]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[disney] improve extraction
[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 .commonprotocols import RtmpIE
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 .drtuber import DrTuberIE
52 from .redtube import RedTubeIE
53 from .vimeo import VimeoIE
54 from .dailymotion import (
55 DailymotionIE,
56 DailymotionCloudIE,
57 )
58 from .onionstudios import OnionStudiosIE
59 from .viewlift import ViewLiftEmbedIE
60 from .mtv import MTVServicesEmbeddedIE
61 from .pladform import PladformIE
62 from .videomore import VideomoreIE
63 from .webcaster import WebcasterFeedIE
64 from .googledrive import GoogleDriveIE
65 from .jwplatform import JWPlatformIE
66 from .digiteka import DigitekaIE
67 from .arkena import ArkenaIE
68 from .instagram import InstagramIE
69 from .liveleak import LiveLeakIE
70 from .threeqsdn import ThreeQSDNIE
71 from .theplatform import ThePlatformIE
72 from .vessel import VesselIE
73 from .kaltura import KalturaIE
74 from .eagleplatform import EaglePlatformIE
75 from .facebook import FacebookIE
76 from .soundcloud import SoundcloudIE
77 from .tunein import TuneInBaseIE
78 from .vbox7 import Vbox7IE
79 from .dbtv import DBTVIE
80 from .piksel import PikselIE
81 from .videa import VideaIE
82 from .twentymin import TwentyMinutenIE
83 from .ustream import UstreamIE
84 from .openload import OpenloadIE
85 from .videopress import VideoPressIE
86
87
88 class GenericIE(InfoExtractor):
89 IE_DESC = 'Generic downloader that works on some sites'
90 _VALID_URL = r'.*'
91 IE_NAME = 'generic'
92 _TESTS = [
93 # Direct link to a video
94 {
95 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
96 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
97 'info_dict': {
98 'id': 'trailer',
99 'ext': 'mp4',
100 'title': 'trailer',
101 'upload_date': '20100513',
102 }
103 },
104 # Direct link to media delivered compressed (until Accept-Encoding is *)
105 {
106 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
107 'md5': '128c42e68b13950268b648275386fc74',
108 'info_dict': {
109 'id': 'FictionJunction-Parallel_Hearts',
110 'ext': 'flac',
111 'title': 'FictionJunction-Parallel_Hearts',
112 'upload_date': '20140522',
113 },
114 'expected_warnings': [
115 'URL could be a direct video link, returning it as such.'
116 ],
117 'skip': 'URL invalid',
118 },
119 # Direct download with broken HEAD
120 {
121 'url': 'http://ai-radio.org:8000/radio.opus',
122 'info_dict': {
123 'id': 'radio',
124 'ext': 'opus',
125 'title': 'radio',
126 },
127 'params': {
128 'skip_download': True, # infinite live stream
129 },
130 'expected_warnings': [
131 r'501.*Not Implemented',
132 r'400.*Bad Request',
133 ],
134 },
135 # Direct link with incorrect MIME type
136 {
137 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
138 'md5': '4ccbebe5f36706d85221f204d7eb5913',
139 'info_dict': {
140 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
141 'id': '5_Lennart_Poettering_-_Systemd',
142 'ext': 'webm',
143 'title': '5_Lennart_Poettering_-_Systemd',
144 'upload_date': '20141120',
145 },
146 'expected_warnings': [
147 'URL could be a direct video link, returning it as such.'
148 ]
149 },
150 # RSS feed
151 {
152 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
153 'info_dict': {
154 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
155 'title': 'Zero Punctuation',
156 'description': 're:.*groundbreaking video review series.*'
157 },
158 'playlist_mincount': 11,
159 },
160 # RSS feed with enclosure
161 {
162 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
163 'info_dict': {
164 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
165 'ext': 'm4v',
166 'upload_date': '20150228',
167 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
168 }
169 },
170 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
171 {
172 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
173 'info_dict': {
174 'id': 'smil',
175 'ext': 'mp4',
176 'title': 'Automatics, robotics and biocybernetics',
177 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
178 'upload_date': '20130627',
179 'formats': 'mincount:16',
180 'subtitles': 'mincount:1',
181 },
182 'params': {
183 'force_generic_extractor': True,
184 'skip_download': True,
185 },
186 },
187 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
188 {
189 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
190 'info_dict': {
191 'id': 'hds',
192 'ext': 'flv',
193 'title': 'hds',
194 'formats': 'mincount:1',
195 },
196 'params': {
197 'skip_download': True,
198 },
199 },
200 # SMIL from https://www.restudy.dk/video/play/id/1637
201 {
202 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
203 'info_dict': {
204 'id': 'video_1637',
205 'ext': 'flv',
206 'title': 'video_1637',
207 'formats': 'mincount:3',
208 },
209 'params': {
210 'skip_download': True,
211 },
212 },
213 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
214 {
215 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
216 'info_dict': {
217 'id': 'smil-service',
218 'ext': 'flv',
219 'title': 'smil-service',
220 'formats': 'mincount:1',
221 },
222 'params': {
223 'skip_download': True,
224 },
225 },
226 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
227 {
228 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
229 'info_dict': {
230 'id': '4719370',
231 'ext': 'mp4',
232 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
233 'formats': 'mincount:3',
234 },
235 'params': {
236 'skip_download': True,
237 },
238 },
239 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
240 {
241 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
242 'info_dict': {
243 'id': 'mZlp2ctYIUEB',
244 'ext': 'mp4',
245 'title': 'Tikibad ontruimd wegens brand',
246 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'duration': 33,
249 },
250 'params': {
251 'skip_download': True,
252 },
253 },
254 # MPD from http://dash-mse-test.appspot.com/media.html
255 {
256 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
257 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
258 'info_dict': {
259 'id': 'car-20120827-manifest',
260 'ext': 'mp4',
261 'title': 'car-20120827-manifest',
262 'formats': 'mincount:9',
263 'upload_date': '20130904',
264 },
265 'params': {
266 'format': 'bestvideo',
267 },
268 },
269 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
270 {
271 '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',
272 'info_dict': {
273 'id': 'content',
274 'ext': 'mp4',
275 'title': 'content',
276 'formats': 'mincount:8',
277 },
278 'params': {
279 # m3u8 downloads
280 'skip_download': True,
281 },
282 'skip': 'video gone',
283 },
284 # m3u8 served with Content-Type: text/plain
285 {
286 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
287 'info_dict': {
288 'id': 'index',
289 'ext': 'mp4',
290 'title': 'index',
291 'upload_date': '20140720',
292 'formats': 'mincount:11',
293 },
294 'params': {
295 # m3u8 downloads
296 'skip_download': True,
297 },
298 'skip': 'video gone',
299 },
300 # google redirect
301 {
302 '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',
303 'info_dict': {
304 'id': 'cmQHVoWB5FY',
305 'ext': 'mp4',
306 'upload_date': '20130224',
307 'uploader_id': 'TheVerge',
308 'description': r're:^Chris Ziegler takes a look at the\.*',
309 'uploader': 'The Verge',
310 'title': 'First Firefox OS phones side-by-side',
311 },
312 'params': {
313 'skip_download': False,
314 }
315 },
316 {
317 # redirect in Refresh HTTP header
318 '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',
319 'info_dict': {
320 'id': 'pO8h3EaFRdo',
321 'ext': 'mp4',
322 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
323 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
324 'upload_date': '20150917',
325 'uploader_id': 'brtvofficial',
326 'uploader': 'Boiler Room',
327 },
328 'params': {
329 'skip_download': False,
330 },
331 },
332 {
333 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
334 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
335 'info_dict': {
336 'id': '13601338388002',
337 'ext': 'mp4',
338 'uploader': 'www.hodiho.fr',
339 'title': 'R\u00e9gis plante sa Jeep',
340 }
341 },
342 # bandcamp page with custom domain
343 {
344 'add_ie': ['Bandcamp'],
345 'url': 'http://bronyrock.com/track/the-pony-mash',
346 'info_dict': {
347 'id': '3235767654',
348 'ext': 'mp3',
349 'title': 'The Pony Mash',
350 'uploader': 'M_Pallante',
351 },
352 'skip': 'There is a limit of 200 free downloads / month for the test song',
353 },
354 {
355 # embedded brightcove video
356 # it also tests brightcove videos that need to set the 'Referer'
357 # in the http requests
358 'add_ie': ['BrightcoveLegacy'],
359 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
360 'info_dict': {
361 'id': '2765128793001',
362 'ext': 'mp4',
363 'title': 'Le cours de bourse : l’analyse technique',
364 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
365 'uploader': 'BFM BUSINESS',
366 },
367 'params': {
368 'skip_download': True,
369 },
370 },
371 {
372 # embedded with itemprop embedURL and video id spelled as `idVideo`
373 'add_id': ['BrightcoveLegacy'],
374 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
375 'info_dict': {
376 'id': '5255628253001',
377 'ext': 'mp4',
378 'title': 'md5:37c519b1128915607601e75a87995fc0',
379 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
380 'uploader': 'BFM BUSINESS',
381 'uploader_id': '876450612001',
382 'timestamp': 1482255315,
383 'upload_date': '20161220',
384 },
385 'params': {
386 'skip_download': True,
387 },
388 },
389 {
390 # https://github.com/rg3/youtube-dl/issues/2253
391 'url': 'http://bcove.me/i6nfkrc3',
392 'md5': '0ba9446db037002366bab3b3eb30c88c',
393 'info_dict': {
394 'id': '3101154703001',
395 'ext': 'mp4',
396 'title': 'Still no power',
397 'uploader': 'thestar.com',
398 '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.',
399 },
400 'add_ie': ['BrightcoveLegacy'],
401 'skip': 'video gone',
402 },
403 {
404 'url': 'http://www.championat.com/video/football/v/87/87499.html',
405 'md5': 'fb973ecf6e4a78a67453647444222983',
406 'info_dict': {
407 'id': '3414141473001',
408 'ext': 'mp4',
409 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
410 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
411 'uploader': 'Championat',
412 },
413 },
414 {
415 # https://github.com/rg3/youtube-dl/issues/3541
416 'add_ie': ['BrightcoveLegacy'],
417 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
418 'info_dict': {
419 'id': '3866516442001',
420 'ext': 'mp4',
421 'title': 'Leer mij vrouwen kennen: Aflevering 1',
422 'description': 'Leer mij vrouwen kennen: Aflevering 1',
423 'uploader': 'SBS Broadcasting',
424 },
425 'skip': 'Restricted to Netherlands',
426 'params': {
427 'skip_download': True, # m3u8 download
428 },
429 },
430 {
431 # Brightcove with alternative playerID key
432 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
433 'info_dict': {
434 'id': 'nmeth.2062_SV1',
435 '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',
436 },
437 'playlist': [{
438 'info_dict': {
439 'id': '2228375078001',
440 'ext': 'mp4',
441 'title': 'nmeth.2062-sv1',
442 'description': 'nmeth.2062-sv1',
443 'timestamp': 1363357591,
444 'upload_date': '20130315',
445 'uploader': 'Nature Publishing Group',
446 'uploader_id': '1964492299001',
447 },
448 }],
449 },
450 # ooyala video
451 {
452 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
453 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
454 'info_dict': {
455 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
456 'ext': 'mp4',
457 'title': '2cc213299525360.mov', # that's what we get
458 'duration': 238.231,
459 },
460 'add_ie': ['Ooyala'],
461 },
462 {
463 # ooyala video embedded with http://player.ooyala.com/iframe.js
464 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
465 'info_dict': {
466 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
467 'ext': 'mp4',
468 'title': '"Steve Jobs: Man in the Machine" trailer',
469 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
470 'duration': 135.427,
471 },
472 'params': {
473 'skip_download': True,
474 },
475 'skip': 'movie expired',
476 },
477 # embed.ly video
478 {
479 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
480 'info_dict': {
481 'id': '9ODmcdjQcHQ',
482 'ext': 'mp4',
483 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
484 'upload_date': '20140225',
485 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
486 'uploader': 'Tested',
487 'uploader_id': 'testedcom',
488 },
489 # No need to test YoutubeIE here
490 'params': {
491 'skip_download': True,
492 },
493 },
494 # funnyordie embed
495 {
496 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
497 'info_dict': {
498 'id': '18e820ec3f',
499 'ext': 'mp4',
500 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
501 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
502 },
503 # HEAD requests lead to endless 301, while GET is OK
504 'expected_warnings': ['301'],
505 },
506 # RUTV embed
507 {
508 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
509 'info_dict': {
510 'id': '776940',
511 'ext': 'mp4',
512 'title': 'Охотское море стало целиком российским',
513 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
514 },
515 'params': {
516 # m3u8 download
517 'skip_download': True,
518 },
519 },
520 # TVC embed
521 {
522 '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/',
523 'info_dict': {
524 'id': '55304',
525 'ext': 'mp4',
526 'title': 'Дошкольное воспитание',
527 },
528 },
529 # SportBox embed
530 {
531 'url': 'http://www.vestifinance.ru/articles/25753',
532 'info_dict': {
533 'id': '25753',
534 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
535 },
536 'playlist': [{
537 'info_dict': {
538 'id': '370908',
539 'title': 'Госзаказ. День 3',
540 'ext': 'mp4',
541 }
542 }, {
543 'info_dict': {
544 'id': '370905',
545 'title': 'Госзаказ. День 2',
546 'ext': 'mp4',
547 }
548 }, {
549 'info_dict': {
550 'id': '370902',
551 'title': 'Госзаказ. День 1',
552 'ext': 'mp4',
553 }
554 }],
555 'params': {
556 # m3u8 download
557 'skip_download': True,
558 },
559 },
560 # Myvi.ru embed
561 {
562 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
563 'info_dict': {
564 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
565 'ext': 'mp4',
566 'title': 'Ужастики, русский трейлер (2015)',
567 'thumbnail': r're:^https?://.*\.jpg$',
568 'duration': 153,
569 }
570 },
571 # XHamster embed
572 {
573 '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',
574 'info_dict': {
575 'id': 'showthread',
576 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
577 },
578 'playlist_mincount': 7,
579 # This forum does not allow <iframe> syntaxes anymore
580 # Now HTML tags are displayed as-is
581 'skip': 'No videos on this page',
582 },
583 # Embedded TED video
584 {
585 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
586 'md5': '65fdff94098e4a607385a60c5177c638',
587 'info_dict': {
588 'id': '1969',
589 'ext': 'mp4',
590 'title': 'Hidden miracles of the natural world',
591 'uploader': 'Louie Schwartzberg',
592 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
593 }
594 },
595 # nowvideo embed hidden behind percent encoding
596 {
597 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
598 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
599 'info_dict': {
600 'id': '06e53103ca9aa',
601 'ext': 'flv',
602 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
603 'description': 'No description',
604 },
605 },
606 # arte embed
607 {
608 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
609 'md5': '7653032cbb25bf6c80d80f217055fa43',
610 'info_dict': {
611 'id': '048195-004_PLUS7-F',
612 'ext': 'flv',
613 'title': 'X:enius',
614 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
615 'upload_date': '20140320',
616 },
617 'params': {
618 'skip_download': 'Requires rtmpdump'
619 },
620 'skip': 'video gone',
621 },
622 # francetv embed
623 {
624 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
625 'info_dict': {
626 'id': 'EV_30231',
627 'ext': 'mp4',
628 'title': 'Alcaline, le concert avec Calogero',
629 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
630 'upload_date': '20150226',
631 'timestamp': 1424989860,
632 'duration': 5400,
633 },
634 'params': {
635 # m3u8 downloads
636 'skip_download': True,
637 },
638 'expected_warnings': [
639 'Forbidden'
640 ]
641 },
642 # Condé Nast embed
643 {
644 'url': 'http://www.wired.com/2014/04/honda-asimo/',
645 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
646 'info_dict': {
647 'id': '53501be369702d3275860000',
648 'ext': 'mp4',
649 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
650 }
651 },
652 # Dailymotion embed
653 {
654 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
655 'md5': '441aeeb82eb72c422c7f14ec533999cd',
656 'info_dict': {
657 'id': 'k2mm4bCdJ6CQ2i7c8o2',
658 'ext': 'mp4',
659 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
660 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
661 'uploader': 'Spi0n',
662 'uploader_id': 'xgditw',
663 'upload_date': '20140425',
664 'timestamp': 1398441542,
665 },
666 'add_ie': ['Dailymotion'],
667 },
668 # YouTube embed
669 {
670 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
671 'info_dict': {
672 'id': 'FXRb4ykk4S0',
673 'ext': 'mp4',
674 'title': 'The NBL Auction 2014',
675 'uploader': 'BADMINTON England',
676 'uploader_id': 'BADMINTONEvents',
677 'upload_date': '20140603',
678 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
679 },
680 'add_ie': ['Youtube'],
681 'params': {
682 'skip_download': True,
683 }
684 },
685 # MTVSercices embed
686 {
687 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
688 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
689 'info_dict': {
690 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
691 'ext': 'mp4',
692 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
693 'description': 'Two valets share their love for movie star Liam Neesons.',
694 'timestamp': 1349922600,
695 'upload_date': '20121011',
696 },
697 },
698 # YouTube embed via <data-embed-url="">
699 {
700 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
701 'info_dict': {
702 'id': '4vAffPZIT44',
703 'ext': 'mp4',
704 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
705 'uploader': 'Gameloft',
706 'uploader_id': 'gameloft',
707 'upload_date': '20140828',
708 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
709 },
710 'params': {
711 'skip_download': True,
712 }
713 },
714 # Camtasia studio
715 {
716 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
717 'playlist': [{
718 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
719 'info_dict': {
720 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
721 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
722 'ext': 'flv',
723 'duration': 2235.90,
724 }
725 }, {
726 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
727 'info_dict': {
728 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
729 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
730 'ext': 'flv',
731 'duration': 2235.93,
732 }
733 }],
734 'info_dict': {
735 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
736 }
737 },
738 # Flowplayer
739 {
740 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
741 'md5': '9d65602bf31c6e20014319c7d07fba27',
742 'info_dict': {
743 'id': '5123ea6d5e5a7',
744 'ext': 'mp4',
745 'age_limit': 18,
746 'uploader': 'www.handjobhub.com',
747 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
748 }
749 },
750 # Multiple brightcove videos
751 # https://github.com/rg3/youtube-dl/issues/2283
752 {
753 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
754 'info_dict': {
755 'id': 'always-never',
756 'title': 'Always / Never - The New Yorker',
757 },
758 'playlist_count': 3,
759 'params': {
760 'extract_flat': False,
761 'skip_download': True,
762 }
763 },
764 # MLB embed
765 {
766 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
767 'md5': '96f09a37e44da40dd083e12d9a683327',
768 'info_dict': {
769 'id': '33322633',
770 'ext': 'mp4',
771 'title': 'Ump changes call to ball',
772 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
773 'duration': 48,
774 'timestamp': 1401537900,
775 'upload_date': '20140531',
776 'thumbnail': r're:^https?://.*\.jpg$',
777 },
778 },
779 # Wistia embed
780 {
781 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
782 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
783 'info_dict': {
784 'id': '6e2wtrbdaf',
785 'ext': 'mov',
786 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
787 'description': 'a Paywall Videos video from Remilon',
788 'duration': 644.072,
789 'uploader': 'study.com',
790 'timestamp': 1459678540,
791 'upload_date': '20160403',
792 'filesize': 24687186,
793 },
794 },
795 {
796 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
797 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
798 'info_dict': {
799 'id': 'uxjb0lwrcz',
800 'ext': 'mp4',
801 'title': 'Conversation about Hexagonal Rails Part 1',
802 'description': 'a Martin Fowler video from ThoughtWorks',
803 'duration': 1715.0,
804 'uploader': 'thoughtworks.wistia.com',
805 'timestamp': 1401832161,
806 'upload_date': '20140603',
807 },
808 },
809 # Wistia standard embed (async)
810 {
811 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
812 'info_dict': {
813 'id': '807fafadvk',
814 'ext': 'mp4',
815 'title': 'Drip Brennan Dunn Workshop',
816 'description': 'a JV Webinars video from getdrip-1',
817 'duration': 4986.95,
818 'timestamp': 1463607249,
819 'upload_date': '20160518',
820 },
821 'params': {
822 'skip_download': True,
823 }
824 },
825 # Soundcloud embed
826 {
827 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
828 'info_dict': {
829 'id': '174391317',
830 'ext': 'mp3',
831 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
832 'uploader': 'Sophos Security',
833 'title': 'Chet Chat 171 - Oct 29, 2014',
834 'upload_date': '20141029',
835 }
836 },
837 # Soundcloud multiple embeds
838 {
839 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
840 'info_dict': {
841 'id': '52809',
842 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
843 },
844 'playlist_mincount': 7,
845 },
846 # TuneIn station embed
847 {
848 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
849 'info_dict': {
850 'id': '204146',
851 'ext': 'mp3',
852 'title': 'CNRV',
853 'location': 'Paris, France',
854 'is_live': True,
855 },
856 'params': {
857 # Live stream
858 'skip_download': True,
859 },
860 },
861 # Livestream embed
862 {
863 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
864 'info_dict': {
865 'id': '67864563',
866 'ext': 'flv',
867 'upload_date': '20141112',
868 'title': 'Rosetta #CometLanding webcast HL 10',
869 }
870 },
871 # Another Livestream embed, without 'new.' in URL
872 {
873 'url': 'https://www.freespeech.org/',
874 'info_dict': {
875 'id': '123537347',
876 'ext': 'mp4',
877 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
878 },
879 'params': {
880 # Live stream
881 'skip_download': True,
882 },
883 },
884 # LazyYT
885 {
886 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
887 'info_dict': {
888 'id': '1986',
889 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
890 },
891 'playlist_mincount': 2,
892 },
893 # Cinchcast embed
894 {
895 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
896 'info_dict': {
897 'id': '7141703',
898 'ext': 'mp3',
899 'upload_date': '20141126',
900 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
901 }
902 },
903 # Cinerama player
904 {
905 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
906 'info_dict': {
907 'id': '730m_DandD_1901_512k',
908 'ext': 'mp4',
909 'uploader': 'www.abc.net.au',
910 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
911 }
912 },
913 # embedded viddler video
914 {
915 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
916 'info_dict': {
917 'id': '4d03aad9',
918 'ext': 'mp4',
919 'uploader': 'deadspin',
920 'title': 'WALL-TO-GORTAT',
921 'timestamp': 1422285291,
922 'upload_date': '20150126',
923 },
924 'add_ie': ['Viddler'],
925 },
926 # Libsyn embed
927 {
928 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
929 'info_dict': {
930 'id': '3377616',
931 'ext': 'mp3',
932 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
933 'description': 'md5:601cb790edd05908957dae8aaa866465',
934 'upload_date': '20150220',
935 },
936 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
937 },
938 # jwplayer YouTube
939 {
940 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
941 'info_dict': {
942 'id': 'Mrj4DVp2zeA',
943 'ext': 'mp4',
944 'upload_date': '20150212',
945 'uploader': 'The National Archives UK',
946 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
947 'uploader_id': 'NationalArchives08',
948 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
949 },
950 },
951 # jwplayer rtmp
952 {
953 'url': 'http://www.suffolk.edu/sjc/',
954 'info_dict': {
955 'id': 'sjclive',
956 'ext': 'flv',
957 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
958 'uploader': 'www.suffolk.edu',
959 },
960 'params': {
961 'skip_download': True,
962 }
963 },
964 # rtl.nl embed
965 {
966 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
967 'playlist_mincount': 5,
968 'info_dict': {
969 'id': 'aanslagen-kopenhagen',
970 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
971 }
972 },
973 # Zapiks embed
974 {
975 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
976 'info_dict': {
977 'id': '118046',
978 'ext': 'mp4',
979 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
980 }
981 },
982 # Kaltura embed (different embed code)
983 {
984 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
985 'info_dict': {
986 'id': '1_a52wc67y',
987 'ext': 'flv',
988 'upload_date': '20150127',
989 'uploader_id': 'PremierMedia',
990 'timestamp': int,
991 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
992 },
993 },
994 # Kaltura embed with single quotes
995 {
996 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
997 'info_dict': {
998 'id': '0_izeg5utt',
999 'ext': 'mp4',
1000 'title': '35871',
1001 'timestamp': 1355743100,
1002 'upload_date': '20121217',
1003 'uploader_id': 'batchUser',
1004 },
1005 'add_ie': ['Kaltura'],
1006 },
1007 {
1008 # Kaltura embedded via quoted entry_id
1009 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1010 'info_dict': {
1011 'id': '0_utuok90b',
1012 'ext': 'mp4',
1013 'title': '06_matthew_brender_raj_dutt',
1014 'timestamp': 1466638791,
1015 'upload_date': '20160622',
1016 },
1017 'add_ie': ['Kaltura'],
1018 'expected_warnings': [
1019 'Could not send HEAD request'
1020 ],
1021 'params': {
1022 'skip_download': True,
1023 }
1024 },
1025 {
1026 # Kaltura embedded, some fileExt broken (#11480)
1027 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1028 'info_dict': {
1029 'id': '1_sgtvehim',
1030 'ext': 'mp4',
1031 'title': 'Our "Standard Models" of particle physics and cosmology',
1032 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1033 'timestamp': 1321158993,
1034 'upload_date': '20111113',
1035 'uploader_id': 'kps1',
1036 },
1037 'add_ie': ['Kaltura'],
1038 },
1039 # Eagle.Platform embed (generic URL)
1040 {
1041 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1042 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1043 'info_dict': {
1044 'id': '227304',
1045 'ext': 'mp4',
1046 'title': 'Навальный вышел на свободу',
1047 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1048 'thumbnail': r're:^https?://.*\.jpg$',
1049 'duration': 87,
1050 'view_count': int,
1051 'age_limit': 0,
1052 },
1053 },
1054 # ClipYou (Eagle.Platform) embed (custom URL)
1055 {
1056 'url': 'http://muz-tv.ru/play/7129/',
1057 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1058 'info_dict': {
1059 'id': '12820',
1060 'ext': 'mp4',
1061 'title': "'O Sole Mio",
1062 'thumbnail': r're:^https?://.*\.jpg$',
1063 'duration': 216,
1064 'view_count': int,
1065 },
1066 },
1067 # Pladform embed
1068 {
1069 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1070 'info_dict': {
1071 'id': '100183293',
1072 'ext': 'mp4',
1073 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1074 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1075 'thumbnail': r're:^https?://.*\.jpg$',
1076 'duration': 694,
1077 'age_limit': 0,
1078 },
1079 },
1080 # Playwire embed
1081 {
1082 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1083 'info_dict': {
1084 'id': '3519514',
1085 'ext': 'mp4',
1086 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1087 'thumbnail': r're:^https?://.*\.png$',
1088 'duration': 45.115,
1089 },
1090 },
1091 # 5min embed
1092 {
1093 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1094 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1095 'info_dict': {
1096 'id': '518726732',
1097 'ext': 'mp4',
1098 'title': 'Facebook Creates "On This Day" | Crunch Report',
1099 },
1100 },
1101 # SVT embed
1102 {
1103 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1104 'info_dict': {
1105 'id': '2900353',
1106 'ext': 'flv',
1107 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1108 'duration': 27,
1109 'age_limit': 0,
1110 },
1111 },
1112 # Crooks and Liars embed
1113 {
1114 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1115 'info_dict': {
1116 'id': '8RUoRhRi',
1117 'ext': 'mp4',
1118 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1119 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1120 'timestamp': 1428207000,
1121 'upload_date': '20150405',
1122 'uploader': 'Heather',
1123 },
1124 },
1125 # Crooks and Liars external embed
1126 {
1127 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1128 'info_dict': {
1129 'id': 'MTE3MjUtMzQ2MzA',
1130 'ext': 'mp4',
1131 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1132 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1133 'timestamp': 1265032391,
1134 'upload_date': '20100201',
1135 'uploader': 'Heather',
1136 },
1137 },
1138 # NBC Sports vplayer embed
1139 {
1140 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1141 'info_dict': {
1142 'id': 'ln7x1qSThw4k',
1143 'ext': 'flv',
1144 'title': "PFT Live: New leader in the 'new-look' defense",
1145 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1146 'uploader': 'NBCU-SPORTS',
1147 'upload_date': '20140107',
1148 'timestamp': 1389118457,
1149 },
1150 },
1151 # NBC News embed
1152 {
1153 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1154 'md5': '1aa589c675898ae6d37a17913cf68d66',
1155 'info_dict': {
1156 'id': '701714499682',
1157 'ext': 'mp4',
1158 'title': 'PREVIEW: On Assignment: David Letterman',
1159 '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.',
1160 },
1161 },
1162 # UDN embed
1163 {
1164 'url': 'https://video.udn.com/news/300346',
1165 'md5': 'fd2060e988c326991037b9aff9df21a6',
1166 'info_dict': {
1167 'id': '300346',
1168 'ext': 'mp4',
1169 'title': '中一中男師變性 全校師生力挺',
1170 'thumbnail': r're:^https?://.*\.jpg$',
1171 },
1172 'params': {
1173 # m3u8 download
1174 'skip_download': True,
1175 },
1176 },
1177 # Ooyala embed
1178 {
1179 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1180 'info_dict': {
1181 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1182 'ext': 'mp4',
1183 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1184 'title': 'This is what separates the Excel masters from the wannabes',
1185 'duration': 191.933,
1186 },
1187 'params': {
1188 # m3u8 downloads
1189 'skip_download': True,
1190 }
1191 },
1192 # Brightcove URL in single quotes
1193 {
1194 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1195 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1196 'info_dict': {
1197 'id': '4255764656001',
1198 'ext': 'mp4',
1199 'title': 'SN Presents: Russell Martin, World Citizen',
1200 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1201 'uploader': 'Rogers Sportsnet',
1202 'uploader_id': '1704050871',
1203 'upload_date': '20150525',
1204 'timestamp': 1432570283,
1205 },
1206 },
1207 # Dailymotion Cloud video
1208 {
1209 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1210 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1211 'info_dict': {
1212 'id': 'x2uy8t3',
1213 'ext': 'mp4',
1214 'title': 'Sauvons les abeilles ! - Le débat',
1215 'description': 'md5:d9082128b1c5277987825d684939ca26',
1216 'thumbnail': r're:^https?://.*\.jpe?g$',
1217 'timestamp': 1434970506,
1218 'upload_date': '20150622',
1219 'uploader': 'Public Sénat',
1220 'uploader_id': 'xa9gza',
1221 }
1222 },
1223 # OnionStudios embed
1224 {
1225 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1226 'info_dict': {
1227 'id': '2855',
1228 'ext': 'mp4',
1229 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1230 'thumbnail': r're:^https?://.*\.jpe?g$',
1231 'uploader': 'ClickHole',
1232 'uploader_id': 'clickhole',
1233 }
1234 },
1235 # SnagFilms embed
1236 {
1237 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1238 'info_dict': {
1239 'id': '74849a00-85a9-11e1-9660-123139220831',
1240 'ext': 'mp4',
1241 'title': '#whilewewatch',
1242 }
1243 },
1244 # AdobeTVVideo embed
1245 {
1246 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1247 'md5': '43662b577c018ad707a63766462b1e87',
1248 'info_dict': {
1249 'id': '2456',
1250 'ext': 'mp4',
1251 'title': 'New experience with Acrobat DC',
1252 'description': 'New experience with Acrobat DC',
1253 'duration': 248.667,
1254 },
1255 },
1256 # BrightcoveInPageEmbed embed
1257 {
1258 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1259 'info_dict': {
1260 'id': '4238694884001',
1261 'ext': 'flv',
1262 'title': 'Tabletop: Dread, Last Thoughts',
1263 'description': 'Tabletop: Dread, Last Thoughts',
1264 'duration': 51690,
1265 },
1266 },
1267 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1268 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1269 {
1270 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1271 'info_dict': {
1272 'id': '4785848093001',
1273 'ext': 'mp4',
1274 'title': 'The Cardinal Pell Interview',
1275 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1276 'uploader': 'GlobeCast Australia - GlobeStream',
1277 'uploader_id': '2733773828001',
1278 'upload_date': '20160304',
1279 'timestamp': 1457083087,
1280 },
1281 'params': {
1282 # m3u8 downloads
1283 'skip_download': True,
1284 },
1285 },
1286 # Another form of arte.tv embed
1287 {
1288 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1289 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1290 'info_dict': {
1291 'id': '030273-562_PLUS7-F',
1292 'ext': 'mp4',
1293 'title': 'ARTE Reportage - Nulle part, en France',
1294 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1295 'upload_date': '20160409',
1296 },
1297 },
1298 # LiveLeak embed
1299 {
1300 'url': 'http://www.wykop.pl/link/3088787/',
1301 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1302 'info_dict': {
1303 'id': '874_1459135191',
1304 'ext': 'mp4',
1305 'title': 'Man shows poor quality of new apartment building',
1306 'description': 'The wall is like a sand pile.',
1307 'uploader': 'Lake8737',
1308 }
1309 },
1310 # Duplicated embedded video URLs
1311 {
1312 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1313 'info_dict': {
1314 'id': '149298443_480_16c25b74_2',
1315 'ext': 'mp4',
1316 'title': 'vs. Blue Orange Spring Game',
1317 'uploader': 'www.hudl.com',
1318 },
1319 },
1320 # twitter:player:stream embed
1321 {
1322 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1323 'info_dict': {
1324 'id': 'master',
1325 'ext': 'mp4',
1326 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1327 'uploader': 'www.rtl.be',
1328 },
1329 'params': {
1330 # m3u8 downloads
1331 'skip_download': True,
1332 },
1333 },
1334 # twitter:player embed
1335 {
1336 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1337 'md5': 'a3e0df96369831de324f0778e126653c',
1338 'info_dict': {
1339 'id': '4909620399001',
1340 'ext': 'mp4',
1341 'title': 'What Do Black Holes Sound Like?',
1342 'description': 'what do black holes sound like',
1343 'upload_date': '20160524',
1344 'uploader_id': '29913724001',
1345 'timestamp': 1464107587,
1346 'uploader': 'TheAtlantic',
1347 },
1348 'add_ie': ['BrightcoveLegacy'],
1349 },
1350 # Facebook <iframe> embed
1351 {
1352 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1353 'md5': 'fbcde74f534176ecb015849146dd3aee',
1354 'info_dict': {
1355 'id': '599637780109885',
1356 'ext': 'mp4',
1357 'title': 'Facebook video #599637780109885',
1358 },
1359 },
1360 # Facebook API embed
1361 {
1362 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1363 'md5': 'a47372ee61b39a7b90287094d447d94e',
1364 'info_dict': {
1365 'id': '10153467542406923',
1366 'ext': 'mp4',
1367 'title': 'Facebook video #10153467542406923',
1368 },
1369 },
1370 # Wordpress "YouTube Video Importer" plugin
1371 {
1372 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1373 'md5': 'd16797741b560b485194eddda8121b48',
1374 'info_dict': {
1375 'id': 'HNTXWDXV9Is',
1376 'ext': 'mp4',
1377 'title': 'Blue Devils Drumline Stanford lot 2016',
1378 'upload_date': '20160627',
1379 'uploader_id': 'GENOCIDE8GENERAL10',
1380 'uploader': 'cylus cyrus',
1381 },
1382 },
1383 {
1384 # video stored on custom kaltura server
1385 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1386 'md5': '537617d06e64dfed891fa1593c4b30cc',
1387 'info_dict': {
1388 'id': '0_1iotm5bh',
1389 'ext': 'mp4',
1390 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1391 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1392 'uploader_id': 'videos.expansion@el-mundo.net',
1393 'upload_date': '20150429',
1394 'timestamp': 1430303472,
1395 },
1396 'add_ie': ['Kaltura'],
1397 },
1398 {
1399 # Non-standard Vimeo embed
1400 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1401 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1402 'info_dict': {
1403 'id': '148867247',
1404 'ext': 'mp4',
1405 'title': 'Understanding the web - Teaser',
1406 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1407 'upload_date': '20151214',
1408 'uploader': 'OpenClassrooms',
1409 'uploader_id': 'openclassrooms',
1410 },
1411 'add_ie': ['Vimeo'],
1412 },
1413 {
1414 # generic vimeo embed that requires original URL passed as Referer
1415 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1416 'only_matching': True,
1417 },
1418 {
1419 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1420 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1421 'info_dict': {
1422 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1423 'ext': 'mp4',
1424 'title': 'Big Buck Bunny',
1425 'description': 'Royalty free test video',
1426 'timestamp': 1432816365,
1427 'upload_date': '20150528',
1428 'is_live': False,
1429 },
1430 'params': {
1431 'skip_download': True,
1432 },
1433 'add_ie': [ArkenaIE.ie_key()],
1434 },
1435 {
1436 '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/',
1437 'info_dict': {
1438 'id': '1c7141f46c',
1439 'ext': 'mp4',
1440 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1441 },
1442 'params': {
1443 'skip_download': True,
1444 },
1445 'add_ie': [Vbox7IE.ie_key()],
1446 },
1447 {
1448 # DBTV embeds
1449 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1450 'info_dict': {
1451 'id': '43254897',
1452 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1453 },
1454 'playlist_mincount': 3,
1455 },
1456 {
1457 # Videa embeds
1458 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1459 'info_dict': {
1460 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1461 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1462 },
1463 'playlist_mincount': 2,
1464 },
1465 {
1466 # 20 minuten embed
1467 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1468 'info_dict': {
1469 'id': '523629',
1470 'ext': 'mp4',
1471 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1472 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1473 },
1474 'params': {
1475 'skip_download': True,
1476 },
1477 'add_ie': [TwentyMinutenIE.ie_key()],
1478 },
1479 {
1480 # VideoPress embed
1481 'url': 'https://en.support.wordpress.com/videopress/',
1482 'info_dict': {
1483 'id': 'OcobLTqC',
1484 'ext': 'm4v',
1485 'title': 'IMG_5786',
1486 'timestamp': 1435711927,
1487 'upload_date': '20150701',
1488 },
1489 'params': {
1490 'skip_download': True,
1491 },
1492 'add_ie': [VideoPressIE.ie_key()],
1493 }
1494 # {
1495 # # TODO: find another test
1496 # # http://schema.org/VideoObject
1497 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1498 # 'md5': '888dcf08b7ea671381f00fab74692755',
1499 # 'info_dict': {
1500 # 'id': 'nyvTSJMKId',
1501 # 'ext': 'mp4',
1502 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1503 # 'description': '#love for cats.',
1504 # 'timestamp': 1461244995,
1505 # 'upload_date': '20160421',
1506 # },
1507 # 'params': {
1508 # 'force_generic_extractor': True,
1509 # },
1510 # }
1511 ]
1512
1513 def report_following_redirect(self, new_url):
1514 """Report information extraction."""
1515 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1516
1517 def _extract_rss(self, url, video_id, doc):
1518 playlist_title = doc.find('./channel/title').text
1519 playlist_desc_el = doc.find('./channel/description')
1520 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1521
1522 entries = []
1523 for it in doc.findall('./channel/item'):
1524 next_url = xpath_text(it, 'link', fatal=False)
1525 if not next_url:
1526 enclosure_nodes = it.findall('./enclosure')
1527 for e in enclosure_nodes:
1528 next_url = e.attrib.get('url')
1529 if next_url:
1530 break
1531
1532 if not next_url:
1533 continue
1534
1535 entries.append({
1536 '_type': 'url',
1537 'url': next_url,
1538 'title': it.find('title').text,
1539 })
1540
1541 return {
1542 '_type': 'playlist',
1543 'id': url,
1544 'title': playlist_title,
1545 'description': playlist_desc,
1546 'entries': entries,
1547 }
1548
1549 def _extract_camtasia(self, url, video_id, webpage):
1550 """ Returns None if no camtasia video can be found. """
1551
1552 camtasia_cfg = self._search_regex(
1553 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1554 webpage, 'camtasia configuration file', default=None)
1555 if camtasia_cfg is None:
1556 return None
1557
1558 title = self._html_search_meta('DC.title', webpage, fatal=True)
1559
1560 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1561 camtasia_cfg = self._download_xml(
1562 camtasia_url, video_id,
1563 note='Downloading camtasia configuration',
1564 errnote='Failed to download camtasia configuration')
1565 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1566
1567 entries = []
1568 for n in fileset_node.getchildren():
1569 url_n = n.find('./uri')
1570 if url_n is None:
1571 continue
1572
1573 entries.append({
1574 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1575 'title': '%s - %s' % (title, n.tag),
1576 'url': compat_urlparse.urljoin(url, url_n.text),
1577 'duration': float_or_none(n.find('./duration').text),
1578 })
1579
1580 return {
1581 '_type': 'playlist',
1582 'entries': entries,
1583 'title': title,
1584 }
1585
1586 def _real_extract(self, url):
1587 if url.startswith('//'):
1588 return {
1589 '_type': 'url',
1590 'url': self.http_scheme() + url,
1591 }
1592
1593 parsed_url = compat_urlparse.urlparse(url)
1594 if not parsed_url.scheme:
1595 default_search = self._downloader.params.get('default_search')
1596 if default_search is None:
1597 default_search = 'fixup_error'
1598
1599 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1600 if '/' in url:
1601 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1602 return self.url_result('http://' + url)
1603 elif default_search != 'fixup_error':
1604 if default_search == 'auto_warning':
1605 if re.match(r'^(?:url|URL)$', url):
1606 raise ExtractorError(
1607 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1608 expected=True)
1609 else:
1610 self._downloader.report_warning(
1611 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1612 return self.url_result('ytsearch:' + url)
1613
1614 if default_search in ('error', 'fixup_error'):
1615 raise ExtractorError(
1616 '%r is not a valid URL. '
1617 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1618 % (url, url), expected=True)
1619 else:
1620 if ':' not in default_search:
1621 default_search += ':'
1622 return self.url_result(default_search + url)
1623
1624 url, smuggled_data = unsmuggle_url(url)
1625 force_videoid = None
1626 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1627 if smuggled_data and 'force_videoid' in smuggled_data:
1628 force_videoid = smuggled_data['force_videoid']
1629 video_id = force_videoid
1630 else:
1631 video_id = self._generic_id(url)
1632
1633 self.to_screen('%s: Requesting header' % video_id)
1634
1635 head_req = HEADRequest(url)
1636 head_response = self._request_webpage(
1637 head_req, video_id,
1638 note=False, errnote='Could not send HEAD request to %s' % url,
1639 fatal=False)
1640
1641 if head_response is not False:
1642 # Check for redirect
1643 new_url = head_response.geturl()
1644 if url != new_url:
1645 self.report_following_redirect(new_url)
1646 if force_videoid:
1647 new_url = smuggle_url(
1648 new_url, {'force_videoid': force_videoid})
1649 return self.url_result(new_url)
1650
1651 full_response = None
1652 if head_response is False:
1653 request = sanitized_Request(url)
1654 request.add_header('Accept-Encoding', '*')
1655 full_response = self._request_webpage(request, video_id)
1656 head_response = full_response
1657
1658 info_dict = {
1659 'id': video_id,
1660 'title': self._generic_title(url),
1661 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1662 }
1663
1664 # Check for direct link to a video
1665 content_type = head_response.headers.get('Content-Type', '').lower()
1666 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1667 if m:
1668 format_id = m.group('format_id')
1669 if format_id.endswith('mpegurl'):
1670 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1671 elif format_id == 'f4m':
1672 formats = self._extract_f4m_formats(url, video_id)
1673 else:
1674 formats = [{
1675 'format_id': m.group('format_id'),
1676 'url': url,
1677 'vcodec': 'none' if m.group('type') == 'audio' else None
1678 }]
1679 info_dict['direct'] = True
1680 self._sort_formats(formats)
1681 info_dict['formats'] = formats
1682 return info_dict
1683
1684 if not self._downloader.params.get('test', False) and not is_intentional:
1685 force = self._downloader.params.get('force_generic_extractor', False)
1686 self._downloader.report_warning(
1687 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1688
1689 if not full_response:
1690 request = sanitized_Request(url)
1691 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1692 # making it impossible to download only chunk of the file (yet we need only 512kB to
1693 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1694 # that will always result in downloading the whole file that is not desirable.
1695 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1696 # to accept raw bytes and being able to download only a chunk.
1697 # It may probably better to solve this by checking Content-Type for application/octet-stream
1698 # after HEAD request finishes, but not sure if we can rely on this.
1699 request.add_header('Accept-Encoding', '*')
1700 full_response = self._request_webpage(request, video_id)
1701
1702 first_bytes = full_response.read(512)
1703
1704 # Is it an M3U playlist?
1705 if first_bytes.startswith(b'#EXTM3U'):
1706 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1707 self._sort_formats(info_dict['formats'])
1708 return info_dict
1709
1710 # Maybe it's a direct link to a video?
1711 # Be careful not to download the whole thing!
1712 if not is_html(first_bytes):
1713 self._downloader.report_warning(
1714 'URL could be a direct video link, returning it as such.')
1715 info_dict.update({
1716 'direct': True,
1717 'url': url,
1718 })
1719 return info_dict
1720
1721 webpage = self._webpage_read_content(
1722 full_response, url, video_id, prefix=first_bytes)
1723
1724 self.report_extraction(video_id)
1725
1726 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1727 try:
1728 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1729 if doc.tag == 'rss':
1730 return self._extract_rss(url, video_id, doc)
1731 elif doc.tag == 'SmoothStreamingMedia':
1732 info_dict['formats'] = self._parse_ism_formats(doc, url)
1733 self._sort_formats(info_dict['formats'])
1734 return info_dict
1735 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1736 smil = self._parse_smil(doc, url, video_id)
1737 self._sort_formats(smil['formats'])
1738 return smil
1739 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1740 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1741 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1742 info_dict['formats'] = self._parse_mpd_formats(
1743 doc, video_id,
1744 mpd_base_url=full_response.geturl().rpartition('/')[0],
1745 mpd_url=url)
1746 self._sort_formats(info_dict['formats'])
1747 return info_dict
1748 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1749 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1750 self._sort_formats(info_dict['formats'])
1751 return info_dict
1752 except compat_xml_parse_error:
1753 pass
1754
1755 # Is it a Camtasia project?
1756 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1757 if camtasia_res is not None:
1758 return camtasia_res
1759
1760 # Sometimes embedded video player is hidden behind percent encoding
1761 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1762 # Unescaping the whole page allows to handle those cases in a generic way
1763 webpage = compat_urllib_parse_unquote(webpage)
1764
1765 # it's tempting to parse this further, but you would
1766 # have to take into account all the variations like
1767 # Video Title - Site Name
1768 # Site Name | Video Title
1769 # Video Title - Tagline | Site Name
1770 # and so on and so forth; it's just not practical
1771 video_title = self._og_search_title(
1772 webpage, default=None) or self._html_search_regex(
1773 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1774 default='video')
1775
1776 # Try to detect age limit automatically
1777 age_limit = self._rta_search(webpage)
1778 # And then there are the jokers who advertise that they use RTA,
1779 # but actually don't.
1780 AGE_LIMIT_MARKERS = [
1781 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1782 ]
1783 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1784 age_limit = 18
1785
1786 # video uploader is domain name
1787 video_uploader = self._search_regex(
1788 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1789
1790 video_description = self._og_search_description(webpage, default=None)
1791 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1792
1793 # Helper method
1794 def _playlist_from_matches(matches, getter=None, ie=None):
1795 urlrs = orderedSet(
1796 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1797 for m in matches)
1798 return self.playlist_result(
1799 urlrs, playlist_id=video_id, playlist_title=video_title)
1800
1801 # Look for Brightcove Legacy Studio embeds
1802 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1803 if bc_urls:
1804 self.to_screen('Brightcove video detected.')
1805 entries = [{
1806 '_type': 'url',
1807 'url': smuggle_url(bc_url, {'Referer': url}),
1808 'ie_key': 'BrightcoveLegacy'
1809 } for bc_url in bc_urls]
1810
1811 return {
1812 '_type': 'playlist',
1813 'title': video_title,
1814 'id': video_id,
1815 'entries': entries,
1816 }
1817
1818 # Look for Brightcove New Studio embeds
1819 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1820 if bc_urls:
1821 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1822
1823 # Look for ThePlatform embeds
1824 tp_urls = ThePlatformIE._extract_urls(webpage)
1825 if tp_urls:
1826 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1827
1828 # Look for Vessel embeds
1829 vessel_urls = VesselIE._extract_urls(webpage)
1830 if vessel_urls:
1831 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1832
1833 # Look for embedded rtl.nl player
1834 matches = re.findall(
1835 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1836 webpage)
1837 if matches:
1838 return _playlist_from_matches(matches, ie='RtlNl')
1839
1840 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1841 if vimeo_urls:
1842 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1843
1844 vid_me_embed_url = self._search_regex(
1845 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1846 webpage, 'vid.me embed', default=None)
1847 if vid_me_embed_url is not None:
1848 return self.url_result(vid_me_embed_url, 'Vidme')
1849
1850 # Look for embedded YouTube player
1851 matches = re.findall(r'''(?x)
1852 (?:
1853 <iframe[^>]+?src=|
1854 data-video-url=|
1855 <embed[^>]+?src=|
1856 embedSWF\(?:\s*|
1857 new\s+SWFObject\(
1858 )
1859 (["\'])
1860 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1861 (?:embed|v|p)/.+?)
1862 \1''', webpage)
1863 if matches:
1864 return _playlist_from_matches(
1865 matches, lambda m: unescapeHTML(m[1]))
1866
1867 # Look for lazyYT YouTube embed
1868 matches = re.findall(
1869 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1870 if matches:
1871 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1872
1873 # Look for Wordpress "YouTube Video Importer" plugin
1874 matches = re.findall(r'''(?x)<div[^>]+
1875 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1876 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1877 if matches:
1878 return _playlist_from_matches(matches, lambda m: m[-1])
1879
1880 matches = DailymotionIE._extract_urls(webpage)
1881 if matches:
1882 return _playlist_from_matches(matches)
1883
1884 # Look for embedded Dailymotion playlist player (#3822)
1885 m = re.search(
1886 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1887 if m:
1888 playlists = re.findall(
1889 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1890 if playlists:
1891 return _playlist_from_matches(
1892 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1893
1894 # Look for embedded Wistia player
1895 match = re.search(
1896 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1897 if match:
1898 embed_url = self._proto_relative_url(
1899 unescapeHTML(match.group('url')))
1900 return {
1901 '_type': 'url_transparent',
1902 'url': embed_url,
1903 'ie_key': 'Wistia',
1904 'uploader': video_uploader,
1905 }
1906
1907 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1908 if match:
1909 return {
1910 '_type': 'url_transparent',
1911 'url': 'wistia:%s' % match.group('id'),
1912 'ie_key': 'Wistia',
1913 'uploader': video_uploader,
1914 }
1915
1916 match = re.search(
1917 r'''(?sx)
1918 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1919 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1920 ''', webpage)
1921 if match:
1922 return self.url_result(self._proto_relative_url(
1923 'wistia:%s' % match.group('id')), 'Wistia')
1924
1925 # Look for SVT player
1926 svt_url = SVTIE._extract_url(webpage)
1927 if svt_url:
1928 return self.url_result(svt_url, 'SVT')
1929
1930 # Look for embedded condenast player
1931 matches = re.findall(
1932 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1933 webpage)
1934 if matches:
1935 return {
1936 '_type': 'playlist',
1937 'entries': [{
1938 '_type': 'url',
1939 'ie_key': 'CondeNast',
1940 'url': ma,
1941 } for ma in matches],
1942 'title': video_title,
1943 'id': video_id,
1944 }
1945
1946 # Look for Bandcamp pages with custom domain
1947 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1948 if mobj is not None:
1949 burl = unescapeHTML(mobj.group(1))
1950 # Don't set the extractor because it can be a track url or an album
1951 return self.url_result(burl)
1952
1953 # Look for embedded Vevo player
1954 mobj = re.search(
1955 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1956 if mobj is not None:
1957 return self.url_result(mobj.group('url'))
1958
1959 # Look for embedded Viddler player
1960 mobj = re.search(
1961 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1962 webpage)
1963 if mobj is not None:
1964 return self.url_result(mobj.group('url'))
1965
1966 # Look for NYTimes player
1967 mobj = re.search(
1968 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1969 webpage)
1970 if mobj is not None:
1971 return self.url_result(mobj.group('url'))
1972
1973 # Look for Libsyn player
1974 mobj = re.search(
1975 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1976 if mobj is not None:
1977 return self.url_result(mobj.group('url'))
1978
1979 # Look for Ooyala videos
1980 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1981 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1982 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1983 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1984 if mobj is not None:
1985 embed_token = self._search_regex(
1986 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1987 webpage, 'ooyala embed token', default=None)
1988 return OoyalaIE._build_url_result(smuggle_url(
1989 mobj.group('ec'), {
1990 'domain': url,
1991 'embed_token': embed_token,
1992 }))
1993
1994 # Look for multiple Ooyala embeds on SBN network websites
1995 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1996 if mobj is not None:
1997 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1998 if embeds:
1999 return _playlist_from_matches(
2000 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2001
2002 # Look for Aparat videos
2003 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2004 if mobj is not None:
2005 return self.url_result(mobj.group(1), 'Aparat')
2006
2007 # Look for MPORA videos
2008 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2009 if mobj is not None:
2010 return self.url_result(mobj.group(1), 'Mpora')
2011
2012 # Look for embedded NovaMov-based player
2013 mobj = re.search(
2014 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2015 (?P<url>http://(?:(?:embed|www)\.)?
2016 (?:novamov\.com|
2017 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2018 videoweed\.(?:es|com)|
2019 movshare\.(?:net|sx|ag)|
2020 divxstage\.(?:eu|net|ch|co|at|ag))
2021 /embed\.php.+?)\1''', webpage)
2022 if mobj is not None:
2023 return self.url_result(mobj.group('url'))
2024
2025 # Look for embedded Facebook player
2026 facebook_url = FacebookIE._extract_url(webpage)
2027 if facebook_url is not None:
2028 return self.url_result(facebook_url, 'Facebook')
2029
2030 # Look for embedded VK player
2031 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2032 if mobj is not None:
2033 return self.url_result(mobj.group('url'), 'VK')
2034
2035 # Look for embedded Odnoklassniki player
2036 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2037 if mobj is not None:
2038 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2039
2040 # Look for embedded ivi player
2041 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2042 if mobj is not None:
2043 return self.url_result(mobj.group('url'), 'Ivi')
2044
2045 # Look for embedded Huffington Post player
2046 mobj = re.search(
2047 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2048 if mobj is not None:
2049 return self.url_result(mobj.group('url'), 'HuffPost')
2050
2051 # Look for embed.ly
2052 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2053 if mobj is not None:
2054 return self.url_result(mobj.group('url'))
2055 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2056 if mobj is not None:
2057 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2058
2059 # Look for funnyordie embed
2060 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2061 if matches:
2062 return _playlist_from_matches(
2063 matches, getter=unescapeHTML, ie='FunnyOrDie')
2064
2065 # Look for BBC iPlayer embed
2066 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2067 if matches:
2068 return _playlist_from_matches(matches, ie='BBCCoUk')
2069
2070 # Look for embedded RUTV player
2071 rutv_url = RUTVIE._extract_url(webpage)
2072 if rutv_url:
2073 return self.url_result(rutv_url, 'RUTV')
2074
2075 # Look for embedded TVC player
2076 tvc_url = TVCIE._extract_url(webpage)
2077 if tvc_url:
2078 return self.url_result(tvc_url, 'TVC')
2079
2080 # Look for embedded SportBox player
2081 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2082 if sportbox_urls:
2083 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2084
2085 # Look for embedded XHamster player
2086 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2087 if xhamster_urls:
2088 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2089
2090 # Look for embedded TNAFlixNetwork player
2091 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2092 if tnaflix_urls:
2093 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2094
2095 # Look for embedded PornHub player
2096 pornhub_urls = PornHubIE._extract_urls(webpage)
2097 if pornhub_urls:
2098 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2099
2100 # Look for embedded DrTuber player
2101 drtuber_urls = DrTuberIE._extract_urls(webpage)
2102 if drtuber_urls:
2103 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2104
2105 # Look for embedded RedTube player
2106 redtube_urls = RedTubeIE._extract_urls(webpage)
2107 if redtube_urls:
2108 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2109
2110 # Look for embedded Tvigle player
2111 mobj = re.search(
2112 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2113 if mobj is not None:
2114 return self.url_result(mobj.group('url'), 'Tvigle')
2115
2116 # Look for embedded TED player
2117 mobj = re.search(
2118 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2119 if mobj is not None:
2120 return self.url_result(mobj.group('url'), 'TED')
2121
2122 # Look for embedded Ustream videos
2123 ustream_url = UstreamIE._extract_url(webpage)
2124 if ustream_url:
2125 return self.url_result(ustream_url, UstreamIE.ie_key())
2126
2127 # Look for embedded arte.tv player
2128 mobj = re.search(
2129 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2130 webpage)
2131 if mobj is not None:
2132 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2133
2134 # Look for embedded francetv player
2135 mobj = re.search(
2136 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2137 webpage)
2138 if mobj is not None:
2139 return self.url_result(mobj.group('url'))
2140
2141 # Look for embedded smotri.com player
2142 smotri_url = SmotriIE._extract_url(webpage)
2143 if smotri_url:
2144 return self.url_result(smotri_url, 'Smotri')
2145
2146 # Look for embedded Myvi.ru player
2147 myvi_url = MyviIE._extract_url(webpage)
2148 if myvi_url:
2149 return self.url_result(myvi_url)
2150
2151 # Look for embedded soundcloud player
2152 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2153 if soundcloud_urls:
2154 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2155
2156 # Look for tunein player
2157 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2158 if tunein_urls:
2159 return _playlist_from_matches(tunein_urls)
2160
2161 # Look for embedded mtvservices player
2162 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2163 if mtvservices_url:
2164 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2165
2166 # Look for embedded yahoo player
2167 mobj = re.search(
2168 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2169 webpage)
2170 if mobj is not None:
2171 return self.url_result(mobj.group('url'), 'Yahoo')
2172
2173 # Look for embedded sbs.com.au player
2174 mobj = re.search(
2175 r'''(?x)
2176 (?:
2177 <meta\s+property="og:video"\s+content=|
2178 <iframe[^>]+?src=
2179 )
2180 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2181 webpage)
2182 if mobj is not None:
2183 return self.url_result(mobj.group('url'), 'SBS')
2184
2185 # Look for embedded Cinchcast player
2186 mobj = re.search(
2187 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2188 webpage)
2189 if mobj is not None:
2190 return self.url_result(mobj.group('url'), 'Cinchcast')
2191
2192 mobj = re.search(
2193 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2194 webpage)
2195 if not mobj:
2196 mobj = re.search(
2197 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2198 webpage)
2199 if mobj is not None:
2200 return self.url_result(mobj.group('url'), 'MLB')
2201
2202 mobj = re.search(
2203 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2204 webpage)
2205 if mobj is not None:
2206 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2207
2208 mobj = re.search(
2209 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2210 webpage)
2211 if mobj is not None:
2212 return self.url_result(mobj.group('url'), 'Livestream')
2213
2214 # Look for Zapiks embed
2215 mobj = re.search(
2216 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2217 if mobj is not None:
2218 return self.url_result(mobj.group('url'), 'Zapiks')
2219
2220 # Look for Kaltura embeds
2221 kaltura_url = KalturaIE._extract_url(webpage)
2222 if kaltura_url:
2223 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2224
2225 # Look for Eagle.Platform embeds
2226 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2227 if eagleplatform_url:
2228 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2229
2230 # Look for ClipYou (uses Eagle.Platform) embeds
2231 mobj = re.search(
2232 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2233 if mobj is not None:
2234 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2235
2236 # Look for Pladform embeds
2237 pladform_url = PladformIE._extract_url(webpage)
2238 if pladform_url:
2239 return self.url_result(pladform_url)
2240
2241 # Look for Videomore embeds
2242 videomore_url = VideomoreIE._extract_url(webpage)
2243 if videomore_url:
2244 return self.url_result(videomore_url)
2245
2246 # Look for Webcaster embeds
2247 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2248 if webcaster_url:
2249 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2250
2251 # Look for Playwire embeds
2252 mobj = re.search(
2253 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2254 if mobj is not None:
2255 return self.url_result(mobj.group('url'))
2256
2257 # Look for 5min embeds
2258 mobj = re.search(
2259 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2260 if mobj is not None:
2261 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2262
2263 # Look for Crooks and Liars embeds
2264 mobj = re.search(
2265 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2266 if mobj is not None:
2267 return self.url_result(mobj.group('url'))
2268
2269 # Look for NBC Sports VPlayer embeds
2270 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2271 if nbc_sports_url:
2272 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2273
2274 # Look for NBC News embeds
2275 nbc_news_embed_url = re.search(
2276 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2277 if nbc_news_embed_url:
2278 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2279
2280 # Look for Google Drive embeds
2281 google_drive_url = GoogleDriveIE._extract_url(webpage)
2282 if google_drive_url:
2283 return self.url_result(google_drive_url, 'GoogleDrive')
2284
2285 # Look for UDN embeds
2286 mobj = re.search(
2287 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2288 if mobj is not None:
2289 return self.url_result(
2290 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2291
2292 # Look for Senate ISVP iframe
2293 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2294 if senate_isvp_url:
2295 return self.url_result(senate_isvp_url, 'SenateISVP')
2296
2297 # Look for Dailymotion Cloud videos
2298 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2299 if dmcloud_url:
2300 return self.url_result(dmcloud_url, 'DailymotionCloud')
2301
2302 # Look for OnionStudios embeds
2303 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2304 if onionstudios_url:
2305 return self.url_result(onionstudios_url)
2306
2307 # Look for ViewLift embeds
2308 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2309 if viewlift_url:
2310 return self.url_result(viewlift_url)
2311
2312 # Look for JWPlatform embeds
2313 jwplatform_url = JWPlatformIE._extract_url(webpage)
2314 if jwplatform_url:
2315 return self.url_result(jwplatform_url, 'JWPlatform')
2316
2317 # Look for Digiteka embeds
2318 digiteka_url = DigitekaIE._extract_url(webpage)
2319 if digiteka_url:
2320 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2321
2322 # Look for Arkena embeds
2323 arkena_url = ArkenaIE._extract_url(webpage)
2324 if arkena_url:
2325 return self.url_result(arkena_url, ArkenaIE.ie_key())
2326
2327 # Look for Piksel embeds
2328 piksel_url = PikselIE._extract_url(webpage)
2329 if piksel_url:
2330 return self.url_result(piksel_url, PikselIE.ie_key())
2331
2332 # Look for Limelight embeds
2333 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2334 if mobj:
2335 lm = {
2336 'Media': 'media',
2337 'Channel': 'channel',
2338 'ChannelList': 'channel_list',
2339 }
2340 return self.url_result('limelight:%s:%s' % (
2341 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2342
2343 mobj = re.search(
2344 r'''(?sx)
2345 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2346 <param[^>]+
2347 name=(["\'])flashVars\2[^>]+
2348 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2349 ''', webpage)
2350 if mobj:
2351 return self.url_result('limelight:media:%s' % mobj.group('id'))
2352
2353 # Look for AdobeTVVideo embeds
2354 mobj = re.search(
2355 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2356 webpage)
2357 if mobj is not None:
2358 return self.url_result(
2359 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2360 'AdobeTVVideo')
2361
2362 # Look for Vine embeds
2363 mobj = re.search(
2364 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2365 webpage)
2366 if mobj is not None:
2367 return self.url_result(
2368 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2369
2370 # Look for VODPlatform embeds
2371 mobj = re.search(
2372 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2373 webpage)
2374 if mobj is not None:
2375 return self.url_result(
2376 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2377
2378 # Look for Mangomolo embeds
2379 mobj = re.search(
2380 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2381 (?:
2382 video\?.*?\bid=(?P<video_id>\d+)|
2383 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2384 ).+?)\1''', webpage)
2385 if mobj is not None:
2386 info = {
2387 '_type': 'url_transparent',
2388 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2389 'title': video_title,
2390 'description': video_description,
2391 'thumbnail': video_thumbnail,
2392 'uploader': video_uploader,
2393 }
2394 video_id = mobj.group('video_id')
2395 if video_id:
2396 info.update({
2397 'ie_key': 'MangomoloVideo',
2398 'id': video_id,
2399 })
2400 else:
2401 info.update({
2402 'ie_key': 'MangomoloLive',
2403 'id': mobj.group('channel_id'),
2404 })
2405 return info
2406
2407 # Look for Instagram embeds
2408 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2409 if instagram_embed_url is not None:
2410 return self.url_result(
2411 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2412
2413 # Look for LiveLeak embeds
2414 liveleak_url = LiveLeakIE._extract_url(webpage)
2415 if liveleak_url:
2416 return self.url_result(liveleak_url, 'LiveLeak')
2417
2418 # Look for 3Q SDN embeds
2419 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2420 if threeqsdn_url:
2421 return {
2422 '_type': 'url_transparent',
2423 'ie_key': ThreeQSDNIE.ie_key(),
2424 'url': self._proto_relative_url(threeqsdn_url),
2425 'title': video_title,
2426 'description': video_description,
2427 'thumbnail': video_thumbnail,
2428 'uploader': video_uploader,
2429 }
2430
2431 # Look for VBOX7 embeds
2432 vbox7_url = Vbox7IE._extract_url(webpage)
2433 if vbox7_url:
2434 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2435
2436 # Look for DBTV embeds
2437 dbtv_urls = DBTVIE._extract_urls(webpage)
2438 if dbtv_urls:
2439 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2440
2441 # Look for Videa embeds
2442 videa_urls = VideaIE._extract_urls(webpage)
2443 if videa_urls:
2444 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2445
2446 # Look for 20 minuten embeds
2447 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2448 if twentymin_urls:
2449 return _playlist_from_matches(
2450 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2451
2452 # Look for Openload embeds
2453 openload_urls = OpenloadIE._extract_urls(webpage)
2454 if openload_urls:
2455 return _playlist_from_matches(
2456 openload_urls, ie=OpenloadIE.ie_key())
2457
2458 # Look for VideoPress embeds
2459 videopress_urls = VideoPressIE._extract_urls(webpage)
2460 if videopress_urls:
2461 return _playlist_from_matches(
2462 videopress_urls, ie=VideoPressIE.ie_key())
2463
2464 # Looking for http://schema.org/VideoObject
2465 json_ld = self._search_json_ld(
2466 webpage, video_id, default={}, expected_type='VideoObject')
2467 if json_ld.get('url'):
2468 info_dict.update({
2469 'title': video_title or info_dict['title'],
2470 'description': video_description,
2471 'thumbnail': video_thumbnail,
2472 'age_limit': age_limit
2473 })
2474 info_dict.update(json_ld)
2475 return info_dict
2476
2477 # Look for HTML5 media
2478 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2479 if entries:
2480 for entry in entries:
2481 entry.update({
2482 'id': video_id,
2483 'title': video_title,
2484 })
2485 self._sort_formats(entry['formats'])
2486 return self.playlist_result(entries)
2487
2488 def check_video(vurl):
2489 if YoutubeIE.suitable(vurl):
2490 return True
2491 if RtmpIE.suitable(vurl):
2492 return True
2493 vpath = compat_urlparse.urlparse(vurl).path
2494 vext = determine_ext(vpath)
2495 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2496
2497 def filter_video(urls):
2498 return list(filter(check_video, urls))
2499
2500 # Start with something easy: JW Player in SWFObject
2501 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2502 if not found:
2503 # Look for gorilla-vid style embedding
2504 found = filter_video(re.findall(r'''(?sx)
2505 (?:
2506 jw_plugins|
2507 JWPlayerOptions|
2508 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2509 )
2510 .*?
2511 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2512 if not found:
2513 # Broaden the search a little bit
2514 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2515 if not found:
2516 # Broaden the findall a little bit: JWPlayer JS loader
2517 found = filter_video(re.findall(
2518 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2519 if not found:
2520 # Flow player
2521 found = filter_video(re.findall(r'''(?xs)
2522 flowplayer\("[^"]+",\s*
2523 \{[^}]+?\}\s*,
2524 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2525 ["']?url["']?\s*:\s*["']([^"']+)["']
2526 ''', webpage))
2527 if not found:
2528 # Cinerama player
2529 found = re.findall(
2530 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2531 if not found:
2532 # Try to find twitter cards info
2533 # twitter:player:stream should be checked before twitter:player since
2534 # it is expected to contain a raw stream (see
2535 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2536 found = filter_video(re.findall(
2537 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2538 if not found:
2539 # We look for Open Graph info:
2540 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2541 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2542 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2543 if m_video_type is not None:
2544 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2545 if not found:
2546 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2547 found = re.search(
2548 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2549 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2550 webpage)
2551 if not found:
2552 # Look also in Refresh HTTP header
2553 refresh_header = head_response.headers.get('Refresh')
2554 if refresh_header:
2555 # In python 2 response HTTP headers are bytestrings
2556 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2557 refresh_header = refresh_header.decode('iso-8859-1')
2558 found = re.search(REDIRECT_REGEX, refresh_header)
2559 if found:
2560 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2561 self.report_following_redirect(new_url)
2562 return {
2563 '_type': 'url',
2564 'url': new_url,
2565 }
2566
2567 if not found:
2568 # twitter:player is a https URL to iframe player that may or may not
2569 # be supported by youtube-dl thus this is checked the very last (see
2570 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2571 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2572 if embed_url:
2573 return self.url_result(embed_url)
2574
2575 if not found:
2576 raise UnsupportedError(url)
2577
2578 entries = []
2579 for video_url in orderedSet(found):
2580 video_url = unescapeHTML(video_url)
2581 video_url = video_url.replace('\\/', '/')
2582 video_url = compat_urlparse.urljoin(url, video_url)
2583 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2584
2585 # Sometimes, jwplayer extraction will result in a YouTube URL
2586 if YoutubeIE.suitable(video_url):
2587 entries.append(self.url_result(video_url, 'Youtube'))
2588 continue
2589
2590 # here's a fun little line of code for you:
2591 video_id = os.path.splitext(video_id)[0]
2592
2593 entry_info_dict = {
2594 'id': video_id,
2595 'uploader': video_uploader,
2596 'title': video_title,
2597 'age_limit': age_limit,
2598 }
2599
2600 if RtmpIE.suitable(video_url):
2601 entry_info_dict.update({
2602 '_type': 'url_transparent',
2603 'ie_key': RtmpIE.ie_key(),
2604 'url': video_url,
2605 })
2606 entries.append(entry_info_dict)
2607 continue
2608
2609 ext = determine_ext(video_url)
2610 if ext == 'smil':
2611 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2612 elif ext == 'xspf':
2613 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2614 elif ext == 'm3u8':
2615 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2616 elif ext == 'mpd':
2617 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2618 elif ext == 'f4m':
2619 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2620 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2621 # Just matching .ism/manifest is not enough to be reliably sure
2622 # whether it's actually an ISM manifest or some other streaming
2623 # manifest since there are various streaming URL formats
2624 # possible (see [1]) as well as some other shenanigans like
2625 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2626 # so on.
2627 # Thus the most reasonable way to solve this is to delegate
2628 # to generic extractor in order to look into the contents of
2629 # the manifest itself.
2630 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2631 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2632 entry_info_dict = self.url_result(
2633 smuggle_url(video_url, {'to_generic': True}),
2634 GenericIE.ie_key())
2635 else:
2636 entry_info_dict['url'] = video_url
2637
2638 if entry_info_dict.get('formats'):
2639 self._sort_formats(entry_info_dict['formats'])
2640
2641 entries.append(entry_info_dict)
2642
2643 if len(entries) == 1:
2644 return entries[0]
2645 else:
2646 for num, e in enumerate(entries, start=1):
2647 # 'url' results don't have a title
2648 if e.get('title') is not None:
2649 e['title'] = '%s (%d)' % (e['title'], num)
2650 return {
2651 '_type': 'playlist',
2652 'entries': entries,
2653 }