]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
projects / yt-dlp.git / blob
? search:
summary | shortlog | log | commit | commitdiff | tree
blame | history | raw | HEAD
[extractor/generic] Use _extract_url for kaltura embeds (Closes #9922)
[yt-dlp.git] / youtube_dl / extractor / generic.py
1 # encoding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 orderedSet,
24 sanitized_Request,
25 smuggle_url,
26 unescapeHTML,
27 unified_strdate,
28 unsmuggle_url,
29 UnsupportedError,
30 url_basename,
31 xpath_text,
32 )
33 from .brightcove import (
34 BrightcoveLegacyIE,
35 BrightcoveNewIE,
36 )
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .viewlift import ViewLiftEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
64 from .threeqsdn import ThreeQSDNIE
65 from .theplatform import ThePlatformIE
66 from .vessel import VesselIE
67 from .kaltura import KalturaIE
68
69
70 class GenericIE(InfoExtractor):
71 IE_DESC = 'Generic downloader that works on some sites'
72 _VALID_URL = r'.*'
73 IE_NAME = 'generic'
74 _TESTS = [
75 # Direct link to a video
76 {
77 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
78 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
79 'info_dict': {
80 'id': 'trailer',
81 'ext': 'mp4',
82 'title': 'trailer',
83 'upload_date': '20100513',
84 }
85 },
86 # Direct link to media delivered compressed (until Accept-Encoding is *)
87 {
88 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
89 'md5': '128c42e68b13950268b648275386fc74',
90 'info_dict': {
91 'id': 'FictionJunction-Parallel_Hearts',
92 'ext': 'flac',
93 'title': 'FictionJunction-Parallel_Hearts',
94 'upload_date': '20140522',
95 },
96 'expected_warnings': [
97 'URL could be a direct video link, returning it as such.'
98 ]
99 },
100 # Direct download with broken HEAD
101 {
102 'url': 'http://ai-radio.org:8000/radio.opus',
103 'info_dict': {
104 'id': 'radio',
105 'ext': 'opus',
106 'title': 'radio',
107 },
108 'params': {
109 'skip_download': True, # infinite live stream
110 },
111 'expected_warnings': [
112 r'501.*Not Implemented',
113 r'400.*Bad Request',
114 ],
115 },
116 # Direct link with incorrect MIME type
117 {
118 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
119 'md5': '4ccbebe5f36706d85221f204d7eb5913',
120 'info_dict': {
121 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
122 'id': '5_Lennart_Poettering_-_Systemd',
123 'ext': 'webm',
124 'title': '5_Lennart_Poettering_-_Systemd',
125 'upload_date': '20141120',
126 },
127 'expected_warnings': [
128 'URL could be a direct video link, returning it as such.'
129 ]
130 },
131 # RSS feed
132 {
133 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
134 'info_dict': {
135 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
136 'title': 'Zero Punctuation',
137 'description': 're:.*groundbreaking video review series.*'
138 },
139 'playlist_mincount': 11,
140 },
141 # RSS feed with enclosure
142 {
143 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
144 'info_dict': {
145 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
146 'ext': 'm4v',
147 'upload_date': '20150228',
148 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
149 }
150 },
151 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
152 {
153 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
154 'info_dict': {
155 'id': 'smil',
156 'ext': 'mp4',
157 'title': 'Automatics, robotics and biocybernetics',
158 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
159 'upload_date': '20130627',
160 'formats': 'mincount:16',
161 'subtitles': 'mincount:1',
162 },
163 'params': {
164 'force_generic_extractor': True,
165 'skip_download': True,
166 },
167 },
168 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
169 {
170 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
171 'info_dict': {
172 'id': 'hds',
173 'ext': 'flv',
174 'title': 'hds',
175 'formats': 'mincount:1',
176 },
177 'params': {
178 'skip_download': True,
179 },
180 },
181 # SMIL from https://www.restudy.dk/video/play/id/1637
182 {
183 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
184 'info_dict': {
185 'id': 'video_1637',
186 'ext': 'flv',
187 'title': 'video_1637',
188 'formats': 'mincount:3',
189 },
190 'params': {
191 'skip_download': True,
192 },
193 },
194 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
195 {
196 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
197 'info_dict': {
198 'id': 'smil-service',
199 'ext': 'flv',
200 'title': 'smil-service',
201 'formats': 'mincount:1',
202 },
203 'params': {
204 'skip_download': True,
205 },
206 },
207 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
208 {
209 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
210 'info_dict': {
211 'id': '4719370',
212 'ext': 'mp4',
213 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
214 'formats': 'mincount:3',
215 },
216 'params': {
217 'skip_download': True,
218 },
219 },
220 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
221 {
222 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
223 'info_dict': {
224 'id': 'mZlp2ctYIUEB',
225 'ext': 'mp4',
226 'title': 'Tikibad ontruimd wegens brand',
227 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
228 'thumbnail': 're:^https?://.*\.jpg$',
229 'duration': 33,
230 },
231 'params': {
232 'skip_download': True,
233 },
234 },
235 # MPD from http://dash-mse-test.appspot.com/media.html
236 {
237 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
238 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
239 'info_dict': {
240 'id': 'car-20120827-manifest',
241 'ext': 'mp4',
242 'title': 'car-20120827-manifest',
243 'formats': 'mincount:9',
244 'upload_date': '20130904',
245 },
246 'params': {
247 'format': 'bestvideo',
248 },
249 },
250 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
251 {
252 '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',
253 'info_dict': {
254 'id': 'content',
255 'ext': 'mp4',
256 'title': 'content',
257 'formats': 'mincount:8',
258 },
259 'params': {
260 # m3u8 downloads
261 'skip_download': True,
262 }
263 },
264 # m3u8 served with Content-Type: text/plain
265 {
266 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
267 'info_dict': {
268 'id': 'index',
269 'ext': 'mp4',
270 'title': 'index',
271 'upload_date': '20140720',
272 'formats': 'mincount:11',
273 },
274 'params': {
275 # m3u8 downloads
276 'skip_download': True,
277 }
278 },
279 # google redirect
280 {
281 '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',
282 'info_dict': {
283 'id': 'cmQHVoWB5FY',
284 'ext': 'mp4',
285 'upload_date': '20130224',
286 'uploader_id': 'TheVerge',
287 'description': 're:^Chris Ziegler takes a look at the\.*',
288 'uploader': 'The Verge',
289 'title': 'First Firefox OS phones side-by-side',
290 },
291 'params': {
292 'skip_download': False,
293 }
294 },
295 {
296 # redirect in Refresh HTTP header
297 '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',
298 'info_dict': {
299 'id': 'pO8h3EaFRdo',
300 'ext': 'mp4',
301 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
302 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
303 'upload_date': '20150917',
304 'uploader_id': 'brtvofficial',
305 'uploader': 'Boiler Room',
306 },
307 'params': {
308 'skip_download': False,
309 },
310 },
311 {
312 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
313 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
314 'info_dict': {
315 'id': '13601338388002',
316 'ext': 'mp4',
317 'uploader': 'www.hodiho.fr',
318 'title': 'R\u00e9gis plante sa Jeep',
319 }
320 },
321 # bandcamp page with custom domain
322 {
323 'add_ie': ['Bandcamp'],
324 'url': 'http://bronyrock.com/track/the-pony-mash',
325 'info_dict': {
326 'id': '3235767654',
327 'ext': 'mp3',
328 'title': 'The Pony Mash',
329 'uploader': 'M_Pallante',
330 },
331 'skip': 'There is a limit of 200 free downloads / month for the test song',
332 },
333 # embedded brightcove video
334 # it also tests brightcove videos that need to set the 'Referer' in the
335 # http requests
336 {
337 'add_ie': ['BrightcoveLegacy'],
338 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
339 'info_dict': {
340 'id': '2765128793001',
341 'ext': 'mp4',
342 'title': 'Le cours de bourse : l’analyse technique',
343 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
344 'uploader': 'BFM BUSINESS',
345 },
346 'params': {
347 'skip_download': True,
348 },
349 },
350 {
351 # https://github.com/rg3/youtube-dl/issues/2253
352 'url': 'http://bcove.me/i6nfkrc3',
353 'md5': '0ba9446db037002366bab3b3eb30c88c',
354 'info_dict': {
355 'id': '3101154703001',
356 'ext': 'mp4',
357 'title': 'Still no power',
358 'uploader': 'thestar.com',
359 '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.',
360 },
361 'add_ie': ['BrightcoveLegacy'],
362 },
363 {
364 'url': 'http://www.championat.com/video/football/v/87/87499.html',
365 'md5': 'fb973ecf6e4a78a67453647444222983',
366 'info_dict': {
367 'id': '3414141473001',
368 'ext': 'mp4',
369 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
370 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
371 'uploader': 'Championat',
372 },
373 },
374 {
375 # https://github.com/rg3/youtube-dl/issues/3541
376 'add_ie': ['BrightcoveLegacy'],
377 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
378 'info_dict': {
379 'id': '3866516442001',
380 'ext': 'mp4',
381 'title': 'Leer mij vrouwen kennen: Aflevering 1',
382 'description': 'Leer mij vrouwen kennen: Aflevering 1',
383 'uploader': 'SBS Broadcasting',
384 },
385 'skip': 'Restricted to Netherlands',
386 'params': {
387 'skip_download': True, # m3u8 download
388 },
389 },
390 # ooyala video
391 {
392 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
393 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
394 'info_dict': {
395 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
396 'ext': 'mp4',
397 'title': '2cc213299525360.mov', # that's what we get
398 'duration': 238.231,
399 },
400 'add_ie': ['Ooyala'],
401 },
402 {
403 # ooyala video embedded with http://player.ooyala.com/iframe.js
404 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
405 'info_dict': {
406 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
407 'ext': 'mp4',
408 'title': '"Steve Jobs: Man in the Machine" trailer',
409 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
410 'duration': 135.427,
411 },
412 'params': {
413 'skip_download': True,
414 },
415 },
416 # embed.ly video
417 {
418 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
419 'info_dict': {
420 'id': '9ODmcdjQcHQ',
421 'ext': 'mp4',
422 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
423 'upload_date': '20140225',
424 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
425 'uploader': 'Tested',
426 'uploader_id': 'testedcom',
427 },
428 # No need to test YoutubeIE here
429 'params': {
430 'skip_download': True,
431 },
432 },
433 # funnyordie embed
434 {
435 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
436 'info_dict': {
437 'id': '18e820ec3f',
438 'ext': 'mp4',
439 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
440 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
441 },
442 },
443 # RUTV embed
444 {
445 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
446 'info_dict': {
447 'id': '776940',
448 'ext': 'mp4',
449 'title': 'Охотское море стало целиком российским',
450 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
451 },
452 'params': {
453 # m3u8 download
454 'skip_download': True,
455 },
456 },
457 # TVC embed
458 {
459 '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/',
460 'info_dict': {
461 'id': '55304',
462 'ext': 'mp4',
463 'title': 'Дошкольное воспитание',
464 },
465 },
466 # SportBox embed
467 {
468 'url': 'http://www.vestifinance.ru/articles/25753',
469 'info_dict': {
470 'id': '25753',
471 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
472 },
473 'playlist': [{
474 'info_dict': {
475 'id': '370908',
476 'title': 'Госзаказ. День 3',
477 'ext': 'mp4',
478 }
479 }, {
480 'info_dict': {
481 'id': '370905',
482 'title': 'Госзаказ. День 2',
483 'ext': 'mp4',
484 }
485 }, {
486 'info_dict': {
487 'id': '370902',
488 'title': 'Госзаказ. День 1',
489 'ext': 'mp4',
490 }
491 }],
492 'params': {
493 # m3u8 download
494 'skip_download': True,
495 },
496 },
497 # Myvi.ru embed
498 {
499 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
500 'info_dict': {
501 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
502 'ext': 'mp4',
503 'title': 'Ужастики, русский трейлер (2015)',
504 'thumbnail': 're:^https?://.*\.jpg$',
505 'duration': 153,
506 }
507 },
508 # XHamster embed
509 {
510 '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',
511 'info_dict': {
512 'id': 'showthread',
513 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
514 },
515 'playlist_mincount': 7,
516 },
517 # Embedded TED video
518 {
519 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
520 'md5': '65fdff94098e4a607385a60c5177c638',
521 'info_dict': {
522 'id': '1969',
523 'ext': 'mp4',
524 'title': 'Hidden miracles of the natural world',
525 'uploader': 'Louie Schwartzberg',
526 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
527 }
528 },
529 # Embedded Ustream video
530 {
531 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
532 'md5': '27b99cdb639c9b12a79bca876a073417',
533 'info_dict': {
534 'id': '45734260',
535 'ext': 'flv',
536 'uploader': 'AU SPA: The NSA and Privacy',
537 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
538 }
539 },
540 # nowvideo embed hidden behind percent encoding
541 {
542 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
543 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
544 'info_dict': {
545 'id': '06e53103ca9aa',
546 'ext': 'flv',
547 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
548 'description': 'No description',
549 },
550 },
551 # arte embed
552 {
553 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
554 'md5': '7653032cbb25bf6c80d80f217055fa43',
555 'info_dict': {
556 'id': '048195-004_PLUS7-F',
557 'ext': 'flv',
558 'title': 'X:enius',
559 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
560 'upload_date': '20140320',
561 },
562 'params': {
563 'skip_download': 'Requires rtmpdump'
564 }
565 },
566 # francetv embed
567 {
568 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
569 'info_dict': {
570 'id': 'EV_30231',
571 'ext': 'mp4',
572 'title': 'Alcaline, le concert avec Calogero',
573 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
574 'upload_date': '20150226',
575 'timestamp': 1424989860,
576 'duration': 5400,
577 },
578 'params': {
579 # m3u8 downloads
580 'skip_download': True,
581 },
582 'expected_warnings': [
583 'Forbidden'
584 ]
585 },
586 # Condé Nast embed
587 {
588 'url': 'http://www.wired.com/2014/04/honda-asimo/',
589 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
590 'info_dict': {
591 'id': '53501be369702d3275860000',
592 'ext': 'mp4',
593 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
594 }
595 },
596 # Dailymotion embed
597 {
598 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
599 'md5': '441aeeb82eb72c422c7f14ec533999cd',
600 'info_dict': {
601 'id': 'k2mm4bCdJ6CQ2i7c8o2',
602 'ext': 'mp4',
603 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
604 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
605 'uploader': 'Spi0n',
606 'uploader_id': 'xgditw',
607 'upload_date': '20140425',
608 'timestamp': 1398441542,
609 },
610 'add_ie': ['Dailymotion'],
611 },
612 # YouTube embed
613 {
614 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
615 'info_dict': {
616 'id': 'FXRb4ykk4S0',
617 'ext': 'mp4',
618 'title': 'The NBL Auction 2014',
619 'uploader': 'BADMINTON England',
620 'uploader_id': 'BADMINTONEvents',
621 'upload_date': '20140603',
622 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
623 },
624 'add_ie': ['Youtube'],
625 'params': {
626 'skip_download': True,
627 }
628 },
629 # MTVSercices embed
630 {
631 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
632 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
633 'info_dict': {
634 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
635 'ext': 'mp4',
636 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
637 'description': 'Two valets share their love for movie star Liam Neesons.',
638 },
639 },
640 # YouTube embed via <data-embed-url="">
641 {
642 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
643 'info_dict': {
644 'id': '4vAffPZIT44',
645 'ext': 'mp4',
646 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
647 'uploader': 'Gameloft',
648 'uploader_id': 'gameloft',
649 'upload_date': '20140828',
650 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
651 },
652 'params': {
653 'skip_download': True,
654 }
655 },
656 # Camtasia studio
657 {
658 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
659 'playlist': [{
660 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
661 'info_dict': {
662 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
663 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
664 'ext': 'flv',
665 'duration': 2235.90,
666 }
667 }, {
668 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
669 'info_dict': {
670 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
671 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
672 'ext': 'flv',
673 'duration': 2235.93,
674 }
675 }],
676 'info_dict': {
677 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
678 }
679 },
680 # Flowplayer
681 {
682 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
683 'md5': '9d65602bf31c6e20014319c7d07fba27',
684 'info_dict': {
685 'id': '5123ea6d5e5a7',
686 'ext': 'mp4',
687 'age_limit': 18,
688 'uploader': 'www.handjobhub.com',
689 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
690 }
691 },
692 # Multiple brightcove videos
693 # https://github.com/rg3/youtube-dl/issues/2283
694 {
695 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
696 'info_dict': {
697 'id': 'always-never',
698 'title': 'Always / Never - The New Yorker',
699 },
700 'playlist_count': 3,
701 'params': {
702 'extract_flat': False,
703 'skip_download': True,
704 }
705 },
706 # MLB embed
707 {
708 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
709 'md5': '96f09a37e44da40dd083e12d9a683327',
710 'info_dict': {
711 'id': '33322633',
712 'ext': 'mp4',
713 'title': 'Ump changes call to ball',
714 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
715 'duration': 48,
716 'timestamp': 1401537900,
717 'upload_date': '20140531',
718 'thumbnail': 're:^https?://.*\.jpg$',
719 },
720 },
721 # Wistia embed
722 {
723 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
724 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
725 'info_dict': {
726 'id': '6e2wtrbdaf',
727 'ext': 'mov',
728 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
729 'description': 'a Paywall Videos video from Remilon',
730 'duration': 644.072,
731 'uploader': 'study.com',
732 'timestamp': 1459678540,
733 'upload_date': '20160403',
734 'filesize': 24687186,
735 },
736 },
737 {
738 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
739 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
740 'info_dict': {
741 'id': 'uxjb0lwrcz',
742 'ext': 'mp4',
743 'title': 'Conversation about Hexagonal Rails Part 1',
744 'description': 'a Martin Fowler video from ThoughtWorks',
745 'duration': 1715.0,
746 'uploader': 'thoughtworks.wistia.com',
747 'timestamp': 1401832161,
748 'upload_date': '20140603',
749 },
750 },
751 # Wistia standard embed (async)
752 {
753 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
754 'info_dict': {
755 'id': '807fafadvk',
756 'ext': 'mp4',
757 'title': 'Drip Brennan Dunn Workshop',
758 'description': 'a JV Webinars video from getdrip-1',
759 'duration': 4986.95,
760 'timestamp': 1463607249,
761 'upload_date': '20160518',
762 },
763 'params': {
764 'skip_download': True,
765 }
766 },
767 # Soundcloud embed
768 {
769 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
770 'info_dict': {
771 'id': '174391317',
772 'ext': 'mp3',
773 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
774 'uploader': 'Sophos Security',
775 'title': 'Chet Chat 171 - Oct 29, 2014',
776 'upload_date': '20141029',
777 }
778 },
779 # Livestream embed
780 {
781 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
782 'info_dict': {
783 'id': '67864563',
784 'ext': 'flv',
785 'upload_date': '20141112',
786 'title': 'Rosetta #CometLanding webcast HL 10',
787 }
788 },
789 # Another Livestream embed, without 'new.' in URL
790 {
791 'url': 'https://www.freespeech.org/',
792 'info_dict': {
793 'id': '123537347',
794 'ext': 'mp4',
795 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
796 },
797 'params': {
798 # Live stream
799 'skip_download': True,
800 },
801 },
802 # LazyYT
803 {
804 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
805 'info_dict': {
806 'id': '1986',
807 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
808 },
809 'playlist_mincount': 2,
810 },
811 # Cinchcast embed
812 {
813 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
814 'info_dict': {
815 'id': '7141703',
816 'ext': 'mp3',
817 'upload_date': '20141126',
818 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
819 }
820 },
821 # Cinerama player
822 {
823 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
824 'info_dict': {
825 'id': '730m_DandD_1901_512k',
826 'ext': 'mp4',
827 'uploader': 'www.abc.net.au',
828 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
829 }
830 },
831 # embedded viddler video
832 {
833 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
834 'info_dict': {
835 'id': '4d03aad9',
836 'ext': 'mp4',
837 'uploader': 'deadspin',
838 'title': 'WALL-TO-GORTAT',
839 'timestamp': 1422285291,
840 'upload_date': '20150126',
841 },
842 'add_ie': ['Viddler'],
843 },
844 # Libsyn embed
845 {
846 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
847 'info_dict': {
848 'id': '3377616',
849 'ext': 'mp3',
850 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
851 'description': 'md5:601cb790edd05908957dae8aaa866465',
852 'upload_date': '20150220',
853 },
854 },
855 # jwplayer YouTube
856 {
857 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
858 'info_dict': {
859 'id': 'Mrj4DVp2zeA',
860 'ext': 'mp4',
861 'upload_date': '20150212',
862 'uploader': 'The National Archives UK',
863 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
864 'uploader_id': 'NationalArchives08',
865 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
866 },
867 },
868 # rtl.nl embed
869 {
870 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
871 'playlist_mincount': 5,
872 'info_dict': {
873 'id': 'aanslagen-kopenhagen',
874 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
875 }
876 },
877 # Zapiks embed
878 {
879 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
880 'info_dict': {
881 'id': '118046',
882 'ext': 'mp4',
883 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
884 }
885 },
886 # Kaltura embed (different embed code)
887 {
888 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
889 'info_dict': {
890 'id': '1_a52wc67y',
891 'ext': 'flv',
892 'upload_date': '20150127',
893 'uploader_id': 'PremierMedia',
894 'timestamp': int,
895 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
896 },
897 },
898 # Kaltura embed protected with referrer
899 {
900 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
901 'info_dict': {
902 'id': '1_g4fbemnq',
903 'ext': 'mp4',
904 'title': 'Violetta - Achter De Schermen - Ruggero',
905 'description': 'Achter de schermen met Ruggero',
906 'timestamp': 1435133761,
907 'upload_date': '20150624',
908 'uploader_id': 'echojecka',
909 },
910 },
911 # Kaltura embed with single quotes
912 {
913 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
914 'info_dict': {
915 'id': '0_izeg5utt',
916 'ext': 'mp4',
917 'title': '35871',
918 'timestamp': 1355743100,
919 'upload_date': '20121217',
920 'uploader_id': 'batchUser',
921 },
922 'add_ie': ['Kaltura'],
923 },
924 {
925 # Kaltura embedded via quoted entry_id
926 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
927 'info_dict': {
928 'id': '0_utuok90b',
929 'ext': 'mp4',
930 'title': '06_matthew_brender_raj_dutt',
931 'timestamp': 1466638791,
932 'upload_date': '20160622',
933 },
934 'add_ie': ['Kaltura'],
935 'expected_warnings': [
936 'Could not send HEAD request'
937 ],
938 'params': {
939 'skip_download': True,
940 }
941 },
942 # Eagle.Platform embed (generic URL)
943 {
944 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
945 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
946 'info_dict': {
947 'id': '227304',
948 'ext': 'mp4',
949 'title': 'Навальный вышел на свободу',
950 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
951 'thumbnail': 're:^https?://.*\.jpg$',
952 'duration': 87,
953 'view_count': int,
954 'age_limit': 0,
955 },
956 },
957 # ClipYou (Eagle.Platform) embed (custom URL)
958 {
959 'url': 'http://muz-tv.ru/play/7129/',
960 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
961 'info_dict': {
962 'id': '12820',
963 'ext': 'mp4',
964 'title': "'O Sole Mio",
965 'thumbnail': 're:^https?://.*\.jpg$',
966 'duration': 216,
967 'view_count': int,
968 },
969 },
970 # Pladform embed
971 {
972 'url': 'http://muz-tv.ru/kinozal/view/7400/',
973 'info_dict': {
974 'id': '100183293',
975 'ext': 'mp4',
976 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
977 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
978 'thumbnail': 're:^https?://.*\.jpg$',
979 'duration': 694,
980 'age_limit': 0,
981 },
982 },
983 # Playwire embed
984 {
985 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
986 'info_dict': {
987 'id': '3519514',
988 'ext': 'mp4',
989 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
990 'thumbnail': 're:^https?://.*\.png$',
991 'duration': 45.115,
992 },
993 },
994 # 5min embed
995 {
996 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
997 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
998 'info_dict': {
999 'id': '518726732',
1000 'ext': 'mp4',
1001 'title': 'Facebook Creates "On This Day" | Crunch Report',
1002 },
1003 },
1004 # SVT embed
1005 {
1006 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1007 'info_dict': {
1008 'id': '2900353',
1009 'ext': 'flv',
1010 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1011 'duration': 27,
1012 'age_limit': 0,
1013 },
1014 },
1015 # Crooks and Liars embed
1016 {
1017 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1018 'info_dict': {
1019 'id': '8RUoRhRi',
1020 'ext': 'mp4',
1021 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1022 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1023 'timestamp': 1428207000,
1024 'upload_date': '20150405',
1025 'uploader': 'Heather',
1026 },
1027 },
1028 # Crooks and Liars external embed
1029 {
1030 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1031 'info_dict': {
1032 'id': 'MTE3MjUtMzQ2MzA',
1033 'ext': 'mp4',
1034 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1035 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1036 'timestamp': 1265032391,
1037 'upload_date': '20100201',
1038 'uploader': 'Heather',
1039 },
1040 },
1041 # NBC Sports vplayer embed
1042 {
1043 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1044 'info_dict': {
1045 'id': 'ln7x1qSThw4k',
1046 'ext': 'flv',
1047 'title': "PFT Live: New leader in the 'new-look' defense",
1048 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1049 'uploader': 'NBCU-SPORTS',
1050 'upload_date': '20140107',
1051 'timestamp': 1389118457,
1052 },
1053 },
1054 # NBC News embed
1055 {
1056 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1057 'md5': '1aa589c675898ae6d37a17913cf68d66',
1058 'info_dict': {
1059 'id': '701714499682',
1060 'ext': 'mp4',
1061 'title': 'PREVIEW: On Assignment: David Letterman',
1062 '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.',
1063 },
1064 },
1065 # UDN embed
1066 {
1067 'url': 'https://video.udn.com/news/300346',
1068 'md5': 'fd2060e988c326991037b9aff9df21a6',
1069 'info_dict': {
1070 'id': '300346',
1071 'ext': 'mp4',
1072 'title': '中一中男師變性 全校師生力挺',
1073 'thumbnail': 're:^https?://.*\.jpg$',
1074 },
1075 'params': {
1076 # m3u8 download
1077 'skip_download': True,
1078 },
1079 },
1080 # Ooyala embed
1081 {
1082 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1083 'info_dict': {
1084 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1085 'ext': 'mp4',
1086 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1087 'title': 'This is what separates the Excel masters from the wannabes',
1088 'duration': 191.933,
1089 },
1090 'params': {
1091 # m3u8 downloads
1092 'skip_download': True,
1093 }
1094 },
1095 # Brightcove URL in single quotes
1096 {
1097 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1098 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1099 'info_dict': {
1100 'id': '4255764656001',
1101 'ext': 'mp4',
1102 'title': 'SN Presents: Russell Martin, World Citizen',
1103 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1104 'uploader': 'Rogers Sportsnet',
1105 'uploader_id': '1704050871',
1106 'upload_date': '20150525',
1107 'timestamp': 1432570283,
1108 },
1109 },
1110 # Dailymotion Cloud video
1111 {
1112 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1113 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1114 'info_dict': {
1115 'id': 'x2uy8t3',
1116 'ext': 'mp4',
1117 'title': 'Sauvons les abeilles ! - Le débat',
1118 'description': 'md5:d9082128b1c5277987825d684939ca26',
1119 'thumbnail': 're:^https?://.*\.jpe?g$',
1120 'timestamp': 1434970506,
1121 'upload_date': '20150622',
1122 'uploader': 'Public Sénat',
1123 'uploader_id': 'xa9gza',
1124 }
1125 },
1126 # OnionStudios embed
1127 {
1128 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1129 'info_dict': {
1130 'id': '2855',
1131 'ext': 'mp4',
1132 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1133 'thumbnail': 're:^https?://.*\.jpe?g$',
1134 'uploader': 'ClickHole',
1135 'uploader_id': 'clickhole',
1136 }
1137 },
1138 # SnagFilms embed
1139 {
1140 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1141 'info_dict': {
1142 'id': '74849a00-85a9-11e1-9660-123139220831',
1143 'ext': 'mp4',
1144 'title': '#whilewewatch',
1145 }
1146 },
1147 # AdobeTVVideo embed
1148 {
1149 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1150 'md5': '43662b577c018ad707a63766462b1e87',
1151 'info_dict': {
1152 'id': '2456',
1153 'ext': 'mp4',
1154 'title': 'New experience with Acrobat DC',
1155 'description': 'New experience with Acrobat DC',
1156 'duration': 248.667,
1157 },
1158 },
1159 # ScreenwaveMedia embed
1160 {
1161 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1162 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1163 'info_dict': {
1164 'id': 'cinemasnob-55d26273809dd',
1165 'ext': 'mp4',
1166 'title': 'cinemasnob',
1167 },
1168 },
1169 # BrightcoveInPageEmbed embed
1170 {
1171 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1172 'info_dict': {
1173 'id': '4238694884001',
1174 'ext': 'flv',
1175 'title': 'Tabletop: Dread, Last Thoughts',
1176 'description': 'Tabletop: Dread, Last Thoughts',
1177 'duration': 51690,
1178 },
1179 },
1180 # JWPlayer with M3U8
1181 {
1182 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1183 'info_dict': {
1184 'id': 'playlist',
1185 'ext': 'mp4',
1186 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1187 'uploader': 'ren.tv',
1188 },
1189 'params': {
1190 # m3u8 downloads
1191 'skip_download': True,
1192 }
1193 },
1194 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1195 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1196 {
1197 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1198 'info_dict': {
1199 'id': '4785848093001',
1200 'ext': 'mp4',
1201 'title': 'The Cardinal Pell Interview',
1202 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1203 'uploader': 'GlobeCast Australia - GlobeStream',
1204 'uploader_id': '2733773828001',
1205 'upload_date': '20160304',
1206 'timestamp': 1457083087,
1207 },
1208 'params': {
1209 # m3u8 downloads
1210 'skip_download': True,
1211 },
1212 },
1213 # Another form of arte.tv embed
1214 {
1215 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1216 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1217 'info_dict': {
1218 'id': '030273-562_PLUS7-F',
1219 'ext': 'mp4',
1220 'title': 'ARTE Reportage - Nulle part, en France',
1221 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1222 'upload_date': '20160409',
1223 },
1224 },
1225 # LiveLeak embed
1226 {
1227 'url': 'http://www.wykop.pl/link/3088787/',
1228 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1229 'info_dict': {
1230 'id': '874_1459135191',
1231 'ext': 'mp4',
1232 'title': 'Man shows poor quality of new apartment building',
1233 'description': 'The wall is like a sand pile.',
1234 'uploader': 'Lake8737',
1235 }
1236 },
1237 # Duplicated embedded video URLs
1238 {
1239 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1240 'info_dict': {
1241 'id': '149298443_480_16c25b74_2',
1242 'ext': 'mp4',
1243 'title': 'vs. Blue Orange Spring Game',
1244 'uploader': 'www.hudl.com',
1245 },
1246 },
1247 ]
1248
1249 def report_following_redirect(self, new_url):
1250 """Report information extraction."""
1251 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1252
1253 def _extract_rss(self, url, video_id, doc):
1254 playlist_title = doc.find('./channel/title').text
1255 playlist_desc_el = doc.find('./channel/description')
1256 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1257
1258 entries = []
1259 for it in doc.findall('./channel/item'):
1260 next_url = xpath_text(it, 'link', fatal=False)
1261 if not next_url:
1262 enclosure_nodes = it.findall('./enclosure')
1263 for e in enclosure_nodes:
1264 next_url = e.attrib.get('url')
1265 if next_url:
1266 break
1267
1268 if not next_url:
1269 continue
1270
1271 entries.append({
1272 '_type': 'url',
1273 'url': next_url,
1274 'title': it.find('title').text,
1275 })
1276
1277 return {
1278 '_type': 'playlist',
1279 'id': url,
1280 'title': playlist_title,
1281 'description': playlist_desc,
1282 'entries': entries,
1283 }
1284
1285 def _extract_camtasia(self, url, video_id, webpage):
1286 """ Returns None if no camtasia video can be found. """
1287
1288 camtasia_cfg = self._search_regex(
1289 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1290 webpage, 'camtasia configuration file', default=None)
1291 if camtasia_cfg is None:
1292 return None
1293
1294 title = self._html_search_meta('DC.title', webpage, fatal=True)
1295
1296 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1297 camtasia_cfg = self._download_xml(
1298 camtasia_url, video_id,
1299 note='Downloading camtasia configuration',
1300 errnote='Failed to download camtasia configuration')
1301 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1302
1303 entries = []
1304 for n in fileset_node.getchildren():
1305 url_n = n.find('./uri')
1306 if url_n is None:
1307 continue
1308
1309 entries.append({
1310 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1311 'title': '%s - %s' % (title, n.tag),
1312 'url': compat_urlparse.urljoin(url, url_n.text),
1313 'duration': float_or_none(n.find('./duration').text),
1314 })
1315
1316 return {
1317 '_type': 'playlist',
1318 'entries': entries,
1319 'title': title,
1320 }
1321
1322 def _real_extract(self, url):
1323 if url.startswith('//'):
1324 return {
1325 '_type': 'url',
1326 'url': self.http_scheme() + url,
1327 }
1328
1329 parsed_url = compat_urlparse.urlparse(url)
1330 if not parsed_url.scheme:
1331 default_search = self._downloader.params.get('default_search')
1332 if default_search is None:
1333 default_search = 'fixup_error'
1334
1335 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1336 if '/' in url:
1337 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1338 return self.url_result('http://' + url)
1339 elif default_search != 'fixup_error':
1340 if default_search == 'auto_warning':
1341 if re.match(r'^(?:url|URL)$', url):
1342 raise ExtractorError(
1343 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1344 expected=True)
1345 else:
1346 self._downloader.report_warning(
1347 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1348 return self.url_result('ytsearch:' + url)
1349
1350 if default_search in ('error', 'fixup_error'):
1351 raise ExtractorError(
1352 '%r is not a valid URL. '
1353 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1354 % (url, url), expected=True)
1355 else:
1356 if ':' not in default_search:
1357 default_search += ':'
1358 return self.url_result(default_search + url)
1359
1360 url, smuggled_data = unsmuggle_url(url)
1361 force_videoid = None
1362 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1363 if smuggled_data and 'force_videoid' in smuggled_data:
1364 force_videoid = smuggled_data['force_videoid']
1365 video_id = force_videoid
1366 else:
1367 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1368
1369 self.to_screen('%s: Requesting header' % video_id)
1370
1371 head_req = HEADRequest(url)
1372 head_response = self._request_webpage(
1373 head_req, video_id,
1374 note=False, errnote='Could not send HEAD request to %s' % url,
1375 fatal=False)
1376
1377 if head_response is not False:
1378 # Check for redirect
1379 new_url = head_response.geturl()
1380 if url != new_url:
1381 self.report_following_redirect(new_url)
1382 if force_videoid:
1383 new_url = smuggle_url(
1384 new_url, {'force_videoid': force_videoid})
1385 return self.url_result(new_url)
1386
1387 full_response = None
1388 if head_response is False:
1389 request = sanitized_Request(url)
1390 request.add_header('Accept-Encoding', '*')
1391 full_response = self._request_webpage(request, video_id)
1392 head_response = full_response
1393
1394 info_dict = {
1395 'id': video_id,
1396 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1397 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1398 }
1399
1400 # Check for direct link to a video
1401 content_type = head_response.headers.get('Content-Type', '').lower()
1402 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1403 if m:
1404 format_id = m.group('format_id')
1405 if format_id.endswith('mpegurl'):
1406 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1407 elif format_id == 'f4m':
1408 formats = self._extract_f4m_formats(url, video_id)
1409 else:
1410 formats = [{
1411 'format_id': m.group('format_id'),
1412 'url': url,
1413 'vcodec': 'none' if m.group('type') == 'audio' else None
1414 }]
1415 info_dict['direct'] = True
1416 self._sort_formats(formats)
1417 info_dict['formats'] = formats
1418 return info_dict
1419
1420 if not self._downloader.params.get('test', False) and not is_intentional:
1421 force = self._downloader.params.get('force_generic_extractor', False)
1422 self._downloader.report_warning(
1423 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1424
1425 if not full_response:
1426 request = sanitized_Request(url)
1427 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1428 # making it impossible to download only chunk of the file (yet we need only 512kB to
1429 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1430 # that will always result in downloading the whole file that is not desirable.
1431 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1432 # to accept raw bytes and being able to download only a chunk.
1433 # It may probably better to solve this by checking Content-Type for application/octet-stream
1434 # after HEAD request finishes, but not sure if we can rely on this.
1435 request.add_header('Accept-Encoding', '*')
1436 full_response = self._request_webpage(request, video_id)
1437
1438 first_bytes = full_response.read(512)
1439
1440 # Is it an M3U playlist?
1441 if first_bytes.startswith(b'#EXTM3U'):
1442 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1443 self._sort_formats(info_dict['formats'])
1444 return info_dict
1445
1446 # Maybe it's a direct link to a video?
1447 # Be careful not to download the whole thing!
1448 if not is_html(first_bytes):
1449 self._downloader.report_warning(
1450 'URL could be a direct video link, returning it as such.')
1451 info_dict.update({
1452 'direct': True,
1453 'url': url,
1454 })
1455 return info_dict
1456
1457 webpage = self._webpage_read_content(
1458 full_response, url, video_id, prefix=first_bytes)
1459
1460 self.report_extraction(video_id)
1461
1462 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1463 try:
1464 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1465 if doc.tag == 'rss':
1466 return self._extract_rss(url, video_id, doc)
1467 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1468 smil = self._parse_smil(doc, url, video_id)
1469 self._sort_formats(smil['formats'])
1470 return smil
1471 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1472 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1473 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1474 info_dict['formats'] = self._parse_mpd_formats(
1475 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1476 self._sort_formats(info_dict['formats'])
1477 return info_dict
1478 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1479 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1480 self._sort_formats(info_dict['formats'])
1481 return info_dict
1482 except compat_xml_parse_error:
1483 pass
1484
1485 # Is it a Camtasia project?
1486 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1487 if camtasia_res is not None:
1488 return camtasia_res
1489
1490 # Sometimes embedded video player is hidden behind percent encoding
1491 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1492 # Unescaping the whole page allows to handle those cases in a generic way
1493 webpage = compat_urllib_parse_unquote(webpage)
1494
1495 # it's tempting to parse this further, but you would
1496 # have to take into account all the variations like
1497 # Video Title - Site Name
1498 # Site Name | Video Title
1499 # Video Title - Tagline | Site Name
1500 # and so on and so forth; it's just not practical
1501 video_title = self._og_search_title(
1502 webpage, default=None) or self._html_search_regex(
1503 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1504 default='video')
1505
1506 # Try to detect age limit automatically
1507 age_limit = self._rta_search(webpage)
1508 # And then there are the jokers who advertise that they use RTA,
1509 # but actually don't.
1510 AGE_LIMIT_MARKERS = [
1511 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1512 ]
1513 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1514 age_limit = 18
1515
1516 # video uploader is domain name
1517 video_uploader = self._search_regex(
1518 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1519
1520 video_description = self._og_search_description(webpage, default=None)
1521 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1522
1523 # Helper method
1524 def _playlist_from_matches(matches, getter=None, ie=None):
1525 urlrs = orderedSet(
1526 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1527 for m in matches)
1528 return self.playlist_result(
1529 urlrs, playlist_id=video_id, playlist_title=video_title)
1530
1531 # Look for Brightcove Legacy Studio embeds
1532 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1533 if bc_urls:
1534 self.to_screen('Brightcove video detected.')
1535 entries = [{
1536 '_type': 'url',
1537 'url': smuggle_url(bc_url, {'Referer': url}),
1538 'ie_key': 'BrightcoveLegacy'
1539 } for bc_url in bc_urls]
1540
1541 return {
1542 '_type': 'playlist',
1543 'title': video_title,
1544 'id': video_id,
1545 'entries': entries,
1546 }
1547
1548 # Look for Brightcove New Studio embeds
1549 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1550 if bc_urls:
1551 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1552
1553 # Look for ThePlatform embeds
1554 tp_urls = ThePlatformIE._extract_urls(webpage)
1555 if tp_urls:
1556 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1557
1558 # Look for Vessel embeds
1559 vessel_urls = VesselIE._extract_urls(webpage)
1560 if vessel_urls:
1561 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1562
1563 # Look for embedded rtl.nl player
1564 matches = re.findall(
1565 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1566 webpage)
1567 if matches:
1568 return _playlist_from_matches(matches, ie='RtlNl')
1569
1570 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1571 if vimeo_url is not None:
1572 return self.url_result(vimeo_url)
1573
1574 vid_me_embed_url = self._search_regex(
1575 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1576 webpage, 'vid.me embed', default=None)
1577 if vid_me_embed_url is not None:
1578 return self.url_result(vid_me_embed_url, 'Vidme')
1579
1580 # Look for embedded YouTube player
1581 matches = re.findall(r'''(?x)
1582 (?:
1583 <iframe[^>]+?src=|
1584 data-video-url=|
1585 <embed[^>]+?src=|
1586 embedSWF\(?:\s*|
1587 new\s+SWFObject\(
1588 )
1589 (["\'])
1590 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1591 (?:embed|v|p)/.+?)
1592 \1''', webpage)
1593 if matches:
1594 return _playlist_from_matches(
1595 matches, lambda m: unescapeHTML(m[1]))
1596
1597 # Look for lazyYT YouTube embed
1598 matches = re.findall(
1599 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1600 if matches:
1601 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1602
1603 # Look for embedded Dailymotion player
1604 matches = re.findall(
1605 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1606 if matches:
1607 return _playlist_from_matches(
1608 matches, lambda m: unescapeHTML(m[1]))
1609
1610 # Look for embedded Dailymotion playlist player (#3822)
1611 m = re.search(
1612 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1613 if m:
1614 playlists = re.findall(
1615 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1616 if playlists:
1617 return _playlist_from_matches(
1618 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1619
1620 # Look for embedded Wistia player
1621 match = re.search(
1622 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1623 if match:
1624 embed_url = self._proto_relative_url(
1625 unescapeHTML(match.group('url')))
1626 return {
1627 '_type': 'url_transparent',
1628 'url': embed_url,
1629 'ie_key': 'Wistia',
1630 'uploader': video_uploader,
1631 }
1632
1633 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1634 if match:
1635 return {
1636 '_type': 'url_transparent',
1637 'url': 'wistia:%s' % match.group('id'),
1638 'ie_key': 'Wistia',
1639 'uploader': video_uploader,
1640 }
1641
1642 match = re.search(
1643 r'''(?sx)
1644 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1645 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1646 ''', webpage)
1647 if match:
1648 return self.url_result(self._proto_relative_url(
1649 'wistia:%s' % match.group('id')), 'Wistia')
1650
1651 # Look for SVT player
1652 svt_url = SVTIE._extract_url(webpage)
1653 if svt_url:
1654 return self.url_result(svt_url, 'SVT')
1655
1656 # Look for embedded condenast player
1657 matches = re.findall(
1658 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1659 webpage)
1660 if matches:
1661 return {
1662 '_type': 'playlist',
1663 'entries': [{
1664 '_type': 'url',
1665 'ie_key': 'CondeNast',
1666 'url': ma,
1667 } for ma in matches],
1668 'title': video_title,
1669 'id': video_id,
1670 }
1671
1672 # Look for Bandcamp pages with custom domain
1673 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1674 if mobj is not None:
1675 burl = unescapeHTML(mobj.group(1))
1676 # Don't set the extractor because it can be a track url or an album
1677 return self.url_result(burl)
1678
1679 # Look for embedded Vevo player
1680 mobj = re.search(
1681 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1682 if mobj is not None:
1683 return self.url_result(mobj.group('url'))
1684
1685 # Look for embedded Viddler player
1686 mobj = re.search(
1687 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1688 webpage)
1689 if mobj is not None:
1690 return self.url_result(mobj.group('url'))
1691
1692 # Look for NYTimes player
1693 mobj = re.search(
1694 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1695 webpage)
1696 if mobj is not None:
1697 return self.url_result(mobj.group('url'))
1698
1699 # Look for Libsyn player
1700 mobj = re.search(
1701 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1702 if mobj is not None:
1703 return self.url_result(mobj.group('url'))
1704
1705 # Look for Ooyala videos
1706 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1707 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1708 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1709 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1710 if mobj is not None:
1711 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1712
1713 # Look for multiple Ooyala embeds on SBN network websites
1714 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1715 if mobj is not None:
1716 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1717 if embeds:
1718 return _playlist_from_matches(
1719 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1720
1721 # Look for Aparat videos
1722 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1723 if mobj is not None:
1724 return self.url_result(mobj.group(1), 'Aparat')
1725
1726 # Look for MPORA videos
1727 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1728 if mobj is not None:
1729 return self.url_result(mobj.group(1), 'Mpora')
1730
1731 # Look for embedded NovaMov-based player
1732 mobj = re.search(
1733 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1734 (?P<url>http://(?:(?:embed|www)\.)?
1735 (?:novamov\.com|
1736 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1737 videoweed\.(?:es|com)|
1738 movshare\.(?:net|sx|ag)|
1739 divxstage\.(?:eu|net|ch|co|at|ag))
1740 /embed\.php.+?)\1''', webpage)
1741 if mobj is not None:
1742 return self.url_result(mobj.group('url'))
1743
1744 # Look for embedded Facebook player
1745 mobj = re.search(
1746 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1747 if mobj is not None:
1748 return self.url_result(mobj.group('url'), 'Facebook')
1749
1750 # Look for embedded VK player
1751 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'), 'VK')
1754
1755 # Look for embedded Odnoklassniki player
1756 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1757 if mobj is not None:
1758 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1759
1760 # Look for embedded ivi player
1761 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1762 if mobj is not None:
1763 return self.url_result(mobj.group('url'), 'Ivi')
1764
1765 # Look for embedded Huffington Post player
1766 mobj = re.search(
1767 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'), 'HuffPost')
1770
1771 # Look for embed.ly
1772 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1773 if mobj is not None:
1774 return self.url_result(mobj.group('url'))
1775 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1776 if mobj is not None:
1777 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1778
1779 # Look for funnyordie embed
1780 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1781 if matches:
1782 return _playlist_from_matches(
1783 matches, getter=unescapeHTML, ie='FunnyOrDie')
1784
1785 # Look for BBC iPlayer embed
1786 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1787 if matches:
1788 return _playlist_from_matches(matches, ie='BBCCoUk')
1789
1790 # Look for embedded RUTV player
1791 rutv_url = RUTVIE._extract_url(webpage)
1792 if rutv_url:
1793 return self.url_result(rutv_url, 'RUTV')
1794
1795 # Look for embedded TVC player
1796 tvc_url = TVCIE._extract_url(webpage)
1797 if tvc_url:
1798 return self.url_result(tvc_url, 'TVC')
1799
1800 # Look for embedded SportBox player
1801 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1802 if sportbox_urls:
1803 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1804
1805 # Look for embedded PornHub player
1806 pornhub_url = PornHubIE._extract_url(webpage)
1807 if pornhub_url:
1808 return self.url_result(pornhub_url, 'PornHub')
1809
1810 # Look for embedded XHamster player
1811 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1812 if xhamster_urls:
1813 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1814
1815 # Look for embedded TNAFlixNetwork player
1816 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1817 if tnaflix_urls:
1818 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1819
1820 # Look for embedded Tvigle player
1821 mobj = re.search(
1822 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1823 if mobj is not None:
1824 return self.url_result(mobj.group('url'), 'Tvigle')
1825
1826 # Look for embedded TED player
1827 mobj = re.search(
1828 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1829 if mobj is not None:
1830 return self.url_result(mobj.group('url'), 'TED')
1831
1832 # Look for embedded Ustream videos
1833 mobj = re.search(
1834 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1835 if mobj is not None:
1836 return self.url_result(mobj.group('url'), 'Ustream')
1837
1838 # Look for embedded arte.tv player
1839 mobj = re.search(
1840 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1841 webpage)
1842 if mobj is not None:
1843 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1844
1845 # Look for embedded francetv player
1846 mobj = re.search(
1847 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1848 webpage)
1849 if mobj is not None:
1850 return self.url_result(mobj.group('url'))
1851
1852 # Look for embedded smotri.com player
1853 smotri_url = SmotriIE._extract_url(webpage)
1854 if smotri_url:
1855 return self.url_result(smotri_url, 'Smotri')
1856
1857 # Look for embedded Myvi.ru player
1858 myvi_url = MyviIE._extract_url(webpage)
1859 if myvi_url:
1860 return self.url_result(myvi_url)
1861
1862 # Look for embedded soundcloud player
1863 mobj = re.search(
1864 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1865 webpage)
1866 if mobj is not None:
1867 url = unescapeHTML(mobj.group('url'))
1868 return self.url_result(url)
1869
1870 # Look for embedded mtvservices player
1871 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1872 if mtvservices_url:
1873 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1874
1875 # Look for embedded yahoo player
1876 mobj = re.search(
1877 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1878 webpage)
1879 if mobj is not None:
1880 return self.url_result(mobj.group('url'), 'Yahoo')
1881
1882 # Look for embedded sbs.com.au player
1883 mobj = re.search(
1884 r'''(?x)
1885 (?:
1886 <meta\s+property="og:video"\s+content=|
1887 <iframe[^>]+?src=
1888 )
1889 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1890 webpage)
1891 if mobj is not None:
1892 return self.url_result(mobj.group('url'), 'SBS')
1893
1894 # Look for embedded Cinchcast player
1895 mobj = re.search(
1896 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1897 webpage)
1898 if mobj is not None:
1899 return self.url_result(mobj.group('url'), 'Cinchcast')
1900
1901 mobj = re.search(
1902 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1903 webpage)
1904 if not mobj:
1905 mobj = re.search(
1906 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1907 webpage)
1908 if mobj is not None:
1909 return self.url_result(mobj.group('url'), 'MLB')
1910
1911 mobj = re.search(
1912 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1913 webpage)
1914 if mobj is not None:
1915 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1916
1917 mobj = re.search(
1918 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1919 webpage)
1920 if mobj is not None:
1921 return self.url_result(mobj.group('url'), 'Livestream')
1922
1923 # Look for Zapiks embed
1924 mobj = re.search(
1925 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1926 if mobj is not None:
1927 return self.url_result(mobj.group('url'), 'Zapiks')
1928
1929 # Look for Kaltura embeds
1930 kaltura_url = KalturaIE._extract_url(webpage)
1931 if kaltura_url:
1932 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
1933
1934 # Look for Eagle.Platform embeds
1935 mobj = re.search(
1936 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1937 if mobj is not None:
1938 return self.url_result(mobj.group('url'), 'EaglePlatform')
1939
1940 # Look for ClipYou (uses Eagle.Platform) embeds
1941 mobj = re.search(
1942 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1943 if mobj is not None:
1944 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1945
1946 # Look for Pladform embeds
1947 pladform_url = PladformIE._extract_url(webpage)
1948 if pladform_url:
1949 return self.url_result(pladform_url)
1950
1951 # Look for Videomore embeds
1952 videomore_url = VideomoreIE._extract_url(webpage)
1953 if videomore_url:
1954 return self.url_result(videomore_url)
1955
1956 # Look for Playwire embeds
1957 mobj = re.search(
1958 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1959 if mobj is not None:
1960 return self.url_result(mobj.group('url'))
1961
1962 # Look for 5min embeds
1963 mobj = re.search(
1964 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1965 if mobj is not None:
1966 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1967
1968 # Look for Crooks and Liars embeds
1969 mobj = re.search(
1970 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1971 if mobj is not None:
1972 return self.url_result(mobj.group('url'))
1973
1974 # Look for NBC Sports VPlayer embeds
1975 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1976 if nbc_sports_url:
1977 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1978
1979 # Look for NBC News embeds
1980 nbc_news_embed_url = re.search(
1981 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
1982 if nbc_news_embed_url:
1983 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
1984
1985 # Look for Google Drive embeds
1986 google_drive_url = GoogleDriveIE._extract_url(webpage)
1987 if google_drive_url:
1988 return self.url_result(google_drive_url, 'GoogleDrive')
1989
1990 # Look for UDN embeds
1991 mobj = re.search(
1992 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1993 if mobj is not None:
1994 return self.url_result(
1995 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1996
1997 # Look for Senate ISVP iframe
1998 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1999 if senate_isvp_url:
2000 return self.url_result(senate_isvp_url, 'SenateISVP')
2001
2002 # Look for Dailymotion Cloud videos
2003 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2004 if dmcloud_url:
2005 return self.url_result(dmcloud_url, 'DailymotionCloud')
2006
2007 # Look for OnionStudios embeds
2008 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2009 if onionstudios_url:
2010 return self.url_result(onionstudios_url)
2011
2012 # Look for ViewLift embeds
2013 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2014 if viewlift_url:
2015 return self.url_result(viewlift_url)
2016
2017 # Look for JWPlatform embeds
2018 jwplatform_url = JWPlatformIE._extract_url(webpage)
2019 if jwplatform_url:
2020 return self.url_result(jwplatform_url, 'JWPlatform')
2021
2022 # Look for ScreenwaveMedia embeds
2023 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2024 if mobj is not None:
2025 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2026
2027 # Look for Digiteka embeds
2028 digiteka_url = DigitekaIE._extract_url(webpage)
2029 if digiteka_url:
2030 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2031
2032 # Look for Limelight embeds
2033 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2034 if mobj:
2035 lm = {
2036 'Media': 'media',
2037 'Channel': 'channel',
2038 'ChannelList': 'channel_list',
2039 }
2040 return self.url_result('limelight:%s:%s' % (
2041 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2042
2043 # Look for AdobeTVVideo embeds
2044 mobj = re.search(
2045 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2046 webpage)
2047 if mobj is not None:
2048 return self.url_result(
2049 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2050 'AdobeTVVideo')
2051
2052 # Look for Vine embeds
2053 mobj = re.search(
2054 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2055 webpage)
2056 if mobj is not None:
2057 return self.url_result(
2058 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2059
2060 # Look for Instagram embeds
2061 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2062 if instagram_embed_url is not None:
2063 return self.url_result(
2064 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2065
2066 # Look for LiveLeak embeds
2067 liveleak_url = LiveLeakIE._extract_url(webpage)
2068 if liveleak_url:
2069 return self.url_result(liveleak_url, 'LiveLeak')
2070
2071 # Look for 3Q SDN embeds
2072 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2073 if threeqsdn_url:
2074 return {
2075 '_type': 'url_transparent',
2076 'ie_key': ThreeQSDNIE.ie_key(),
2077 'url': self._proto_relative_url(threeqsdn_url),
2078 'title': video_title,
2079 'description': video_description,
2080 'thumbnail': video_thumbnail,
2081 'uploader': video_uploader,
2082 }
2083
2084 def check_video(vurl):
2085 if YoutubeIE.suitable(vurl):
2086 return True
2087 vpath = compat_urlparse.urlparse(vurl).path
2088 vext = determine_ext(vpath)
2089 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2090
2091 def filter_video(urls):
2092 return list(filter(check_video, urls))
2093
2094 # Start with something easy: JW Player in SWFObject
2095 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2096 if not found:
2097 # Look for gorilla-vid style embedding
2098 found = filter_video(re.findall(r'''(?sx)
2099 (?:
2100 jw_plugins|
2101 JWPlayerOptions|
2102 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2103 )
2104 .*?
2105 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2106 if not found:
2107 # Broaden the search a little bit
2108 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2109 if not found:
2110 # Broaden the findall a little bit: JWPlayer JS loader
2111 found = filter_video(re.findall(
2112 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2113 if not found:
2114 # Flow player
2115 found = filter_video(re.findall(r'''(?xs)
2116 flowplayer\("[^"]+",\s*
2117 \{[^}]+?\}\s*,
2118 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2119 ["']?url["']?\s*:\s*["']([^"']+)["']
2120 ''', webpage))
2121 if not found:
2122 # Cinerama player
2123 found = re.findall(
2124 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2125 if not found:
2126 # Try to find twitter cards info
2127 found = filter_video(re.findall(
2128 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2129 if not found:
2130 # We look for Open Graph info:
2131 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2132 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2133 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2134 if m_video_type is not None:
2135 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2136 if not found:
2137 # HTML5 video
2138 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2139 if not found:
2140 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2141 found = re.search(
2142 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2143 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2144 webpage)
2145 if not found:
2146 # Look also in Refresh HTTP header
2147 refresh_header = head_response.headers.get('Refresh')
2148 if refresh_header:
2149 # In python 2 response HTTP headers are bytestrings
2150 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2151 refresh_header = refresh_header.decode('iso-8859-1')
2152 found = re.search(REDIRECT_REGEX, refresh_header)
2153 if found:
2154 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2155 self.report_following_redirect(new_url)
2156 return {
2157 '_type': 'url',
2158 'url': new_url,
2159 }
2160 if not found:
2161 raise UnsupportedError(url)
2162
2163 entries = []
2164 for video_url in orderedSet(found):
2165 video_url = unescapeHTML(video_url)
2166 video_url = video_url.replace('\\/', '/')
2167 video_url = compat_urlparse.urljoin(url, video_url)
2168 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2169
2170 # Sometimes, jwplayer extraction will result in a YouTube URL
2171 if YoutubeIE.suitable(video_url):
2172 entries.append(self.url_result(video_url, 'Youtube'))
2173 continue
2174
2175 # here's a fun little line of code for you:
2176 video_id = os.path.splitext(video_id)[0]
2177
2178 entry_info_dict = {
2179 'id': video_id,
2180 'uploader': video_uploader,
2181 'title': video_title,
2182 'age_limit': age_limit,
2183 }
2184
2185 ext = determine_ext(video_url)
2186 if ext == 'smil':
2187 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2188 elif ext == 'xspf':
2189 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2190 elif ext == 'm3u8':
2191 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2192 elif ext == 'mpd':
2193 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2194 elif ext == 'f4m':
2195 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2196 else:
2197 entry_info_dict['url'] = video_url
2198
2199 if entry_info_dict.get('formats'):
2200 self._sort_formats(entry_info_dict['formats'])
2201
2202 entries.append(entry_info_dict)
2203
2204 if len(entries) == 1:
2205 return entries[0]
2206 else:
2207 for num, e in enumerate(entries, start=1):
2208 # 'url' results don't have a title
2209 if e.get('title') is not None:
2210 e['title'] = '%s (%d)' % (e['title'], num)
2211 return {
2212 '_type': 'playlist',
2213 'entries': entries,
2214 }
fork of https://github.com/yt-dlp/yt-dlp/