]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[generic] Fix test_Generic_76
[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
68
69 class GenericIE(InfoExtractor):
70 IE_DESC = 'Generic downloader that works on some sites'
71 _VALID_URL = r'.*'
72 IE_NAME = 'generic'
73 _TESTS = [
74 # Direct link to a video
75 {
76 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
77 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
78 'info_dict': {
79 'id': 'trailer',
80 'ext': 'mp4',
81 'title': 'trailer',
82 'upload_date': '20100513',
83 }
84 },
85 # Direct link to media delivered compressed (until Accept-Encoding is *)
86 {
87 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
88 'md5': '128c42e68b13950268b648275386fc74',
89 'info_dict': {
90 'id': 'FictionJunction-Parallel_Hearts',
91 'ext': 'flac',
92 'title': 'FictionJunction-Parallel_Hearts',
93 'upload_date': '20140522',
94 },
95 'expected_warnings': [
96 'URL could be a direct video link, returning it as such.'
97 ]
98 },
99 # Direct download with broken HEAD
100 {
101 'url': 'http://ai-radio.org:8000/radio.opus',
102 'info_dict': {
103 'id': 'radio',
104 'ext': 'opus',
105 'title': 'radio',
106 },
107 'params': {
108 'skip_download': True, # infinite live stream
109 },
110 'expected_warnings': [
111 r'501.*Not Implemented',
112 r'400.*Bad Request',
113 ],
114 },
115 # Direct link with incorrect MIME type
116 {
117 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
118 'md5': '4ccbebe5f36706d85221f204d7eb5913',
119 'info_dict': {
120 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
121 'id': '5_Lennart_Poettering_-_Systemd',
122 'ext': 'webm',
123 'title': '5_Lennart_Poettering_-_Systemd',
124 'upload_date': '20141120',
125 },
126 'expected_warnings': [
127 'URL could be a direct video link, returning it as such.'
128 ]
129 },
130 # RSS feed
131 {
132 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
133 'info_dict': {
134 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
135 'title': 'Zero Punctuation',
136 'description': 're:.*groundbreaking video review series.*'
137 },
138 'playlist_mincount': 11,
139 },
140 # RSS feed with enclosure
141 {
142 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
143 'info_dict': {
144 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
145 'ext': 'm4v',
146 'upload_date': '20150228',
147 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
148 }
149 },
150 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
151 {
152 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
153 'info_dict': {
154 'id': 'smil',
155 'ext': 'mp4',
156 'title': 'Automatics, robotics and biocybernetics',
157 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
158 'upload_date': '20130627',
159 'formats': 'mincount:16',
160 'subtitles': 'mincount:1',
161 },
162 'params': {
163 'force_generic_extractor': True,
164 'skip_download': True,
165 },
166 },
167 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
168 {
169 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
170 'info_dict': {
171 'id': 'hds',
172 'ext': 'flv',
173 'title': 'hds',
174 'formats': 'mincount:1',
175 },
176 'params': {
177 'skip_download': True,
178 },
179 },
180 # SMIL from https://www.restudy.dk/video/play/id/1637
181 {
182 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
183 'info_dict': {
184 'id': 'video_1637',
185 'ext': 'flv',
186 'title': 'video_1637',
187 'formats': 'mincount:3',
188 },
189 'params': {
190 'skip_download': True,
191 },
192 },
193 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
194 {
195 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
196 'info_dict': {
197 'id': 'smil-service',
198 'ext': 'flv',
199 'title': 'smil-service',
200 'formats': 'mincount:1',
201 },
202 'params': {
203 'skip_download': True,
204 },
205 },
206 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
207 {
208 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
209 'info_dict': {
210 'id': '4719370',
211 'ext': 'mp4',
212 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
213 'formats': 'mincount:3',
214 },
215 'params': {
216 'skip_download': True,
217 },
218 },
219 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
220 {
221 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
222 'info_dict': {
223 'id': 'mZlp2ctYIUEB',
224 'ext': 'mp4',
225 'title': 'Tikibad ontruimd wegens brand',
226 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
227 'thumbnail': 're:^https?://.*\.jpg$',
228 'duration': 33,
229 },
230 'params': {
231 'skip_download': True,
232 },
233 },
234 # MPD from http://dash-mse-test.appspot.com/media.html
235 {
236 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
237 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
238 'info_dict': {
239 'id': 'car-20120827-manifest',
240 'ext': 'mp4',
241 'title': 'car-20120827-manifest',
242 'formats': 'mincount:9',
243 'upload_date': '20130904',
244 },
245 'params': {
246 'format': 'bestvideo',
247 },
248 },
249 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
250 {
251 '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',
252 'info_dict': {
253 'id': 'content',
254 'ext': 'mp4',
255 'title': 'content',
256 'formats': 'mincount:8',
257 },
258 'params': {
259 # m3u8 downloads
260 'skip_download': True,
261 }
262 },
263 # m3u8 served with Content-Type: text/plain
264 {
265 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
266 'info_dict': {
267 'id': 'index',
268 'ext': 'mp4',
269 'title': 'index',
270 'upload_date': '20140720',
271 'formats': 'mincount:11',
272 },
273 'params': {
274 # m3u8 downloads
275 'skip_download': True,
276 }
277 },
278 # google redirect
279 {
280 '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',
281 'info_dict': {
282 'id': 'cmQHVoWB5FY',
283 'ext': 'mp4',
284 'upload_date': '20130224',
285 'uploader_id': 'TheVerge',
286 'description': 're:^Chris Ziegler takes a look at the\.*',
287 'uploader': 'The Verge',
288 'title': 'First Firefox OS phones side-by-side',
289 },
290 'params': {
291 'skip_download': False,
292 }
293 },
294 {
295 # redirect in Refresh HTTP header
296 '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',
297 'info_dict': {
298 'id': 'pO8h3EaFRdo',
299 'ext': 'mp4',
300 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
301 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
302 'upload_date': '20150917',
303 'uploader_id': 'brtvofficial',
304 'uploader': 'Boiler Room',
305 },
306 'params': {
307 'skip_download': False,
308 },
309 },
310 {
311 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
312 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
313 'info_dict': {
314 'id': '13601338388002',
315 'ext': 'mp4',
316 'uploader': 'www.hodiho.fr',
317 'title': 'R\u00e9gis plante sa Jeep',
318 }
319 },
320 # bandcamp page with custom domain
321 {
322 'add_ie': ['Bandcamp'],
323 'url': 'http://bronyrock.com/track/the-pony-mash',
324 'info_dict': {
325 'id': '3235767654',
326 'ext': 'mp3',
327 'title': 'The Pony Mash',
328 'uploader': 'M_Pallante',
329 },
330 'skip': 'There is a limit of 200 free downloads / month for the test song',
331 },
332 # embedded brightcove video
333 # it also tests brightcove videos that need to set the 'Referer' in the
334 # http requests
335 {
336 'add_ie': ['BrightcoveLegacy'],
337 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
338 'info_dict': {
339 'id': '2765128793001',
340 'ext': 'mp4',
341 'title': 'Le cours de bourse : l’analyse technique',
342 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
343 'uploader': 'BFM BUSINESS',
344 },
345 'params': {
346 'skip_download': True,
347 },
348 },
349 {
350 # https://github.com/rg3/youtube-dl/issues/2253
351 'url': 'http://bcove.me/i6nfkrc3',
352 'md5': '0ba9446db037002366bab3b3eb30c88c',
353 'info_dict': {
354 'id': '3101154703001',
355 'ext': 'mp4',
356 'title': 'Still no power',
357 'uploader': 'thestar.com',
358 '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.',
359 },
360 'add_ie': ['BrightcoveLegacy'],
361 },
362 {
363 'url': 'http://www.championat.com/video/football/v/87/87499.html',
364 'md5': 'fb973ecf6e4a78a67453647444222983',
365 'info_dict': {
366 'id': '3414141473001',
367 'ext': 'mp4',
368 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
369 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
370 'uploader': 'Championat',
371 },
372 },
373 {
374 # https://github.com/rg3/youtube-dl/issues/3541
375 'add_ie': ['BrightcoveLegacy'],
376 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
377 'info_dict': {
378 'id': '3866516442001',
379 'ext': 'mp4',
380 'title': 'Leer mij vrouwen kennen: Aflevering 1',
381 'description': 'Leer mij vrouwen kennen: Aflevering 1',
382 'uploader': 'SBS Broadcasting',
383 },
384 'skip': 'Restricted to Netherlands',
385 'params': {
386 'skip_download': True, # m3u8 download
387 },
388 },
389 # ooyala video
390 {
391 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
392 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
393 'info_dict': {
394 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
395 'ext': 'mp4',
396 'title': '2cc213299525360.mov', # that's what we get
397 'duration': 238.231,
398 },
399 'add_ie': ['Ooyala'],
400 },
401 {
402 # ooyala video embedded with http://player.ooyala.com/iframe.js
403 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
404 'info_dict': {
405 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
406 'ext': 'mp4',
407 'title': '"Steve Jobs: Man in the Machine" trailer',
408 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
409 'duration': 135.427,
410 },
411 'params': {
412 'skip_download': True,
413 },
414 },
415 # embed.ly video
416 {
417 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
418 'info_dict': {
419 'id': '9ODmcdjQcHQ',
420 'ext': 'mp4',
421 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
422 'upload_date': '20140225',
423 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
424 'uploader': 'Tested',
425 'uploader_id': 'testedcom',
426 },
427 # No need to test YoutubeIE here
428 'params': {
429 'skip_download': True,
430 },
431 },
432 # funnyordie embed
433 {
434 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
435 'info_dict': {
436 'id': '18e820ec3f',
437 'ext': 'mp4',
438 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
439 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
440 },
441 },
442 # RUTV embed
443 {
444 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
445 'info_dict': {
446 'id': '776940',
447 'ext': 'mp4',
448 'title': 'Охотское море стало целиком российским',
449 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
450 },
451 'params': {
452 # m3u8 download
453 'skip_download': True,
454 },
455 },
456 # TVC embed
457 {
458 '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/',
459 'info_dict': {
460 'id': '55304',
461 'ext': 'mp4',
462 'title': 'Дошкольное воспитание',
463 },
464 },
465 # SportBox embed
466 {
467 'url': 'http://www.vestifinance.ru/articles/25753',
468 'info_dict': {
469 'id': '25753',
470 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
471 },
472 'playlist': [{
473 'info_dict': {
474 'id': '370908',
475 'title': 'Госзаказ. День 3',
476 'ext': 'mp4',
477 }
478 }, {
479 'info_dict': {
480 'id': '370905',
481 'title': 'Госзаказ. День 2',
482 'ext': 'mp4',
483 }
484 }, {
485 'info_dict': {
486 'id': '370902',
487 'title': 'Госзаказ. День 1',
488 'ext': 'mp4',
489 }
490 }],
491 'params': {
492 # m3u8 download
493 'skip_download': True,
494 },
495 },
496 # Myvi.ru embed
497 {
498 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
499 'info_dict': {
500 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
501 'ext': 'mp4',
502 'title': 'Ужастики, русский трейлер (2015)',
503 'thumbnail': 're:^https?://.*\.jpg$',
504 'duration': 153,
505 }
506 },
507 # XHamster embed
508 {
509 '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',
510 'info_dict': {
511 'id': 'showthread',
512 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
513 },
514 'playlist_mincount': 7,
515 },
516 # Embedded TED video
517 {
518 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
519 'md5': '65fdff94098e4a607385a60c5177c638',
520 'info_dict': {
521 'id': '1969',
522 'ext': 'mp4',
523 'title': 'Hidden miracles of the natural world',
524 'uploader': 'Louie Schwartzberg',
525 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
526 }
527 },
528 # Embedded Ustream video
529 {
530 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
531 'md5': '27b99cdb639c9b12a79bca876a073417',
532 'info_dict': {
533 'id': '45734260',
534 'ext': 'flv',
535 'uploader': 'AU SPA: The NSA and Privacy',
536 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
537 }
538 },
539 # nowvideo embed hidden behind percent encoding
540 {
541 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
542 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
543 'info_dict': {
544 'id': '06e53103ca9aa',
545 'ext': 'flv',
546 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
547 'description': 'No description',
548 },
549 },
550 # arte embed
551 {
552 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
553 'md5': '7653032cbb25bf6c80d80f217055fa43',
554 'info_dict': {
555 'id': '048195-004_PLUS7-F',
556 'ext': 'flv',
557 'title': 'X:enius',
558 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
559 'upload_date': '20140320',
560 },
561 'params': {
562 'skip_download': 'Requires rtmpdump'
563 }
564 },
565 # francetv embed
566 {
567 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
568 'info_dict': {
569 'id': 'EV_30231',
570 'ext': 'mp4',
571 'title': 'Alcaline, le concert avec Calogero',
572 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
573 'upload_date': '20150226',
574 'timestamp': 1424989860,
575 'duration': 5400,
576 },
577 'params': {
578 # m3u8 downloads
579 'skip_download': True,
580 },
581 'expected_warnings': [
582 'Forbidden'
583 ]
584 },
585 # Condé Nast embed
586 {
587 'url': 'http://www.wired.com/2014/04/honda-asimo/',
588 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
589 'info_dict': {
590 'id': '53501be369702d3275860000',
591 'ext': 'mp4',
592 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
593 }
594 },
595 # Dailymotion embed
596 {
597 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
598 'md5': '441aeeb82eb72c422c7f14ec533999cd',
599 'info_dict': {
600 'id': 'k2mm4bCdJ6CQ2i7c8o2',
601 'ext': 'mp4',
602 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
603 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
604 'uploader': 'Spi0n',
605 'uploader_id': 'xgditw',
606 'upload_date': '20140425',
607 'timestamp': 1398441542,
608 },
609 'add_ie': ['Dailymotion'],
610 },
611 # YouTube embed
612 {
613 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
614 'info_dict': {
615 'id': 'FXRb4ykk4S0',
616 'ext': 'mp4',
617 'title': 'The NBL Auction 2014',
618 'uploader': 'BADMINTON England',
619 'uploader_id': 'BADMINTONEvents',
620 'upload_date': '20140603',
621 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
622 },
623 'add_ie': ['Youtube'],
624 'params': {
625 'skip_download': True,
626 }
627 },
628 # MTVSercices embed
629 {
630 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
631 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
632 'info_dict': {
633 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
634 'ext': 'mp4',
635 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
636 'description': 'Two valets share their love for movie star Liam Neesons.',
637 },
638 },
639 # YouTube embed via <data-embed-url="">
640 {
641 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
642 'info_dict': {
643 'id': '4vAffPZIT44',
644 'ext': 'mp4',
645 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
646 'uploader': 'Gameloft',
647 'uploader_id': 'gameloft',
648 'upload_date': '20140828',
649 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
650 },
651 'params': {
652 'skip_download': True,
653 }
654 },
655 # Camtasia studio
656 {
657 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
658 'playlist': [{
659 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
660 'info_dict': {
661 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
662 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
663 'ext': 'flv',
664 'duration': 2235.90,
665 }
666 }, {
667 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
668 'info_dict': {
669 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
670 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
671 'ext': 'flv',
672 'duration': 2235.93,
673 }
674 }],
675 'info_dict': {
676 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
677 }
678 },
679 # Flowplayer
680 {
681 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
682 'md5': '9d65602bf31c6e20014319c7d07fba27',
683 'info_dict': {
684 'id': '5123ea6d5e5a7',
685 'ext': 'mp4',
686 'age_limit': 18,
687 'uploader': 'www.handjobhub.com',
688 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
689 }
690 },
691 # Multiple brightcove videos
692 # https://github.com/rg3/youtube-dl/issues/2283
693 {
694 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
695 'info_dict': {
696 'id': 'always-never',
697 'title': 'Always / Never - The New Yorker',
698 },
699 'playlist_count': 3,
700 'params': {
701 'extract_flat': False,
702 'skip_download': True,
703 }
704 },
705 # MLB embed
706 {
707 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
708 'md5': '96f09a37e44da40dd083e12d9a683327',
709 'info_dict': {
710 'id': '33322633',
711 'ext': 'mp4',
712 'title': 'Ump changes call to ball',
713 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
714 'duration': 48,
715 'timestamp': 1401537900,
716 'upload_date': '20140531',
717 'thumbnail': 're:^https?://.*\.jpg$',
718 },
719 },
720 # Wistia embed
721 {
722 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
723 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
724 'info_dict': {
725 'id': '6e2wtrbdaf',
726 'ext': 'mov',
727 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
728 'description': 'a Paywall Videos video from Remilon',
729 'duration': 644.072,
730 'uploader': 'study.com',
731 'timestamp': 1459678540,
732 'upload_date': '20160403',
733 'filesize': 24687186,
734 },
735 },
736 {
737 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
738 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
739 'info_dict': {
740 'id': 'uxjb0lwrcz',
741 'ext': 'mp4',
742 'title': 'Conversation about Hexagonal Rails Part 1',
743 'description': 'a Martin Fowler video from ThoughtWorks',
744 'duration': 1715.0,
745 'uploader': 'thoughtworks.wistia.com',
746 'timestamp': 1401832161,
747 'upload_date': '20140603',
748 },
749 },
750 # Wistia standard embed (async)
751 {
752 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
753 'info_dict': {
754 'id': '807fafadvk',
755 'ext': 'mp4',
756 'title': 'Drip Brennan Dunn Workshop',
757 'description': 'a JV Webinars video from getdrip-1',
758 'duration': 4986.95,
759 'timestamp': 1463607249,
760 'upload_date': '20160518',
761 },
762 'params': {
763 'skip_download': True,
764 }
765 },
766 # Soundcloud embed
767 {
768 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
769 'info_dict': {
770 'id': '174391317',
771 'ext': 'mp3',
772 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
773 'uploader': 'Sophos Security',
774 'title': 'Chet Chat 171 - Oct 29, 2014',
775 'upload_date': '20141029',
776 }
777 },
778 # Livestream embed
779 {
780 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
781 'info_dict': {
782 'id': '67864563',
783 'ext': 'flv',
784 'upload_date': '20141112',
785 'title': 'Rosetta #CometLanding webcast HL 10',
786 }
787 },
788 # Another Livestream embed, without 'new.' in URL
789 {
790 'url': 'https://www.freespeech.org/',
791 'info_dict': {
792 'id': '123537347',
793 'ext': 'mp4',
794 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
795 },
796 'params': {
797 # Live stream
798 'skip_download': True,
799 },
800 },
801 # LazyYT
802 {
803 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
804 'info_dict': {
805 'id': '1986',
806 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
807 },
808 'playlist_mincount': 2,
809 },
810 # Cinchcast embed
811 {
812 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
813 'info_dict': {
814 'id': '7141703',
815 'ext': 'mp3',
816 'upload_date': '20141126',
817 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
818 }
819 },
820 # Cinerama player
821 {
822 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
823 'info_dict': {
824 'id': '730m_DandD_1901_512k',
825 'ext': 'mp4',
826 'uploader': 'www.abc.net.au',
827 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
828 }
829 },
830 # embedded viddler video
831 {
832 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
833 'info_dict': {
834 'id': '4d03aad9',
835 'ext': 'mp4',
836 'uploader': 'deadspin',
837 'title': 'WALL-TO-GORTAT',
838 'timestamp': 1422285291,
839 'upload_date': '20150126',
840 },
841 'add_ie': ['Viddler'],
842 },
843 # Libsyn embed
844 {
845 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
846 'info_dict': {
847 'id': '3377616',
848 'ext': 'mp3',
849 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
850 'description': 'md5:601cb790edd05908957dae8aaa866465',
851 'upload_date': '20150220',
852 },
853 },
854 # jwplayer YouTube
855 {
856 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
857 'info_dict': {
858 'id': 'Mrj4DVp2zeA',
859 'ext': 'mp4',
860 'upload_date': '20150212',
861 'uploader': 'The National Archives UK',
862 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
863 'uploader_id': 'NationalArchives08',
864 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
865 },
866 },
867 # rtl.nl embed
868 {
869 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
870 'playlist_mincount': 5,
871 'info_dict': {
872 'id': 'aanslagen-kopenhagen',
873 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
874 }
875 },
876 # Zapiks embed
877 {
878 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
879 'info_dict': {
880 'id': '118046',
881 'ext': 'mp4',
882 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
883 }
884 },
885 # Kaltura embed (different embed code)
886 {
887 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
888 'info_dict': {
889 'id': '1_a52wc67y',
890 'ext': 'flv',
891 'upload_date': '20150127',
892 'uploader_id': 'PremierMedia',
893 'timestamp': int,
894 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
895 },
896 },
897 # Kaltura embed protected with referrer
898 {
899 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
900 'info_dict': {
901 'id': '1_g4fbemnq',
902 'ext': 'mp4',
903 'title': 'Violetta - Achter De Schermen - Ruggero',
904 'description': 'Achter de schermen met Ruggero',
905 'timestamp': 1435133761,
906 'upload_date': '20150624',
907 'uploader_id': 'echojecka',
908 },
909 },
910 # Kaltura embed with single quotes
911 {
912 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
913 'info_dict': {
914 'id': '0_izeg5utt',
915 'ext': 'mp4',
916 'title': '35871',
917 'timestamp': 1355743100,
918 'upload_date': '20121217',
919 'uploader_id': 'batchUser',
920 },
921 'add_ie': ['Kaltura'],
922 },
923 # Eagle.Platform embed (generic URL)
924 {
925 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
926 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
927 'info_dict': {
928 'id': '227304',
929 'ext': 'mp4',
930 'title': 'Навальный вышел на свободу',
931 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
932 'thumbnail': 're:^https?://.*\.jpg$',
933 'duration': 87,
934 'view_count': int,
935 'age_limit': 0,
936 },
937 },
938 # ClipYou (Eagle.Platform) embed (custom URL)
939 {
940 'url': 'http://muz-tv.ru/play/7129/',
941 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
942 'info_dict': {
943 'id': '12820',
944 'ext': 'mp4',
945 'title': "'O Sole Mio",
946 'thumbnail': 're:^https?://.*\.jpg$',
947 'duration': 216,
948 'view_count': int,
949 },
950 },
951 # Pladform embed
952 {
953 'url': 'http://muz-tv.ru/kinozal/view/7400/',
954 'info_dict': {
955 'id': '100183293',
956 'ext': 'mp4',
957 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
958 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
959 'thumbnail': 're:^https?://.*\.jpg$',
960 'duration': 694,
961 'age_limit': 0,
962 },
963 },
964 # Playwire embed
965 {
966 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
967 'info_dict': {
968 'id': '3519514',
969 'ext': 'mp4',
970 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
971 'thumbnail': 're:^https?://.*\.png$',
972 'duration': 45.115,
973 },
974 },
975 # 5min embed
976 {
977 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
978 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
979 'info_dict': {
980 'id': '518726732',
981 'ext': 'mp4',
982 'title': 'Facebook Creates "On This Day" | Crunch Report',
983 },
984 },
985 # SVT embed
986 {
987 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
988 'info_dict': {
989 'id': '2900353',
990 'ext': 'flv',
991 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
992 'duration': 27,
993 'age_limit': 0,
994 },
995 },
996 # Crooks and Liars embed
997 {
998 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
999 'info_dict': {
1000 'id': '8RUoRhRi',
1001 'ext': 'mp4',
1002 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1003 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1004 'timestamp': 1428207000,
1005 'upload_date': '20150405',
1006 'uploader': 'Heather',
1007 },
1008 },
1009 # Crooks and Liars external embed
1010 {
1011 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1012 'info_dict': {
1013 'id': 'MTE3MjUtMzQ2MzA',
1014 'ext': 'mp4',
1015 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1016 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1017 'timestamp': 1265032391,
1018 'upload_date': '20100201',
1019 'uploader': 'Heather',
1020 },
1021 },
1022 # NBC Sports vplayer embed
1023 {
1024 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1025 'info_dict': {
1026 'id': 'ln7x1qSThw4k',
1027 'ext': 'flv',
1028 'title': "PFT Live: New leader in the 'new-look' defense",
1029 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1030 'uploader': 'NBCU-SPORTS',
1031 'upload_date': '20140107',
1032 'timestamp': 1389118457,
1033 },
1034 },
1035 # NBC News embed
1036 {
1037 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1038 'md5': '1aa589c675898ae6d37a17913cf68d66',
1039 'info_dict': {
1040 'id': '701714499682',
1041 'ext': 'mp4',
1042 'title': 'PREVIEW: On Assignment: David Letterman',
1043 '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.',
1044 },
1045 },
1046 # UDN embed
1047 {
1048 'url': 'https://video.udn.com/news/300346',
1049 'md5': 'fd2060e988c326991037b9aff9df21a6',
1050 'info_dict': {
1051 'id': '300346',
1052 'ext': 'mp4',
1053 'title': '中一中男師變性 全校師生力挺',
1054 'thumbnail': 're:^https?://.*\.jpg$',
1055 },
1056 'params': {
1057 # m3u8 download
1058 'skip_download': True,
1059 },
1060 },
1061 # Ooyala embed
1062 {
1063 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1064 'info_dict': {
1065 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1066 'ext': 'mp4',
1067 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1068 'title': 'This is what separates the Excel masters from the wannabes',
1069 'duration': 191.933,
1070 },
1071 'params': {
1072 # m3u8 downloads
1073 'skip_download': True,
1074 }
1075 },
1076 # Brightcove URL in single quotes
1077 {
1078 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1079 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1080 'info_dict': {
1081 'id': '4255764656001',
1082 'ext': 'mp4',
1083 'title': 'SN Presents: Russell Martin, World Citizen',
1084 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1085 'uploader': 'Rogers Sportsnet',
1086 'uploader_id': '1704050871',
1087 'upload_date': '20150525',
1088 'timestamp': 1432570283,
1089 },
1090 },
1091 # Dailymotion Cloud video
1092 {
1093 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1094 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1095 'info_dict': {
1096 'id': 'x2uy8t3',
1097 'ext': 'mp4',
1098 'title': 'Sauvons les abeilles ! - Le débat',
1099 'description': 'md5:d9082128b1c5277987825d684939ca26',
1100 'thumbnail': 're:^https?://.*\.jpe?g$',
1101 'timestamp': 1434970506,
1102 'upload_date': '20150622',
1103 'uploader': 'Public Sénat',
1104 'uploader_id': 'xa9gza',
1105 }
1106 },
1107 # OnionStudios embed
1108 {
1109 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1110 'info_dict': {
1111 'id': '2855',
1112 'ext': 'mp4',
1113 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1114 'thumbnail': 're:^https?://.*\.jpe?g$',
1115 'uploader': 'ClickHole',
1116 'uploader_id': 'clickhole',
1117 }
1118 },
1119 # SnagFilms embed
1120 {
1121 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1122 'info_dict': {
1123 'id': '74849a00-85a9-11e1-9660-123139220831',
1124 'ext': 'mp4',
1125 'title': '#whilewewatch',
1126 }
1127 },
1128 # AdobeTVVideo embed
1129 {
1130 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1131 'md5': '43662b577c018ad707a63766462b1e87',
1132 'info_dict': {
1133 'id': '2456',
1134 'ext': 'mp4',
1135 'title': 'New experience with Acrobat DC',
1136 'description': 'New experience with Acrobat DC',
1137 'duration': 248.667,
1138 },
1139 },
1140 # ScreenwaveMedia embed
1141 {
1142 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1143 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1144 'info_dict': {
1145 'id': 'cinemasnob-55d26273809dd',
1146 'ext': 'mp4',
1147 'title': 'cinemasnob',
1148 },
1149 },
1150 # BrightcoveInPageEmbed embed
1151 {
1152 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1153 'info_dict': {
1154 'id': '4238694884001',
1155 'ext': 'flv',
1156 'title': 'Tabletop: Dread, Last Thoughts',
1157 'description': 'Tabletop: Dread, Last Thoughts',
1158 'duration': 51690,
1159 },
1160 },
1161 # JWPlayer with M3U8
1162 {
1163 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1164 'info_dict': {
1165 'id': 'playlist',
1166 'ext': 'mp4',
1167 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1168 'uploader': 'ren.tv',
1169 },
1170 'params': {
1171 # m3u8 downloads
1172 'skip_download': True,
1173 }
1174 },
1175 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1176 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1177 {
1178 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1179 'info_dict': {
1180 'id': '4785848093001',
1181 'ext': 'mp4',
1182 'title': 'The Cardinal Pell Interview',
1183 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1184 'uploader': 'GlobeCast Australia - GlobeStream',
1185 'uploader_id': '2733773828001',
1186 'upload_date': '20160304',
1187 'timestamp': 1457083087,
1188 },
1189 'params': {
1190 # m3u8 downloads
1191 'skip_download': True,
1192 },
1193 },
1194 # Another form of arte.tv embed
1195 {
1196 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1197 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1198 'info_dict': {
1199 'id': '030273-562_PLUS7-F',
1200 'ext': 'mp4',
1201 'title': 'ARTE Reportage - Nulle part, en France',
1202 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1203 'upload_date': '20160409',
1204 },
1205 },
1206 # LiveLeak embed
1207 {
1208 'url': 'http://www.wykop.pl/link/3088787/',
1209 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1210 'info_dict': {
1211 'id': '874_1459135191',
1212 'ext': 'mp4',
1213 'title': 'Man shows poor quality of new apartment building',
1214 'description': 'The wall is like a sand pile.',
1215 'uploader': 'Lake8737',
1216 }
1217 },
1218 # Duplicated embedded video URLs
1219 {
1220 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1221 'info_dict': {
1222 'id': '149298443_480_16c25b74_2',
1223 'ext': 'mp4',
1224 'title': 'vs. Blue Orange Spring Game',
1225 'uploader': 'www.hudl.com',
1226 },
1227 },
1228 ]
1229
1230 def report_following_redirect(self, new_url):
1231 """Report information extraction."""
1232 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1233
1234 def _extract_rss(self, url, video_id, doc):
1235 playlist_title = doc.find('./channel/title').text
1236 playlist_desc_el = doc.find('./channel/description')
1237 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1238
1239 entries = []
1240 for it in doc.findall('./channel/item'):
1241 next_url = xpath_text(it, 'link', fatal=False)
1242 if not next_url:
1243 enclosure_nodes = it.findall('./enclosure')
1244 for e in enclosure_nodes:
1245 next_url = e.attrib.get('url')
1246 if next_url:
1247 break
1248
1249 if not next_url:
1250 continue
1251
1252 entries.append({
1253 '_type': 'url',
1254 'url': next_url,
1255 'title': it.find('title').text,
1256 })
1257
1258 return {
1259 '_type': 'playlist',
1260 'id': url,
1261 'title': playlist_title,
1262 'description': playlist_desc,
1263 'entries': entries,
1264 }
1265
1266 def _extract_camtasia(self, url, video_id, webpage):
1267 """ Returns None if no camtasia video can be found. """
1268
1269 camtasia_cfg = self._search_regex(
1270 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1271 webpage, 'camtasia configuration file', default=None)
1272 if camtasia_cfg is None:
1273 return None
1274
1275 title = self._html_search_meta('DC.title', webpage, fatal=True)
1276
1277 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1278 camtasia_cfg = self._download_xml(
1279 camtasia_url, video_id,
1280 note='Downloading camtasia configuration',
1281 errnote='Failed to download camtasia configuration')
1282 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1283
1284 entries = []
1285 for n in fileset_node.getchildren():
1286 url_n = n.find('./uri')
1287 if url_n is None:
1288 continue
1289
1290 entries.append({
1291 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1292 'title': '%s - %s' % (title, n.tag),
1293 'url': compat_urlparse.urljoin(url, url_n.text),
1294 'duration': float_or_none(n.find('./duration').text),
1295 })
1296
1297 return {
1298 '_type': 'playlist',
1299 'entries': entries,
1300 'title': title,
1301 }
1302
1303 def _real_extract(self, url):
1304 if url.startswith('//'):
1305 return {
1306 '_type': 'url',
1307 'url': self.http_scheme() + url,
1308 }
1309
1310 parsed_url = compat_urlparse.urlparse(url)
1311 if not parsed_url.scheme:
1312 default_search = self._downloader.params.get('default_search')
1313 if default_search is None:
1314 default_search = 'fixup_error'
1315
1316 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1317 if '/' in url:
1318 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1319 return self.url_result('http://' + url)
1320 elif default_search != 'fixup_error':
1321 if default_search == 'auto_warning':
1322 if re.match(r'^(?:url|URL)$', url):
1323 raise ExtractorError(
1324 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1325 expected=True)
1326 else:
1327 self._downloader.report_warning(
1328 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1329 return self.url_result('ytsearch:' + url)
1330
1331 if default_search in ('error', 'fixup_error'):
1332 raise ExtractorError(
1333 '%r is not a valid URL. '
1334 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1335 % (url, url), expected=True)
1336 else:
1337 if ':' not in default_search:
1338 default_search += ':'
1339 return self.url_result(default_search + url)
1340
1341 url, smuggled_data = unsmuggle_url(url)
1342 force_videoid = None
1343 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1344 if smuggled_data and 'force_videoid' in smuggled_data:
1345 force_videoid = smuggled_data['force_videoid']
1346 video_id = force_videoid
1347 else:
1348 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1349
1350 self.to_screen('%s: Requesting header' % video_id)
1351
1352 head_req = HEADRequest(url)
1353 head_response = self._request_webpage(
1354 head_req, video_id,
1355 note=False, errnote='Could not send HEAD request to %s' % url,
1356 fatal=False)
1357
1358 if head_response is not False:
1359 # Check for redirect
1360 new_url = head_response.geturl()
1361 if url != new_url:
1362 self.report_following_redirect(new_url)
1363 if force_videoid:
1364 new_url = smuggle_url(
1365 new_url, {'force_videoid': force_videoid})
1366 return self.url_result(new_url)
1367
1368 full_response = None
1369 if head_response is False:
1370 request = sanitized_Request(url)
1371 request.add_header('Accept-Encoding', '*')
1372 full_response = self._request_webpage(request, video_id)
1373 head_response = full_response
1374
1375 info_dict = {
1376 'id': video_id,
1377 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1378 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1379 }
1380
1381 # Check for direct link to a video
1382 content_type = head_response.headers.get('Content-Type', '').lower()
1383 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1384 if m:
1385 format_id = m.group('format_id')
1386 if format_id.endswith('mpegurl'):
1387 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1388 elif format_id == 'f4m':
1389 formats = self._extract_f4m_formats(url, video_id)
1390 else:
1391 formats = [{
1392 'format_id': m.group('format_id'),
1393 'url': url,
1394 'vcodec': 'none' if m.group('type') == 'audio' else None
1395 }]
1396 info_dict['direct'] = True
1397 self._sort_formats(formats)
1398 info_dict['formats'] = formats
1399 return info_dict
1400
1401 if not self._downloader.params.get('test', False) and not is_intentional:
1402 force = self._downloader.params.get('force_generic_extractor', False)
1403 self._downloader.report_warning(
1404 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1405
1406 if not full_response:
1407 request = sanitized_Request(url)
1408 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1409 # making it impossible to download only chunk of the file (yet we need only 512kB to
1410 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1411 # that will always result in downloading the whole file that is not desirable.
1412 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1413 # to accept raw bytes and being able to download only a chunk.
1414 # It may probably better to solve this by checking Content-Type for application/octet-stream
1415 # after HEAD request finishes, but not sure if we can rely on this.
1416 request.add_header('Accept-Encoding', '*')
1417 full_response = self._request_webpage(request, video_id)
1418
1419 first_bytes = full_response.read(512)
1420
1421 # Is it an M3U playlist?
1422 if first_bytes.startswith(b'#EXTM3U'):
1423 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1424 self._sort_formats(info_dict['formats'])
1425 return info_dict
1426
1427 # Maybe it's a direct link to a video?
1428 # Be careful not to download the whole thing!
1429 if not is_html(first_bytes):
1430 self._downloader.report_warning(
1431 'URL could be a direct video link, returning it as such.')
1432 info_dict.update({
1433 'direct': True,
1434 'url': url,
1435 })
1436 return info_dict
1437
1438 webpage = self._webpage_read_content(
1439 full_response, url, video_id, prefix=first_bytes)
1440
1441 self.report_extraction(video_id)
1442
1443 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1444 try:
1445 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1446 if doc.tag == 'rss':
1447 return self._extract_rss(url, video_id, doc)
1448 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1449 smil = self._parse_smil(doc, url, video_id)
1450 self._sort_formats(smil['formats'])
1451 return smil
1452 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1453 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1454 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1455 info_dict['formats'] = self._parse_mpd_formats(
1456 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1457 self._sort_formats(info_dict['formats'])
1458 return info_dict
1459 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1460 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1461 self._sort_formats(info_dict['formats'])
1462 return info_dict
1463 except compat_xml_parse_error:
1464 pass
1465
1466 # Is it a Camtasia project?
1467 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1468 if camtasia_res is not None:
1469 return camtasia_res
1470
1471 # Sometimes embedded video player is hidden behind percent encoding
1472 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1473 # Unescaping the whole page allows to handle those cases in a generic way
1474 webpage = compat_urllib_parse_unquote(webpage)
1475
1476 # it's tempting to parse this further, but you would
1477 # have to take into account all the variations like
1478 # Video Title - Site Name
1479 # Site Name | Video Title
1480 # Video Title - Tagline | Site Name
1481 # and so on and so forth; it's just not practical
1482 video_title = self._og_search_title(
1483 webpage, default=None) or self._html_search_regex(
1484 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1485 default='video')
1486
1487 # Try to detect age limit automatically
1488 age_limit = self._rta_search(webpage)
1489 # And then there are the jokers who advertise that they use RTA,
1490 # but actually don't.
1491 AGE_LIMIT_MARKERS = [
1492 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1493 ]
1494 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1495 age_limit = 18
1496
1497 # video uploader is domain name
1498 video_uploader = self._search_regex(
1499 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1500
1501 video_description = self._og_search_description(webpage, default=None)
1502 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1503
1504 # Helper method
1505 def _playlist_from_matches(matches, getter=None, ie=None):
1506 urlrs = orderedSet(
1507 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1508 for m in matches)
1509 return self.playlist_result(
1510 urlrs, playlist_id=video_id, playlist_title=video_title)
1511
1512 # Look for Brightcove Legacy Studio embeds
1513 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1514 if bc_urls:
1515 self.to_screen('Brightcove video detected.')
1516 entries = [{
1517 '_type': 'url',
1518 'url': smuggle_url(bc_url, {'Referer': url}),
1519 'ie_key': 'BrightcoveLegacy'
1520 } for bc_url in bc_urls]
1521
1522 return {
1523 '_type': 'playlist',
1524 'title': video_title,
1525 'id': video_id,
1526 'entries': entries,
1527 }
1528
1529 # Look for Brightcove New Studio embeds
1530 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1531 if bc_urls:
1532 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1533
1534 # Look for ThePlatform embeds
1535 tp_urls = ThePlatformIE._extract_urls(webpage)
1536 if tp_urls:
1537 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1538
1539 # Look for Vessel embeds
1540 vessel_urls = VesselIE._extract_urls(webpage)
1541 if vessel_urls:
1542 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1543
1544 # Look for embedded rtl.nl player
1545 matches = re.findall(
1546 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1547 webpage)
1548 if matches:
1549 return _playlist_from_matches(matches, ie='RtlNl')
1550
1551 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1552 if vimeo_url is not None:
1553 return self.url_result(vimeo_url)
1554
1555 vid_me_embed_url = self._search_regex(
1556 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1557 webpage, 'vid.me embed', default=None)
1558 if vid_me_embed_url is not None:
1559 return self.url_result(vid_me_embed_url, 'Vidme')
1560
1561 # Look for embedded YouTube player
1562 matches = re.findall(r'''(?x)
1563 (?:
1564 <iframe[^>]+?src=|
1565 data-video-url=|
1566 <embed[^>]+?src=|
1567 embedSWF\(?:\s*|
1568 new\s+SWFObject\(
1569 )
1570 (["\'])
1571 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1572 (?:embed|v|p)/.+?)
1573 \1''', webpage)
1574 if matches:
1575 return _playlist_from_matches(
1576 matches, lambda m: unescapeHTML(m[1]))
1577
1578 # Look for lazyYT YouTube embed
1579 matches = re.findall(
1580 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1581 if matches:
1582 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1583
1584 # Look for embedded Dailymotion player
1585 matches = re.findall(
1586 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1587 if matches:
1588 return _playlist_from_matches(
1589 matches, lambda m: unescapeHTML(m[1]))
1590
1591 # Look for embedded Dailymotion playlist player (#3822)
1592 m = re.search(
1593 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1594 if m:
1595 playlists = re.findall(
1596 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1597 if playlists:
1598 return _playlist_from_matches(
1599 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1600
1601 # Look for embedded Wistia player
1602 match = re.search(
1603 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1604 if match:
1605 embed_url = self._proto_relative_url(
1606 unescapeHTML(match.group('url')))
1607 return {
1608 '_type': 'url_transparent',
1609 'url': embed_url,
1610 'ie_key': 'Wistia',
1611 'uploader': video_uploader,
1612 }
1613
1614 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1615 if match:
1616 return {
1617 '_type': 'url_transparent',
1618 'url': 'wistia:%s' % match.group('id'),
1619 'ie_key': 'Wistia',
1620 'uploader': video_uploader,
1621 }
1622
1623 match = re.search(
1624 r'''(?sx)
1625 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1626 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1627 ''', webpage)
1628 if match:
1629 return self.url_result(self._proto_relative_url(
1630 'wistia:%s' % match.group('id')), 'Wistia')
1631
1632 # Look for SVT player
1633 svt_url = SVTIE._extract_url(webpage)
1634 if svt_url:
1635 return self.url_result(svt_url, 'SVT')
1636
1637 # Look for embedded condenast player
1638 matches = re.findall(
1639 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1640 webpage)
1641 if matches:
1642 return {
1643 '_type': 'playlist',
1644 'entries': [{
1645 '_type': 'url',
1646 'ie_key': 'CondeNast',
1647 'url': ma,
1648 } for ma in matches],
1649 'title': video_title,
1650 'id': video_id,
1651 }
1652
1653 # Look for Bandcamp pages with custom domain
1654 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1655 if mobj is not None:
1656 burl = unescapeHTML(mobj.group(1))
1657 # Don't set the extractor because it can be a track url or an album
1658 return self.url_result(burl)
1659
1660 # Look for embedded Vevo player
1661 mobj = re.search(
1662 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1663 if mobj is not None:
1664 return self.url_result(mobj.group('url'))
1665
1666 # Look for embedded Viddler player
1667 mobj = re.search(
1668 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1669 webpage)
1670 if mobj is not None:
1671 return self.url_result(mobj.group('url'))
1672
1673 # Look for NYTimes player
1674 mobj = re.search(
1675 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1676 webpage)
1677 if mobj is not None:
1678 return self.url_result(mobj.group('url'))
1679
1680 # Look for Libsyn player
1681 mobj = re.search(
1682 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'))
1685
1686 # Look for Ooyala videos
1687 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1688 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1689 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1690 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1691 if mobj is not None:
1692 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1693
1694 # Look for multiple Ooyala embeds on SBN network websites
1695 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1696 if mobj is not None:
1697 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1698 if embeds:
1699 return _playlist_from_matches(
1700 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1701
1702 # Look for Aparat videos
1703 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1704 if mobj is not None:
1705 return self.url_result(mobj.group(1), 'Aparat')
1706
1707 # Look for MPORA videos
1708 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1709 if mobj is not None:
1710 return self.url_result(mobj.group(1), 'Mpora')
1711
1712 # Look for embedded NovaMov-based player
1713 mobj = re.search(
1714 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1715 (?P<url>http://(?:(?:embed|www)\.)?
1716 (?:novamov\.com|
1717 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1718 videoweed\.(?:es|com)|
1719 movshare\.(?:net|sx|ag)|
1720 divxstage\.(?:eu|net|ch|co|at|ag))
1721 /embed\.php.+?)\1''', webpage)
1722 if mobj is not None:
1723 return self.url_result(mobj.group('url'))
1724
1725 # Look for embedded Facebook player
1726 mobj = re.search(
1727 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1728 if mobj is not None:
1729 return self.url_result(mobj.group('url'), 'Facebook')
1730
1731 # Look for embedded VK player
1732 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1733 if mobj is not None:
1734 return self.url_result(mobj.group('url'), 'VK')
1735
1736 # Look for embedded Odnoklassniki player
1737 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1738 if mobj is not None:
1739 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1740
1741 # Look for embedded ivi player
1742 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1743 if mobj is not None:
1744 return self.url_result(mobj.group('url'), 'Ivi')
1745
1746 # Look for embedded Huffington Post player
1747 mobj = re.search(
1748 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1749 if mobj is not None:
1750 return self.url_result(mobj.group('url'), 'HuffPost')
1751
1752 # Look for embed.ly
1753 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1754 if mobj is not None:
1755 return self.url_result(mobj.group('url'))
1756 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1757 if mobj is not None:
1758 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1759
1760 # Look for funnyordie embed
1761 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1762 if matches:
1763 return _playlist_from_matches(
1764 matches, getter=unescapeHTML, ie='FunnyOrDie')
1765
1766 # Look for BBC iPlayer embed
1767 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1768 if matches:
1769 return _playlist_from_matches(matches, ie='BBCCoUk')
1770
1771 # Look for embedded RUTV player
1772 rutv_url = RUTVIE._extract_url(webpage)
1773 if rutv_url:
1774 return self.url_result(rutv_url, 'RUTV')
1775
1776 # Look for embedded TVC player
1777 tvc_url = TVCIE._extract_url(webpage)
1778 if tvc_url:
1779 return self.url_result(tvc_url, 'TVC')
1780
1781 # Look for embedded SportBox player
1782 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1783 if sportbox_urls:
1784 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1785
1786 # Look for embedded PornHub player
1787 pornhub_url = PornHubIE._extract_url(webpage)
1788 if pornhub_url:
1789 return self.url_result(pornhub_url, 'PornHub')
1790
1791 # Look for embedded XHamster player
1792 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1793 if xhamster_urls:
1794 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1795
1796 # Look for embedded TNAFlixNetwork player
1797 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1798 if tnaflix_urls:
1799 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1800
1801 # Look for embedded Tvigle player
1802 mobj = re.search(
1803 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1804 if mobj is not None:
1805 return self.url_result(mobj.group('url'), 'Tvigle')
1806
1807 # Look for embedded TED player
1808 mobj = re.search(
1809 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1810 if mobj is not None:
1811 return self.url_result(mobj.group('url'), 'TED')
1812
1813 # Look for embedded Ustream videos
1814 mobj = re.search(
1815 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1816 if mobj is not None:
1817 return self.url_result(mobj.group('url'), 'Ustream')
1818
1819 # Look for embedded arte.tv player
1820 mobj = re.search(
1821 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1822 webpage)
1823 if mobj is not None:
1824 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1825
1826 # Look for embedded francetv player
1827 mobj = re.search(
1828 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1829 webpage)
1830 if mobj is not None:
1831 return self.url_result(mobj.group('url'))
1832
1833 # Look for embedded smotri.com player
1834 smotri_url = SmotriIE._extract_url(webpage)
1835 if smotri_url:
1836 return self.url_result(smotri_url, 'Smotri')
1837
1838 # Look for embedded Myvi.ru player
1839 myvi_url = MyviIE._extract_url(webpage)
1840 if myvi_url:
1841 return self.url_result(myvi_url)
1842
1843 # Look for embedded soundcloud player
1844 mobj = re.search(
1845 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1846 webpage)
1847 if mobj is not None:
1848 url = unescapeHTML(mobj.group('url'))
1849 return self.url_result(url)
1850
1851 # Look for embedded mtvservices player
1852 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1853 if mtvservices_url:
1854 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1855
1856 # Look for embedded yahoo player
1857 mobj = re.search(
1858 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1859 webpage)
1860 if mobj is not None:
1861 return self.url_result(mobj.group('url'), 'Yahoo')
1862
1863 # Look for embedded sbs.com.au player
1864 mobj = re.search(
1865 r'''(?x)
1866 (?:
1867 <meta\s+property="og:video"\s+content=|
1868 <iframe[^>]+?src=
1869 )
1870 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1871 webpage)
1872 if mobj is not None:
1873 return self.url_result(mobj.group('url'), 'SBS')
1874
1875 # Look for embedded Cinchcast player
1876 mobj = re.search(
1877 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1878 webpage)
1879 if mobj is not None:
1880 return self.url_result(mobj.group('url'), 'Cinchcast')
1881
1882 mobj = re.search(
1883 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1884 webpage)
1885 if not mobj:
1886 mobj = re.search(
1887 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1888 webpage)
1889 if mobj is not None:
1890 return self.url_result(mobj.group('url'), 'MLB')
1891
1892 mobj = re.search(
1893 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1894 webpage)
1895 if mobj is not None:
1896 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1897
1898 mobj = re.search(
1899 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1900 webpage)
1901 if mobj is not None:
1902 return self.url_result(mobj.group('url'), 'Livestream')
1903
1904 # Look for Zapiks embed
1905 mobj = re.search(
1906 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1907 if mobj is not None:
1908 return self.url_result(mobj.group('url'), 'Zapiks')
1909
1910 # Look for Kaltura embeds
1911 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?(?P<q1>['\"])wid(?P=q1)\s*:\s*(?P<q2>['\"])_?(?P<partner_id>[^'\"]+)(?P=q2),.*?(?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*(?P<q4>['\"])(?P<id>[^'\"]+)(?P=q4),", webpage) or
1912 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1913 if mobj is not None:
1914 return self.url_result(smuggle_url(
1915 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1916 {'source_url': url}), 'Kaltura')
1917
1918 # Look for Eagle.Platform embeds
1919 mobj = re.search(
1920 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1921 if mobj is not None:
1922 return self.url_result(mobj.group('url'), 'EaglePlatform')
1923
1924 # Look for ClipYou (uses Eagle.Platform) embeds
1925 mobj = re.search(
1926 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1927 if mobj is not None:
1928 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1929
1930 # Look for Pladform embeds
1931 pladform_url = PladformIE._extract_url(webpage)
1932 if pladform_url:
1933 return self.url_result(pladform_url)
1934
1935 # Look for Videomore embeds
1936 videomore_url = VideomoreIE._extract_url(webpage)
1937 if videomore_url:
1938 return self.url_result(videomore_url)
1939
1940 # Look for Playwire embeds
1941 mobj = re.search(
1942 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1943 if mobj is not None:
1944 return self.url_result(mobj.group('url'))
1945
1946 # Look for 5min embeds
1947 mobj = re.search(
1948 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1949 if mobj is not None:
1950 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1951
1952 # Look for Crooks and Liars embeds
1953 mobj = re.search(
1954 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1955 if mobj is not None:
1956 return self.url_result(mobj.group('url'))
1957
1958 # Look for NBC Sports VPlayer embeds
1959 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1960 if nbc_sports_url:
1961 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1962
1963 # Look for NBC News embeds
1964 nbc_news_embed_url = re.search(
1965 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
1966 if nbc_news_embed_url:
1967 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
1968
1969 # Look for Google Drive embeds
1970 google_drive_url = GoogleDriveIE._extract_url(webpage)
1971 if google_drive_url:
1972 return self.url_result(google_drive_url, 'GoogleDrive')
1973
1974 # Look for UDN embeds
1975 mobj = re.search(
1976 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1977 if mobj is not None:
1978 return self.url_result(
1979 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1980
1981 # Look for Senate ISVP iframe
1982 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1983 if senate_isvp_url:
1984 return self.url_result(senate_isvp_url, 'SenateISVP')
1985
1986 # Look for Dailymotion Cloud videos
1987 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1988 if dmcloud_url:
1989 return self.url_result(dmcloud_url, 'DailymotionCloud')
1990
1991 # Look for OnionStudios embeds
1992 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1993 if onionstudios_url:
1994 return self.url_result(onionstudios_url)
1995
1996 # Look for ViewLift embeds
1997 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1998 if viewlift_url:
1999 return self.url_result(viewlift_url)
2000
2001 # Look for JWPlatform embeds
2002 jwplatform_url = JWPlatformIE._extract_url(webpage)
2003 if jwplatform_url:
2004 return self.url_result(jwplatform_url, 'JWPlatform')
2005
2006 # Look for ScreenwaveMedia embeds
2007 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2008 if mobj is not None:
2009 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2010
2011 # Look for Digiteka embeds
2012 digiteka_url = DigitekaIE._extract_url(webpage)
2013 if digiteka_url:
2014 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2015
2016 # Look for Limelight embeds
2017 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2018 if mobj:
2019 lm = {
2020 'Media': 'media',
2021 'Channel': 'channel',
2022 'ChannelList': 'channel_list',
2023 }
2024 return self.url_result('limelight:%s:%s' % (
2025 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2026
2027 # Look for AdobeTVVideo embeds
2028 mobj = re.search(
2029 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2030 webpage)
2031 if mobj is not None:
2032 return self.url_result(
2033 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2034 'AdobeTVVideo')
2035
2036 # Look for Vine embeds
2037 mobj = re.search(
2038 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2039 webpage)
2040 if mobj is not None:
2041 return self.url_result(
2042 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2043
2044 # Look for Instagram embeds
2045 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2046 if instagram_embed_url is not None:
2047 return self.url_result(
2048 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2049
2050 # Look for LiveLeak embeds
2051 liveleak_url = LiveLeakIE._extract_url(webpage)
2052 if liveleak_url:
2053 return self.url_result(liveleak_url, 'LiveLeak')
2054
2055 # Look for 3Q SDN embeds
2056 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2057 if threeqsdn_url:
2058 return {
2059 '_type': 'url_transparent',
2060 'ie_key': ThreeQSDNIE.ie_key(),
2061 'url': self._proto_relative_url(threeqsdn_url),
2062 'title': video_title,
2063 'description': video_description,
2064 'thumbnail': video_thumbnail,
2065 'uploader': video_uploader,
2066 }
2067
2068 def check_video(vurl):
2069 if YoutubeIE.suitable(vurl):
2070 return True
2071 vpath = compat_urlparse.urlparse(vurl).path
2072 vext = determine_ext(vpath)
2073 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2074
2075 def filter_video(urls):
2076 return list(filter(check_video, urls))
2077
2078 # Start with something easy: JW Player in SWFObject
2079 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2080 if not found:
2081 # Look for gorilla-vid style embedding
2082 found = filter_video(re.findall(r'''(?sx)
2083 (?:
2084 jw_plugins|
2085 JWPlayerOptions|
2086 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2087 )
2088 .*?
2089 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2090 if not found:
2091 # Broaden the search a little bit
2092 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2093 if not found:
2094 # Broaden the findall a little bit: JWPlayer JS loader
2095 found = filter_video(re.findall(
2096 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2097 if not found:
2098 # Flow player
2099 found = filter_video(re.findall(r'''(?xs)
2100 flowplayer\("[^"]+",\s*
2101 \{[^}]+?\}\s*,
2102 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2103 ["']?url["']?\s*:\s*["']([^"']+)["']
2104 ''', webpage))
2105 if not found:
2106 # Cinerama player
2107 found = re.findall(
2108 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2109 if not found:
2110 # Try to find twitter cards info
2111 found = filter_video(re.findall(
2112 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2113 if not found:
2114 # We look for Open Graph info:
2115 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2116 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2117 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2118 if m_video_type is not None:
2119 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2120 if not found:
2121 # HTML5 video
2122 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2123 if not found:
2124 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2125 found = re.search(
2126 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2127 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2128 webpage)
2129 if not found:
2130 # Look also in Refresh HTTP header
2131 refresh_header = head_response.headers.get('Refresh')
2132 if refresh_header:
2133 # In python 2 response HTTP headers are bytestrings
2134 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2135 refresh_header = refresh_header.decode('iso-8859-1')
2136 found = re.search(REDIRECT_REGEX, refresh_header)
2137 if found:
2138 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2139 self.report_following_redirect(new_url)
2140 return {
2141 '_type': 'url',
2142 'url': new_url,
2143 }
2144 if not found:
2145 raise UnsupportedError(url)
2146
2147 entries = []
2148 for video_url in orderedSet(found):
2149 video_url = unescapeHTML(video_url)
2150 video_url = video_url.replace('\\/', '/')
2151 video_url = compat_urlparse.urljoin(url, video_url)
2152 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2153
2154 # Sometimes, jwplayer extraction will result in a YouTube URL
2155 if YoutubeIE.suitable(video_url):
2156 entries.append(self.url_result(video_url, 'Youtube'))
2157 continue
2158
2159 # here's a fun little line of code for you:
2160 video_id = os.path.splitext(video_id)[0]
2161
2162 entry_info_dict = {
2163 'id': video_id,
2164 'uploader': video_uploader,
2165 'title': video_title,
2166 'age_limit': age_limit,
2167 }
2168
2169 ext = determine_ext(video_url)
2170 if ext == 'smil':
2171 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2172 elif ext == 'xspf':
2173 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2174 elif ext == 'm3u8':
2175 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2176 elif ext == 'mpd':
2177 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2178 elif ext == 'f4m':
2179 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2180 else:
2181 entry_info_dict['url'] = video_url
2182
2183 if entry_info_dict.get('formats'):
2184 self._sort_formats(entry_info_dict['formats'])
2185
2186 entries.append(entry_info_dict)
2187
2188 if len(entries) == 1:
2189 return entries[0]
2190 else:
2191 for num, e in enumerate(entries, start=1):
2192 # 'url' results don't have a title
2193 if e.get('title') is not None:
2194 e['title'] = '%s (%d)' % (e['title'], num)
2195 return {
2196 '_type': 'playlist',
2197 'entries': entries,
2198 }