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
1922 # Look for lazyYT YouTube embed
1923 matches = re.findall(
1924 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1926 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
1928 # Look for Wordpress "YouTube Video Importer" plugin
1929 matches = re.findall(r'''(?x
)<div
[^
>]+
1930 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1931 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1933 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
1935 matches = DailymotionIE._extract_urls(webpage)
1937 return self.playlist_from_matches(matches, video_id, video_title)
1939 # Look for embedded Dailymotion playlist player (#3822)
1941 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}
/widget
/jukebox
\?.+?
)\
1', webpage)
1943 playlists = re.findall(
1944 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
1946 return self.playlist_from_matches(
1947 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
1949 # Look for embedded Wistia player
1951 r'<(?
:meta
[^
>]+?content|iframe
[^
>]+?src
)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1953 embed_url = self._proto_relative_url(
1954 unescapeHTML(match.group('url')))
1956 '_type': 'url_transparent',
1959 'uploader': video_uploader,
1962 match = re.search(r'(?:id=["\']wistia_|data
-wistia
-?
id=["\']|Wistia\.embed\(["\'])(?P
<id>[^
"\']+)', webpage)
1965 '_type': 'url_transparent',
1966 'url': 'wistia:%s' % match.group('id'),
1968 'uploader': video_uploader,
1973 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1974 <div[^>]+class=(["']).*?
\bwistia
_async
_(?P
<id>[a
-z0
-9]+)\b.*?\
2
1977 return self.url_result(self._proto_relative_url(
1978 'wistia:%s' % match.group('id')), 'Wistia')
1980 # Look for SVT player
1981 svt_url = SVTIE._extract_url(webpage)
1983 return self.url_result(svt_url, 'SVT')
1985 # Look for embedded condenast player
1986 matches = re.findall(
1987 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1991 '_type': 'playlist',
1994 'ie_key': 'CondeNast',
1996 } for ma in matches],
1997 'title': video_title,
2001 # Look for Bandcamp pages with custom domain
2002 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2003 if mobj is not None:
2004 burl = unescapeHTML(mobj.group(1))
2005 # Don't set the extractor because it can be a track url or an album
2006 return self.url_result(burl)
2008 # Look for embedded Vevo player
2010 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2011 if mobj is not None:
2012 return self.url_result(mobj.group('url'))
2014 # Look for embedded Viddler player
2016 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2018 if mobj is not None:
2019 return self.url_result(mobj.group('url'))
2021 # Look for NYTimes player
2023 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2025 if mobj is not None:
2026 return self.url_result(mobj.group('url'))
2028 # Look for Libsyn player
2030 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2031 if mobj is not None:
2032 return self.url_result(mobj.group('url'))
2034 # Look for Ooyala videos
2035 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2036 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2037 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2038 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2039 if mobj is not None:
2040 embed_token = self._search_regex(
2041 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2042 webpage, 'ooyala embed token', default=None)
2043 return OoyalaIE._build_url_result(smuggle_url(
2046 'embed_token': embed_token,
2049 # Look for multiple Ooyala embeds on SBN network websites
2050 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2051 if mobj is not None:
2052 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2054 return self.playlist_from_matches(
2055 embeds, video_id, video_title,
2056 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2058 # Look for Aparat videos
2059 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2060 if mobj is not None:
2061 return self.url_result(mobj.group(1), 'Aparat')
2063 # Look for MPORA videos
2064 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2065 if mobj is not None:
2066 return self.url_result(mobj.group(1), 'Mpora')
2068 # Look for embedded NovaMov-based player
2070 r'''(?x
)<(?
:pagespeed_
)?iframe
[^
>]+?src
=(["\'])
2071 (?P<url>http://(?:(?:embed|www)\.)?
2073 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2074 videoweed\.(?:es|com)|
2075 movshare\.(?:net|sx|ag)|
2076 divxstage\.(?:eu|net|ch|co|at|ag))
2077 /embed\.php.+?)\1''', webpage)
2078 if mobj is not None:
2079 return self.url_result(mobj.group('url'))
2081 # Look for embedded Facebook player
2082 facebook_url = FacebookIE._extract_url(webpage)
2083 if facebook_url is not None:
2084 return self.url_result(facebook_url, 'Facebook')
2086 # Look for embedded VK player
2087 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://vk\
.com
/video_ext\
.php
.+?
)\
1', webpage)
2088 if mobj is not None:
2089 return self.url_result(mobj.group('url
'), 'VK
')
2091 # Look for embedded Odnoklassniki player
2092 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2093 if mobj is not None:
2094 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2096 # Look for embedded ivi player
2097 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
2098 if mobj is not None:
2099 return self.url_result(mobj.group('url
'), 'Ivi
')
2101 # Look for embedded Huffington Post player
2103 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2104 if mobj is not None:
2105 return self.url_result(mobj.group('url'), 'HuffPost')
2108 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
2109 if mobj is not None:
2110 return self.url_result(mobj.group('url'))
2111 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
2112 if mobj is not None:
2113 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2115 # Look for funnyordie embed
2116 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
2118 return self.playlist_from_matches(
2119 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie
')
2121 # Look for BBC iPlayer embed
2122 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
2124 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk
')
2126 # Look for embedded RUTV player
2127 rutv_url = RUTVIE._extract_url(webpage)
2129 return self.url_result(rutv_url, 'RUTV
')
2131 # Look for embedded TVC player
2132 tvc_url = TVCIE._extract_url(webpage)
2134 return self.url_result(tvc_url, 'TVC
')
2136 # Look for embedded SportBox player
2137 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2139 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed
')
2141 # Look for embedded XHamster player
2142 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2144 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed
')
2146 # Look for embedded TNAFlixNetwork player
2147 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2149 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2151 # Look for embedded PornHub player
2152 pornhub_urls = PornHubIE._extract_urls(webpage)
2154 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2156 # Look for embedded DrTuber player
2157 drtuber_urls = DrTuberIE._extract_urls(webpage)
2159 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2161 # Look for embedded RedTube player
2162 redtube_urls = RedTubeIE._extract_urls(webpage)
2164 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2166 # Look for embedded Tvigle player
2168 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2169 if mobj is not None:
2170 return self.url_result(mobj.group('url'), 'Tvigle')
2172 # Look for embedded TED player
2174 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
2175 if mobj is not None:
2176 return self.url_result(mobj.group('url
'), 'TED
')
2178 # Look for embedded Ustream videos
2179 ustream_url = UstreamIE._extract_url(webpage)
2181 return self.url_result(ustream_url, UstreamIE.ie_key())
2183 # Look for embedded arte.tv player
2185 r'<(?
:script|iframe
) [^
>]*?src
="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2187 if mobj is not None:
2188 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2190 # Look for embedded francetv player
2192 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
://)?embed\
.francetv\
.fr
/\?ue
=.+?
)\
1',
2194 if mobj is not None:
2195 return self.url_result(mobj.group('url
'))
2197 # Look for embedded smotri.com player
2198 smotri_url = SmotriIE._extract_url(webpage)
2200 return self.url_result(smotri_url, 'Smotri
')
2202 # Look for embedded Myvi.ru player
2203 myvi_url = MyviIE._extract_url(webpage)
2205 return self.url_result(myvi_url)
2207 # Look for embedded soundcloud player
2208 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2210 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2212 # Look for tunein player
2213 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2215 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2217 # Look for embedded mtvservices player
2218 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2220 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded
')
2222 # Look for embedded yahoo player
2224 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2226 if mobj is not None:
2227 return self.url_result(mobj.group('url'), 'Yahoo')
2229 # Look for embedded sbs.com.au player
2233 <meta\s+property="og
:video
"\s+content=|
2236 (["\'])(?P
<url
>https?
://(?
:www\
.)?sbs\
.com\
.au
/ondemand
/video
/.+?
)\
1''',
2238 if mobj is not None:
2239 return self.url_result(mobj.group('url'), 'SBS')
2241 # Look for embedded Cinchcast player
2243 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2245 if mobj is not None:
2246 return self.url_result(mobj.group('url'), 'Cinchcast')
2249 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2253 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2255 if mobj is not None:
2256 return self.url_result(mobj.group('url'), 'MLB')
2259 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2261 if mobj is not None:
2262 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2265 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2267 if mobj is not None:
2268 return self.url_result(mobj.group('url'), 'Livestream')
2270 # Look for Zapiks embed
2272 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2273 if mobj is not None:
2274 return self.url_result(mobj.group('url'), 'Zapiks')
2276 # Look for Kaltura embeds
2277 kaltura_url = KalturaIE._extract_url(webpage)
2279 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2281 # Look for Eagle.Platform embeds
2282 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2283 if eagleplatform_url:
2284 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2286 # Look for ClipYou (uses Eagle.Platform) embeds
2288 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2289 if mobj is not None:
2290 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2292 # Look for Pladform embeds
2293 pladform_url = PladformIE._extract_url(webpage)
2295 return self.url_result(pladform_url)
2297 # Look for Videomore embeds
2298 videomore_url = VideomoreIE._extract_url(webpage)
2300 return self.url_result(videomore_url)
2302 # Look for Webcaster embeds
2303 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2305 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2307 # Look for Playwire embeds
2309 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2310 if mobj is not None:
2311 return self.url_result(mobj.group('url'))
2313 # Look for 5min embeds
2315 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2316 if mobj is not None:
2317 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2319 # Look for Crooks and Liars embeds
2321 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2322 if mobj is not None:
2323 return self.url_result(mobj.group('url'))
2325 # Look for NBC Sports VPlayer embeds
2326 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2328 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2330 # Look for NBC News embeds
2331 nbc_news_embed_url = re.search(
2332 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2333 if nbc_news_embed_url:
2334 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2336 # Look for Google Drive embeds
2337 google_drive_url = GoogleDriveIE._extract_url(webpage)
2338 if google_drive_url:
2339 return self.url_result(google_drive_url, 'GoogleDrive')
2341 # Look for UDN embeds
2343 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2344 if mobj is not None:
2345 return self.url_result(
2346 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2348 # Look for Senate ISVP iframe
2349 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2351 return self.url_result(senate_isvp_url, 'SenateISVP')
2353 # Look for Dailymotion Cloud videos
2354 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2356 return self.url_result(dmcloud_url, 'DailymotionCloud')
2358 # Look for OnionStudios embeds
2359 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2360 if onionstudios_url:
2361 return self.url_result(onionstudios_url)
2363 # Look for ViewLift embeds
2364 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2366 return self.url_result(viewlift_url)
2368 # Look for JWPlatform embeds
2369 jwplatform_url = JWPlatformIE._extract_url(webpage)
2371 return self.url_result(jwplatform_url, 'JWPlatform')
2373 # Look for Digiteka embeds
2374 digiteka_url = DigitekaIE._extract_url(webpage)
2376 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2378 # Look for Arkena embeds
2379 arkena_url = ArkenaIE._extract_url(webpage)
2381 return self.url_result(arkena_url, ArkenaIE.ie_key())
2383 # Look for Piksel embeds
2384 piksel_url = PikselIE._extract_url(webpage)
2386 return self.url_result(piksel_url, PikselIE.ie_key())
2388 # Look for Limelight embeds
2389 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2393 'Channel': 'channel',
2394 'ChannelList': 'channel_list',
2396 return self.url_result(smuggle_url('limelight:%s:%s' % (
2397 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2398 'Limelight%s' % mobj.group(1), mobj.group(2))
2402 <object[^
>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2404 name=(["\'])flashVars\
2[^
>]+
2405 value
=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2408 return self.url_result(smuggle_url(
2409 'limelight:media:%s' % mobj.group('id'),
2410 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2412 # Look for AdobeTVVideo embeds
2414 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//video\
.tv\
.adobe\
.com
/v
/\d
+[^
"]+)[\'"]',
2416 if mobj is not None:
2417 return self.url_result(
2418 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2421 # Look for Vine embeds
2423 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2425 if mobj is not None:
2426 return self.url_result(
2427 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2429 # Look for VODPlatform embeds
2431 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?vod
-platform\
.net
/[eE
]mbed
/.+?
)\
1',
2433 if mobj is not None:
2434 return self.url_result(
2435 self._proto_relative_url(unescapeHTML(mobj.group('url
'))), 'VODPlatform
')
2437 # Look for Mangomolo embeds
2439 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2441 video\?.*?\bid=(?P<video_id>\d+)|
2442 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2443 ).+?)\1''', webpage)
2444 if mobj is not None:
2446 '_type
': 'url_transparent
',
2447 'url
': self._proto_relative_url(unescapeHTML(mobj.group('url
'))),
2448 'title
': video_title,
2449 'description
': video_description,
2450 'thumbnail
': video_thumbnail,
2451 'uploader
': video_uploader,
2453 video_id = mobj.group('video_id
')
2456 'ie_key
': 'MangomoloVideo
',
2461 'ie_key
': 'MangomoloLive
',
2462 'id': mobj.group('channel_id
'),
2466 # Look for Instagram embeds
2467 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2468 if instagram_embed_url is not None:
2469 return self.url_result(
2470 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2472 # Look for LiveLeak embeds
2473 liveleak_url = LiveLeakIE._extract_url(webpage)
2475 return self.url_result(liveleak_url, 'LiveLeak
')
2477 # Look for 3Q SDN embeds
2478 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2481 '_type
': 'url_transparent
',
2482 'ie_key
': ThreeQSDNIE.ie_key(),
2483 'url
': self._proto_relative_url(threeqsdn_url),
2484 'title
': video_title,
2485 'description
': video_description,
2486 'thumbnail
': video_thumbnail,
2487 'uploader
': video_uploader,
2490 # Look for VBOX7 embeds
2491 vbox7_url = Vbox7IE._extract_url(webpage)
2493 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2495 # Look for DBTV embeds
2496 dbtv_urls = DBTVIE._extract_urls(webpage)
2498 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2500 # Look for Videa embeds
2501 videa_urls = VideaIE._extract_urls(webpage)
2503 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2505 # Look for 20 minuten embeds
2506 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2508 return self.playlist_from_matches(
2509 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2511 # Look for Openload embeds
2512 openload_urls = OpenloadIE._extract_urls(webpage)
2514 return self.playlist_from_matches(
2515 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2517 # Look for VideoPress embeds
2518 videopress_urls = VideoPressIE._extract_urls(webpage)
2520 return self.playlist_from_matches(
2521 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2523 # Look for Rutube embeds
2524 rutube_urls = RutubeIE._extract_urls(webpage)
2526 return self.playlist_from_matches(
2527 rutube_urls, ie=RutubeIE.ie_key())
2529 # Looking for http://schema.org/VideoObject
2530 json_ld = self._search_json_ld(
2531 webpage, video_id, default={}, expected_type='VideoObject
')
2532 if json_ld.get('url
'):
2534 'title
': video_title or info_dict['title
'],
2535 'description
': video_description,
2536 'thumbnail
': video_thumbnail,
2537 'age_limit
': age_limit
2539 info_dict.update(json_ld)
2542 # Look for HTML5 media
2543 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls
')
2545 for entry in entries:
2548 'title
': video_title,
2550 self._sort_formats(entry['formats
'])
2551 return self.playlist_result(entries)
2553 jwplayer_data_str = self._find_jwplayer_data(webpage)
2554 if jwplayer_data_str:
2556 jwplayer_data = self._parse_json(
2557 jwplayer_data_str, video_id, transform_source=js_to_json)
2558 info = self._parse_jwplayer_data(
2559 jwplayer_data, video_id, require_title=False)
2560 if not info.get('title
'):
2561 info['title
'] = video_title
2563 except ExtractorError:
2566 def check_video(vurl):
2567 if YoutubeIE.suitable(vurl):
2569 if RtmpIE.suitable(vurl):
2571 vpath = compat_urlparse.urlparse(vurl).path
2572 vext = determine_ext(vpath)
2573 return '.' in vpath and vext not in ('swf
', 'png
', 'jpg
', 'srt
', 'sbv
', 'sub
', 'vtt
', 'ttml
', 'js
')
2575 def filter_video(urls):
2576 return list(filter(check_video, urls))
2578 # Start with something easy: JW Player in SWFObject
2579 found = filter_video(re.findall(r'flashvars
: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2581 # Look for gorilla-vid style embedding
2582 found = filter_video(re.findall(r'''(?sx)
2586 jwplayer\s*\(\s*["'][^
'"]+["']\s
*\
)\s
*\
.setup
2589 ['"]?file['"]?\s*:\s*["\'](.*?
)["\']''', webpage))
2591 # Broaden the search a little bit
2592 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2594 # Broaden the findall a little bit: JWPlayer JS loader
2595 found = filter_video(re.findall(
2596 r'[^A
-Za
-z0
-9]?
(?
:file|video_url
)["\']?:\s*["\'](http(?
![^
\'"]+\.[0-9]+[\'"])[^
\'"]+)["\']', webpage))
2599 found = filter_video(re.findall(r'''(?xs)
2600 flowplayer\("[^"]+",\s*
2602 \s*\{[^}]+? ["']?clip
["']?\s*:\s*\{\s*
2603 ["']?url["']?\s
*:\s
*["']([^"']+)["']
2608 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2610 # Try to find twitter cards info
2611 # twitter:player:stream should be checked before twitter:player since
2612 # it is expected to contain a raw stream (see
2613 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2614 found = filter_video(re.findall(
2615 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2617 # We look for Open Graph info:
2618 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2619 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2620 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2621 if m_video_type is not None:
2622 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2624 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2626 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2627 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2630 # Look also in Refresh HTTP header
2631 refresh_header = head_response.headers.get('Refresh')
2633 # In python 2 response HTTP headers are bytestrings
2634 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2635 refresh_header = refresh_header.decode('iso-8859-1')
2636 found = re.search(REDIRECT_REGEX, refresh_header)
2638 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2640 self.report_following_redirect(new_url)
2649 # twitter:player is a https URL to iframe player that may or may not
2650 # be supported by youtube-dl thus this is checked the very last (see
2651 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2652 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2654 return self.url_result(embed_url)
2657 raise UnsupportedError(url)
2660 for video_url in orderedSet(found):
2661 video_url = unescapeHTML(video_url)
2662 video_url = video_url.replace('\\/', '/')
2663 video_url = compat_urlparse.urljoin(url, video_url)
2664 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2666 # Sometimes, jwplayer extraction will result in a YouTube URL
2667 if YoutubeIE.suitable(video_url):
2668 entries.append(self.url_result(video_url, 'Youtube'))
2671 # here's a fun little line of code for you:
2672 video_id = os.path.splitext(video_id)[0]
2676 'uploader': video_uploader,
2677 'title': video_title,
2678 'age_limit': age_limit,
2681 if RtmpIE.suitable(video_url):
2682 entry_info_dict.update({
2683 '_type': 'url_transparent',
2684 'ie_key': RtmpIE.ie_key(),
2687 entries.append(entry_info_dict)
2690 ext = determine_ext(video_url)
2692 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2694 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2696 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2698 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2700 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2701 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2702 # Just matching .ism/manifest is not enough to be reliably sure
2703 # whether it's actually an ISM manifest or some other streaming
2704 # manifest since there are various streaming URL formats
2705 # possible (see [1]) as well as some other shenanigans like
2706 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2708 # Thus the most reasonable way to solve this is to delegate
2709 # to generic extractor in order to look into the contents of
2710 # the manifest itself.
2711 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2712 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2713 entry_info_dict = self.url_result(
2714 smuggle_url(video_url, {'to_generic': True}),
2717 entry_info_dict['url'] = video_url
2719 if entry_info_dict.get('formats'):
2720 self._sort_formats(entry_info_dict['formats'])
2722 entries.append(entry_info_dict)
2724 if len(entries) == 1:
2727 for num, e in enumerate(entries, start=1):
2728 # 'url' results don't have a title
2729 if e.get('title') is not None:
2730 e['title'] = '%s (%d)' % (e['title'], num)
2732 '_type': 'playlist',