]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[videopress] Add extractor
[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 from .videopress import VideoPressIE
85
86
87 class GenericIE(InfoExtractor):
88 IE_DESC = 'Generic downloader that works on some sites'
89 _VALID_URL = r'.*'
90 IE_NAME = 'generic'
91 _TESTS = [
92 # Direct link to a video
93 {
94 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
95 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
96 'info_dict': {
97 'id': 'trailer',
98 'ext': 'mp4',
99 'title': 'trailer',
100 'upload_date': '20100513',
101 }
102 },
103 # Direct link to media delivered compressed (until Accept-Encoding is *)
104 {
105 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
106 'md5': '128c42e68b13950268b648275386fc74',
107 'info_dict': {
108 'id': 'FictionJunction-Parallel_Hearts',
109 'ext': 'flac',
110 'title': 'FictionJunction-Parallel_Hearts',
111 'upload_date': '20140522',
112 },
113 'expected_warnings': [
114 'URL could be a direct video link, returning it as such.'
115 ],
116 'skip': 'URL invalid',
117 },
118 # Direct download with broken HEAD
119 {
120 'url': 'http://ai-radio.org:8000/radio.opus',
121 'info_dict': {
122 'id': 'radio',
123 'ext': 'opus',
124 'title': 'radio',
125 },
126 'params': {
127 'skip_download': True, # infinite live stream
128 },
129 'expected_warnings': [
130 r'501.*Not Implemented',
131 r'400.*Bad Request',
132 ],
133 },
134 # Direct link with incorrect MIME type
135 {
136 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
137 'md5': '4ccbebe5f36706d85221f204d7eb5913',
138 'info_dict': {
139 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
140 'id': '5_Lennart_Poettering_-_Systemd',
141 'ext': 'webm',
142 'title': '5_Lennart_Poettering_-_Systemd',
143 'upload_date': '20141120',
144 },
145 'expected_warnings': [
146 'URL could be a direct video link, returning it as such.'
147 ]
148 },
149 # RSS feed
150 {
151 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
152 'info_dict': {
153 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
154 'title': 'Zero Punctuation',
155 'description': 're:.*groundbreaking video review series.*'
156 },
157 'playlist_mincount': 11,
158 },
159 # RSS feed with enclosure
160 {
161 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
162 'info_dict': {
163 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
164 'ext': 'm4v',
165 'upload_date': '20150228',
166 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
167 }
168 },
169 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
170 {
171 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
172 'info_dict': {
173 'id': 'smil',
174 'ext': 'mp4',
175 'title': 'Automatics, robotics and biocybernetics',
176 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
177 'upload_date': '20130627',
178 'formats': 'mincount:16',
179 'subtitles': 'mincount:1',
180 },
181 'params': {
182 'force_generic_extractor': True,
183 'skip_download': True,
184 },
185 },
186 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
187 {
188 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
189 'info_dict': {
190 'id': 'hds',
191 'ext': 'flv',
192 'title': 'hds',
193 'formats': 'mincount:1',
194 },
195 'params': {
196 'skip_download': True,
197 },
198 },
199 # SMIL from https://www.restudy.dk/video/play/id/1637
200 {
201 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
202 'info_dict': {
203 'id': 'video_1637',
204 'ext': 'flv',
205 'title': 'video_1637',
206 'formats': 'mincount:3',
207 },
208 'params': {
209 'skip_download': True,
210 },
211 },
212 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
213 {
214 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
215 'info_dict': {
216 'id': 'smil-service',
217 'ext': 'flv',
218 'title': 'smil-service',
219 'formats': 'mincount:1',
220 },
221 'params': {
222 'skip_download': True,
223 },
224 },
225 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
226 {
227 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
228 'info_dict': {
229 'id': '4719370',
230 'ext': 'mp4',
231 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
232 'formats': 'mincount:3',
233 },
234 'params': {
235 'skip_download': True,
236 },
237 },
238 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
239 {
240 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
241 'info_dict': {
242 'id': 'mZlp2ctYIUEB',
243 'ext': 'mp4',
244 'title': 'Tikibad ontruimd wegens brand',
245 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
246 'thumbnail': r're:^https?://.*\.jpg$',
247 'duration': 33,
248 },
249 'params': {
250 'skip_download': True,
251 },
252 },
253 # MPD from http://dash-mse-test.appspot.com/media.html
254 {
255 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
256 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
257 'info_dict': {
258 'id': 'car-20120827-manifest',
259 'ext': 'mp4',
260 'title': 'car-20120827-manifest',
261 'formats': 'mincount:9',
262 'upload_date': '20130904',
263 },
264 'params': {
265 'format': 'bestvideo',
266 },
267 },
268 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
269 {
270 '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',
271 'info_dict': {
272 'id': 'content',
273 'ext': 'mp4',
274 'title': 'content',
275 'formats': 'mincount:8',
276 },
277 'params': {
278 # m3u8 downloads
279 'skip_download': True,
280 },
281 'skip': 'video gone',
282 },
283 # m3u8 served with Content-Type: text/plain
284 {
285 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
286 'info_dict': {
287 'id': 'index',
288 'ext': 'mp4',
289 'title': 'index',
290 'upload_date': '20140720',
291 'formats': 'mincount:11',
292 },
293 'params': {
294 # m3u8 downloads
295 'skip_download': True,
296 },
297 'skip': 'video gone',
298 },
299 # google redirect
300 {
301 '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',
302 'info_dict': {
303 'id': 'cmQHVoWB5FY',
304 'ext': 'mp4',
305 'upload_date': '20130224',
306 'uploader_id': 'TheVerge',
307 'description': r're:^Chris Ziegler takes a look at the\.*',
308 'uploader': 'The Verge',
309 'title': 'First Firefox OS phones side-by-side',
310 },
311 'params': {
312 'skip_download': False,
313 }
314 },
315 {
316 # redirect in Refresh HTTP header
317 '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',
318 'info_dict': {
319 'id': 'pO8h3EaFRdo',
320 'ext': 'mp4',
321 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
322 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
323 'upload_date': '20150917',
324 'uploader_id': 'brtvofficial',
325 'uploader': 'Boiler Room',
326 },
327 'params': {
328 'skip_download': False,
329 },
330 },
331 {
332 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
333 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
334 'info_dict': {
335 'id': '13601338388002',
336 'ext': 'mp4',
337 'uploader': 'www.hodiho.fr',
338 'title': 'R\u00e9gis plante sa Jeep',
339 }
340 },
341 # bandcamp page with custom domain
342 {
343 'add_ie': ['Bandcamp'],
344 'url': 'http://bronyrock.com/track/the-pony-mash',
345 'info_dict': {
346 'id': '3235767654',
347 'ext': 'mp3',
348 'title': 'The Pony Mash',
349 'uploader': 'M_Pallante',
350 },
351 'skip': 'There is a limit of 200 free downloads / month for the test song',
352 },
353 {
354 # embedded brightcove video
355 # it also tests brightcove videos that need to set the 'Referer'
356 # in the http requests
357 'add_ie': ['BrightcoveLegacy'],
358 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
359 'info_dict': {
360 'id': '2765128793001',
361 'ext': 'mp4',
362 'title': 'Le cours de bourse : l’analyse technique',
363 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
364 'uploader': 'BFM BUSINESS',
365 },
366 'params': {
367 'skip_download': True,
368 },
369 },
370 {
371 # embedded with itemprop embedURL and video id spelled as `idVideo`
372 'add_id': ['BrightcoveLegacy'],
373 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
374 'info_dict': {
375 'id': '5255628253001',
376 'ext': 'mp4',
377 'title': 'md5:37c519b1128915607601e75a87995fc0',
378 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
379 'uploader': 'BFM BUSINESS',
380 'uploader_id': '876450612001',
381 'timestamp': 1482255315,
382 'upload_date': '20161220',
383 },
384 'params': {
385 'skip_download': True,
386 },
387 },
388 {
389 # https://github.com/rg3/youtube-dl/issues/2253
390 'url': 'http://bcove.me/i6nfkrc3',
391 'md5': '0ba9446db037002366bab3b3eb30c88c',
392 'info_dict': {
393 'id': '3101154703001',
394 'ext': 'mp4',
395 'title': 'Still no power',
396 'uploader': 'thestar.com',
397 '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.',
398 },
399 'add_ie': ['BrightcoveLegacy'],
400 'skip': 'video gone',
401 },
402 {
403 'url': 'http://www.championat.com/video/football/v/87/87499.html',
404 'md5': 'fb973ecf6e4a78a67453647444222983',
405 'info_dict': {
406 'id': '3414141473001',
407 'ext': 'mp4',
408 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
409 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
410 'uploader': 'Championat',
411 },
412 },
413 {
414 # https://github.com/rg3/youtube-dl/issues/3541
415 'add_ie': ['BrightcoveLegacy'],
416 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
417 'info_dict': {
418 'id': '3866516442001',
419 'ext': 'mp4',
420 'title': 'Leer mij vrouwen kennen: Aflevering 1',
421 'description': 'Leer mij vrouwen kennen: Aflevering 1',
422 'uploader': 'SBS Broadcasting',
423 },
424 'skip': 'Restricted to Netherlands',
425 'params': {
426 'skip_download': True, # m3u8 download
427 },
428 },
429 {
430 # Brightcove with alternative playerID key
431 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
432 'info_dict': {
433 'id': 'nmeth.2062_SV1',
434 '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',
435 },
436 'playlist': [{
437 'info_dict': {
438 'id': '2228375078001',
439 'ext': 'mp4',
440 'title': 'nmeth.2062-sv1',
441 'description': 'nmeth.2062-sv1',
442 'timestamp': 1363357591,
443 'upload_date': '20130315',
444 'uploader': 'Nature Publishing Group',
445 'uploader_id': '1964492299001',
446 },
447 }],
448 },
449 # ooyala video
450 {
451 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
452 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
453 'info_dict': {
454 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
455 'ext': 'mp4',
456 'title': '2cc213299525360.mov', # that's what we get
457 'duration': 238.231,
458 },
459 'add_ie': ['Ooyala'],
460 },
461 {
462 # ooyala video embedded with http://player.ooyala.com/iframe.js
463 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
464 'info_dict': {
465 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
466 'ext': 'mp4',
467 'title': '"Steve Jobs: Man in the Machine" trailer',
468 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
469 'duration': 135.427,
470 },
471 'params': {
472 'skip_download': True,
473 },
474 'skip': 'movie expired',
475 },
476 # embed.ly video
477 {
478 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
479 'info_dict': {
480 'id': '9ODmcdjQcHQ',
481 'ext': 'mp4',
482 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
483 'upload_date': '20140225',
484 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
485 'uploader': 'Tested',
486 'uploader_id': 'testedcom',
487 },
488 # No need to test YoutubeIE here
489 'params': {
490 'skip_download': True,
491 },
492 },
493 # funnyordie embed
494 {
495 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
496 'info_dict': {
497 'id': '18e820ec3f',
498 'ext': 'mp4',
499 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
500 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
501 },
502 # HEAD requests lead to endless 301, while GET is OK
503 'expected_warnings': ['301'],
504 },
505 # RUTV embed
506 {
507 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
508 'info_dict': {
509 'id': '776940',
510 'ext': 'mp4',
511 'title': 'Охотское море стало целиком российским',
512 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
513 },
514 'params': {
515 # m3u8 download
516 'skip_download': True,
517 },
518 },
519 # TVC embed
520 {
521 '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/',
522 'info_dict': {
523 'id': '55304',
524 'ext': 'mp4',
525 'title': 'Дошкольное воспитание',
526 },
527 },
528 # SportBox embed
529 {
530 'url': 'http://www.vestifinance.ru/articles/25753',
531 'info_dict': {
532 'id': '25753',
533 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
534 },
535 'playlist': [{
536 'info_dict': {
537 'id': '370908',
538 'title': 'Госзаказ. День 3',
539 'ext': 'mp4',
540 }
541 }, {
542 'info_dict': {
543 'id': '370905',
544 'title': 'Госзаказ. День 2',
545 'ext': 'mp4',
546 }
547 }, {
548 'info_dict': {
549 'id': '370902',
550 'title': 'Госзаказ. День 1',
551 'ext': 'mp4',
552 }
553 }],
554 'params': {
555 # m3u8 download
556 'skip_download': True,
557 },
558 },
559 # Myvi.ru embed
560 {
561 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
562 'info_dict': {
563 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
564 'ext': 'mp4',
565 'title': 'Ужастики, русский трейлер (2015)',
566 'thumbnail': r're:^https?://.*\.jpg$',
567 'duration': 153,
568 }
569 },
570 # XHamster embed
571 {
572 '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',
573 'info_dict': {
574 'id': 'showthread',
575 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
576 },
577 'playlist_mincount': 7,
578 # This forum does not allow <iframe> syntaxes anymore
579 # Now HTML tags are displayed as-is
580 'skip': 'No videos on this page',
581 },
582 # Embedded TED video
583 {
584 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
585 'md5': '65fdff94098e4a607385a60c5177c638',
586 'info_dict': {
587 'id': '1969',
588 'ext': 'mp4',
589 'title': 'Hidden miracles of the natural world',
590 'uploader': 'Louie Schwartzberg',
591 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
592 }
593 },
594 # nowvideo embed hidden behind percent encoding
595 {
596 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
597 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
598 'info_dict': {
599 'id': '06e53103ca9aa',
600 'ext': 'flv',
601 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
602 'description': 'No description',
603 },
604 },
605 # arte embed
606 {
607 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
608 'md5': '7653032cbb25bf6c80d80f217055fa43',
609 'info_dict': {
610 'id': '048195-004_PLUS7-F',
611 'ext': 'flv',
612 'title': 'X:enius',
613 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
614 'upload_date': '20140320',
615 },
616 'params': {
617 'skip_download': 'Requires rtmpdump'
618 },
619 'skip': 'video gone',
620 },
621 # francetv embed
622 {
623 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
624 'info_dict': {
625 'id': 'EV_30231',
626 'ext': 'mp4',
627 'title': 'Alcaline, le concert avec Calogero',
628 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
629 'upload_date': '20150226',
630 'timestamp': 1424989860,
631 'duration': 5400,
632 },
633 'params': {
634 # m3u8 downloads
635 'skip_download': True,
636 },
637 'expected_warnings': [
638 'Forbidden'
639 ]
640 },
641 # Condé Nast embed
642 {
643 'url': 'http://www.wired.com/2014/04/honda-asimo/',
644 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
645 'info_dict': {
646 'id': '53501be369702d3275860000',
647 'ext': 'mp4',
648 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
649 }
650 },
651 # Dailymotion embed
652 {
653 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
654 'md5': '441aeeb82eb72c422c7f14ec533999cd',
655 'info_dict': {
656 'id': 'k2mm4bCdJ6CQ2i7c8o2',
657 'ext': 'mp4',
658 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
659 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
660 'uploader': 'Spi0n',
661 'uploader_id': 'xgditw',
662 'upload_date': '20140425',
663 'timestamp': 1398441542,
664 },
665 'add_ie': ['Dailymotion'],
666 },
667 # YouTube embed
668 {
669 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
670 'info_dict': {
671 'id': 'FXRb4ykk4S0',
672 'ext': 'mp4',
673 'title': 'The NBL Auction 2014',
674 'uploader': 'BADMINTON England',
675 'uploader_id': 'BADMINTONEvents',
676 'upload_date': '20140603',
677 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
678 },
679 'add_ie': ['Youtube'],
680 'params': {
681 'skip_download': True,
682 }
683 },
684 # MTVSercices embed
685 {
686 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
687 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
688 'info_dict': {
689 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
690 'ext': 'mp4',
691 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
692 'description': 'Two valets share their love for movie star Liam Neesons.',
693 'timestamp': 1349922600,
694 'upload_date': '20121011',
695 },
696 },
697 # YouTube embed via <data-embed-url="">
698 {
699 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
700 'info_dict': {
701 'id': '4vAffPZIT44',
702 'ext': 'mp4',
703 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
704 'uploader': 'Gameloft',
705 'uploader_id': 'gameloft',
706 'upload_date': '20140828',
707 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
708 },
709 'params': {
710 'skip_download': True,
711 }
712 },
713 # Camtasia studio
714 {
715 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
716 'playlist': [{
717 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
718 'info_dict': {
719 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
720 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
721 'ext': 'flv',
722 'duration': 2235.90,
723 }
724 }, {
725 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
726 'info_dict': {
727 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
728 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
729 'ext': 'flv',
730 'duration': 2235.93,
731 }
732 }],
733 'info_dict': {
734 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
735 }
736 },
737 # Flowplayer
738 {
739 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
740 'md5': '9d65602bf31c6e20014319c7d07fba27',
741 'info_dict': {
742 'id': '5123ea6d5e5a7',
743 'ext': 'mp4',
744 'age_limit': 18,
745 'uploader': 'www.handjobhub.com',
746 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
747 }
748 },
749 # Multiple brightcove videos
750 # https://github.com/rg3/youtube-dl/issues/2283
751 {
752 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
753 'info_dict': {
754 'id': 'always-never',
755 'title': 'Always / Never - The New Yorker',
756 },
757 'playlist_count': 3,
758 'params': {
759 'extract_flat': False,
760 'skip_download': True,
761 }
762 },
763 # MLB embed
764 {
765 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
766 'md5': '96f09a37e44da40dd083e12d9a683327',
767 'info_dict': {
768 'id': '33322633',
769 'ext': 'mp4',
770 'title': 'Ump changes call to ball',
771 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
772 'duration': 48,
773 'timestamp': 1401537900,
774 'upload_date': '20140531',
775 'thumbnail': r're:^https?://.*\.jpg$',
776 },
777 },
778 # Wistia embed
779 {
780 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
781 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
782 'info_dict': {
783 'id': '6e2wtrbdaf',
784 'ext': 'mov',
785 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
786 'description': 'a Paywall Videos video from Remilon',
787 'duration': 644.072,
788 'uploader': 'study.com',
789 'timestamp': 1459678540,
790 'upload_date': '20160403',
791 'filesize': 24687186,
792 },
793 },
794 {
795 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
796 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
797 'info_dict': {
798 'id': 'uxjb0lwrcz',
799 'ext': 'mp4',
800 'title': 'Conversation about Hexagonal Rails Part 1',
801 'description': 'a Martin Fowler video from ThoughtWorks',
802 'duration': 1715.0,
803 'uploader': 'thoughtworks.wistia.com',
804 'timestamp': 1401832161,
805 'upload_date': '20140603',
806 },
807 },
808 # Wistia standard embed (async)
809 {
810 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
811 'info_dict': {
812 'id': '807fafadvk',
813 'ext': 'mp4',
814 'title': 'Drip Brennan Dunn Workshop',
815 'description': 'a JV Webinars video from getdrip-1',
816 'duration': 4986.95,
817 'timestamp': 1463607249,
818 'upload_date': '20160518',
819 },
820 'params': {
821 'skip_download': True,
822 }
823 },
824 # Soundcloud embed
825 {
826 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
827 'info_dict': {
828 'id': '174391317',
829 'ext': 'mp3',
830 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
831 'uploader': 'Sophos Security',
832 'title': 'Chet Chat 171 - Oct 29, 2014',
833 'upload_date': '20141029',
834 }
835 },
836 # Soundcloud multiple embeds
837 {
838 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
839 'info_dict': {
840 'id': '52809',
841 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
842 },
843 'playlist_mincount': 7,
844 },
845 # TuneIn station embed
846 {
847 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
848 'info_dict': {
849 'id': '204146',
850 'ext': 'mp3',
851 'title': 'CNRV',
852 'location': 'Paris, France',
853 'is_live': True,
854 },
855 'params': {
856 # Live stream
857 'skip_download': True,
858 },
859 },
860 # Livestream embed
861 {
862 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
863 'info_dict': {
864 'id': '67864563',
865 'ext': 'flv',
866 'upload_date': '20141112',
867 'title': 'Rosetta #CometLanding webcast HL 10',
868 }
869 },
870 # Another Livestream embed, without 'new.' in URL
871 {
872 'url': 'https://www.freespeech.org/',
873 'info_dict': {
874 'id': '123537347',
875 'ext': 'mp4',
876 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
877 },
878 'params': {
879 # Live stream
880 'skip_download': True,
881 },
882 },
883 # LazyYT
884 {
885 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
886 'info_dict': {
887 'id': '1986',
888 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
889 },
890 'playlist_mincount': 2,
891 },
892 # Cinchcast embed
893 {
894 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
895 'info_dict': {
896 'id': '7141703',
897 'ext': 'mp3',
898 'upload_date': '20141126',
899 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
900 }
901 },
902 # Cinerama player
903 {
904 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
905 'info_dict': {
906 'id': '730m_DandD_1901_512k',
907 'ext': 'mp4',
908 'uploader': 'www.abc.net.au',
909 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
910 }
911 },
912 # embedded viddler video
913 {
914 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
915 'info_dict': {
916 'id': '4d03aad9',
917 'ext': 'mp4',
918 'uploader': 'deadspin',
919 'title': 'WALL-TO-GORTAT',
920 'timestamp': 1422285291,
921 'upload_date': '20150126',
922 },
923 'add_ie': ['Viddler'],
924 },
925 # Libsyn embed
926 {
927 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
928 'info_dict': {
929 'id': '3377616',
930 'ext': 'mp3',
931 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
932 'description': 'md5:601cb790edd05908957dae8aaa866465',
933 'upload_date': '20150220',
934 },
935 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
936 },
937 # jwplayer YouTube
938 {
939 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
940 'info_dict': {
941 'id': 'Mrj4DVp2zeA',
942 'ext': 'mp4',
943 'upload_date': '20150212',
944 'uploader': 'The National Archives UK',
945 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
946 'uploader_id': 'NationalArchives08',
947 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
948 },
949 },
950 # rtl.nl embed
951 {
952 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
953 'playlist_mincount': 5,
954 'info_dict': {
955 'id': 'aanslagen-kopenhagen',
956 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
957 }
958 },
959 # Zapiks embed
960 {
961 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
962 'info_dict': {
963 'id': '118046',
964 'ext': 'mp4',
965 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
966 }
967 },
968 # Kaltura embed (different embed code)
969 {
970 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
971 'info_dict': {
972 'id': '1_a52wc67y',
973 'ext': 'flv',
974 'upload_date': '20150127',
975 'uploader_id': 'PremierMedia',
976 'timestamp': int,
977 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
978 },
979 },
980 # Kaltura embed protected with referrer
981 {
982 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
983 'info_dict': {
984 'id': '1_g4fbemnq',
985 'ext': 'mp4',
986 'title': 'Violetta - Achter De Schermen - Ruggero',
987 'description': 'Achter de schermen met Ruggero',
988 'timestamp': 1435133761,
989 'upload_date': '20150624',
990 'uploader_id': 'echojecka',
991 },
992 },
993 # Kaltura embed with single quotes
994 {
995 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
996 'info_dict': {
997 'id': '0_izeg5utt',
998 'ext': 'mp4',
999 'title': '35871',
1000 'timestamp': 1355743100,
1001 'upload_date': '20121217',
1002 'uploader_id': 'batchUser',
1003 },
1004 'add_ie': ['Kaltura'],
1005 },
1006 {
1007 # Kaltura embedded via quoted entry_id
1008 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1009 'info_dict': {
1010 'id': '0_utuok90b',
1011 'ext': 'mp4',
1012 'title': '06_matthew_brender_raj_dutt',
1013 'timestamp': 1466638791,
1014 'upload_date': '20160622',
1015 },
1016 'add_ie': ['Kaltura'],
1017 'expected_warnings': [
1018 'Could not send HEAD request'
1019 ],
1020 'params': {
1021 'skip_download': True,
1022 }
1023 },
1024 {
1025 # Kaltura embedded, some fileExt broken (#11480)
1026 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1027 'info_dict': {
1028 'id': '1_sgtvehim',
1029 'ext': 'mp4',
1030 'title': 'Our "Standard Models" of particle physics and cosmology',
1031 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1032 'timestamp': 1321158993,
1033 'upload_date': '20111113',
1034 'uploader_id': 'kps1',
1035 },
1036 'add_ie': ['Kaltura'],
1037 },
1038 # Eagle.Platform embed (generic URL)
1039 {
1040 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1041 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1042 'info_dict': {
1043 'id': '227304',
1044 'ext': 'mp4',
1045 'title': 'Навальный вышел на свободу',
1046 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1047 'thumbnail': r're:^https?://.*\.jpg$',
1048 'duration': 87,
1049 'view_count': int,
1050 'age_limit': 0,
1051 },
1052 },
1053 # ClipYou (Eagle.Platform) embed (custom URL)
1054 {
1055 'url': 'http://muz-tv.ru/play/7129/',
1056 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1057 'info_dict': {
1058 'id': '12820',
1059 'ext': 'mp4',
1060 'title': "'O Sole Mio",
1061 'thumbnail': r're:^https?://.*\.jpg$',
1062 'duration': 216,
1063 'view_count': int,
1064 },
1065 },
1066 # Pladform embed
1067 {
1068 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1069 'info_dict': {
1070 'id': '100183293',
1071 'ext': 'mp4',
1072 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1073 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1074 'thumbnail': r're:^https?://.*\.jpg$',
1075 'duration': 694,
1076 'age_limit': 0,
1077 },
1078 },
1079 # Playwire embed
1080 {
1081 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1082 'info_dict': {
1083 'id': '3519514',
1084 'ext': 'mp4',
1085 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1086 'thumbnail': r're:^https?://.*\.png$',
1087 'duration': 45.115,
1088 },
1089 },
1090 # 5min embed
1091 {
1092 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1093 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1094 'info_dict': {
1095 'id': '518726732',
1096 'ext': 'mp4',
1097 'title': 'Facebook Creates "On This Day" | Crunch Report',
1098 },
1099 },
1100 # SVT embed
1101 {
1102 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1103 'info_dict': {
1104 'id': '2900353',
1105 'ext': 'flv',
1106 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1107 'duration': 27,
1108 'age_limit': 0,
1109 },
1110 },
1111 # Crooks and Liars embed
1112 {
1113 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1114 'info_dict': {
1115 'id': '8RUoRhRi',
1116 'ext': 'mp4',
1117 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1118 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1119 'timestamp': 1428207000,
1120 'upload_date': '20150405',
1121 'uploader': 'Heather',
1122 },
1123 },
1124 # Crooks and Liars external embed
1125 {
1126 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1127 'info_dict': {
1128 'id': 'MTE3MjUtMzQ2MzA',
1129 'ext': 'mp4',
1130 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1131 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1132 'timestamp': 1265032391,
1133 'upload_date': '20100201',
1134 'uploader': 'Heather',
1135 },
1136 },
1137 # NBC Sports vplayer embed
1138 {
1139 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1140 'info_dict': {
1141 'id': 'ln7x1qSThw4k',
1142 'ext': 'flv',
1143 'title': "PFT Live: New leader in the 'new-look' defense",
1144 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1145 'uploader': 'NBCU-SPORTS',
1146 'upload_date': '20140107',
1147 'timestamp': 1389118457,
1148 },
1149 },
1150 # NBC News embed
1151 {
1152 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1153 'md5': '1aa589c675898ae6d37a17913cf68d66',
1154 'info_dict': {
1155 'id': '701714499682',
1156 'ext': 'mp4',
1157 'title': 'PREVIEW: On Assignment: David Letterman',
1158 '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.',
1159 },
1160 },
1161 # UDN embed
1162 {
1163 'url': 'https://video.udn.com/news/300346',
1164 'md5': 'fd2060e988c326991037b9aff9df21a6',
1165 'info_dict': {
1166 'id': '300346',
1167 'ext': 'mp4',
1168 'title': '中一中男師變性 全校師生力挺',
1169 'thumbnail': r're:^https?://.*\.jpg$',
1170 },
1171 'params': {
1172 # m3u8 download
1173 'skip_download': True,
1174 },
1175 },
1176 # Ooyala embed
1177 {
1178 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1179 'info_dict': {
1180 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1181 'ext': 'mp4',
1182 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1183 'title': 'This is what separates the Excel masters from the wannabes',
1184 'duration': 191.933,
1185 },
1186 'params': {
1187 # m3u8 downloads
1188 'skip_download': True,
1189 }
1190 },
1191 # Brightcove URL in single quotes
1192 {
1193 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1194 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1195 'info_dict': {
1196 'id': '4255764656001',
1197 'ext': 'mp4',
1198 'title': 'SN Presents: Russell Martin, World Citizen',
1199 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1200 'uploader': 'Rogers Sportsnet',
1201 'uploader_id': '1704050871',
1202 'upload_date': '20150525',
1203 'timestamp': 1432570283,
1204 },
1205 },
1206 # Dailymotion Cloud video
1207 {
1208 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1209 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1210 'info_dict': {
1211 'id': 'x2uy8t3',
1212 'ext': 'mp4',
1213 'title': 'Sauvons les abeilles ! - Le débat',
1214 'description': 'md5:d9082128b1c5277987825d684939ca26',
1215 'thumbnail': r're:^https?://.*\.jpe?g$',
1216 'timestamp': 1434970506,
1217 'upload_date': '20150622',
1218 'uploader': 'Public Sénat',
1219 'uploader_id': 'xa9gza',
1220 }
1221 },
1222 # OnionStudios embed
1223 {
1224 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1225 'info_dict': {
1226 'id': '2855',
1227 'ext': 'mp4',
1228 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1229 'thumbnail': r're:^https?://.*\.jpe?g$',
1230 'uploader': 'ClickHole',
1231 'uploader_id': 'clickhole',
1232 }
1233 },
1234 # SnagFilms embed
1235 {
1236 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1237 'info_dict': {
1238 'id': '74849a00-85a9-11e1-9660-123139220831',
1239 'ext': 'mp4',
1240 'title': '#whilewewatch',
1241 }
1242 },
1243 # AdobeTVVideo embed
1244 {
1245 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1246 'md5': '43662b577c018ad707a63766462b1e87',
1247 'info_dict': {
1248 'id': '2456',
1249 'ext': 'mp4',
1250 'title': 'New experience with Acrobat DC',
1251 'description': 'New experience with Acrobat DC',
1252 'duration': 248.667,
1253 },
1254 },
1255 # BrightcoveInPageEmbed embed
1256 {
1257 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1258 'info_dict': {
1259 'id': '4238694884001',
1260 'ext': 'flv',
1261 'title': 'Tabletop: Dread, Last Thoughts',
1262 'description': 'Tabletop: Dread, Last Thoughts',
1263 'duration': 51690,
1264 },
1265 },
1266 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1267 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1268 {
1269 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1270 'info_dict': {
1271 'id': '4785848093001',
1272 'ext': 'mp4',
1273 'title': 'The Cardinal Pell Interview',
1274 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1275 'uploader': 'GlobeCast Australia - GlobeStream',
1276 'uploader_id': '2733773828001',
1277 'upload_date': '20160304',
1278 'timestamp': 1457083087,
1279 },
1280 'params': {
1281 # m3u8 downloads
1282 'skip_download': True,
1283 },
1284 },
1285 # Another form of arte.tv embed
1286 {
1287 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1288 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1289 'info_dict': {
1290 'id': '030273-562_PLUS7-F',
1291 'ext': 'mp4',
1292 'title': 'ARTE Reportage - Nulle part, en France',
1293 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1294 'upload_date': '20160409',
1295 },
1296 },
1297 # LiveLeak embed
1298 {
1299 'url': 'http://www.wykop.pl/link/3088787/',
1300 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1301 'info_dict': {
1302 'id': '874_1459135191',
1303 'ext': 'mp4',
1304 'title': 'Man shows poor quality of new apartment building',
1305 'description': 'The wall is like a sand pile.',
1306 'uploader': 'Lake8737',
1307 }
1308 },
1309 # Duplicated embedded video URLs
1310 {
1311 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1312 'info_dict': {
1313 'id': '149298443_480_16c25b74_2',
1314 'ext': 'mp4',
1315 'title': 'vs. Blue Orange Spring Game',
1316 'uploader': 'www.hudl.com',
1317 },
1318 },
1319 # twitter:player:stream embed
1320 {
1321 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1322 'info_dict': {
1323 'id': 'master',
1324 'ext': 'mp4',
1325 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1326 'uploader': 'www.rtl.be',
1327 },
1328 'params': {
1329 # m3u8 downloads
1330 'skip_download': True,
1331 },
1332 },
1333 # twitter:player embed
1334 {
1335 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1336 'md5': 'a3e0df96369831de324f0778e126653c',
1337 'info_dict': {
1338 'id': '4909620399001',
1339 'ext': 'mp4',
1340 'title': 'What Do Black Holes Sound Like?',
1341 'description': 'what do black holes sound like',
1342 'upload_date': '20160524',
1343 'uploader_id': '29913724001',
1344 'timestamp': 1464107587,
1345 'uploader': 'TheAtlantic',
1346 },
1347 'add_ie': ['BrightcoveLegacy'],
1348 },
1349 # Facebook <iframe> embed
1350 {
1351 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1352 'md5': 'fbcde74f534176ecb015849146dd3aee',
1353 'info_dict': {
1354 'id': '599637780109885',
1355 'ext': 'mp4',
1356 'title': 'Facebook video #599637780109885',
1357 },
1358 },
1359 # Facebook API embed
1360 {
1361 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1362 'md5': 'a47372ee61b39a7b90287094d447d94e',
1363 'info_dict': {
1364 'id': '10153467542406923',
1365 'ext': 'mp4',
1366 'title': 'Facebook video #10153467542406923',
1367 },
1368 },
1369 # Wordpress "YouTube Video Importer" plugin
1370 {
1371 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1372 'md5': 'd16797741b560b485194eddda8121b48',
1373 'info_dict': {
1374 'id': 'HNTXWDXV9Is',
1375 'ext': 'mp4',
1376 'title': 'Blue Devils Drumline Stanford lot 2016',
1377 'upload_date': '20160627',
1378 'uploader_id': 'GENOCIDE8GENERAL10',
1379 'uploader': 'cylus cyrus',
1380 },
1381 },
1382 {
1383 # video stored on custom kaltura server
1384 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1385 'md5': '537617d06e64dfed891fa1593c4b30cc',
1386 'info_dict': {
1387 'id': '0_1iotm5bh',
1388 'ext': 'mp4',
1389 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1390 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1391 'uploader_id': 'videos.expansion@el-mundo.net',
1392 'upload_date': '20150429',
1393 'timestamp': 1430303472,
1394 },
1395 'add_ie': ['Kaltura'],
1396 },
1397 {
1398 # Non-standard Vimeo embed
1399 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1400 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1401 'info_dict': {
1402 'id': '148867247',
1403 'ext': 'mp4',
1404 'title': 'Understanding the web - Teaser',
1405 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1406 'upload_date': '20151214',
1407 'uploader': 'OpenClassrooms',
1408 'uploader_id': 'openclassrooms',
1409 },
1410 'add_ie': ['Vimeo'],
1411 },
1412 {
1413 # generic vimeo embed that requires original URL passed as Referer
1414 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1415 'only_matching': True,
1416 },
1417 {
1418 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1419 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1420 'info_dict': {
1421 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1422 'ext': 'mp4',
1423 'title': 'Big Buck Bunny',
1424 'description': 'Royalty free test video',
1425 'timestamp': 1432816365,
1426 'upload_date': '20150528',
1427 'is_live': False,
1428 },
1429 'params': {
1430 'skip_download': True,
1431 },
1432 'add_ie': [ArkenaIE.ie_key()],
1433 },
1434 {
1435 '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/',
1436 'info_dict': {
1437 'id': '1c7141f46c',
1438 'ext': 'mp4',
1439 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1440 },
1441 'params': {
1442 'skip_download': True,
1443 },
1444 'add_ie': [Vbox7IE.ie_key()],
1445 },
1446 {
1447 # DBTV embeds
1448 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1449 'info_dict': {
1450 'id': '43254897',
1451 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1452 },
1453 'playlist_mincount': 3,
1454 },
1455 {
1456 # Videa embeds
1457 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1458 'info_dict': {
1459 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1460 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1461 },
1462 'playlist_mincount': 2,
1463 },
1464 {
1465 # 20 minuten embed
1466 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1467 'info_dict': {
1468 'id': '523629',
1469 'ext': 'mp4',
1470 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1471 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1472 },
1473 'params': {
1474 'skip_download': True,
1475 },
1476 'add_ie': [TwentyMinutenIE.ie_key()],
1477 },
1478 {
1479 # VideoPress embed
1480 'url': 'https://en.support.wordpress.com/videopress/',
1481 'info_dict': {
1482 'id': 'OcobLTqC',
1483 'ext': 'm4v',
1484 'title': 'IMG_5786',
1485 'timestamp': 1435711927,
1486 'upload_date': '20150701',
1487 },
1488 'params': {
1489 'skip_download': True,
1490 },
1491 'add_ie': [VideoPressIE.ie_key()],
1492 }
1493 # {
1494 # # TODO: find another test
1495 # # http://schema.org/VideoObject
1496 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1497 # 'md5': '888dcf08b7ea671381f00fab74692755',
1498 # 'info_dict': {
1499 # 'id': 'nyvTSJMKId',
1500 # 'ext': 'mp4',
1501 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1502 # 'description': '#love for cats.',
1503 # 'timestamp': 1461244995,
1504 # 'upload_date': '20160421',
1505 # },
1506 # 'params': {
1507 # 'force_generic_extractor': True,
1508 # },
1509 # }
1510 ]
1511
1512 def report_following_redirect(self, new_url):
1513 """Report information extraction."""
1514 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1515
1516 def _extract_rss(self, url, video_id, doc):
1517 playlist_title = doc.find('./channel/title').text
1518 playlist_desc_el = doc.find('./channel/description')
1519 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1520
1521 entries = []
1522 for it in doc.findall('./channel/item'):
1523 next_url = xpath_text(it, 'link', fatal=False)
1524 if not next_url:
1525 enclosure_nodes = it.findall('./enclosure')
1526 for e in enclosure_nodes:
1527 next_url = e.attrib.get('url')
1528 if next_url:
1529 break
1530
1531 if not next_url:
1532 continue
1533
1534 entries.append({
1535 '_type': 'url',
1536 'url': next_url,
1537 'title': it.find('title').text,
1538 })
1539
1540 return {
1541 '_type': 'playlist',
1542 'id': url,
1543 'title': playlist_title,
1544 'description': playlist_desc,
1545 'entries': entries,
1546 }
1547
1548 def _extract_camtasia(self, url, video_id, webpage):
1549 """ Returns None if no camtasia video can be found. """
1550
1551 camtasia_cfg = self._search_regex(
1552 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1553 webpage, 'camtasia configuration file', default=None)
1554 if camtasia_cfg is None:
1555 return None
1556
1557 title = self._html_search_meta('DC.title', webpage, fatal=True)
1558
1559 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1560 camtasia_cfg = self._download_xml(
1561 camtasia_url, video_id,
1562 note='Downloading camtasia configuration',
1563 errnote='Failed to download camtasia configuration')
1564 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1565
1566 entries = []
1567 for n in fileset_node.getchildren():
1568 url_n = n.find('./uri')
1569 if url_n is None:
1570 continue
1571
1572 entries.append({
1573 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1574 'title': '%s - %s' % (title, n.tag),
1575 'url': compat_urlparse.urljoin(url, url_n.text),
1576 'duration': float_or_none(n.find('./duration').text),
1577 })
1578
1579 return {
1580 '_type': 'playlist',
1581 'entries': entries,
1582 'title': title,
1583 }
1584
1585 def _real_extract(self, url):
1586 if url.startswith('//'):
1587 return {
1588 '_type': 'url',
1589 'url': self.http_scheme() + url,
1590 }
1591
1592 parsed_url = compat_urlparse.urlparse(url)
1593 if not parsed_url.scheme:
1594 default_search = self._downloader.params.get('default_search')
1595 if default_search is None:
1596 default_search = 'fixup_error'
1597
1598 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1599 if '/' in url:
1600 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1601 return self.url_result('http://' + url)
1602 elif default_search != 'fixup_error':
1603 if default_search == 'auto_warning':
1604 if re.match(r'^(?:url|URL)$', url):
1605 raise ExtractorError(
1606 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1607 expected=True)
1608 else:
1609 self._downloader.report_warning(
1610 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1611 return self.url_result('ytsearch:' + url)
1612
1613 if default_search in ('error', 'fixup_error'):
1614 raise ExtractorError(
1615 '%r is not a valid URL. '
1616 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1617 % (url, url), expected=True)
1618 else:
1619 if ':' not in default_search:
1620 default_search += ':'
1621 return self.url_result(default_search + url)
1622
1623 url, smuggled_data = unsmuggle_url(url)
1624 force_videoid = None
1625 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1626 if smuggled_data and 'force_videoid' in smuggled_data:
1627 force_videoid = smuggled_data['force_videoid']
1628 video_id = force_videoid
1629 else:
1630 video_id = self._generic_id(url)
1631
1632 self.to_screen('%s: Requesting header' % video_id)
1633
1634 head_req = HEADRequest(url)
1635 head_response = self._request_webpage(
1636 head_req, video_id,
1637 note=False, errnote='Could not send HEAD request to %s' % url,
1638 fatal=False)
1639
1640 if head_response is not False:
1641 # Check for redirect
1642 new_url = head_response.geturl()
1643 if url != new_url:
1644 self.report_following_redirect(new_url)
1645 if force_videoid:
1646 new_url = smuggle_url(
1647 new_url, {'force_videoid': force_videoid})
1648 return self.url_result(new_url)
1649
1650 full_response = None
1651 if head_response is False:
1652 request = sanitized_Request(url)
1653 request.add_header('Accept-Encoding', '*')
1654 full_response = self._request_webpage(request, video_id)
1655 head_response = full_response
1656
1657 info_dict = {
1658 'id': video_id,
1659 'title': self._generic_title(url),
1660 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1661 }
1662
1663 # Check for direct link to a video
1664 content_type = head_response.headers.get('Content-Type', '').lower()
1665 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1666 if m:
1667 format_id = m.group('format_id')
1668 if format_id.endswith('mpegurl'):
1669 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1670 elif format_id == 'f4m':
1671 formats = self._extract_f4m_formats(url, video_id)
1672 else:
1673 formats = [{
1674 'format_id': m.group('format_id'),
1675 'url': url,
1676 'vcodec': 'none' if m.group('type') == 'audio' else None
1677 }]
1678 info_dict['direct'] = True
1679 self._sort_formats(formats)
1680 info_dict['formats'] = formats
1681 return info_dict
1682
1683 if not self._downloader.params.get('test', False) and not is_intentional:
1684 force = self._downloader.params.get('force_generic_extractor', False)
1685 self._downloader.report_warning(
1686 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1687
1688 if not full_response:
1689 request = sanitized_Request(url)
1690 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1691 # making it impossible to download only chunk of the file (yet we need only 512kB to
1692 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1693 # that will always result in downloading the whole file that is not desirable.
1694 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1695 # to accept raw bytes and being able to download only a chunk.
1696 # It may probably better to solve this by checking Content-Type for application/octet-stream
1697 # after HEAD request finishes, but not sure if we can rely on this.
1698 request.add_header('Accept-Encoding', '*')
1699 full_response = self._request_webpage(request, video_id)
1700
1701 first_bytes = full_response.read(512)
1702
1703 # Is it an M3U playlist?
1704 if first_bytes.startswith(b'#EXTM3U'):
1705 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1706 self._sort_formats(info_dict['formats'])
1707 return info_dict
1708
1709 # Maybe it's a direct link to a video?
1710 # Be careful not to download the whole thing!
1711 if not is_html(first_bytes):
1712 self._downloader.report_warning(
1713 'URL could be a direct video link, returning it as such.')
1714 info_dict.update({
1715 'direct': True,
1716 'url': url,
1717 })
1718 return info_dict
1719
1720 webpage = self._webpage_read_content(
1721 full_response, url, video_id, prefix=first_bytes)
1722
1723 self.report_extraction(video_id)
1724
1725 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1726 try:
1727 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1728 if doc.tag == 'rss':
1729 return self._extract_rss(url, video_id, doc)
1730 elif doc.tag == 'SmoothStreamingMedia':
1731 info_dict['formats'] = self._parse_ism_formats(doc, url)
1732 self._sort_formats(info_dict['formats'])
1733 return info_dict
1734 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1735 smil = self._parse_smil(doc, url, video_id)
1736 self._sort_formats(smil['formats'])
1737 return smil
1738 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1739 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1740 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1741 info_dict['formats'] = self._parse_mpd_formats(
1742 doc, video_id,
1743 mpd_base_url=full_response.geturl().rpartition('/')[0],
1744 mpd_url=url)
1745 self._sort_formats(info_dict['formats'])
1746 return info_dict
1747 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1748 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1749 self._sort_formats(info_dict['formats'])
1750 return info_dict
1751 except compat_xml_parse_error:
1752 pass
1753
1754 # Is it a Camtasia project?
1755 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1756 if camtasia_res is not None:
1757 return camtasia_res
1758
1759 # Sometimes embedded video player is hidden behind percent encoding
1760 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1761 # Unescaping the whole page allows to handle those cases in a generic way
1762 webpage = compat_urllib_parse_unquote(webpage)
1763
1764 # it's tempting to parse this further, but you would
1765 # have to take into account all the variations like
1766 # Video Title - Site Name
1767 # Site Name | Video Title
1768 # Video Title - Tagline | Site Name
1769 # and so on and so forth; it's just not practical
1770 video_title = self._og_search_title(
1771 webpage, default=None) or self._html_search_regex(
1772 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1773 default='video')
1774
1775 # Try to detect age limit automatically
1776 age_limit = self._rta_search(webpage)
1777 # And then there are the jokers who advertise that they use RTA,
1778 # but actually don't.
1779 AGE_LIMIT_MARKERS = [
1780 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1781 ]
1782 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1783 age_limit = 18
1784
1785 # video uploader is domain name
1786 video_uploader = self._search_regex(
1787 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1788
1789 video_description = self._og_search_description(webpage, default=None)
1790 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1791
1792 # Helper method
1793 def _playlist_from_matches(matches, getter=None, ie=None):
1794 urlrs = orderedSet(
1795 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1796 for m in matches)
1797 return self.playlist_result(
1798 urlrs, playlist_id=video_id, playlist_title=video_title)
1799
1800 # Look for Brightcove Legacy Studio embeds
1801 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1802 if bc_urls:
1803 self.to_screen('Brightcove video detected.')
1804 entries = [{
1805 '_type': 'url',
1806 'url': smuggle_url(bc_url, {'Referer': url}),
1807 'ie_key': 'BrightcoveLegacy'
1808 } for bc_url in bc_urls]
1809
1810 return {
1811 '_type': 'playlist',
1812 'title': video_title,
1813 'id': video_id,
1814 'entries': entries,
1815 }
1816
1817 # Look for Brightcove New Studio embeds
1818 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1819 if bc_urls:
1820 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1821
1822 # Look for ThePlatform embeds
1823 tp_urls = ThePlatformIE._extract_urls(webpage)
1824 if tp_urls:
1825 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1826
1827 # Look for Vessel embeds
1828 vessel_urls = VesselIE._extract_urls(webpage)
1829 if vessel_urls:
1830 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1831
1832 # Look for embedded rtl.nl player
1833 matches = re.findall(
1834 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1835 webpage)
1836 if matches:
1837 return _playlist_from_matches(matches, ie='RtlNl')
1838
1839 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1840 if vimeo_urls:
1841 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1842
1843 vid_me_embed_url = self._search_regex(
1844 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1845 webpage, 'vid.me embed', default=None)
1846 if vid_me_embed_url is not None:
1847 return self.url_result(vid_me_embed_url, 'Vidme')
1848
1849 # Look for embedded YouTube player
1850 matches = re.findall(r'''(?x)
1851 (?:
1852 <iframe[^>]+?src=|
1853 data-video-url=|
1854 <embed[^>]+?src=|
1855 embedSWF\(?:\s*|
1856 new\s+SWFObject\(
1857 )
1858 (["\'])
1859 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1860 (?:embed|v|p)/.+?)
1861 \1''', webpage)
1862 if matches:
1863 return _playlist_from_matches(
1864 matches, lambda m: unescapeHTML(m[1]))
1865
1866 # Look for lazyYT YouTube embed
1867 matches = re.findall(
1868 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1869 if matches:
1870 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1871
1872 # Look for Wordpress "YouTube Video Importer" plugin
1873 matches = re.findall(r'''(?x)<div[^>]+
1874 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1875 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1876 if matches:
1877 return _playlist_from_matches(matches, lambda m: m[-1])
1878
1879 matches = DailymotionIE._extract_urls(webpage)
1880 if matches:
1881 return _playlist_from_matches(matches)
1882
1883 # Look for embedded Dailymotion playlist player (#3822)
1884 m = re.search(
1885 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1886 if m:
1887 playlists = re.findall(
1888 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1889 if playlists:
1890 return _playlist_from_matches(
1891 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1892
1893 # Look for embedded Wistia player
1894 match = re.search(
1895 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1896 if match:
1897 embed_url = self._proto_relative_url(
1898 unescapeHTML(match.group('url')))
1899 return {
1900 '_type': 'url_transparent',
1901 'url': embed_url,
1902 'ie_key': 'Wistia',
1903 'uploader': video_uploader,
1904 }
1905
1906 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1907 if match:
1908 return {
1909 '_type': 'url_transparent',
1910 'url': 'wistia:%s' % match.group('id'),
1911 'ie_key': 'Wistia',
1912 'uploader': video_uploader,
1913 }
1914
1915 match = re.search(
1916 r'''(?sx)
1917 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1918 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1919 ''', webpage)
1920 if match:
1921 return self.url_result(self._proto_relative_url(
1922 'wistia:%s' % match.group('id')), 'Wistia')
1923
1924 # Look for SVT player
1925 svt_url = SVTIE._extract_url(webpage)
1926 if svt_url:
1927 return self.url_result(svt_url, 'SVT')
1928
1929 # Look for embedded condenast player
1930 matches = re.findall(
1931 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1932 webpage)
1933 if matches:
1934 return {
1935 '_type': 'playlist',
1936 'entries': [{
1937 '_type': 'url',
1938 'ie_key': 'CondeNast',
1939 'url': ma,
1940 } for ma in matches],
1941 'title': video_title,
1942 'id': video_id,
1943 }
1944
1945 # Look for Bandcamp pages with custom domain
1946 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1947 if mobj is not None:
1948 burl = unescapeHTML(mobj.group(1))
1949 # Don't set the extractor because it can be a track url or an album
1950 return self.url_result(burl)
1951
1952 # Look for embedded Vevo player
1953 mobj = re.search(
1954 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1955 if mobj is not None:
1956 return self.url_result(mobj.group('url'))
1957
1958 # Look for embedded Viddler player
1959 mobj = re.search(
1960 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1961 webpage)
1962 if mobj is not None:
1963 return self.url_result(mobj.group('url'))
1964
1965 # Look for NYTimes player
1966 mobj = re.search(
1967 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1968 webpage)
1969 if mobj is not None:
1970 return self.url_result(mobj.group('url'))
1971
1972 # Look for Libsyn player
1973 mobj = re.search(
1974 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1975 if mobj is not None:
1976 return self.url_result(mobj.group('url'))
1977
1978 # Look for Ooyala videos
1979 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1980 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1981 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1982 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1983 if mobj is not None:
1984 embed_token = self._search_regex(
1985 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1986 webpage, 'ooyala embed token', default=None)
1987 return OoyalaIE._build_url_result(smuggle_url(
1988 mobj.group('ec'), {
1989 'domain': url,
1990 'embed_token': embed_token,
1991 }))
1992
1993 # Look for multiple Ooyala embeds on SBN network websites
1994 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1995 if mobj is not None:
1996 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1997 if embeds:
1998 return _playlist_from_matches(
1999 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2000
2001 # Look for Aparat videos
2002 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2003 if mobj is not None:
2004 return self.url_result(mobj.group(1), 'Aparat')
2005
2006 # Look for MPORA videos
2007 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2008 if mobj is not None:
2009 return self.url_result(mobj.group(1), 'Mpora')
2010
2011 # Look for embedded NovaMov-based player
2012 mobj = re.search(
2013 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2014 (?P<url>http://(?:(?:embed|www)\.)?
2015 (?:novamov\.com|
2016 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2017 videoweed\.(?:es|com)|
2018 movshare\.(?:net|sx|ag)|
2019 divxstage\.(?:eu|net|ch|co|at|ag))
2020 /embed\.php.+?)\1''', webpage)
2021 if mobj is not None:
2022 return self.url_result(mobj.group('url'))
2023
2024 # Look for embedded Facebook player
2025 facebook_url = FacebookIE._extract_url(webpage)
2026 if facebook_url is not None:
2027 return self.url_result(facebook_url, 'Facebook')
2028
2029 # Look for embedded VK player
2030 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2031 if mobj is not None:
2032 return self.url_result(mobj.group('url'), 'VK')
2033
2034 # Look for embedded Odnoklassniki player
2035 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2036 if mobj is not None:
2037 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2038
2039 # Look for embedded ivi player
2040 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2041 if mobj is not None:
2042 return self.url_result(mobj.group('url'), 'Ivi')
2043
2044 # Look for embedded Huffington Post player
2045 mobj = re.search(
2046 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2047 if mobj is not None:
2048 return self.url_result(mobj.group('url'), 'HuffPost')
2049
2050 # Look for embed.ly
2051 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2052 if mobj is not None:
2053 return self.url_result(mobj.group('url'))
2054 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2055 if mobj is not None:
2056 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2057
2058 # Look for funnyordie embed
2059 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2060 if matches:
2061 return _playlist_from_matches(
2062 matches, getter=unescapeHTML, ie='FunnyOrDie')
2063
2064 # Look for BBC iPlayer embed
2065 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2066 if matches:
2067 return _playlist_from_matches(matches, ie='BBCCoUk')
2068
2069 # Look for embedded RUTV player
2070 rutv_url = RUTVIE._extract_url(webpage)
2071 if rutv_url:
2072 return self.url_result(rutv_url, 'RUTV')
2073
2074 # Look for embedded TVC player
2075 tvc_url = TVCIE._extract_url(webpage)
2076 if tvc_url:
2077 return self.url_result(tvc_url, 'TVC')
2078
2079 # Look for embedded SportBox player
2080 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2081 if sportbox_urls:
2082 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2083
2084 # Look for embedded XHamster player
2085 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2086 if xhamster_urls:
2087 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2088
2089 # Look for embedded TNAFlixNetwork player
2090 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2091 if tnaflix_urls:
2092 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2093
2094 # Look for embedded PornHub player
2095 pornhub_urls = PornHubIE._extract_urls(webpage)
2096 if pornhub_urls:
2097 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2098
2099 # Look for embedded DrTuber player
2100 drtuber_urls = DrTuberIE._extract_urls(webpage)
2101 if drtuber_urls:
2102 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2103
2104 # Look for embedded RedTube player
2105 redtube_urls = RedTubeIE._extract_urls(webpage)
2106 if redtube_urls:
2107 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2108
2109 # Look for embedded Tvigle player
2110 mobj = re.search(
2111 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2112 if mobj is not None:
2113 return self.url_result(mobj.group('url'), 'Tvigle')
2114
2115 # Look for embedded TED player
2116 mobj = re.search(
2117 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2118 if mobj is not None:
2119 return self.url_result(mobj.group('url'), 'TED')
2120
2121 # Look for embedded Ustream videos
2122 ustream_url = UstreamIE._extract_url(webpage)
2123 if ustream_url:
2124 return self.url_result(ustream_url, UstreamIE.ie_key())
2125
2126 # Look for embedded arte.tv player
2127 mobj = re.search(
2128 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2129 webpage)
2130 if mobj is not None:
2131 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2132
2133 # Look for embedded francetv player
2134 mobj = re.search(
2135 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2136 webpage)
2137 if mobj is not None:
2138 return self.url_result(mobj.group('url'))
2139
2140 # Look for embedded smotri.com player
2141 smotri_url = SmotriIE._extract_url(webpage)
2142 if smotri_url:
2143 return self.url_result(smotri_url, 'Smotri')
2144
2145 # Look for embedded Myvi.ru player
2146 myvi_url = MyviIE._extract_url(webpage)
2147 if myvi_url:
2148 return self.url_result(myvi_url)
2149
2150 # Look for embedded soundcloud player
2151 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2152 if soundcloud_urls:
2153 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2154
2155 # Look for tunein player
2156 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2157 if tunein_urls:
2158 return _playlist_from_matches(tunein_urls)
2159
2160 # Look for embedded mtvservices player
2161 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2162 if mtvservices_url:
2163 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2164
2165 # Look for embedded yahoo player
2166 mobj = re.search(
2167 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2168 webpage)
2169 if mobj is not None:
2170 return self.url_result(mobj.group('url'), 'Yahoo')
2171
2172 # Look for embedded sbs.com.au player
2173 mobj = re.search(
2174 r'''(?x)
2175 (?:
2176 <meta\s+property="og:video"\s+content=|
2177 <iframe[^>]+?src=
2178 )
2179 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2180 webpage)
2181 if mobj is not None:
2182 return self.url_result(mobj.group('url'), 'SBS')
2183
2184 # Look for embedded Cinchcast player
2185 mobj = re.search(
2186 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2187 webpage)
2188 if mobj is not None:
2189 return self.url_result(mobj.group('url'), 'Cinchcast')
2190
2191 mobj = re.search(
2192 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2193 webpage)
2194 if not mobj:
2195 mobj = re.search(
2196 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2197 webpage)
2198 if mobj is not None:
2199 return self.url_result(mobj.group('url'), 'MLB')
2200
2201 mobj = re.search(
2202 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2203 webpage)
2204 if mobj is not None:
2205 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2206
2207 mobj = re.search(
2208 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2209 webpage)
2210 if mobj is not None:
2211 return self.url_result(mobj.group('url'), 'Livestream')
2212
2213 # Look for Zapiks embed
2214 mobj = re.search(
2215 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2216 if mobj is not None:
2217 return self.url_result(mobj.group('url'), 'Zapiks')
2218
2219 # Look for Kaltura embeds
2220 kaltura_url = KalturaIE._extract_url(webpage)
2221 if kaltura_url:
2222 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2223
2224 # Look for Eagle.Platform embeds
2225 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2226 if eagleplatform_url:
2227 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2228
2229 # Look for ClipYou (uses Eagle.Platform) embeds
2230 mobj = re.search(
2231 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2232 if mobj is not None:
2233 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2234
2235 # Look for Pladform embeds
2236 pladform_url = PladformIE._extract_url(webpage)
2237 if pladform_url:
2238 return self.url_result(pladform_url)
2239
2240 # Look for Videomore embeds
2241 videomore_url = VideomoreIE._extract_url(webpage)
2242 if videomore_url:
2243 return self.url_result(videomore_url)
2244
2245 # Look for Webcaster embeds
2246 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2247 if webcaster_url:
2248 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2249
2250 # Look for Playwire embeds
2251 mobj = re.search(
2252 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2253 if mobj is not None:
2254 return self.url_result(mobj.group('url'))
2255
2256 # Look for 5min embeds
2257 mobj = re.search(
2258 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2259 if mobj is not None:
2260 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2261
2262 # Look for Crooks and Liars embeds
2263 mobj = re.search(
2264 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2265 if mobj is not None:
2266 return self.url_result(mobj.group('url'))
2267
2268 # Look for NBC Sports VPlayer embeds
2269 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2270 if nbc_sports_url:
2271 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2272
2273 # Look for NBC News embeds
2274 nbc_news_embed_url = re.search(
2275 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2276 if nbc_news_embed_url:
2277 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2278
2279 # Look for Google Drive embeds
2280 google_drive_url = GoogleDriveIE._extract_url(webpage)
2281 if google_drive_url:
2282 return self.url_result(google_drive_url, 'GoogleDrive')
2283
2284 # Look for UDN embeds
2285 mobj = re.search(
2286 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2287 if mobj is not None:
2288 return self.url_result(
2289 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2290
2291 # Look for Senate ISVP iframe
2292 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2293 if senate_isvp_url:
2294 return self.url_result(senate_isvp_url, 'SenateISVP')
2295
2296 # Look for Dailymotion Cloud videos
2297 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2298 if dmcloud_url:
2299 return self.url_result(dmcloud_url, 'DailymotionCloud')
2300
2301 # Look for OnionStudios embeds
2302 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2303 if onionstudios_url:
2304 return self.url_result(onionstudios_url)
2305
2306 # Look for ViewLift embeds
2307 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2308 if viewlift_url:
2309 return self.url_result(viewlift_url)
2310
2311 # Look for JWPlatform embeds
2312 jwplatform_url = JWPlatformIE._extract_url(webpage)
2313 if jwplatform_url:
2314 return self.url_result(jwplatform_url, 'JWPlatform')
2315
2316 # Look for Digiteka embeds
2317 digiteka_url = DigitekaIE._extract_url(webpage)
2318 if digiteka_url:
2319 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2320
2321 # Look for Arkena embeds
2322 arkena_url = ArkenaIE._extract_url(webpage)
2323 if arkena_url:
2324 return self.url_result(arkena_url, ArkenaIE.ie_key())
2325
2326 # Look for Piksel embeds
2327 piksel_url = PikselIE._extract_url(webpage)
2328 if piksel_url:
2329 return self.url_result(piksel_url, PikselIE.ie_key())
2330
2331 # Look for Limelight embeds
2332 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2333 if mobj:
2334 lm = {
2335 'Media': 'media',
2336 'Channel': 'channel',
2337 'ChannelList': 'channel_list',
2338 }
2339 return self.url_result('limelight:%s:%s' % (
2340 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2341
2342 mobj = re.search(
2343 r'''(?sx)
2344 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2345 <param[^>]+
2346 name=(["\'])flashVars\2[^>]+
2347 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2348 ''', webpage)
2349 if mobj:
2350 return self.url_result('limelight:media:%s' % mobj.group('id'))
2351
2352 # Look for AdobeTVVideo embeds
2353 mobj = re.search(
2354 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2355 webpage)
2356 if mobj is not None:
2357 return self.url_result(
2358 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2359 'AdobeTVVideo')
2360
2361 # Look for Vine embeds
2362 mobj = re.search(
2363 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2364 webpage)
2365 if mobj is not None:
2366 return self.url_result(
2367 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2368
2369 # Look for VODPlatform embeds
2370 mobj = re.search(
2371 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2372 webpage)
2373 if mobj is not None:
2374 return self.url_result(
2375 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2376
2377 # Look for Mangomolo embeds
2378 mobj = re.search(
2379 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2380 (?:
2381 video\?.*?\bid=(?P<video_id>\d+)|
2382 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2383 ).+?)\1''', webpage)
2384 if mobj is not None:
2385 info = {
2386 '_type': 'url_transparent',
2387 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2388 'title': video_title,
2389 'description': video_description,
2390 'thumbnail': video_thumbnail,
2391 'uploader': video_uploader,
2392 }
2393 video_id = mobj.group('video_id')
2394 if video_id:
2395 info.update({
2396 'ie_key': 'MangomoloVideo',
2397 'id': video_id,
2398 })
2399 else:
2400 info.update({
2401 'ie_key': 'MangomoloLive',
2402 'id': mobj.group('channel_id'),
2403 })
2404 return info
2405
2406 # Look for Instagram embeds
2407 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2408 if instagram_embed_url is not None:
2409 return self.url_result(
2410 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2411
2412 # Look for LiveLeak embeds
2413 liveleak_url = LiveLeakIE._extract_url(webpage)
2414 if liveleak_url:
2415 return self.url_result(liveleak_url, 'LiveLeak')
2416
2417 # Look for 3Q SDN embeds
2418 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2419 if threeqsdn_url:
2420 return {
2421 '_type': 'url_transparent',
2422 'ie_key': ThreeQSDNIE.ie_key(),
2423 'url': self._proto_relative_url(threeqsdn_url),
2424 'title': video_title,
2425 'description': video_description,
2426 'thumbnail': video_thumbnail,
2427 'uploader': video_uploader,
2428 }
2429
2430 # Look for VBOX7 embeds
2431 vbox7_url = Vbox7IE._extract_url(webpage)
2432 if vbox7_url:
2433 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2434
2435 # Look for DBTV embeds
2436 dbtv_urls = DBTVIE._extract_urls(webpage)
2437 if dbtv_urls:
2438 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2439
2440 # Look for Videa embeds
2441 videa_urls = VideaIE._extract_urls(webpage)
2442 if videa_urls:
2443 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2444
2445 # Look for 20 minuten embeds
2446 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2447 if twentymin_urls:
2448 return _playlist_from_matches(
2449 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2450
2451 # Look for Openload embeds
2452 openload_urls = OpenloadIE._extract_urls(webpage)
2453 if openload_urls:
2454 return _playlist_from_matches(
2455 openload_urls, ie=OpenloadIE.ie_key())
2456
2457 # Look for VideoPress embeds
2458 videopress_urls = VideoPressIE._extract_urls(webpage)
2459 if videopress_urls:
2460 return _playlist_from_matches(
2461 videopress_urls, ie=VideoPressIE.ie_key())
2462
2463 # Looking for http://schema.org/VideoObject
2464 json_ld = self._search_json_ld(
2465 webpage, video_id, default={}, expected_type='VideoObject')
2466 if json_ld.get('url'):
2467 info_dict.update({
2468 'title': video_title or info_dict['title'],
2469 'description': video_description,
2470 'thumbnail': video_thumbnail,
2471 'age_limit': age_limit
2472 })
2473 info_dict.update(json_ld)
2474 return info_dict
2475
2476 # Look for HTML5 media
2477 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2478 if entries:
2479 for entry in entries:
2480 entry.update({
2481 'id': video_id,
2482 'title': video_title,
2483 })
2484 self._sort_formats(entry['formats'])
2485 return self.playlist_result(entries)
2486
2487 def check_video(vurl):
2488 if YoutubeIE.suitable(vurl):
2489 return True
2490 vpath = compat_urlparse.urlparse(vurl).path
2491 vext = determine_ext(vpath)
2492 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2493
2494 def filter_video(urls):
2495 return list(filter(check_video, urls))
2496
2497 # Start with something easy: JW Player in SWFObject
2498 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2499 if not found:
2500 # Look for gorilla-vid style embedding
2501 found = filter_video(re.findall(r'''(?sx)
2502 (?:
2503 jw_plugins|
2504 JWPlayerOptions|
2505 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2506 )
2507 .*?
2508 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2509 if not found:
2510 # Broaden the search a little bit
2511 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2512 if not found:
2513 # Broaden the findall a little bit: JWPlayer JS loader
2514 found = filter_video(re.findall(
2515 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2516 if not found:
2517 # Flow player
2518 found = filter_video(re.findall(r'''(?xs)
2519 flowplayer\("[^"]+",\s*
2520 \{[^}]+?\}\s*,
2521 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2522 ["']?url["']?\s*:\s*["']([^"']+)["']
2523 ''', webpage))
2524 if not found:
2525 # Cinerama player
2526 found = re.findall(
2527 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2528 if not found:
2529 # Try to find twitter cards info
2530 # twitter:player:stream should be checked before twitter:player since
2531 # it is expected to contain a raw stream (see
2532 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2533 found = filter_video(re.findall(
2534 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2535 if not found:
2536 # We look for Open Graph info:
2537 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2538 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2539 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2540 if m_video_type is not None:
2541 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2542 if not found:
2543 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2544 found = re.search(
2545 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2546 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2547 webpage)
2548 if not found:
2549 # Look also in Refresh HTTP header
2550 refresh_header = head_response.headers.get('Refresh')
2551 if refresh_header:
2552 # In python 2 response HTTP headers are bytestrings
2553 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2554 refresh_header = refresh_header.decode('iso-8859-1')
2555 found = re.search(REDIRECT_REGEX, refresh_header)
2556 if found:
2557 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2558 self.report_following_redirect(new_url)
2559 return {
2560 '_type': 'url',
2561 'url': new_url,
2562 }
2563
2564 if not found:
2565 # twitter:player is a https URL to iframe player that may or may not
2566 # be supported by youtube-dl thus this is checked the very last (see
2567 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2568 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2569 if embed_url:
2570 return self.url_result(embed_url)
2571
2572 if not found:
2573 raise UnsupportedError(url)
2574
2575 entries = []
2576 for video_url in orderedSet(found):
2577 video_url = unescapeHTML(video_url)
2578 video_url = video_url.replace('\\/', '/')
2579 video_url = compat_urlparse.urljoin(url, video_url)
2580 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2581
2582 # Sometimes, jwplayer extraction will result in a YouTube URL
2583 if YoutubeIE.suitable(video_url):
2584 entries.append(self.url_result(video_url, 'Youtube'))
2585 continue
2586
2587 # here's a fun little line of code for you:
2588 video_id = os.path.splitext(video_id)[0]
2589
2590 entry_info_dict = {
2591 'id': video_id,
2592 'uploader': video_uploader,
2593 'title': video_title,
2594 'age_limit': age_limit,
2595 }
2596
2597 ext = determine_ext(video_url)
2598 if ext == 'smil':
2599 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2600 elif ext == 'xspf':
2601 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2602 elif ext == 'm3u8':
2603 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2604 elif ext == 'mpd':
2605 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2606 elif ext == 'f4m':
2607 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2608 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2609 # Just matching .ism/manifest is not enough to be reliably sure
2610 # whether it's actually an ISM manifest or some other streaming
2611 # manifest since there are various streaming URL formats
2612 # possible (see [1]) as well as some other shenanigans like
2613 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2614 # so on.
2615 # Thus the most reasonable way to solve this is to delegate
2616 # to generic extractor in order to look into the contents of
2617 # the manifest itself.
2618 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2619 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2620 entry_info_dict = self.url_result(
2621 smuggle_url(video_url, {'to_generic': True}),
2622 GenericIE.ie_key())
2623 else:
2624 entry_info_dict['url'] = video_url
2625
2626 if entry_info_dict.get('formats'):
2627 self._sort_formats(entry_info_dict['formats'])
2628
2629 entries.append(entry_info_dict)
2630
2631 if len(entries) == 1:
2632 return entries[0]
2633 else:
2634 for num, e in enumerate(entries, start=1):
2635 # 'url' results don't have a title
2636 if e.get('title') is not None:
2637 e['title'] = '%s (%d)' % (e['title'], num)
2638 return {
2639 '_type': 'playlist',
2640 'entries': entries,
2641 }