]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[extractor/generic] Add support for openload embeds (closes #11536, closes #11812)
[yt-dlp.git] / youtube_dl / extractor / generic.py
1 # coding: 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 xpath_text,
31 )
32 from .brightcove import (
33 BrightcoveLegacyIE,
34 BrightcoveNewIE,
35 )
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .drtuber import DrTuberIE
51 from .redtube import RedTubeIE
52 from .vimeo import VimeoIE
53 from .dailymotion import (
54 DailymotionIE,
55 DailymotionCloudIE,
56 )
57 from .onionstudios import OnionStudiosIE
58 from .viewlift import ViewLiftEmbedIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .webcaster import WebcasterFeedIE
63 from .googledrive import GoogleDriveIE
64 from .jwplatform import JWPlatformIE
65 from .digiteka import DigitekaIE
66 from .arkena import ArkenaIE
67 from .instagram import InstagramIE
68 from .liveleak import LiveLeakIE
69 from .threeqsdn import ThreeQSDNIE
70 from .theplatform import ThePlatformIE
71 from .vessel import VesselIE
72 from .kaltura import KalturaIE
73 from .eagleplatform import EaglePlatformIE
74 from .facebook import FacebookIE
75 from .soundcloud import SoundcloudIE
76 from .tunein import TuneInBaseIE
77 from .vbox7 import Vbox7IE
78 from .dbtv import DBTVIE
79 from .piksel import PikselIE
80 from .videa import VideaIE
81 from .twentymin import TwentyMinutenIE
82 from .ustream import UstreamIE
83 from .openload import OpenloadIE
84
85
86 class GenericIE(InfoExtractor):
87 IE_DESC = 'Generic downloader that works on some sites'
88 _VALID_URL = r'.*'
89 IE_NAME = 'generic'
90 _TESTS = [
91 # Direct link to a video
92 {
93 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
94 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
95 'info_dict': {
96 'id': 'trailer',
97 'ext': 'mp4',
98 'title': 'trailer',
99 'upload_date': '20100513',
100 }
101 },
102 # Direct link to media delivered compressed (until Accept-Encoding is *)
103 {
104 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
105 'md5': '128c42e68b13950268b648275386fc74',
106 'info_dict': {
107 'id': 'FictionJunction-Parallel_Hearts',
108 'ext': 'flac',
109 'title': 'FictionJunction-Parallel_Hearts',
110 'upload_date': '20140522',
111 },
112 'expected_warnings': [
113 'URL could be a direct video link, returning it as such.'
114 ],
115 'skip': 'URL invalid',
116 },
117 # Direct download with broken HEAD
118 {
119 'url': 'http://ai-radio.org:8000/radio.opus',
120 'info_dict': {
121 'id': 'radio',
122 'ext': 'opus',
123 'title': 'radio',
124 },
125 'params': {
126 'skip_download': True, # infinite live stream
127 },
128 'expected_warnings': [
129 r'501.*Not Implemented',
130 r'400.*Bad Request',
131 ],
132 },
133 # Direct link with incorrect MIME type
134 {
135 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
136 'md5': '4ccbebe5f36706d85221f204d7eb5913',
137 'info_dict': {
138 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
139 'id': '5_Lennart_Poettering_-_Systemd',
140 'ext': 'webm',
141 'title': '5_Lennart_Poettering_-_Systemd',
142 'upload_date': '20141120',
143 },
144 'expected_warnings': [
145 'URL could be a direct video link, returning it as such.'
146 ]
147 },
148 # RSS feed
149 {
150 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
151 'info_dict': {
152 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
153 'title': 'Zero Punctuation',
154 'description': 're:.*groundbreaking video review series.*'
155 },
156 'playlist_mincount': 11,
157 },
158 # RSS feed with enclosure
159 {
160 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
161 'info_dict': {
162 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
163 'ext': 'm4v',
164 'upload_date': '20150228',
165 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
166 }
167 },
168 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
169 {
170 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
171 'info_dict': {
172 'id': 'smil',
173 'ext': 'mp4',
174 'title': 'Automatics, robotics and biocybernetics',
175 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
176 'upload_date': '20130627',
177 'formats': 'mincount:16',
178 'subtitles': 'mincount:1',
179 },
180 'params': {
181 'force_generic_extractor': True,
182 'skip_download': True,
183 },
184 },
185 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
186 {
187 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
188 'info_dict': {
189 'id': 'hds',
190 'ext': 'flv',
191 'title': 'hds',
192 'formats': 'mincount:1',
193 },
194 'params': {
195 'skip_download': True,
196 },
197 },
198 # SMIL from https://www.restudy.dk/video/play/id/1637
199 {
200 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
201 'info_dict': {
202 'id': 'video_1637',
203 'ext': 'flv',
204 'title': 'video_1637',
205 'formats': 'mincount:3',
206 },
207 'params': {
208 'skip_download': True,
209 },
210 },
211 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
212 {
213 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
214 'info_dict': {
215 'id': 'smil-service',
216 'ext': 'flv',
217 'title': 'smil-service',
218 'formats': 'mincount:1',
219 },
220 'params': {
221 'skip_download': True,
222 },
223 },
224 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
225 {
226 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
227 'info_dict': {
228 'id': '4719370',
229 'ext': 'mp4',
230 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
231 'formats': 'mincount:3',
232 },
233 'params': {
234 'skip_download': True,
235 },
236 },
237 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
238 {
239 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
240 'info_dict': {
241 'id': 'mZlp2ctYIUEB',
242 'ext': 'mp4',
243 'title': 'Tikibad ontruimd wegens brand',
244 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
245 'thumbnail': r're:^https?://.*\.jpg$',
246 'duration': 33,
247 },
248 'params': {
249 'skip_download': True,
250 },
251 },
252 # MPD from http://dash-mse-test.appspot.com/media.html
253 {
254 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
255 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
256 'info_dict': {
257 'id': 'car-20120827-manifest',
258 'ext': 'mp4',
259 'title': 'car-20120827-manifest',
260 'formats': 'mincount:9',
261 'upload_date': '20130904',
262 },
263 'params': {
264 'format': 'bestvideo',
265 },
266 },
267 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
268 {
269 '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',
270 'info_dict': {
271 'id': 'content',
272 'ext': 'mp4',
273 'title': 'content',
274 'formats': 'mincount:8',
275 },
276 'params': {
277 # m3u8 downloads
278 'skip_download': True,
279 },
280 'skip': 'video gone',
281 },
282 # m3u8 served with Content-Type: text/plain
283 {
284 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
285 'info_dict': {
286 'id': 'index',
287 'ext': 'mp4',
288 'title': 'index',
289 'upload_date': '20140720',
290 'formats': 'mincount:11',
291 },
292 'params': {
293 # m3u8 downloads
294 'skip_download': True,
295 },
296 'skip': 'video gone',
297 },
298 # google redirect
299 {
300 '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',
301 'info_dict': {
302 'id': 'cmQHVoWB5FY',
303 'ext': 'mp4',
304 'upload_date': '20130224',
305 'uploader_id': 'TheVerge',
306 'description': r're:^Chris Ziegler takes a look at the\.*',
307 'uploader': 'The Verge',
308 'title': 'First Firefox OS phones side-by-side',
309 },
310 'params': {
311 'skip_download': False,
312 }
313 },
314 {
315 # redirect in Refresh HTTP header
316 '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',
317 'info_dict': {
318 'id': 'pO8h3EaFRdo',
319 'ext': 'mp4',
320 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
321 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
322 'upload_date': '20150917',
323 'uploader_id': 'brtvofficial',
324 'uploader': 'Boiler Room',
325 },
326 'params': {
327 'skip_download': False,
328 },
329 },
330 {
331 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
332 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
333 'info_dict': {
334 'id': '13601338388002',
335 'ext': 'mp4',
336 'uploader': 'www.hodiho.fr',
337 'title': 'R\u00e9gis plante sa Jeep',
338 }
339 },
340 # bandcamp page with custom domain
341 {
342 'add_ie': ['Bandcamp'],
343 'url': 'http://bronyrock.com/track/the-pony-mash',
344 'info_dict': {
345 'id': '3235767654',
346 'ext': 'mp3',
347 'title': 'The Pony Mash',
348 'uploader': 'M_Pallante',
349 },
350 'skip': 'There is a limit of 200 free downloads / month for the test song',
351 },
352 {
353 # embedded brightcove video
354 # it also tests brightcove videos that need to set the 'Referer'
355 # in the http requests
356 'add_ie': ['BrightcoveLegacy'],
357 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
358 'info_dict': {
359 'id': '2765128793001',
360 'ext': 'mp4',
361 'title': 'Le cours de bourse : l’analyse technique',
362 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
363 'uploader': 'BFM BUSINESS',
364 },
365 'params': {
366 'skip_download': True,
367 },
368 },
369 {
370 # embedded with itemprop embedURL and video id spelled as `idVideo`
371 'add_id': ['BrightcoveLegacy'],
372 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
373 'info_dict': {
374 'id': '5255628253001',
375 'ext': 'mp4',
376 'title': 'md5:37c519b1128915607601e75a87995fc0',
377 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
378 'uploader': 'BFM BUSINESS',
379 'uploader_id': '876450612001',
380 'timestamp': 1482255315,
381 'upload_date': '20161220',
382 },
383 'params': {
384 'skip_download': True,
385 },
386 },
387 {
388 # https://github.com/rg3/youtube-dl/issues/2253
389 'url': 'http://bcove.me/i6nfkrc3',
390 'md5': '0ba9446db037002366bab3b3eb30c88c',
391 'info_dict': {
392 'id': '3101154703001',
393 'ext': 'mp4',
394 'title': 'Still no power',
395 'uploader': 'thestar.com',
396 '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.',
397 },
398 'add_ie': ['BrightcoveLegacy'],
399 'skip': 'video gone',
400 },
401 {
402 'url': 'http://www.championat.com/video/football/v/87/87499.html',
403 'md5': 'fb973ecf6e4a78a67453647444222983',
404 'info_dict': {
405 'id': '3414141473001',
406 'ext': 'mp4',
407 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
408 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
409 'uploader': 'Championat',
410 },
411 },
412 {
413 # https://github.com/rg3/youtube-dl/issues/3541
414 'add_ie': ['BrightcoveLegacy'],
415 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
416 'info_dict': {
417 'id': '3866516442001',
418 'ext': 'mp4',
419 'title': 'Leer mij vrouwen kennen: Aflevering 1',
420 'description': 'Leer mij vrouwen kennen: Aflevering 1',
421 'uploader': 'SBS Broadcasting',
422 },
423 'skip': 'Restricted to Netherlands',
424 'params': {
425 'skip_download': True, # m3u8 download
426 },
427 },
428 {
429 # Brightcove with alternative playerID key
430 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
431 'info_dict': {
432 'id': 'nmeth.2062_SV1',
433 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
434 },
435 'playlist': [{
436 'info_dict': {
437 'id': '2228375078001',
438 'ext': 'mp4',
439 'title': 'nmeth.2062-sv1',
440 'description': 'nmeth.2062-sv1',
441 'timestamp': 1363357591,
442 'upload_date': '20130315',
443 'uploader': 'Nature Publishing Group',
444 'uploader_id': '1964492299001',
445 },
446 }],
447 },
448 # ooyala video
449 {
450 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
451 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
452 'info_dict': {
453 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
454 'ext': 'mp4',
455 'title': '2cc213299525360.mov', # that's what we get
456 'duration': 238.231,
457 },
458 'add_ie': ['Ooyala'],
459 },
460 {
461 # ooyala video embedded with http://player.ooyala.com/iframe.js
462 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
463 'info_dict': {
464 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
465 'ext': 'mp4',
466 'title': '"Steve Jobs: Man in the Machine" trailer',
467 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
468 'duration': 135.427,
469 },
470 'params': {
471 'skip_download': True,
472 },
473 'skip': 'movie expired',
474 },
475 # embed.ly video
476 {
477 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
478 'info_dict': {
479 'id': '9ODmcdjQcHQ',
480 'ext': 'mp4',
481 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
482 'upload_date': '20140225',
483 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
484 'uploader': 'Tested',
485 'uploader_id': 'testedcom',
486 },
487 # No need to test YoutubeIE here
488 'params': {
489 'skip_download': True,
490 },
491 },
492 # funnyordie embed
493 {
494 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
495 'info_dict': {
496 'id': '18e820ec3f',
497 'ext': 'mp4',
498 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
499 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
500 },
501 # HEAD requests lead to endless 301, while GET is OK
502 'expected_warnings': ['301'],
503 },
504 # RUTV embed
505 {
506 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
507 'info_dict': {
508 'id': '776940',
509 'ext': 'mp4',
510 'title': 'Охотское море стало целиком российским',
511 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
512 },
513 'params': {
514 # m3u8 download
515 'skip_download': True,
516 },
517 },
518 # TVC embed
519 {
520 '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/',
521 'info_dict': {
522 'id': '55304',
523 'ext': 'mp4',
524 'title': 'Дошкольное воспитание',
525 },
526 },
527 # SportBox embed
528 {
529 'url': 'http://www.vestifinance.ru/articles/25753',
530 'info_dict': {
531 'id': '25753',
532 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
533 },
534 'playlist': [{
535 'info_dict': {
536 'id': '370908',
537 'title': 'Госзаказ. День 3',
538 'ext': 'mp4',
539 }
540 }, {
541 'info_dict': {
542 'id': '370905',
543 'title': 'Госзаказ. День 2',
544 'ext': 'mp4',
545 }
546 }, {
547 'info_dict': {
548 'id': '370902',
549 'title': 'Госзаказ. День 1',
550 'ext': 'mp4',
551 }
552 }],
553 'params': {
554 # m3u8 download
555 'skip_download': True,
556 },
557 },
558 # Myvi.ru embed
559 {
560 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
561 'info_dict': {
562 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
563 'ext': 'mp4',
564 'title': 'Ужастики, русский трейлер (2015)',
565 'thumbnail': r're:^https?://.*\.jpg$',
566 'duration': 153,
567 }
568 },
569 # XHamster embed
570 {
571 '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',
572 'info_dict': {
573 'id': 'showthread',
574 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
575 },
576 'playlist_mincount': 7,
577 # This forum does not allow <iframe> syntaxes anymore
578 # Now HTML tags are displayed as-is
579 'skip': 'No videos on this page',
580 },
581 # Embedded TED video
582 {
583 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
584 'md5': '65fdff94098e4a607385a60c5177c638',
585 'info_dict': {
586 'id': '1969',
587 'ext': 'mp4',
588 'title': 'Hidden miracles of the natural world',
589 'uploader': 'Louie Schwartzberg',
590 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
591 }
592 },
593 # nowvideo embed hidden behind percent encoding
594 {
595 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
596 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
597 'info_dict': {
598 'id': '06e53103ca9aa',
599 'ext': 'flv',
600 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
601 'description': 'No description',
602 },
603 },
604 # arte embed
605 {
606 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
607 'md5': '7653032cbb25bf6c80d80f217055fa43',
608 'info_dict': {
609 'id': '048195-004_PLUS7-F',
610 'ext': 'flv',
611 'title': 'X:enius',
612 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
613 'upload_date': '20140320',
614 },
615 'params': {
616 'skip_download': 'Requires rtmpdump'
617 },
618 'skip': 'video gone',
619 },
620 # francetv embed
621 {
622 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
623 'info_dict': {
624 'id': 'EV_30231',
625 'ext': 'mp4',
626 'title': 'Alcaline, le concert avec Calogero',
627 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
628 'upload_date': '20150226',
629 'timestamp': 1424989860,
630 'duration': 5400,
631 },
632 'params': {
633 # m3u8 downloads
634 'skip_download': True,
635 },
636 'expected_warnings': [
637 'Forbidden'
638 ]
639 },
640 # Condé Nast embed
641 {
642 'url': 'http://www.wired.com/2014/04/honda-asimo/',
643 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
644 'info_dict': {
645 'id': '53501be369702d3275860000',
646 'ext': 'mp4',
647 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
648 }
649 },
650 # Dailymotion embed
651 {
652 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
653 'md5': '441aeeb82eb72c422c7f14ec533999cd',
654 'info_dict': {
655 'id': 'k2mm4bCdJ6CQ2i7c8o2',
656 'ext': 'mp4',
657 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
658 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
659 'uploader': 'Spi0n',
660 'uploader_id': 'xgditw',
661 'upload_date': '20140425',
662 'timestamp': 1398441542,
663 },
664 'add_ie': ['Dailymotion'],
665 },
666 # YouTube embed
667 {
668 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
669 'info_dict': {
670 'id': 'FXRb4ykk4S0',
671 'ext': 'mp4',
672 'title': 'The NBL Auction 2014',
673 'uploader': 'BADMINTON England',
674 'uploader_id': 'BADMINTONEvents',
675 'upload_date': '20140603',
676 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
677 },
678 'add_ie': ['Youtube'],
679 'params': {
680 'skip_download': True,
681 }
682 },
683 # MTVSercices embed
684 {
685 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
686 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
687 'info_dict': {
688 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
689 'ext': 'mp4',
690 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
691 'description': 'Two valets share their love for movie star Liam Neesons.',
692 'timestamp': 1349922600,
693 'upload_date': '20121011',
694 },
695 },
696 # YouTube embed via <data-embed-url="">
697 {
698 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
699 'info_dict': {
700 'id': '4vAffPZIT44',
701 'ext': 'mp4',
702 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
703 'uploader': 'Gameloft',
704 'uploader_id': 'gameloft',
705 'upload_date': '20140828',
706 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
707 },
708 'params': {
709 'skip_download': True,
710 }
711 },
712 # Camtasia studio
713 {
714 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
715 'playlist': [{
716 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
717 'info_dict': {
718 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
719 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
720 'ext': 'flv',
721 'duration': 2235.90,
722 }
723 }, {
724 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
725 'info_dict': {
726 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
727 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
728 'ext': 'flv',
729 'duration': 2235.93,
730 }
731 }],
732 'info_dict': {
733 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
734 }
735 },
736 # Flowplayer
737 {
738 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
739 'md5': '9d65602bf31c6e20014319c7d07fba27',
740 'info_dict': {
741 'id': '5123ea6d5e5a7',
742 'ext': 'mp4',
743 'age_limit': 18,
744 'uploader': 'www.handjobhub.com',
745 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
746 }
747 },
748 # Multiple brightcove videos
749 # https://github.com/rg3/youtube-dl/issues/2283
750 {
751 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
752 'info_dict': {
753 'id': 'always-never',
754 'title': 'Always / Never - The New Yorker',
755 },
756 'playlist_count': 3,
757 'params': {
758 'extract_flat': False,
759 'skip_download': True,
760 }
761 },
762 # MLB embed
763 {
764 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
765 'md5': '96f09a37e44da40dd083e12d9a683327',
766 'info_dict': {
767 'id': '33322633',
768 'ext': 'mp4',
769 'title': 'Ump changes call to ball',
770 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
771 'duration': 48,
772 'timestamp': 1401537900,
773 'upload_date': '20140531',
774 'thumbnail': r're:^https?://.*\.jpg$',
775 },
776 },
777 # Wistia embed
778 {
779 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
780 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
781 'info_dict': {
782 'id': '6e2wtrbdaf',
783 'ext': 'mov',
784 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
785 'description': 'a Paywall Videos video from Remilon',
786 'duration': 644.072,
787 'uploader': 'study.com',
788 'timestamp': 1459678540,
789 'upload_date': '20160403',
790 'filesize': 24687186,
791 },
792 },
793 {
794 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
795 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
796 'info_dict': {
797 'id': 'uxjb0lwrcz',
798 'ext': 'mp4',
799 'title': 'Conversation about Hexagonal Rails Part 1',
800 'description': 'a Martin Fowler video from ThoughtWorks',
801 'duration': 1715.0,
802 'uploader': 'thoughtworks.wistia.com',
803 'timestamp': 1401832161,
804 'upload_date': '20140603',
805 },
806 },
807 # Wistia standard embed (async)
808 {
809 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
810 'info_dict': {
811 'id': '807fafadvk',
812 'ext': 'mp4',
813 'title': 'Drip Brennan Dunn Workshop',
814 'description': 'a JV Webinars video from getdrip-1',
815 'duration': 4986.95,
816 'timestamp': 1463607249,
817 'upload_date': '20160518',
818 },
819 'params': {
820 'skip_download': True,
821 }
822 },
823 # Soundcloud embed
824 {
825 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
826 'info_dict': {
827 'id': '174391317',
828 'ext': 'mp3',
829 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
830 'uploader': 'Sophos Security',
831 'title': 'Chet Chat 171 - Oct 29, 2014',
832 'upload_date': '20141029',
833 }
834 },
835 # Soundcloud multiple embeds
836 {
837 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
838 'info_dict': {
839 'id': '52809',
840 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
841 },
842 'playlist_mincount': 7,
843 },
844 # TuneIn station embed
845 {
846 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
847 'info_dict': {
848 'id': '204146',
849 'ext': 'mp3',
850 'title': 'CNRV',
851 'location': 'Paris, France',
852 'is_live': True,
853 },
854 'params': {
855 # Live stream
856 'skip_download': True,
857 },
858 },
859 # Livestream embed
860 {
861 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
862 'info_dict': {
863 'id': '67864563',
864 'ext': 'flv',
865 'upload_date': '20141112',
866 'title': 'Rosetta #CometLanding webcast HL 10',
867 }
868 },
869 # Another Livestream embed, without 'new.' in URL
870 {
871 'url': 'https://www.freespeech.org/',
872 'info_dict': {
873 'id': '123537347',
874 'ext': 'mp4',
875 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
876 },
877 'params': {
878 # Live stream
879 'skip_download': True,
880 },
881 },
882 # LazyYT
883 {
884 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
885 'info_dict': {
886 'id': '1986',
887 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
888 },
889 'playlist_mincount': 2,
890 },
891 # Cinchcast embed
892 {
893 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
894 'info_dict': {
895 'id': '7141703',
896 'ext': 'mp3',
897 'upload_date': '20141126',
898 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
899 }
900 },
901 # Cinerama player
902 {
903 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
904 'info_dict': {
905 'id': '730m_DandD_1901_512k',
906 'ext': 'mp4',
907 'uploader': 'www.abc.net.au',
908 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
909 }
910 },
911 # embedded viddler video
912 {
913 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
914 'info_dict': {
915 'id': '4d03aad9',
916 'ext': 'mp4',
917 'uploader': 'deadspin',
918 'title': 'WALL-TO-GORTAT',
919 'timestamp': 1422285291,
920 'upload_date': '20150126',
921 },
922 'add_ie': ['Viddler'],
923 },
924 # Libsyn embed
925 {
926 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
927 'info_dict': {
928 'id': '3377616',
929 'ext': 'mp3',
930 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
931 'description': 'md5:601cb790edd05908957dae8aaa866465',
932 'upload_date': '20150220',
933 },
934 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
935 },
936 # jwplayer YouTube
937 {
938 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
939 'info_dict': {
940 'id': 'Mrj4DVp2zeA',
941 'ext': 'mp4',
942 'upload_date': '20150212',
943 'uploader': 'The National Archives UK',
944 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
945 'uploader_id': 'NationalArchives08',
946 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
947 },
948 },
949 # rtl.nl embed
950 {
951 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
952 'playlist_mincount': 5,
953 'info_dict': {
954 'id': 'aanslagen-kopenhagen',
955 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
956 }
957 },
958 # Zapiks embed
959 {
960 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
961 'info_dict': {
962 'id': '118046',
963 'ext': 'mp4',
964 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
965 }
966 },
967 # Kaltura embed (different embed code)
968 {
969 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
970 'info_dict': {
971 'id': '1_a52wc67y',
972 'ext': 'flv',
973 'upload_date': '20150127',
974 'uploader_id': 'PremierMedia',
975 'timestamp': int,
976 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
977 },
978 },
979 # Kaltura embed protected with referrer
980 {
981 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
982 'info_dict': {
983 'id': '1_g4fbemnq',
984 'ext': 'mp4',
985 'title': 'Violetta - Achter De Schermen - Ruggero',
986 'description': 'Achter de schermen met Ruggero',
987 'timestamp': 1435133761,
988 'upload_date': '20150624',
989 'uploader_id': 'echojecka',
990 },
991 },
992 # Kaltura embed with single quotes
993 {
994 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
995 'info_dict': {
996 'id': '0_izeg5utt',
997 'ext': 'mp4',
998 'title': '35871',
999 'timestamp': 1355743100,
1000 'upload_date': '20121217',
1001 'uploader_id': 'batchUser',
1002 },
1003 'add_ie': ['Kaltura'],
1004 },
1005 {
1006 # Kaltura embedded via quoted entry_id
1007 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1008 'info_dict': {
1009 'id': '0_utuok90b',
1010 'ext': 'mp4',
1011 'title': '06_matthew_brender_raj_dutt',
1012 'timestamp': 1466638791,
1013 'upload_date': '20160622',
1014 },
1015 'add_ie': ['Kaltura'],
1016 'expected_warnings': [
1017 'Could not send HEAD request'
1018 ],
1019 'params': {
1020 'skip_download': True,
1021 }
1022 },
1023 {
1024 # Kaltura embedded, some fileExt broken (#11480)
1025 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1026 'info_dict': {
1027 'id': '1_sgtvehim',
1028 'ext': 'mp4',
1029 'title': 'Our "Standard Models" of particle physics and cosmology',
1030 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1031 'timestamp': 1321158993,
1032 'upload_date': '20111113',
1033 'uploader_id': 'kps1',
1034 },
1035 'add_ie': ['Kaltura'],
1036 },
1037 # Eagle.Platform embed (generic URL)
1038 {
1039 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1040 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1041 'info_dict': {
1042 'id': '227304',
1043 'ext': 'mp4',
1044 'title': 'Навальный вышел на свободу',
1045 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1046 'thumbnail': r're:^https?://.*\.jpg$',
1047 'duration': 87,
1048 'view_count': int,
1049 'age_limit': 0,
1050 },
1051 },
1052 # ClipYou (Eagle.Platform) embed (custom URL)
1053 {
1054 'url': 'http://muz-tv.ru/play/7129/',
1055 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1056 'info_dict': {
1057 'id': '12820',
1058 'ext': 'mp4',
1059 'title': "'O Sole Mio",
1060 'thumbnail': r're:^https?://.*\.jpg$',
1061 'duration': 216,
1062 'view_count': int,
1063 },
1064 },
1065 # Pladform embed
1066 {
1067 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1068 'info_dict': {
1069 'id': '100183293',
1070 'ext': 'mp4',
1071 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1072 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1073 'thumbnail': r're:^https?://.*\.jpg$',
1074 'duration': 694,
1075 'age_limit': 0,
1076 },
1077 },
1078 # Playwire embed
1079 {
1080 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1081 'info_dict': {
1082 'id': '3519514',
1083 'ext': 'mp4',
1084 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1085 'thumbnail': r're:^https?://.*\.png$',
1086 'duration': 45.115,
1087 },
1088 },
1089 # 5min embed
1090 {
1091 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1092 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1093 'info_dict': {
1094 'id': '518726732',
1095 'ext': 'mp4',
1096 'title': 'Facebook Creates "On This Day" | Crunch Report',
1097 },
1098 },
1099 # SVT embed
1100 {
1101 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1102 'info_dict': {
1103 'id': '2900353',
1104 'ext': 'flv',
1105 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1106 'duration': 27,
1107 'age_limit': 0,
1108 },
1109 },
1110 # Crooks and Liars embed
1111 {
1112 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1113 'info_dict': {
1114 'id': '8RUoRhRi',
1115 'ext': 'mp4',
1116 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1117 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1118 'timestamp': 1428207000,
1119 'upload_date': '20150405',
1120 'uploader': 'Heather',
1121 },
1122 },
1123 # Crooks and Liars external embed
1124 {
1125 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1126 'info_dict': {
1127 'id': 'MTE3MjUtMzQ2MzA',
1128 'ext': 'mp4',
1129 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1130 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1131 'timestamp': 1265032391,
1132 'upload_date': '20100201',
1133 'uploader': 'Heather',
1134 },
1135 },
1136 # NBC Sports vplayer embed
1137 {
1138 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1139 'info_dict': {
1140 'id': 'ln7x1qSThw4k',
1141 'ext': 'flv',
1142 'title': "PFT Live: New leader in the 'new-look' defense",
1143 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1144 'uploader': 'NBCU-SPORTS',
1145 'upload_date': '20140107',
1146 'timestamp': 1389118457,
1147 },
1148 },
1149 # NBC News embed
1150 {
1151 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1152 'md5': '1aa589c675898ae6d37a17913cf68d66',
1153 'info_dict': {
1154 'id': '701714499682',
1155 'ext': 'mp4',
1156 'title': 'PREVIEW: On Assignment: David Letterman',
1157 '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.',
1158 },
1159 },
1160 # UDN embed
1161 {
1162 'url': 'https://video.udn.com/news/300346',
1163 'md5': 'fd2060e988c326991037b9aff9df21a6',
1164 'info_dict': {
1165 'id': '300346',
1166 'ext': 'mp4',
1167 'title': '中一中男師變性 全校師生力挺',
1168 'thumbnail': r're:^https?://.*\.jpg$',
1169 },
1170 'params': {
1171 # m3u8 download
1172 'skip_download': True,
1173 },
1174 },
1175 # Ooyala embed
1176 {
1177 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1178 'info_dict': {
1179 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1180 'ext': 'mp4',
1181 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1182 'title': 'This is what separates the Excel masters from the wannabes',
1183 'duration': 191.933,
1184 },
1185 'params': {
1186 # m3u8 downloads
1187 'skip_download': True,
1188 }
1189 },
1190 # Brightcove URL in single quotes
1191 {
1192 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1193 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1194 'info_dict': {
1195 'id': '4255764656001',
1196 'ext': 'mp4',
1197 'title': 'SN Presents: Russell Martin, World Citizen',
1198 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1199 'uploader': 'Rogers Sportsnet',
1200 'uploader_id': '1704050871',
1201 'upload_date': '20150525',
1202 'timestamp': 1432570283,
1203 },
1204 },
1205 # Dailymotion Cloud video
1206 {
1207 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1208 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1209 'info_dict': {
1210 'id': 'x2uy8t3',
1211 'ext': 'mp4',
1212 'title': 'Sauvons les abeilles ! - Le débat',
1213 'description': 'md5:d9082128b1c5277987825d684939ca26',
1214 'thumbnail': r're:^https?://.*\.jpe?g$',
1215 'timestamp': 1434970506,
1216 'upload_date': '20150622',
1217 'uploader': 'Public Sénat',
1218 'uploader_id': 'xa9gza',
1219 }
1220 },
1221 # OnionStudios embed
1222 {
1223 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1224 'info_dict': {
1225 'id': '2855',
1226 'ext': 'mp4',
1227 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1228 'thumbnail': r're:^https?://.*\.jpe?g$',
1229 'uploader': 'ClickHole',
1230 'uploader_id': 'clickhole',
1231 }
1232 },
1233 # SnagFilms embed
1234 {
1235 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1236 'info_dict': {
1237 'id': '74849a00-85a9-11e1-9660-123139220831',
1238 'ext': 'mp4',
1239 'title': '#whilewewatch',
1240 }
1241 },
1242 # AdobeTVVideo embed
1243 {
1244 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1245 'md5': '43662b577c018ad707a63766462b1e87',
1246 'info_dict': {
1247 'id': '2456',
1248 'ext': 'mp4',
1249 'title': 'New experience with Acrobat DC',
1250 'description': 'New experience with Acrobat DC',
1251 'duration': 248.667,
1252 },
1253 },
1254 # BrightcoveInPageEmbed embed
1255 {
1256 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1257 'info_dict': {
1258 'id': '4238694884001',
1259 'ext': 'flv',
1260 'title': 'Tabletop: Dread, Last Thoughts',
1261 'description': 'Tabletop: Dread, Last Thoughts',
1262 'duration': 51690,
1263 },
1264 },
1265 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1266 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1267 {
1268 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1269 'info_dict': {
1270 'id': '4785848093001',
1271 'ext': 'mp4',
1272 'title': 'The Cardinal Pell Interview',
1273 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1274 'uploader': 'GlobeCast Australia - GlobeStream',
1275 'uploader_id': '2733773828001',
1276 'upload_date': '20160304',
1277 'timestamp': 1457083087,
1278 },
1279 'params': {
1280 # m3u8 downloads
1281 'skip_download': True,
1282 },
1283 },
1284 # Another form of arte.tv embed
1285 {
1286 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1287 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1288 'info_dict': {
1289 'id': '030273-562_PLUS7-F',
1290 'ext': 'mp4',
1291 'title': 'ARTE Reportage - Nulle part, en France',
1292 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1293 'upload_date': '20160409',
1294 },
1295 },
1296 # LiveLeak embed
1297 {
1298 'url': 'http://www.wykop.pl/link/3088787/',
1299 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1300 'info_dict': {
1301 'id': '874_1459135191',
1302 'ext': 'mp4',
1303 'title': 'Man shows poor quality of new apartment building',
1304 'description': 'The wall is like a sand pile.',
1305 'uploader': 'Lake8737',
1306 }
1307 },
1308 # Duplicated embedded video URLs
1309 {
1310 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1311 'info_dict': {
1312 'id': '149298443_480_16c25b74_2',
1313 'ext': 'mp4',
1314 'title': 'vs. Blue Orange Spring Game',
1315 'uploader': 'www.hudl.com',
1316 },
1317 },
1318 # twitter:player:stream embed
1319 {
1320 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1321 'info_dict': {
1322 'id': 'master',
1323 'ext': 'mp4',
1324 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1325 'uploader': 'www.rtl.be',
1326 },
1327 'params': {
1328 # m3u8 downloads
1329 'skip_download': True,
1330 },
1331 },
1332 # twitter:player embed
1333 {
1334 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1335 'md5': 'a3e0df96369831de324f0778e126653c',
1336 'info_dict': {
1337 'id': '4909620399001',
1338 'ext': 'mp4',
1339 'title': 'What Do Black Holes Sound Like?',
1340 'description': 'what do black holes sound like',
1341 'upload_date': '20160524',
1342 'uploader_id': '29913724001',
1343 'timestamp': 1464107587,
1344 'uploader': 'TheAtlantic',
1345 },
1346 'add_ie': ['BrightcoveLegacy'],
1347 },
1348 # Facebook <iframe> embed
1349 {
1350 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1351 'md5': 'fbcde74f534176ecb015849146dd3aee',
1352 'info_dict': {
1353 'id': '599637780109885',
1354 'ext': 'mp4',
1355 'title': 'Facebook video #599637780109885',
1356 },
1357 },
1358 # Facebook API embed
1359 {
1360 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1361 'md5': 'a47372ee61b39a7b90287094d447d94e',
1362 'info_dict': {
1363 'id': '10153467542406923',
1364 'ext': 'mp4',
1365 'title': 'Facebook video #10153467542406923',
1366 },
1367 },
1368 # Wordpress "YouTube Video Importer" plugin
1369 {
1370 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1371 'md5': 'd16797741b560b485194eddda8121b48',
1372 'info_dict': {
1373 'id': 'HNTXWDXV9Is',
1374 'ext': 'mp4',
1375 'title': 'Blue Devils Drumline Stanford lot 2016',
1376 'upload_date': '20160627',
1377 'uploader_id': 'GENOCIDE8GENERAL10',
1378 'uploader': 'cylus cyrus',
1379 },
1380 },
1381 {
1382 # video stored on custom kaltura server
1383 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1384 'md5': '537617d06e64dfed891fa1593c4b30cc',
1385 'info_dict': {
1386 'id': '0_1iotm5bh',
1387 'ext': 'mp4',
1388 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1389 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1390 'uploader_id': 'videos.expansion@el-mundo.net',
1391 'upload_date': '20150429',
1392 'timestamp': 1430303472,
1393 },
1394 'add_ie': ['Kaltura'],
1395 },
1396 {
1397 # Non-standard Vimeo embed
1398 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1399 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1400 'info_dict': {
1401 'id': '148867247',
1402 'ext': 'mp4',
1403 'title': 'Understanding the web - Teaser',
1404 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1405 'upload_date': '20151214',
1406 'uploader': 'OpenClassrooms',
1407 'uploader_id': 'openclassrooms',
1408 },
1409 'add_ie': ['Vimeo'],
1410 },
1411 {
1412 # generic vimeo embed that requires original URL passed as Referer
1413 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1414 'only_matching': True,
1415 },
1416 {
1417 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1418 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1419 'info_dict': {
1420 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1421 'ext': 'mp4',
1422 'title': 'Big Buck Bunny',
1423 'description': 'Royalty free test video',
1424 'timestamp': 1432816365,
1425 'upload_date': '20150528',
1426 'is_live': False,
1427 },
1428 'params': {
1429 'skip_download': True,
1430 },
1431 'add_ie': [ArkenaIE.ie_key()],
1432 },
1433 {
1434 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1435 'info_dict': {
1436 'id': '1c7141f46c',
1437 'ext': 'mp4',
1438 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1439 },
1440 'params': {
1441 'skip_download': True,
1442 },
1443 'add_ie': [Vbox7IE.ie_key()],
1444 },
1445 {
1446 # DBTV embeds
1447 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1448 'info_dict': {
1449 'id': '43254897',
1450 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1451 },
1452 'playlist_mincount': 3,
1453 },
1454 {
1455 # Videa embeds
1456 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1457 'info_dict': {
1458 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1459 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1460 },
1461 'playlist_mincount': 2,
1462 },
1463 {
1464 # 20 minuten embed
1465 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1466 'info_dict': {
1467 'id': '523629',
1468 'ext': 'mp4',
1469 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1470 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1471 },
1472 'params': {
1473 'skip_download': True,
1474 },
1475 'add_ie': [TwentyMinutenIE.ie_key()],
1476 }
1477 # {
1478 # # TODO: find another test
1479 # # http://schema.org/VideoObject
1480 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1481 # 'md5': '888dcf08b7ea671381f00fab74692755',
1482 # 'info_dict': {
1483 # 'id': 'nyvTSJMKId',
1484 # 'ext': 'mp4',
1485 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1486 # 'description': '#love for cats.',
1487 # 'timestamp': 1461244995,
1488 # 'upload_date': '20160421',
1489 # },
1490 # 'params': {
1491 # 'force_generic_extractor': True,
1492 # },
1493 # }
1494 ]
1495
1496 def report_following_redirect(self, new_url):
1497 """Report information extraction."""
1498 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1499
1500 def _extract_rss(self, url, video_id, doc):
1501 playlist_title = doc.find('./channel/title').text
1502 playlist_desc_el = doc.find('./channel/description')
1503 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1504
1505 entries = []
1506 for it in doc.findall('./channel/item'):
1507 next_url = xpath_text(it, 'link', fatal=False)
1508 if not next_url:
1509 enclosure_nodes = it.findall('./enclosure')
1510 for e in enclosure_nodes:
1511 next_url = e.attrib.get('url')
1512 if next_url:
1513 break
1514
1515 if not next_url:
1516 continue
1517
1518 entries.append({
1519 '_type': 'url',
1520 'url': next_url,
1521 'title': it.find('title').text,
1522 })
1523
1524 return {
1525 '_type': 'playlist',
1526 'id': url,
1527 'title': playlist_title,
1528 'description': playlist_desc,
1529 'entries': entries,
1530 }
1531
1532 def _extract_camtasia(self, url, video_id, webpage):
1533 """ Returns None if no camtasia video can be found. """
1534
1535 camtasia_cfg = self._search_regex(
1536 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1537 webpage, 'camtasia configuration file', default=None)
1538 if camtasia_cfg is None:
1539 return None
1540
1541 title = self._html_search_meta('DC.title', webpage, fatal=True)
1542
1543 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1544 camtasia_cfg = self._download_xml(
1545 camtasia_url, video_id,
1546 note='Downloading camtasia configuration',
1547 errnote='Failed to download camtasia configuration')
1548 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1549
1550 entries = []
1551 for n in fileset_node.getchildren():
1552 url_n = n.find('./uri')
1553 if url_n is None:
1554 continue
1555
1556 entries.append({
1557 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1558 'title': '%s - %s' % (title, n.tag),
1559 'url': compat_urlparse.urljoin(url, url_n.text),
1560 'duration': float_or_none(n.find('./duration').text),
1561 })
1562
1563 return {
1564 '_type': 'playlist',
1565 'entries': entries,
1566 'title': title,
1567 }
1568
1569 def _real_extract(self, url):
1570 if url.startswith('//'):
1571 return {
1572 '_type': 'url',
1573 'url': self.http_scheme() + url,
1574 }
1575
1576 parsed_url = compat_urlparse.urlparse(url)
1577 if not parsed_url.scheme:
1578 default_search = self._downloader.params.get('default_search')
1579 if default_search is None:
1580 default_search = 'fixup_error'
1581
1582 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1583 if '/' in url:
1584 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1585 return self.url_result('http://' + url)
1586 elif default_search != 'fixup_error':
1587 if default_search == 'auto_warning':
1588 if re.match(r'^(?:url|URL)$', url):
1589 raise ExtractorError(
1590 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1591 expected=True)
1592 else:
1593 self._downloader.report_warning(
1594 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1595 return self.url_result('ytsearch:' + url)
1596
1597 if default_search in ('error', 'fixup_error'):
1598 raise ExtractorError(
1599 '%r is not a valid URL. '
1600 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1601 % (url, url), expected=True)
1602 else:
1603 if ':' not in default_search:
1604 default_search += ':'
1605 return self.url_result(default_search + url)
1606
1607 url, smuggled_data = unsmuggle_url(url)
1608 force_videoid = None
1609 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1610 if smuggled_data and 'force_videoid' in smuggled_data:
1611 force_videoid = smuggled_data['force_videoid']
1612 video_id = force_videoid
1613 else:
1614 video_id = self._generic_id(url)
1615
1616 self.to_screen('%s: Requesting header' % video_id)
1617
1618 head_req = HEADRequest(url)
1619 head_response = self._request_webpage(
1620 head_req, video_id,
1621 note=False, errnote='Could not send HEAD request to %s' % url,
1622 fatal=False)
1623
1624 if head_response is not False:
1625 # Check for redirect
1626 new_url = head_response.geturl()
1627 if url != new_url:
1628 self.report_following_redirect(new_url)
1629 if force_videoid:
1630 new_url = smuggle_url(
1631 new_url, {'force_videoid': force_videoid})
1632 return self.url_result(new_url)
1633
1634 full_response = None
1635 if head_response is False:
1636 request = sanitized_Request(url)
1637 request.add_header('Accept-Encoding', '*')
1638 full_response = self._request_webpage(request, video_id)
1639 head_response = full_response
1640
1641 info_dict = {
1642 'id': video_id,
1643 'title': self._generic_title(url),
1644 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1645 }
1646
1647 # Check for direct link to a video
1648 content_type = head_response.headers.get('Content-Type', '').lower()
1649 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1650 if m:
1651 format_id = m.group('format_id')
1652 if format_id.endswith('mpegurl'):
1653 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1654 elif format_id == 'f4m':
1655 formats = self._extract_f4m_formats(url, video_id)
1656 else:
1657 formats = [{
1658 'format_id': m.group('format_id'),
1659 'url': url,
1660 'vcodec': 'none' if m.group('type') == 'audio' else None
1661 }]
1662 info_dict['direct'] = True
1663 self._sort_formats(formats)
1664 info_dict['formats'] = formats
1665 return info_dict
1666
1667 if not self._downloader.params.get('test', False) and not is_intentional:
1668 force = self._downloader.params.get('force_generic_extractor', False)
1669 self._downloader.report_warning(
1670 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1671
1672 if not full_response:
1673 request = sanitized_Request(url)
1674 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1675 # making it impossible to download only chunk of the file (yet we need only 512kB to
1676 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1677 # that will always result in downloading the whole file that is not desirable.
1678 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1679 # to accept raw bytes and being able to download only a chunk.
1680 # It may probably better to solve this by checking Content-Type for application/octet-stream
1681 # after HEAD request finishes, but not sure if we can rely on this.
1682 request.add_header('Accept-Encoding', '*')
1683 full_response = self._request_webpage(request, video_id)
1684
1685 first_bytes = full_response.read(512)
1686
1687 # Is it an M3U playlist?
1688 if first_bytes.startswith(b'#EXTM3U'):
1689 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1690 self._sort_formats(info_dict['formats'])
1691 return info_dict
1692
1693 # Maybe it's a direct link to a video?
1694 # Be careful not to download the whole thing!
1695 if not is_html(first_bytes):
1696 self._downloader.report_warning(
1697 'URL could be a direct video link, returning it as such.')
1698 info_dict.update({
1699 'direct': True,
1700 'url': url,
1701 })
1702 return info_dict
1703
1704 webpage = self._webpage_read_content(
1705 full_response, url, video_id, prefix=first_bytes)
1706
1707 self.report_extraction(video_id)
1708
1709 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1710 try:
1711 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1712 if doc.tag == 'rss':
1713 return self._extract_rss(url, video_id, doc)
1714 elif doc.tag == 'SmoothStreamingMedia':
1715 info_dict['formats'] = self._parse_ism_formats(doc, url)
1716 self._sort_formats(info_dict['formats'])
1717 return info_dict
1718 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1719 smil = self._parse_smil(doc, url, video_id)
1720 self._sort_formats(smil['formats'])
1721 return smil
1722 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1723 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1724 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1725 info_dict['formats'] = self._parse_mpd_formats(
1726 doc, video_id,
1727 mpd_base_url=full_response.geturl().rpartition('/')[0],
1728 mpd_url=url)
1729 self._sort_formats(info_dict['formats'])
1730 return info_dict
1731 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1732 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1733 self._sort_formats(info_dict['formats'])
1734 return info_dict
1735 except compat_xml_parse_error:
1736 pass
1737
1738 # Is it a Camtasia project?
1739 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1740 if camtasia_res is not None:
1741 return camtasia_res
1742
1743 # Sometimes embedded video player is hidden behind percent encoding
1744 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1745 # Unescaping the whole page allows to handle those cases in a generic way
1746 webpage = compat_urllib_parse_unquote(webpage)
1747
1748 # it's tempting to parse this further, but you would
1749 # have to take into account all the variations like
1750 # Video Title - Site Name
1751 # Site Name | Video Title
1752 # Video Title - Tagline | Site Name
1753 # and so on and so forth; it's just not practical
1754 video_title = self._og_search_title(
1755 webpage, default=None) or self._html_search_regex(
1756 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1757 default='video')
1758
1759 # Try to detect age limit automatically
1760 age_limit = self._rta_search(webpage)
1761 # And then there are the jokers who advertise that they use RTA,
1762 # but actually don't.
1763 AGE_LIMIT_MARKERS = [
1764 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1765 ]
1766 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1767 age_limit = 18
1768
1769 # video uploader is domain name
1770 video_uploader = self._search_regex(
1771 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1772
1773 video_description = self._og_search_description(webpage, default=None)
1774 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1775
1776 # Helper method
1777 def _playlist_from_matches(matches, getter=None, ie=None):
1778 urlrs = orderedSet(
1779 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1780 for m in matches)
1781 return self.playlist_result(
1782 urlrs, playlist_id=video_id, playlist_title=video_title)
1783
1784 # Look for Brightcove Legacy Studio embeds
1785 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1786 if bc_urls:
1787 self.to_screen('Brightcove video detected.')
1788 entries = [{
1789 '_type': 'url',
1790 'url': smuggle_url(bc_url, {'Referer': url}),
1791 'ie_key': 'BrightcoveLegacy'
1792 } for bc_url in bc_urls]
1793
1794 return {
1795 '_type': 'playlist',
1796 'title': video_title,
1797 'id': video_id,
1798 'entries': entries,
1799 }
1800
1801 # Look for Brightcove New Studio embeds
1802 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1803 if bc_urls:
1804 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1805
1806 # Look for ThePlatform embeds
1807 tp_urls = ThePlatformIE._extract_urls(webpage)
1808 if tp_urls:
1809 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1810
1811 # Look for Vessel embeds
1812 vessel_urls = VesselIE._extract_urls(webpage)
1813 if vessel_urls:
1814 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1815
1816 # Look for embedded rtl.nl player
1817 matches = re.findall(
1818 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1819 webpage)
1820 if matches:
1821 return _playlist_from_matches(matches, ie='RtlNl')
1822
1823 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1824 if vimeo_urls:
1825 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1826
1827 vid_me_embed_url = self._search_regex(
1828 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1829 webpage, 'vid.me embed', default=None)
1830 if vid_me_embed_url is not None:
1831 return self.url_result(vid_me_embed_url, 'Vidme')
1832
1833 # Look for embedded YouTube player
1834 matches = re.findall(r'''(?x)
1835 (?:
1836 <iframe[^>]+?src=|
1837 data-video-url=|
1838 <embed[^>]+?src=|
1839 embedSWF\(?:\s*|
1840 new\s+SWFObject\(
1841 )
1842 (["\'])
1843 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1844 (?:embed|v|p)/.+?)
1845 \1''', webpage)
1846 if matches:
1847 return _playlist_from_matches(
1848 matches, lambda m: unescapeHTML(m[1]))
1849
1850 # Look for lazyYT YouTube embed
1851 matches = re.findall(
1852 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1853 if matches:
1854 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1855
1856 # Look for Wordpress "YouTube Video Importer" plugin
1857 matches = re.findall(r'''(?x)<div[^>]+
1858 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1859 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1860 if matches:
1861 return _playlist_from_matches(matches, lambda m: m[-1])
1862
1863 matches = DailymotionIE._extract_urls(webpage)
1864 if matches:
1865 return _playlist_from_matches(matches)
1866
1867 # Look for embedded Dailymotion playlist player (#3822)
1868 m = re.search(
1869 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1870 if m:
1871 playlists = re.findall(
1872 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1873 if playlists:
1874 return _playlist_from_matches(
1875 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1876
1877 # Look for embedded Wistia player
1878 match = re.search(
1879 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1880 if match:
1881 embed_url = self._proto_relative_url(
1882 unescapeHTML(match.group('url')))
1883 return {
1884 '_type': 'url_transparent',
1885 'url': embed_url,
1886 'ie_key': 'Wistia',
1887 'uploader': video_uploader,
1888 }
1889
1890 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1891 if match:
1892 return {
1893 '_type': 'url_transparent',
1894 'url': 'wistia:%s' % match.group('id'),
1895 'ie_key': 'Wistia',
1896 'uploader': video_uploader,
1897 }
1898
1899 match = re.search(
1900 r'''(?sx)
1901 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1902 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1903 ''', webpage)
1904 if match:
1905 return self.url_result(self._proto_relative_url(
1906 'wistia:%s' % match.group('id')), 'Wistia')
1907
1908 # Look for SVT player
1909 svt_url = SVTIE._extract_url(webpage)
1910 if svt_url:
1911 return self.url_result(svt_url, 'SVT')
1912
1913 # Look for embedded condenast player
1914 matches = re.findall(
1915 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1916 webpage)
1917 if matches:
1918 return {
1919 '_type': 'playlist',
1920 'entries': [{
1921 '_type': 'url',
1922 'ie_key': 'CondeNast',
1923 'url': ma,
1924 } for ma in matches],
1925 'title': video_title,
1926 'id': video_id,
1927 }
1928
1929 # Look for Bandcamp pages with custom domain
1930 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1931 if mobj is not None:
1932 burl = unescapeHTML(mobj.group(1))
1933 # Don't set the extractor because it can be a track url or an album
1934 return self.url_result(burl)
1935
1936 # Look for embedded Vevo player
1937 mobj = re.search(
1938 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1939 if mobj is not None:
1940 return self.url_result(mobj.group('url'))
1941
1942 # Look for embedded Viddler player
1943 mobj = re.search(
1944 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1945 webpage)
1946 if mobj is not None:
1947 return self.url_result(mobj.group('url'))
1948
1949 # Look for NYTimes player
1950 mobj = re.search(
1951 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1952 webpage)
1953 if mobj is not None:
1954 return self.url_result(mobj.group('url'))
1955
1956 # Look for Libsyn player
1957 mobj = re.search(
1958 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1959 if mobj is not None:
1960 return self.url_result(mobj.group('url'))
1961
1962 # Look for Ooyala videos
1963 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1964 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1965 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1966 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1967 if mobj is not None:
1968 embed_token = self._search_regex(
1969 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1970 webpage, 'ooyala embed token', default=None)
1971 return OoyalaIE._build_url_result(smuggle_url(
1972 mobj.group('ec'), {
1973 'domain': url,
1974 'embed_token': embed_token,
1975 }))
1976
1977 # Look for multiple Ooyala embeds on SBN network websites
1978 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1979 if mobj is not None:
1980 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1981 if embeds:
1982 return _playlist_from_matches(
1983 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1984
1985 # Look for Aparat videos
1986 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1987 if mobj is not None:
1988 return self.url_result(mobj.group(1), 'Aparat')
1989
1990 # Look for MPORA videos
1991 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1992 if mobj is not None:
1993 return self.url_result(mobj.group(1), 'Mpora')
1994
1995 # Look for embedded NovaMov-based player
1996 mobj = re.search(
1997 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1998 (?P<url>http://(?:(?:embed|www)\.)?
1999 (?:novamov\.com|
2000 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2001 videoweed\.(?:es|com)|
2002 movshare\.(?:net|sx|ag)|
2003 divxstage\.(?:eu|net|ch|co|at|ag))
2004 /embed\.php.+?)\1''', webpage)
2005 if mobj is not None:
2006 return self.url_result(mobj.group('url'))
2007
2008 # Look for embedded Facebook player
2009 facebook_url = FacebookIE._extract_url(webpage)
2010 if facebook_url is not None:
2011 return self.url_result(facebook_url, 'Facebook')
2012
2013 # Look for embedded VK player
2014 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2015 if mobj is not None:
2016 return self.url_result(mobj.group('url'), 'VK')
2017
2018 # Look for embedded Odnoklassniki player
2019 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2020 if mobj is not None:
2021 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2022
2023 # Look for embedded ivi player
2024 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2025 if mobj is not None:
2026 return self.url_result(mobj.group('url'), 'Ivi')
2027
2028 # Look for embedded Huffington Post player
2029 mobj = re.search(
2030 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2031 if mobj is not None:
2032 return self.url_result(mobj.group('url'), 'HuffPost')
2033
2034 # Look for embed.ly
2035 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2036 if mobj is not None:
2037 return self.url_result(mobj.group('url'))
2038 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2039 if mobj is not None:
2040 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2041
2042 # Look for funnyordie embed
2043 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2044 if matches:
2045 return _playlist_from_matches(
2046 matches, getter=unescapeHTML, ie='FunnyOrDie')
2047
2048 # Look for BBC iPlayer embed
2049 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2050 if matches:
2051 return _playlist_from_matches(matches, ie='BBCCoUk')
2052
2053 # Look for embedded RUTV player
2054 rutv_url = RUTVIE._extract_url(webpage)
2055 if rutv_url:
2056 return self.url_result(rutv_url, 'RUTV')
2057
2058 # Look for embedded TVC player
2059 tvc_url = TVCIE._extract_url(webpage)
2060 if tvc_url:
2061 return self.url_result(tvc_url, 'TVC')
2062
2063 # Look for embedded SportBox player
2064 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2065 if sportbox_urls:
2066 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2067
2068 # Look for embedded XHamster player
2069 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2070 if xhamster_urls:
2071 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2072
2073 # Look for embedded TNAFlixNetwork player
2074 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2075 if tnaflix_urls:
2076 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2077
2078 # Look for embedded PornHub player
2079 pornhub_urls = PornHubIE._extract_urls(webpage)
2080 if pornhub_urls:
2081 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2082
2083 # Look for embedded DrTuber player
2084 drtuber_urls = DrTuberIE._extract_urls(webpage)
2085 if drtuber_urls:
2086 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2087
2088 # Look for embedded RedTube player
2089 redtube_urls = RedTubeIE._extract_urls(webpage)
2090 if redtube_urls:
2091 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2092
2093 # Look for embedded Tvigle player
2094 mobj = re.search(
2095 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2096 if mobj is not None:
2097 return self.url_result(mobj.group('url'), 'Tvigle')
2098
2099 # Look for embedded TED player
2100 mobj = re.search(
2101 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2102 if mobj is not None:
2103 return self.url_result(mobj.group('url'), 'TED')
2104
2105 # Look for embedded Ustream videos
2106 ustream_url = UstreamIE._extract_url(webpage)
2107 if ustream_url:
2108 return self.url_result(ustream_url, UstreamIE.ie_key())
2109
2110 # Look for embedded arte.tv player
2111 mobj = re.search(
2112 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2113 webpage)
2114 if mobj is not None:
2115 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2116
2117 # Look for embedded francetv player
2118 mobj = re.search(
2119 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2120 webpage)
2121 if mobj is not None:
2122 return self.url_result(mobj.group('url'))
2123
2124 # Look for embedded smotri.com player
2125 smotri_url = SmotriIE._extract_url(webpage)
2126 if smotri_url:
2127 return self.url_result(smotri_url, 'Smotri')
2128
2129 # Look for embedded Myvi.ru player
2130 myvi_url = MyviIE._extract_url(webpage)
2131 if myvi_url:
2132 return self.url_result(myvi_url)
2133
2134 # Look for embedded soundcloud player
2135 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2136 if soundcloud_urls:
2137 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2138
2139 # Look for tunein player
2140 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2141 if tunein_urls:
2142 return _playlist_from_matches(tunein_urls)
2143
2144 # Look for embedded mtvservices player
2145 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2146 if mtvservices_url:
2147 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2148
2149 # Look for embedded yahoo player
2150 mobj = re.search(
2151 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2152 webpage)
2153 if mobj is not None:
2154 return self.url_result(mobj.group('url'), 'Yahoo')
2155
2156 # Look for embedded sbs.com.au player
2157 mobj = re.search(
2158 r'''(?x)
2159 (?:
2160 <meta\s+property="og:video"\s+content=|
2161 <iframe[^>]+?src=
2162 )
2163 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2164 webpage)
2165 if mobj is not None:
2166 return self.url_result(mobj.group('url'), 'SBS')
2167
2168 # Look for embedded Cinchcast player
2169 mobj = re.search(
2170 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2171 webpage)
2172 if mobj is not None:
2173 return self.url_result(mobj.group('url'), 'Cinchcast')
2174
2175 mobj = re.search(
2176 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2177 webpage)
2178 if not mobj:
2179 mobj = re.search(
2180 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2181 webpage)
2182 if mobj is not None:
2183 return self.url_result(mobj.group('url'), 'MLB')
2184
2185 mobj = re.search(
2186 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2187 webpage)
2188 if mobj is not None:
2189 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2190
2191 mobj = re.search(
2192 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2193 webpage)
2194 if mobj is not None:
2195 return self.url_result(mobj.group('url'), 'Livestream')
2196
2197 # Look for Zapiks embed
2198 mobj = re.search(
2199 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2200 if mobj is not None:
2201 return self.url_result(mobj.group('url'), 'Zapiks')
2202
2203 # Look for Kaltura embeds
2204 kaltura_url = KalturaIE._extract_url(webpage)
2205 if kaltura_url:
2206 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2207
2208 # Look for Eagle.Platform embeds
2209 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2210 if eagleplatform_url:
2211 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2212
2213 # Look for ClipYou (uses Eagle.Platform) embeds
2214 mobj = re.search(
2215 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2216 if mobj is not None:
2217 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2218
2219 # Look for Pladform embeds
2220 pladform_url = PladformIE._extract_url(webpage)
2221 if pladform_url:
2222 return self.url_result(pladform_url)
2223
2224 # Look for Videomore embeds
2225 videomore_url = VideomoreIE._extract_url(webpage)
2226 if videomore_url:
2227 return self.url_result(videomore_url)
2228
2229 # Look for Webcaster embeds
2230 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2231 if webcaster_url:
2232 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2233
2234 # Look for Playwire embeds
2235 mobj = re.search(
2236 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2237 if mobj is not None:
2238 return self.url_result(mobj.group('url'))
2239
2240 # Look for 5min embeds
2241 mobj = re.search(
2242 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2243 if mobj is not None:
2244 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2245
2246 # Look for Crooks and Liars embeds
2247 mobj = re.search(
2248 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2249 if mobj is not None:
2250 return self.url_result(mobj.group('url'))
2251
2252 # Look for NBC Sports VPlayer embeds
2253 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2254 if nbc_sports_url:
2255 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2256
2257 # Look for NBC News embeds
2258 nbc_news_embed_url = re.search(
2259 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2260 if nbc_news_embed_url:
2261 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2262
2263 # Look for Google Drive embeds
2264 google_drive_url = GoogleDriveIE._extract_url(webpage)
2265 if google_drive_url:
2266 return self.url_result(google_drive_url, 'GoogleDrive')
2267
2268 # Look for UDN embeds
2269 mobj = re.search(
2270 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2271 if mobj is not None:
2272 return self.url_result(
2273 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2274
2275 # Look for Senate ISVP iframe
2276 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2277 if senate_isvp_url:
2278 return self.url_result(senate_isvp_url, 'SenateISVP')
2279
2280 # Look for Dailymotion Cloud videos
2281 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2282 if dmcloud_url:
2283 return self.url_result(dmcloud_url, 'DailymotionCloud')
2284
2285 # Look for OnionStudios embeds
2286 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2287 if onionstudios_url:
2288 return self.url_result(onionstudios_url)
2289
2290 # Look for ViewLift embeds
2291 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2292 if viewlift_url:
2293 return self.url_result(viewlift_url)
2294
2295 # Look for JWPlatform embeds
2296 jwplatform_url = JWPlatformIE._extract_url(webpage)
2297 if jwplatform_url:
2298 return self.url_result(jwplatform_url, 'JWPlatform')
2299
2300 # Look for Digiteka embeds
2301 digiteka_url = DigitekaIE._extract_url(webpage)
2302 if digiteka_url:
2303 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2304
2305 # Look for Arkena embeds
2306 arkena_url = ArkenaIE._extract_url(webpage)
2307 if arkena_url:
2308 return self.url_result(arkena_url, ArkenaIE.ie_key())
2309
2310 # Look for Piksel embeds
2311 piksel_url = PikselIE._extract_url(webpage)
2312 if piksel_url:
2313 return self.url_result(piksel_url, PikselIE.ie_key())
2314
2315 # Look for Limelight embeds
2316 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2317 if mobj:
2318 lm = {
2319 'Media': 'media',
2320 'Channel': 'channel',
2321 'ChannelList': 'channel_list',
2322 }
2323 return self.url_result('limelight:%s:%s' % (
2324 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2325
2326 mobj = re.search(
2327 r'''(?sx)
2328 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2329 <param[^>]+
2330 name=(["\'])flashVars\2[^>]+
2331 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2332 ''', webpage)
2333 if mobj:
2334 return self.url_result('limelight:media:%s' % mobj.group('id'))
2335
2336 # Look for AdobeTVVideo embeds
2337 mobj = re.search(
2338 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2339 webpage)
2340 if mobj is not None:
2341 return self.url_result(
2342 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2343 'AdobeTVVideo')
2344
2345 # Look for Vine embeds
2346 mobj = re.search(
2347 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2348 webpage)
2349 if mobj is not None:
2350 return self.url_result(
2351 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2352
2353 # Look for VODPlatform embeds
2354 mobj = re.search(
2355 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2356 webpage)
2357 if mobj is not None:
2358 return self.url_result(
2359 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2360
2361 # Look for Mangomolo embeds
2362 mobj = re.search(
2363 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2364 (?:
2365 video\?.*?\bid=(?P<video_id>\d+)|
2366 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2367 ).+?)\1''', webpage)
2368 if mobj is not None:
2369 info = {
2370 '_type': 'url_transparent',
2371 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2372 'title': video_title,
2373 'description': video_description,
2374 'thumbnail': video_thumbnail,
2375 'uploader': video_uploader,
2376 }
2377 video_id = mobj.group('video_id')
2378 if video_id:
2379 info.update({
2380 'ie_key': 'MangomoloVideo',
2381 'id': video_id,
2382 })
2383 else:
2384 info.update({
2385 'ie_key': 'MangomoloLive',
2386 'id': mobj.group('channel_id'),
2387 })
2388 return info
2389
2390 # Look for Instagram embeds
2391 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2392 if instagram_embed_url is not None:
2393 return self.url_result(
2394 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2395
2396 # Look for LiveLeak embeds
2397 liveleak_url = LiveLeakIE._extract_url(webpage)
2398 if liveleak_url:
2399 return self.url_result(liveleak_url, 'LiveLeak')
2400
2401 # Look for 3Q SDN embeds
2402 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2403 if threeqsdn_url:
2404 return {
2405 '_type': 'url_transparent',
2406 'ie_key': ThreeQSDNIE.ie_key(),
2407 'url': self._proto_relative_url(threeqsdn_url),
2408 'title': video_title,
2409 'description': video_description,
2410 'thumbnail': video_thumbnail,
2411 'uploader': video_uploader,
2412 }
2413
2414 # Look for VBOX7 embeds
2415 vbox7_url = Vbox7IE._extract_url(webpage)
2416 if vbox7_url:
2417 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2418
2419 # Look for DBTV embeds
2420 dbtv_urls = DBTVIE._extract_urls(webpage)
2421 if dbtv_urls:
2422 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2423
2424 # Look for Videa embeds
2425 videa_urls = VideaIE._extract_urls(webpage)
2426 if videa_urls:
2427 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2428
2429 # Look for 20 minuten embeds
2430 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2431 if twentymin_urls:
2432 return _playlist_from_matches(
2433 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2434
2435 # Look for Openload embeds
2436 openload_urls = OpenloadIE._extract_urls(webpage)
2437 if openload_urls:
2438 return _playlist_from_matches(
2439 openload_urls, ie=OpenloadIE.ie_key())
2440
2441 # Looking for http://schema.org/VideoObject
2442 json_ld = self._search_json_ld(
2443 webpage, video_id, default={}, expected_type='VideoObject')
2444 if json_ld.get('url'):
2445 info_dict.update({
2446 'title': video_title or info_dict['title'],
2447 'description': video_description,
2448 'thumbnail': video_thumbnail,
2449 'age_limit': age_limit
2450 })
2451 info_dict.update(json_ld)
2452 return info_dict
2453
2454 # Look for HTML5 media
2455 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2456 if entries:
2457 for entry in entries:
2458 entry.update({
2459 'id': video_id,
2460 'title': video_title,
2461 })
2462 self._sort_formats(entry['formats'])
2463 return self.playlist_result(entries)
2464
2465 def check_video(vurl):
2466 if YoutubeIE.suitable(vurl):
2467 return True
2468 vpath = compat_urlparse.urlparse(vurl).path
2469 vext = determine_ext(vpath)
2470 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2471
2472 def filter_video(urls):
2473 return list(filter(check_video, urls))
2474
2475 # Start with something easy: JW Player in SWFObject
2476 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2477 if not found:
2478 # Look for gorilla-vid style embedding
2479 found = filter_video(re.findall(r'''(?sx)
2480 (?:
2481 jw_plugins|
2482 JWPlayerOptions|
2483 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2484 )
2485 .*?
2486 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2487 if not found:
2488 # Broaden the search a little bit
2489 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2490 if not found:
2491 # Broaden the findall a little bit: JWPlayer JS loader
2492 found = filter_video(re.findall(
2493 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2494 if not found:
2495 # Flow player
2496 found = filter_video(re.findall(r'''(?xs)
2497 flowplayer\("[^"]+",\s*
2498 \{[^}]+?\}\s*,
2499 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2500 ["']?url["']?\s*:\s*["']([^"']+)["']
2501 ''', webpage))
2502 if not found:
2503 # Cinerama player
2504 found = re.findall(
2505 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2506 if not found:
2507 # Try to find twitter cards info
2508 # twitter:player:stream should be checked before twitter:player since
2509 # it is expected to contain a raw stream (see
2510 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2511 found = filter_video(re.findall(
2512 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2513 if not found:
2514 # We look for Open Graph info:
2515 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2516 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2517 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2518 if m_video_type is not None:
2519 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2520 if not found:
2521 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2522 found = re.search(
2523 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2524 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2525 webpage)
2526 if not found:
2527 # Look also in Refresh HTTP header
2528 refresh_header = head_response.headers.get('Refresh')
2529 if refresh_header:
2530 # In python 2 response HTTP headers are bytestrings
2531 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2532 refresh_header = refresh_header.decode('iso-8859-1')
2533 found = re.search(REDIRECT_REGEX, refresh_header)
2534 if found:
2535 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2536 self.report_following_redirect(new_url)
2537 return {
2538 '_type': 'url',
2539 'url': new_url,
2540 }
2541
2542 if not found:
2543 # twitter:player is a https URL to iframe player that may or may not
2544 # be supported by youtube-dl thus this is checked the very last (see
2545 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2546 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2547 if embed_url:
2548 return self.url_result(embed_url)
2549
2550 if not found:
2551 raise UnsupportedError(url)
2552
2553 entries = []
2554 for video_url in orderedSet(found):
2555 video_url = unescapeHTML(video_url)
2556 video_url = video_url.replace('\\/', '/')
2557 video_url = compat_urlparse.urljoin(url, video_url)
2558 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2559
2560 # Sometimes, jwplayer extraction will result in a YouTube URL
2561 if YoutubeIE.suitable(video_url):
2562 entries.append(self.url_result(video_url, 'Youtube'))
2563 continue
2564
2565 # here's a fun little line of code for you:
2566 video_id = os.path.splitext(video_id)[0]
2567
2568 entry_info_dict = {
2569 'id': video_id,
2570 'uploader': video_uploader,
2571 'title': video_title,
2572 'age_limit': age_limit,
2573 }
2574
2575 ext = determine_ext(video_url)
2576 if ext == 'smil':
2577 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2578 elif ext == 'xspf':
2579 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2580 elif ext == 'm3u8':
2581 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2582 elif ext == 'mpd':
2583 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2584 elif ext == 'f4m':
2585 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2586 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2587 # Just matching .ism/manifest is not enough to be reliably sure
2588 # whether it's actually an ISM manifest or some other streaming
2589 # manifest since there are various streaming URL formats
2590 # possible (see [1]) as well as some other shenanigans like
2591 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2592 # so on.
2593 # Thus the most reasonable way to solve this is to delegate
2594 # to generic extractor in order to look into the contents of
2595 # the manifest itself.
2596 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2597 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2598 entry_info_dict = self.url_result(
2599 smuggle_url(video_url, {'to_generic': True}),
2600 GenericIE.ie_key())
2601 else:
2602 entry_info_dict['url'] = video_url
2603
2604 if entry_info_dict.get('formats'):
2605 self._sort_formats(entry_info_dict['formats'])
2606
2607 entries.append(entry_info_dict)
2608
2609 if len(entries) == 1:
2610 return entries[0]
2611 else:
2612 for num, e in enumerate(entries, start=1):
2613 # 'url' results don't have a title
2614 if e.get('title') is not None:
2615 e['title'] = '%s (%d)' % (e['title'], num)
2616 return {
2617 '_type': 'playlist',
2618 'entries': entries,
2619 }