]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[livestream] Video IDs should always be strings (#2234)
[yt-dlp.git] / youtube_dl / extractor / generic.py
CommitLineData
cfe50f04
JMF
1# encoding: utf-8
2
79649588
PH
3from __future__ import unicode_literals
4
9b122384
PH
5import os
6import re
6c91a5a7 7import sys
9b122384
PH
8
9from .common import InfoExtractor
fc9713a1 10from .youtube import YoutubeIE
8c25f81b 11from ..compat import (
f7854627 12 compat_etree_fromstring,
1ddb9456 13 compat_urllib_parse_unquote,
a5caba1e 14 compat_urlparse,
f7300c5c 15 compat_xml_parse_error,
8c25f81b
PH
16)
17from ..utils import (
b759a0d4 18 determine_ext,
9b122384 19 ExtractorError,
c8e9a235 20 float_or_none,
aa94a6d3 21 HEADRequest,
61ca9a80 22 is_html,
ed2d6a19 23 orderedSet,
5c2266df 24 sanitized_Request,
9d4660ca
PH
25 smuggle_url,
26 unescapeHTML,
42393ce2 27 unified_strdate,
4d54ef20 28 unsmuggle_url,
416c7fcb 29 UnsupportedError,
42393ce2 30 url_basename,
76c73715 31 xpath_text,
9b122384 32)
ed126900 33from .brightcove import (
4fcaa4f4 34 BrightcoveLegacyIE,
5c17f0a6 35 BrightcoveNewIE,
ed126900 36)
a2edf2e7 37from .nbc import NBCSportsVPlayerIE
c0d0b01f 38from .ooyala import OoyalaIE
93d020dd 39from .rutv import RUTVIE
954c1d05 40from .tvc import TVCIE
d40a3b5b 41from .sportbox import SportBoxEmbedIE
cb3ac1c6 42from .smotri import SmotriIE
6dd94d3a 43from .myvi import MyviIE
1419fafd 44from .condenast import CondeNastIE
418c5cc3 45from .udn import UDNEmbedIE
2fe1b5bd 46from .senateisvp import SenateISVPIE
bab19a8e 47from .svt import SVTIE
65d161c4 48from .pornhub import PornHubIE
2bb5b6d0 49from .xhamster import XHamsterEmbedIE
2c9ca782 50from .tnaflix import TNAFlixNetworkEmbedIE
b407e173 51from .vimeo import VimeoIE
756f574e 52from .dailymotion import DailymotionCloudIE
1ac1c4c2 53from .onionstudios import OnionStudiosIE
67167920 54from .viewlift import ViewLiftEmbedIE
efd712c6 55from .screenwavemedia import ScreenwaveMediaIE
46fde8a1 56from .mtv import MTVServicesEmbeddedIE
45dad7ba 57from .pladform import PladformIE
ff18735c 58from .videomore import VideomoreIE
5b251628 59from .googledrive import GoogleDriveIE
7cb09524 60from .jwplatform import JWPlatformIE
aecfcd4e 61from .digiteka import DigitekaIE
5a51775a 62from .instagram import InstagramIE
b8f67449 63from .liveleak import LiveLeakIE
5d39176f 64from .threeqsdn import ThreeQSDNIE
4d8819d2 65from .theplatform import ThePlatformIE
9b122384 66
0838239e 67
9b122384 68class GenericIE(InfoExtractor):
79649588 69 IE_DESC = 'Generic downloader that works on some sites'
9b122384 70 _VALID_URL = r'.*'
79649588 71 IE_NAME = 'generic'
cfe50f04 72 _TESTS = [
c5fa81fe
S
73 # Direct link to a video
74 {
75 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
76 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
77 'info_dict': {
78 'id': 'trailer',
79 'ext': 'mp4',
80 'title': 'trailer',
81 'upload_date': '20100513',
82 }
83 },
c5138a7c 84 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
85 {
86 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
87 'md5': '128c42e68b13950268b648275386fc74',
88 'info_dict': {
89 'id': 'FictionJunction-Parallel_Hearts',
90 'ext': 'flac',
91 'title': 'FictionJunction-Parallel_Hearts',
92 'upload_date': '20140522',
93 },
94 'expected_warnings': [
95 'URL could be a direct video link, returning it as such.'
96 ]
97 },
98 # Direct download with broken HEAD
99 {
100 'url': 'http://ai-radio.org:8000/radio.opus',
101 'info_dict': {
102 'id': 'radio',
103 'ext': 'opus',
104 'title': 'radio',
105 },
106 'params': {
107 'skip_download': True, # infinite live stream
108 },
109 'expected_warnings': [
ef0e4e7b
YCH
110 r'501.*Not Implemented',
111 r'400.*Bad Request',
c5fa81fe
S
112 ],
113 },
114 # Direct link with incorrect MIME type
115 {
116 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
117 'md5': '4ccbebe5f36706d85221f204d7eb5913',
118 'info_dict': {
119 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
120 'id': '5_Lennart_Poettering_-_Systemd',
121 'ext': 'webm',
122 'title': '5_Lennart_Poettering_-_Systemd',
123 'upload_date': '20141120',
124 },
125 'expected_warnings': [
126 'URL could be a direct video link, returning it as such.'
127 ]
128 },
129 # RSS feed
130 {
131 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
132 'info_dict': {
133 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
134 'title': 'Zero Punctuation',
135 'description': 're:.*groundbreaking video review series.*'
136 },
137 'playlist_mincount': 11,
138 },
139 # RSS feed with enclosure
140 {
141 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
142 'info_dict': {
143 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
144 'ext': 'm4v',
145 'upload_date': '20150228',
146 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
147 }
148 },
8765222d
S
149 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
150 {
151 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
152 'info_dict': {
153 'id': 'smil',
154 'ext': 'mp4',
155 'title': 'Automatics, robotics and biocybernetics',
156 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 157 'upload_date': '20130627',
8765222d
S
158 'formats': 'mincount:16',
159 'subtitles': 'mincount:1',
160 },
161 'params': {
162 'force_generic_extractor': True,
163 'skip_download': True,
164 },
165 },
166 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
167 {
168 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
169 'info_dict': {
170 'id': 'hds',
171 'ext': 'flv',
172 'title': 'hds',
173 'formats': 'mincount:1',
174 },
175 'params': {
176 'skip_download': True,
177 },
178 },
179 # SMIL from https://www.restudy.dk/video/play/id/1637
180 {
181 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
182 'info_dict': {
183 'id': 'video_1637',
184 'ext': 'flv',
185 'title': 'video_1637',
186 'formats': 'mincount:3',
187 },
188 'params': {
189 'skip_download': True,
190 },
191 },
192 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
193 {
194 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
195 'info_dict': {
196 'id': 'smil-service',
197 'ext': 'flv',
198 'title': 'smil-service',
199 'formats': 'mincount:1',
200 },
201 'params': {
202 'skip_download': True,
203 },
204 },
205 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
206 {
207 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
208 'info_dict': {
209 'id': '4719370',
210 'ext': 'mp4',
211 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
212 'formats': 'mincount:3',
213 },
214 'params': {
215 'skip_download': True,
216 },
217 },
1de5cd3b
S
218 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
219 {
220 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
221 'info_dict': {
222 'id': 'mZlp2ctYIUEB',
223 'ext': 'mp4',
224 'title': 'Tikibad ontruimd wegens brand',
225 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
226 'thumbnail': 're:^https?://.*\.jpg$',
227 'duration': 33,
228 },
229 'params': {
230 'skip_download': True,
231 },
232 },
9d939cec
S
233 # MPD from http://dash-mse-test.appspot.com/media.html
234 {
235 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
236 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
237 'info_dict': {
238 'id': 'car-20120827-manifest',
239 'ext': 'mp4',
240 'title': 'car-20120827-manifest',
241 'formats': 'mincount:9',
0738187f 242 'upload_date': '20130904',
9d939cec
S
243 },
244 'params': {
245 'format': 'bestvideo',
246 },
247 },
20938f76
S
248 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
249 {
250 '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',
251 'info_dict': {
252 'id': 'content',
253 'ext': 'mp4',
254 'title': 'content',
255 'formats': 'mincount:8',
256 },
257 'params': {
258 # m3u8 downloads
259 'skip_download': True,
260 }
261 },
edd9b71c
S
262 # m3u8 served with Content-Type: text/plain
263 {
264 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
265 'info_dict': {
266 'id': 'index',
267 'ext': 'mp4',
268 'title': 'index',
269 'upload_date': '20140720',
270 'formats': 'mincount:11',
271 },
272 'params': {
273 # m3u8 downloads
274 'skip_download': True,
275 }
276 },
c5fa81fe
S
277 # google redirect
278 {
279 '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',
280 'info_dict': {
281 'id': 'cmQHVoWB5FY',
282 'ext': 'mp4',
283 'upload_date': '20130224',
284 'uploader_id': 'TheVerge',
285 'description': 're:^Chris Ziegler takes a look at the\.*',
286 'uploader': 'The Verge',
287 'title': 'First Firefox OS phones side-by-side',
288 },
289 'params': {
290 'skip_download': False,
291 }
292 },
6c91a5a7
S
293 {
294 # redirect in Refresh HTTP header
295 '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',
296 'info_dict': {
297 'id': 'pO8h3EaFRdo',
298 'ext': 'mp4',
299 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
300 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
301 'upload_date': '20150917',
302 'uploader_id': 'brtvofficial',
303 'uploader': 'Boiler Room',
304 },
305 'params': {
306 'skip_download': False,
307 },
308 },
cfe50f04 309 {
79649588 310 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 311 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 312 'info_dict': {
d360a146
S
313 'id': '13601338388002',
314 'ext': 'mp4',
79649588
PH
315 'uploader': 'www.hodiho.fr',
316 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
317 }
318 },
c19f7764
JMF
319 # bandcamp page with custom domain
320 {
79649588
PH
321 'add_ie': ['Bandcamp'],
322 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 323 'info_dict': {
fd50bf62
S
324 'id': '3235767654',
325 'ext': 'mp3',
79649588
PH
326 'title': 'The Pony Mash',
327 'uploader': 'M_Pallante',
c19f7764 328 },
79649588 329 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 330 },
eeb165e6 331 # embedded brightcove video
dd5bcdc4
JMF
332 # it also tests brightcove videos that need to set the 'Referer' in the
333 # http requests
eeb165e6 334 {
3b7d9aa4 335 'add_ie': ['BrightcoveLegacy'],
79649588
PH
336 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
337 'info_dict': {
338 'id': '2765128793001',
339 'ext': 'mp4',
340 'title': 'Le cours de bourse : l’analyse technique',
341 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
342 'uploader': 'BFM BUSINESS',
eeb165e6 343 },
79649588
PH
344 'params': {
345 'skip_download': True,
eeb165e6
JMF
346 },
347 },
17ab4d3b
PH
348 {
349 # https://github.com/rg3/youtube-dl/issues/2253
350 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
351 'md5': '0ba9446db037002366bab3b3eb30c88c',
352 'info_dict': {
fd50bf62
S
353 'id': '3101154703001',
354 'ext': 'mp4',
17ab4d3b
PH
355 'title': 'Still no power',
356 'uploader': 'thestar.com',
357 '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.',
358 },
3b7d9aa4 359 'add_ie': ['BrightcoveLegacy'],
17ab4d3b 360 },
0479c625
S
361 {
362 'url': 'http://www.championat.com/video/football/v/87/87499.html',
363 'md5': 'fb973ecf6e4a78a67453647444222983',
364 'info_dict': {
365 'id': '3414141473001',
366 'ext': 'mp4',
367 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
368 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
369 'uploader': 'Championat',
370 },
371 },
bdf97017 372 {
37aab278 373 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 374 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
375 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
376 'info_dict': {
377 'id': '3866516442001',
37aab278 378 'ext': 'mp4',
bdf97017
NJ
379 'title': 'Leer mij vrouwen kennen: Aflevering 1',
380 'description': 'Leer mij vrouwen kennen: Aflevering 1',
381 'uploader': 'SBS Broadcasting',
382 },
37aab278 383 'skip': 'Restricted to Netherlands',
bdf97017 384 'params': {
37aab278 385 'skip_download': True, # m3u8 download
bdf97017
NJ
386 },
387 },
c0d0b01f
JMF
388 # ooyala video
389 {
79649588 390 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 391 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
392 'info_dict': {
393 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
394 'ext': 'mp4',
3486df38 395 'title': '2cc213299525360.mov', # that's what we get
53e06b25 396 'duration': 238.231,
c0d0b01f 397 },
87830900 398 'add_ie': ['Ooyala'],
c0d0b01f 399 },
bf94d763
S
400 {
401 # ooyala video embedded with http://player.ooyala.com/iframe.js
402 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
403 'info_dict': {
404 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
405 'ext': 'mp4',
406 'title': '"Steve Jobs: Man in the Machine" trailer',
407 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 408 'duration': 135.427,
bf94d763
S
409 },
410 'params': {
411 'skip_download': True,
412 },
413 },
1b86cc41 414 # embed.ly video
415 {
416 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
417 'info_dict': {
418 'id': '9ODmcdjQcHQ',
419 'ext': 'mp4',
0a5bce56
PH
420 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
421 'upload_date': '20140225',
422 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
423 'uploader': 'Tested',
424 'uploader_id': 'testedcom',
1b86cc41 425 },
426 # No need to test YoutubeIE here
427 'params': {
428 'skip_download': True,
429 },
430 },
60cc4dc4
PH
431 # funnyordie embed
432 {
433 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
434 'info_dict': {
435 'id': '18e820ec3f',
436 'ext': 'mp4',
437 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
438 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 439 },
60cc4dc4 440 },
93d020dd
S
441 # RUTV embed
442 {
443 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
444 'info_dict': {
445 'id': '776940',
446 'ext': 'mp4',
447 'title': 'Охотское море стало целиком российским',
448 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
449 },
450 'params': {
451 # m3u8 download
452 'skip_download': True,
453 },
aab74fa1 454 },
f37bdbe5
S
455 # TVC embed
456 {
457 '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/',
458 'info_dict': {
459 'id': '55304',
460 'ext': 'mp4',
461 'title': 'Дошкольное воспитание',
462 },
463 },
b827a601
S
464 # SportBox embed
465 {
466 'url': 'http://www.vestifinance.ru/articles/25753',
467 'info_dict': {
468 'id': '25753',
469 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
470 },
471 'playlist': [{
472 'info_dict': {
473 'id': '370908',
474 'title': 'Госзаказ. День 3',
475 'ext': 'mp4',
476 }
477 }, {
478 'info_dict': {
479 'id': '370905',
480 'title': 'Госзаказ. День 2',
481 'ext': 'mp4',
482 }
483 }, {
484 'info_dict': {
485 'id': '370902',
486 'title': 'Госзаказ. День 1',
487 'ext': 'mp4',
488 }
489 }],
490 'params': {
491 # m3u8 download
492 'skip_download': True,
493 },
494 },
bf20b9c5
S
495 # Myvi.ru embed
496 {
497 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
498 'info_dict': {
499 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
500 'ext': 'mp4',
501 'title': 'Ужастики, русский трейлер (2015)',
502 'thumbnail': 're:^https?://.*\.jpg$',
503 'duration': 153,
504 }
505 },
c76799c5
S
506 # XHamster embed
507 {
508 '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',
509 'info_dict': {
510 'id': 'showthread',
511 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
512 },
513 'playlist_mincount': 7,
514 },
aab74fa1
PH
515 # Embedded TED video
516 {
517 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 518 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 519 'info_dict': {
a8eb5a8e 520 'id': '1969',
aab74fa1 521 'ext': 'mp4',
a8eb5a8e
PH
522 'title': 'Hidden miracles of the natural world',
523 'uploader': 'Louie Schwartzberg',
524 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 525 }
60cc4dc4 526 },
dfb1b146 527 # Embedded Ustream video
5c386252 528 {
529 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
530 'md5': '27b99cdb639c9b12a79bca876a073417',
531 'info_dict': {
ca6aada4 532 'id': '45734260',
533 'ext': 'flv',
534 'uploader': 'AU SPA: The NSA and Privacy',
5c386252 535 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
536 }
537 },
d95e35d6
S
538 # nowvideo embed hidden behind percent encoding
539 {
540 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
541 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
542 'info_dict': {
543 'id': '06e53103ca9aa',
544 'ext': 'flv',
545 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
546 'description': 'No description',
547 },
0f2a2ba1 548 },
893f8832
PH
549 # arte embed
550 {
551 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
552 'md5': '7653032cbb25bf6c80d80f217055fa43',
553 'info_dict': {
554 'id': '048195-004_PLUS7-F',
555 'ext': 'flv',
556 'title': 'X:enius',
557 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
558 'upload_date': '20140320',
559 },
560 'params': {
561 'skip_download': 'Requires rtmpdump'
562 }
563 },
cbd55ade
S
564 # francetv embed
565 {
566 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
567 'info_dict': {
568 'id': 'EV_30231',
569 'ext': 'mp4',
570 'title': 'Alcaline, le concert avec Calogero',
571 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
572 'upload_date': '20150226',
573 'timestamp': 1424989860,
574 'duration': 5400,
575 },
576 'params': {
577 # m3u8 downloads
578 'skip_download': True,
579 },
580 'expected_warnings': [
581 'Forbidden'
582 ]
583 },
fa35cdad
PH
584 # Condé Nast embed
585 {
586 'url': 'http://www.wired.com/2014/04/honda-asimo/',
587 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
588 'info_dict': {
589 'id': '53501be369702d3275860000',
590 'ext': 'mp4',
591 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
592 }
ebd3c7b3
PH
593 },
594 # Dailymotion embed
595 {
596 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
597 'md5': '441aeeb82eb72c422c7f14ec533999cd',
598 'info_dict': {
599 'id': 'k2mm4bCdJ6CQ2i7c8o2',
600 'ext': 'mp4',
601 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 602 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 603 'uploader': 'Spi0n',
0738187f
YCH
604 'uploader_id': 'xgditw',
605 'upload_date': '20140425',
606 'timestamp': 1398441542,
ebd3c7b3
PH
607 },
608 'add_ie': ['Dailymotion'],
2b88feed
PH
609 },
610 # YouTube embed
611 {
612 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
613 'info_dict': {
614 'id': 'FXRb4ykk4S0',
615 'ext': 'mp4',
616 'title': 'The NBL Auction 2014',
617 'uploader': 'BADMINTON England',
618 'uploader_id': 'BADMINTONEvents',
619 'upload_date': '20140603',
620 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
621 },
622 'add_ie': ['Youtube'],
623 'params': {
624 'skip_download': True,
625 }
626 },
c5cd249e
JMF
627 # MTVSercices embed
628 {
629 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
630 'md5': '35727f82f58c76d996fc188f9755b0d5',
631 'info_dict': {
632 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
633 'ext': 'mp4',
634 'title': 'Review',
635 'description': 'Mario\'s life in the fast lane has never looked so good.',
636 },
637 },
61013473 638 # YouTube embed via <data-embed-url="">
639 {
640 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 641 'info_dict': {
a8eb5a8e 642 'id': '4vAffPZIT44',
61013473 643 'ext': 'mp4',
a8eb5a8e 644 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
645 'uploader': 'Gameloft',
646 'uploader_id': 'gameloft',
a8eb5a8e
PH
647 'upload_date': '20140828',
648 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
649 },
650 'params': {
651 'skip_download': True,
61013473 652 }
c8e9a235
PH
653 },
654 # Camtasia studio
655 {
656 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
657 'playlist': [{
658 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
659 'info_dict': {
660 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
661 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
662 'ext': 'flv',
663 'duration': 2235.90,
664 }
665 }, {
666 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
667 'info_dict': {
668 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
669 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
670 'ext': 'flv',
671 'duration': 2235.93,
672 }
673 }],
674 'info_dict': {
675 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
676 }
4d805e06
PH
677 },
678 # Flowplayer
679 {
680 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
681 'md5': '9d65602bf31c6e20014319c7d07fba27',
682 'info_dict': {
683 'id': '5123ea6d5e5a7',
684 'ext': 'mp4',
685 'age_limit': 18,
686 'uploader': 'www.handjobhub.com',
d6d9186f 687 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 688 }
0990305d 689 },
22a6f150
PH
690 # Multiple brightcove videos
691 # https://github.com/rg3/youtube-dl/issues/2283
692 {
693 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
694 'info_dict': {
695 'id': 'always-never',
696 'title': 'Always / Never - The New Yorker',
697 },
698 'playlist_count': 3,
699 'params': {
700 'extract_flat': False,
701 'skip_download': True,
702 }
1a94ff68
S
703 },
704 # MLB embed
705 {
706 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
707 'md5': '96f09a37e44da40dd083e12d9a683327',
708 'info_dict': {
709 'id': '33322633',
710 'ext': 'mp4',
711 'title': 'Ump changes call to ball',
712 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
713 'duration': 48,
714 'timestamp': 1401537900,
715 'upload_date': '20140531',
716 'thumbnail': 're:^https?://.*\.jpg$',
717 },
718 },
746c67d7
NJ
719 # Wistia embed
720 {
6c114b12
S
721 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
722 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 723 'info_dict': {
6c114b12 724 'id': '6e2wtrbdaf',
746c67d7 725 'ext': 'mov',
6c114b12
S
726 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
727 'description': 'a Paywall Videos video from Remilon',
728 'duration': 644.072,
729 'uploader': 'study.com',
730 'timestamp': 1459678540,
731 'upload_date': '20160403',
732 'filesize': 24687186,
746c67d7
NJ
733 },
734 },
52cffcb1 735 {
736 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
737 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
738 'info_dict': {
739 'id': 'uxjb0lwrcz',
740 'ext': 'mp4',
6c114b12 741 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 742 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 743 'duration': 1715.0,
85d7b765 744 'uploader': 'thoughtworks.wistia.com',
0738187f 745 'timestamp': 1401832161,
6c114b12 746 'upload_date': '20140603',
70b7e3fb 747 },
52cffcb1 748 },
7ded6545
S
749 # Wistia standard embed (async)
750 {
751 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
752 'info_dict': {
753 'id': '807fafadvk',
754 'ext': 'mp4',
755 'title': 'Drip Brennan Dunn Workshop',
756 'description': 'a JV Webinars video from getdrip-1',
757 'duration': 4986.95,
7ded6545 758 'timestamp': 1463607249,
6c114b12 759 'upload_date': '20160518',
7ded6545
S
760 },
761 'params': {
762 'skip_download': True,
763 }
764 },
ac645ac7
PH
765 # Soundcloud embed
766 {
767 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
768 'info_dict': {
769 'id': '174391317',
770 'ext': 'mp3',
771 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
772 'uploader': 'Sophos Security',
773 'title': 'Chet Chat 171 - Oct 29, 2014',
774 'upload_date': '20141029',
775 }
af63fed7
PH
776 },
777 # Livestream embed
778 {
779 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
780 'info_dict': {
781 'id': '67864563',
782 'ext': 'flv',
783 'upload_date': '20141112',
784 'title': 'Rosetta #CometLanding webcast HL 10',
785 }
786 },
65f3a228
PH
787 # LazyYT
788 {
789 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
790 'info_dict': {
11e611a7 791 'id': '1986',
65f3a228
PH
792 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
793 },
794 'playlist_mincount': 2,
4e262a88 795 },
42bdd9d0
PH
796 # Cinchcast embed
797 {
798 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
799 'info_dict': {
800 'id': '7141703',
801 'ext': 'mp3',
802 'upload_date': '20141126',
803 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
804 }
805 },
501f13fb
PH
806 # Cinerama player
807 {
808 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
809 'info_dict': {
810 'id': '730m_DandD_1901_512k',
811 'ext': 'mp4',
812 'uploader': 'www.abc.net.au',
813 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
814 }
796df3c6
S
815 },
816 # embedded viddler video
817 {
818 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
819 'info_dict': {
820 'id': '4d03aad9',
821 'ext': 'mp4',
822 'uploader': 'deadspin',
823 'title': 'WALL-TO-GORTAT',
824 'timestamp': 1422285291,
825 'upload_date': '20150126',
826 },
827 'add_ie': ['Viddler'],
a0f71985 828 },
2051acde
S
829 # Libsyn embed
830 {
831 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
832 'info_dict': {
833 'id': '3377616',
834 'ext': 'mp3',
835 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
836 'description': 'md5:601cb790edd05908957dae8aaa866465',
837 'upload_date': '20150220',
838 },
839 },
a0f71985
PH
840 # jwplayer YouTube
841 {
842 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
843 'info_dict': {
844 'id': 'Mrj4DVp2zeA',
845 'ext': 'mp4',
f37e3f99 846 'upload_date': '20150212',
a0f71985
PH
847 'uploader': 'The National Archives UK',
848 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
849 'uploader_id': 'NationalArchives08',
850 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
851 },
59b8ab58
PH
852 },
853 # rtl.nl embed
854 {
855 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
856 'playlist_mincount': 5,
857 'info_dict': {
858 'id': 'aanslagen-kopenhagen',
859 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
860 }
255fca5e
S
861 },
862 # Zapiks embed
863 {
864 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
865 'info_dict': {
866 'id': '118046',
867 'ext': 'mp4',
868 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
869 }
870 },
e3216b82
NJ
871 # Kaltura embed
872 {
873 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
874 'info_dict': {
875 'id': '1_eergr3h1',
876 'ext': 'mp4',
877 'upload_date': '20150226',
878 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
879 'timestamp': int,
880 'title': 'John Carlson Postgame 2/25/15',
881 },
882 },
66e568de
S
883 # Kaltura embed (different embed code)
884 {
885 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
886 'info_dict': {
887 'id': '1_a52wc67y',
888 'ext': 'flv',
889 'upload_date': '20150127',
890 'uploader_id': 'PremierMedia',
891 'timestamp': int,
892 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
893 },
894 },
6da620de
S
895 # Kaltura embed protected with referrer
896 {
897 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
898 'info_dict': {
899 'id': '1_g4fbemnq',
900 'ext': 'mp4',
901 'title': 'Violetta - Achter De Schermen - Ruggero',
902 'description': 'Achter de schermen met Ruggero',
903 'timestamp': 1435133761,
904 'upload_date': '20150624',
905 'uploader_id': 'echojecka',
906 },
907 },
135c9c42
S
908 # Eagle.Platform embed (generic URL)
909 {
910 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
4645432d 911 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
135c9c42
S
912 'info_dict': {
913 'id': '227304',
914 'ext': 'mp4',
915 'title': 'Навальный вышел на свободу',
916 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
917 'thumbnail': 're:^https?://.*\.jpg$',
918 'duration': 87,
919 'view_count': int,
920 'age_limit': 0,
921 },
922 },
d47ae7f6
S
923 # ClipYou (Eagle.Platform) embed (custom URL)
924 {
925 'url': 'http://muz-tv.ru/play/7129/',
4645432d 926 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
927 'info_dict': {
928 'id': '12820',
929 'ext': 'mp4',
930 'title': "'O Sole Mio",
931 'thumbnail': 're:^https?://.*\.jpg$',
932 'duration': 216,
933 'view_count': int,
934 },
935 },
f8388757
S
936 # Pladform embed
937 {
938 'url': 'http://muz-tv.ru/kinozal/view/7400/',
939 'info_dict': {
940 'id': '100183293',
941 'ext': 'mp4',
62259846 942 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757
S
943 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
944 'thumbnail': 're:^https?://.*\.jpg$',
945 'duration': 694,
946 'age_limit': 0,
947 },
948 },
c798f15b
S
949 # Playwire embed
950 {
951 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
952 'info_dict': {
953 'id': '3519514',
954 'ext': 'mp4',
955 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
956 'thumbnail': 're:^https?://.*\.png$',
957 'duration': 45.115,
958 },
959 },
ad320e9b
NJ
960 # 5min embed
961 {
962 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
963 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
964 'info_dict': {
965 'id': '518726732',
966 'ext': 'mp4',
967 'title': 'Facebook Creates "On This Day" | Crunch Report',
968 },
969 },
dc455a5f
S
970 # SVT embed
971 {
972 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
973 'info_dict': {
974 'id': '2900353',
975 'ext': 'flv',
976 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
977 'duration': 27,
978 'age_limit': 0,
979 },
980 },
a4257017
S
981 # Crooks and Liars embed
982 {
983 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
984 'info_dict': {
985 'id': '8RUoRhRi',
986 'ext': 'mp4',
987 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
988 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
989 'timestamp': 1428207000,
990 'upload_date': '20150405',
991 'uploader': 'Heather',
992 },
993 },
994 # Crooks and Liars external embed
995 {
996 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
997 'info_dict': {
998 'id': 'MTE3MjUtMzQ2MzA',
999 'ext': 'mp4',
1000 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1001 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1002 'timestamp': 1265032391,
1003 'upload_date': '20100201',
1004 'uploader': 'Heather',
1005 },
1006 },
facecb84 1007 # NBC Sports vplayer embed
a2edf2e7 1008 {
facecb84 1009 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1010 'info_dict': {
facecb84
S
1011 'id': 'ln7x1qSThw4k',
1012 'ext': 'flv',
1013 'title': "PFT Live: New leader in the 'new-look' defense",
1014 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1015 'uploader': 'NBCU-SPORTS',
1016 'upload_date': '20140107',
1017 'timestamp': 1389118457,
a2edf2e7 1018 },
418c5cc3
YCH
1019 },
1020 # UDN embed
1021 {
1022 'url': 'http://www.udn.com/news/story/7314/822787',
01c58f84 1023 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1024 'info_dict': {
01c58f84 1025 'id': '300346',
418c5cc3 1026 'ext': 'mp4',
01c58f84 1027 'title': '中一中男師變性 全校師生力挺',
418c5cc3
YCH
1028 'thumbnail': 're:^https?://.*\.jpg$',
1029 }
edfcf7ab
YCH
1030 },
1031 # Ooyala embed
1032 {
1033 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1034 'info_dict': {
1035 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1036 'ext': 'mp4',
cce9d15d 1037 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
edfcf7ab 1038 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1039 'duration': 191.933,
edfcf7ab
YCH
1040 },
1041 'params': {
1042 # m3u8 downloads
1043 'skip_download': True,
1044 }
d6fd958c
YCH
1045 },
1046 # Contains a SMIL manifest
1047 {
1048 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
1049 'info_dict': {
1050 'id': 'file',
1051 'ext': 'flv',
1052 'title': '+ Football: Lottery Champions League Europe',
1053 'uploader': 'www.telewebion.com',
1054 },
1055 'params': {
1056 # rtmpe downloads
1057 'skip_download': True,
1058 }
b26733ba
YCH
1059 },
1060 # Brightcove URL in single quotes
1061 {
1062 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1063 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1064 'info_dict': {
1065 'id': '4255764656001',
1066 'ext': 'mp4',
1067 'title': 'SN Presents: Russell Martin, World Citizen',
1068 '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.',
1069 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1070 'uploader_id': '1704050871',
1071 'upload_date': '20150525',
1072 'timestamp': 1432570283,
b26733ba 1073 },
756f574e
YCH
1074 },
1075 # Dailymotion Cloud video
1076 {
1077 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1078 'md5': '49444254273501a64675a7e68c502681',
1079 'info_dict': {
1080 'id': '5585de919473990de4bee11b',
1081 'ext': 'mp4',
1082 'title': 'Le débat',
1083 'thumbnail': 're:^https?://.*\.jpe?g$',
1084 }
a5158f38 1085 },
8084be78
S
1086 # OnionStudios embed
1087 {
1088 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1089 'info_dict': {
1090 'id': '2855',
1091 'ext': 'mp4',
1092 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1093 'thumbnail': 're:^https?://.*\.jpe?g$',
1094 'uploader': 'ClickHole',
1095 'uploader_id': 'clickhole',
1096 }
1097 },
b8c1cc1a
S
1098 # SnagFilms embed
1099 {
1100 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1101 'info_dict': {
1102 'id': '74849a00-85a9-11e1-9660-123139220831',
1103 'ext': 'mp4',
1104 'title': '#whilewewatch',
1105 }
1106 },
a5158f38
YCH
1107 # AdobeTVVideo embed
1108 {
1109 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1110 'md5': '43662b577c018ad707a63766462b1e87',
1111 'info_dict': {
1112 'id': '2456',
1113 'ext': 'mp4',
1114 'title': 'New experience with Acrobat DC',
1115 'description': 'New experience with Acrobat DC',
1116 'duration': 248.667,
1117 },
1f812580
S
1118 },
1119 # ScreenwaveMedia embed
1120 {
1121 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1122 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1123 'info_dict': {
1124 'id': 'cinemasnob-55d26273809dd',
1125 'ext': 'mp4',
1126 'title': 'cinemasnob',
1127 },
ed126900 1128 },
1129 # BrightcoveInPageEmbed embed
1130 {
1131 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1132 'info_dict': {
1133 'id': '4238694884001',
1134 'ext': 'flv',
1135 'title': 'Tabletop: Dread, Last Thoughts',
1136 'description': 'Tabletop: Dread, Last Thoughts',
1137 'duration': 51690,
1138 },
750b9ff0
YCH
1139 },
1140 # JWPlayer with M3U8
1141 {
1142 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1143 'info_dict': {
1144 'id': 'playlist',
1145 'ext': 'mp4',
1146 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1147 'uploader': 'ren.tv',
1148 },
1149 'params': {
1150 # m3u8 downloads
1151 'skip_download': True,
1152 }
d10fe835
YCH
1153 },
1154 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1155 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1156 {
1157 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1158 'info_dict': {
1159 'id': '4785848093001',
1160 'ext': 'mp4',
1161 'title': 'The Cardinal Pell Interview',
1162 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1163 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1164 'uploader_id': '2733773828001',
1165 'upload_date': '20160304',
1166 'timestamp': 1457083087,
d10fe835
YCH
1167 },
1168 'params': {
1169 # m3u8 downloads
1170 'skip_download': True,
1171 },
1172 },
134c207e
YCH
1173 # Another form of arte.tv embed
1174 {
1175 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1176 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1177 'info_dict': {
1178 'id': '030273-562_PLUS7-F',
1179 'ext': 'mp4',
1180 'title': 'ARTE Reportage - Nulle part, en France',
1181 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1182 'upload_date': '20160409',
1183 },
1184 },
b8f67449
KM
1185 # LiveLeak embed
1186 {
1187 'url': 'http://www.wykop.pl/link/3088787/',
1188 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1189 'info_dict': {
1190 'id': '874_1459135191',
1191 'ext': 'mp4',
1192 'title': 'Man shows poor quality of new apartment building',
1193 'description': 'The wall is like a sand pile.',
1194 'uploader': 'Lake8737',
1195 }
1196 },
4a120778
YCH
1197 # Duplicated embedded video URLs
1198 {
1199 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1200 'info_dict': {
1201 'id': '149298443_480_16c25b74_2',
1202 'ext': 'mp4',
1203 'title': 'vs. Blue Orange Spring Game',
1204 'uploader': 'www.hudl.com',
1205 },
1206 },
cfe50f04 1207 ]
9b122384 1208
9b122384
PH
1209 def report_following_redirect(self, new_url):
1210 """Report information extraction."""
79649588 1211 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1212
4fc946b5
PH
1213 def _extract_rss(self, url, video_id, doc):
1214 playlist_title = doc.find('./channel/title').text
1215 playlist_desc_el = doc.find('./channel/description')
1216 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1217
76c73715
PH
1218 entries = []
1219 for it in doc.findall('./channel/item'):
1220 next_url = xpath_text(it, 'link', fatal=False)
1221 if not next_url:
1222 enclosure_nodes = it.findall('./enclosure')
1223 for e in enclosure_nodes:
1224 next_url = e.attrib.get('url')
1225 if next_url:
1226 break
1227
1228 if not next_url:
1229 continue
1230
1231 entries.append({
1232 '_type': 'url',
1233 'url': next_url,
1234 'title': it.find('title').text,
1235 })
4fc946b5
PH
1236
1237 return {
1238 '_type': 'playlist',
1239 'id': url,
1240 'title': playlist_title,
1241 'description': playlist_desc,
1242 'entries': entries,
1243 }
1244
c8e9a235
PH
1245 def _extract_camtasia(self, url, video_id, webpage):
1246 """ Returns None if no camtasia video can be found. """
1247
1248 camtasia_cfg = self._search_regex(
1249 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1250 webpage, 'camtasia configuration file', default=None)
1251 if camtasia_cfg is None:
1252 return None
1253
1254 title = self._html_search_meta('DC.title', webpage, fatal=True)
1255
1256 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1257 camtasia_cfg = self._download_xml(
1258 camtasia_url, video_id,
1259 note='Downloading camtasia configuration',
1260 errnote='Failed to download camtasia configuration')
1261 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1262
1263 entries = []
1264 for n in fileset_node.getchildren():
1265 url_n = n.find('./uri')
1266 if url_n is None:
1267 continue
1268
1269 entries.append({
1270 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1271 'title': '%s - %s' % (title, n.tag),
1272 'url': compat_urlparse.urljoin(url, url_n.text),
1273 'duration': float_or_none(n.find('./duration').text),
1274 })
1275
1276 return {
1277 '_type': 'playlist',
1278 'entries': entries,
1279 'title': title,
1280 }
1281
9b122384 1282 def _real_extract(self, url):
ebd3c7b3
PH
1283 if url.startswith('//'):
1284 return {
1285 '_type': 'url',
20991253 1286 'url': self.http_scheme() + url,
ebd3c7b3
PH
1287 }
1288
a7130543
JMF
1289 parsed_url = compat_urlparse.urlparse(url)
1290 if not parsed_url.scheme:
04b4d394
PH
1291 default_search = self._downloader.params.get('default_search')
1292 if default_search is None:
1f7ccb90 1293 default_search = 'fixup_error'
04b4d394 1294
1f7ccb90 1295 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
1296 if '/' in url:
1297 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1298 return self.url_result('http://' + url)
1f7ccb90 1299 elif default_search != 'fixup_error':
9c1fc022 1300 if default_search == 'auto_warning':
0e67ab0d
PH
1301 if re.match(r'^(?:url|URL)$', url):
1302 raise ExtractorError(
1303 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1304 expected=True)
1305 else:
1306 self._downloader.report_warning(
7571c02c 1307 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 1308 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
1309
1310 if default_search in ('error', 'fixup_error'):
7571c02c 1311 raise ExtractorError(
b74e86f4
PH
1312 '%r is not a valid URL. '
1313 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1314 % (url, url), expected=True)
04b4d394 1315 else:
f2f2c0c2
PH
1316 if ':' not in default_search:
1317 default_search += ':'
04b4d394 1318 return self.url_result(default_search + url)
4d54ef20
PH
1319
1320 url, smuggled_data = unsmuggle_url(url)
1321 force_videoid = None
d6e6a422 1322 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
1323 if smuggled_data and 'force_videoid' in smuggled_data:
1324 force_videoid = smuggled_data['force_videoid']
1325 video_id = force_videoid
1326 else:
1ddb9456 1327 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
a7130543 1328
79649588 1329 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 1330
ebab4520 1331 head_req = HEADRequest(url)
23be51d8 1332 head_response = self._request_webpage(
ebab4520
PH
1333 head_req, video_id,
1334 note=False, errnote='Could not send HEAD request to %s' % url,
1335 fatal=False)
42393ce2 1336
23be51d8 1337 if head_response is not False:
42393ce2 1338 # Check for redirect
23be51d8 1339 new_url = head_response.geturl()
42393ce2
PH
1340 if url != new_url:
1341 self.report_following_redirect(new_url)
4d54ef20
PH
1342 if force_videoid:
1343 new_url = smuggle_url(
1344 new_url, {'force_videoid': force_videoid})
cecaaf3f 1345 return self.url_result(new_url)
42393ce2 1346
23be51d8
PH
1347 full_response = None
1348 if head_response is False:
5c2266df 1349 request = sanitized_Request(url)
58bde34a
S
1350 request.add_header('Accept-Encoding', '*')
1351 full_response = self._request_webpage(request, video_id)
23be51d8
PH
1352 head_response = full_response
1353
f930e0c7
S
1354 info_dict = {
1355 'id': video_id,
1356 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
303dcdb9 1357 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
1358 }
1359
23be51d8 1360 # Check for direct link to a video
955737b2 1361 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 1362 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 1363 if m:
f930e0c7
S
1364 format_id = m.group('format_id')
1365 if format_id.endswith('mpegurl'):
eadc3ccd 1366 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
1367 elif format_id == 'f4m':
1368 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 1369 else:
1370 formats = [{
1371 'format_id': m.group('format_id'),
1372 'url': url,
1373 'vcodec': 'none' if m.group('type') == 'audio' else None
1374 }]
de6c51e8 1375 info_dict['direct'] = True
19dbaeec 1376 self._sort_formats(formats)
de6c51e8 1377 info_dict['formats'] = formats
f930e0c7 1378 return info_dict
42393ce2 1379
d6e6a422 1380 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
1381 force = self._downloader.params.get('force_generic_extractor', False)
1382 self._downloader.report_warning(
1383 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 1384
4e262a88 1385 if not full_response:
5c2266df 1386 request = sanitized_Request(url)
58bde34a
S
1387 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1388 # making it impossible to download only chunk of the file (yet we need only 512kB to
1389 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1390 # that will always result in downloading the whole file that is not desirable.
1391 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1392 # to accept raw bytes and being able to download only a chunk.
1393 # It may probably better to solve this by checking Content-Type for application/octet-stream
1394 # after HEAD request finishes, but not sure if we can rely on this.
1395 request.add_header('Accept-Encoding', '*')
1396 full_response = self._request_webpage(request, video_id)
4e262a88 1397
5940862d
S
1398 first_bytes = full_response.read(512)
1399
1400 # Is it an M3U playlist?
0d769bcb 1401 if first_bytes.startswith(b'#EXTM3U'):
5940862d 1402 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 1403 self._sort_formats(info_dict['formats'])
5940862d
S
1404 return info_dict
1405
4e262a88
PH
1406 # Maybe it's a direct link to a video?
1407 # Be careful not to download the whole thing!
61ca9a80 1408 if not is_html(first_bytes):
4e262a88
PH
1409 self._downloader.report_warning(
1410 'URL could be a direct video link, returning it as such.')
f930e0c7 1411 info_dict.update({
4e262a88
PH
1412 'direct': True,
1413 'url': url,
f930e0c7
S
1414 })
1415 return info_dict
4e262a88
PH
1416
1417 webpage = self._webpage_read_content(
1418 full_response, url, video_id, prefix=first_bytes)
1419
9b122384 1420 self.report_extraction(video_id)
887c6acd 1421
1b840245 1422 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 1423 try:
f7854627 1424 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
1425 if doc.tag == 'rss':
1426 return self._extract_rss(url, video_id, doc)
e5e8d20a 1427 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
1428 smil = self._parse_smil(doc, url, video_id)
1429 self._sort_formats(smil['formats'])
1430 return smil
729accb4
S
1431 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1432 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245 1433 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7
S
1434 info_dict['formats'] = self._parse_mpd_formats(
1435 doc, video_id, mpd_base_url=url.rpartition('/')[0])
19dbaeec 1436 self._sort_formats(info_dict['formats'])
f930e0c7
S
1437 return info_dict
1438 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1439 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 1440 self._sort_formats(info_dict['formats'])
f930e0c7 1441 return info_dict
f7300c5c 1442 except compat_xml_parse_error:
4fc946b5
PH
1443 pass
1444
c8e9a235
PH
1445 # Is it a Camtasia project?
1446 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1447 if camtasia_res is not None:
1448 return camtasia_res
1449
14390730
S
1450 # Sometimes embedded video player is hidden behind percent encoding
1451 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1452 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 1453 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 1454
887c6acd
PH
1455 # it's tempting to parse this further, but you would
1456 # have to take into account all the variations like
1457 # Video Title - Site Name
1458 # Site Name | Video Title
1459 # Video Title - Tagline | Site Name
1460 # and so on and so forth; it's just not practical
6f41b2bc
S
1461 video_title = self._og_search_title(
1462 webpage, default=None) or self._html_search_regex(
79649588
PH
1463 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1464 default='video')
ef4fd848 1465
4d805e06
PH
1466 # Try to detect age limit automatically
1467 age_limit = self._rta_search(webpage)
1468 # And then there are the jokers who advertise that they use RTA,
1469 # but actually don't.
1470 AGE_LIMIT_MARKERS = [
1471 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1472 ]
1473 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1474 age_limit = 18
1475
ef4fd848
PH
1476 # video uploader is domain name
1477 video_uploader = self._search_regex(
79649588 1478 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 1479
6f41b2bc
S
1480 video_description = self._og_search_description(webpage, default=None)
1481 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1482
ed2d6a19 1483 # Helper method
83992676 1484 def _playlist_from_matches(matches, getter=None, ie=None):
3b2f933b 1485 urlrs = orderedSet(
83992676 1486 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
3b2f933b 1487 for m in matches)
ed2d6a19
PH
1488 return self.playlist_result(
1489 urlrs, playlist_id=video_id, playlist_title=video_title)
1490
1f4b722b 1491 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 1492 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 1493 if bc_urls:
79649588 1494 self.to_screen('Brightcove video detected.')
99877772
PH
1495 entries = [{
1496 '_type': 'url',
1497 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 1498 'ie_key': 'BrightcoveLegacy'
99877772
PH
1499 } for bc_url in bc_urls]
1500
1501 return {
1502 '_type': 'playlist',
1503 'title': video_title,
1504 'id': video_id,
1505 'entries': entries,
1506 }
cfe50f04 1507
f6519f89
S
1508 # Look for Brightcove New Studio embeds
1509 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1510 if bc_urls:
1511 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
ed126900 1512
4d8819d2
S
1513 # Look for ThePlatform embeds
1514 tp_urls = ThePlatformIE._extract_urls(webpage)
1515 if tp_urls:
1516 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1517
59b8ab58
PH
1518 # Look for embedded rtl.nl player
1519 matches = re.findall(
97b570a9 1520 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
59b8ab58
PH
1521 webpage)
1522 if matches:
1523 return _playlist_from_matches(matches, ie='RtlNl')
1524
b407e173
YCH
1525 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1526 if vimeo_url is not None:
1527 return self.url_result(vimeo_url)
7115ca84 1528
a1b85269
YCH
1529 vid_me_embed_url = self._search_regex(
1530 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1531 webpage, 'vid.me embed', default=None)
1532 if vid_me_embed_url is not None:
1533 return self.url_result(vid_me_embed_url, 'Vidme')
1534
53c1d3ef 1535 # Look for embedded YouTube player
1f9da904 1536 matches = re.findall(r'''(?x)
2b88feed
PH
1537 (?:
1538 <iframe[^>]+?src=|
c71dfccc 1539 data-video-url=|
2b88feed 1540 <embed[^>]+?src=|
a7e97f6d
PH
1541 embedSWF\(?:\s*|
1542 new\s+SWFObject\(
2b88feed
PH
1543 )
1544 (["\'])
1bf5423e 1545 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
6b08cdf6 1546 (?:embed|v|p)/.+?)
1f9da904 1547 \1''', webpage)
887c6acd 1548 if matches:
ed2d6a19 1549 return _playlist_from_matches(
3b2f933b 1550 matches, lambda m: unescapeHTML(m[1]))
53c1d3ef 1551
65f3a228
PH
1552 # Look for lazyYT YouTube embed
1553 matches = re.findall(
1554 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1555 if matches:
1556 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1557
355e4fd0
PH
1558 # Look for embedded Dailymotion player
1559 matches = re.findall(
5a490592 1560 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
355e4fd0 1561 if matches:
ed2d6a19
PH
1562 return _playlist_from_matches(
1563 matches, lambda m: unescapeHTML(m[1]))
355e4fd0 1564
8489578d
NJ
1565 # Look for embedded Dailymotion playlist player (#3822)
1566 m = re.search(
1567 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1568 if m:
1569 playlists = re.findall(
1570 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1571 if playlists:
1572 return _playlist_from_matches(
1573 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1574
ef4fd848
PH
1575 # Look for embedded Wistia player
1576 match = re.search(
281d3f1d 1577 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
ef4fd848 1578 if match:
9471c444
NJ
1579 embed_url = self._proto_relative_url(
1580 unescapeHTML(match.group('url')))
ef4fd848
PH
1581 return {
1582 '_type': 'url_transparent',
9471c444 1583 'url': embed_url,
ef4fd848
PH
1584 'ie_key': 'Wistia',
1585 'uploader': video_uploader,
ef4fd848 1586 }
5f6a1245 1587
9471c444 1588 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
746c67d7
NJ
1589 if match:
1590 return {
1591 '_type': 'url_transparent',
6c114b12 1592 'url': 'wistia:%s' % match.group('id'),
746c67d7
NJ
1593 'ie_key': 'Wistia',
1594 'uploader': video_uploader,
746c67d7 1595 }
ef4fd848 1596
aa5957ac
S
1597 match = re.search(
1598 r'''(?sx)
1599 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1600 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1601 ''', webpage)
1602 if match:
1603 return self.url_result(self._proto_relative_url(
1604 'wistia:%s' % match.group('id')), 'Wistia')
1605
bab19a8e
S
1606 # Look for SVT player
1607 svt_url = SVTIE._extract_url(webpage)
1608 if svt_url:
1609 return self.url_result(svt_url, 'SVT')
1610
fa35cdad
PH
1611 # Look for embedded condenast player
1612 matches = re.findall(
1613 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1614 webpage)
1615 if matches:
1616 return {
1617 '_type': 'playlist',
1618 'entries': [{
1619 '_type': 'url',
1620 'ie_key': 'CondeNast',
1621 'url': ma,
1622 } for ma in matches],
1623 'title': video_title,
1624 'id': video_id,
1625 }
1626
c19f7764
JMF
1627 # Look for Bandcamp pages with custom domain
1628 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1629 if mobj is not None:
1630 burl = unescapeHTML(mobj.group(1))
09804265
JMF
1631 # Don't set the extractor because it can be a track url or an album
1632 return self.url_result(burl)
c19f7764 1633
f25571ff
PH
1634 # Look for embedded Vevo player
1635 mobj = re.search(
1636 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1637 if mobj is not None:
1638 return self.url_result(mobj.group('url'))
796df3c6
S
1639
1640 # Look for embedded Viddler player
cb454b33
S
1641 mobj = re.search(
1642 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1643 webpage)
796df3c6
S
1644 if mobj is not None:
1645 return self.url_result(mobj.group('url'))
f25571ff 1646
3378d67a
S
1647 # Look for NYTimes player
1648 mobj = re.search(
1649 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1650 webpage)
1651 if mobj is not None:
1652 return self.url_result(mobj.group('url'))
1653
cefdf970
S
1654 # Look for Libsyn player
1655 mobj = re.search(
1656 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1657 if mobj is not None:
1658 return self.url_result(mobj.group('url'))
1659
c0d0b01f 1660 # Look for Ooyala videos
8a37aa15 1661 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 1662 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
1663 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1664 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 1665 if mobj is not None:
cce9d15d 1666 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
c0d0b01f 1667
f076b638 1668 # Look for multiple Ooyala embeds on SBN network websites
1669 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1670 if mobj is not None:
1671 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1672 if embeds:
1673 return _playlist_from_matches(
cce9d15d 1674 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 1675
aa94a6d3 1676 # Look for Aparat videos
48099643 1677 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
1678 if mobj is not None:
1679 return self.url_result(mobj.group(1), 'Aparat')
1680
c93c2ab1 1681 # Look for MPORA videos
c3f51436 1682 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
1683 if mobj is not None:
1684 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 1685
15c0e8e7 1686 # Look for embedded NovaMov-based player
8f89e687 1687 mobj = re.search(
8dfa187b 1688 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
1689 (?P<url>http://(?:(?:embed|www)\.)?
1690 (?:novamov\.com|
1691 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1692 videoweed\.(?:es|com)|
1693 movshare\.(?:net|sx|ag)|
1694 divxstage\.(?:eu|net|ch|co|at|ag))
1695 /embed\.php.+?)\1''', webpage)
8f89e687 1696 if mobj is not None:
15c0e8e7 1697 return self.url_result(mobj.group('url'))
50f56607 1698
9834872b
PH
1699 # Look for embedded Facebook player
1700 mobj = re.search(
db1f3888 1701 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
9834872b
PH
1702 if mobj is not None:
1703 return self.url_result(mobj.group('url'), 'Facebook')
1704
ca97a56e
S
1705 # Look for embedded VK player
1706 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1707 if mobj is not None:
1708 return self.url_result(mobj.group('url'), 'VK')
1709
33d4fdab
S
1710 # Look for embedded Odnoklassniki player
1711 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1712 if mobj is not None:
1713 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1714
0364fa8b
S
1715 # Look for embedded ivi player
1716 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1717 if mobj is not None:
1718 return self.url_result(mobj.group('url'), 'Ivi')
1719
db1f3888
PH
1720 # Look for embedded Huffington Post player
1721 mobj = re.search(
c3f51436 1722 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
1723 if mobj is not None:
1724 return self.url_result(mobj.group('url'), 'HuffPost')
1725
1b86cc41 1726 # Look for embed.ly
1727 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1728 if mobj is not None:
1729 return self.url_result(mobj.group('url'))
1730 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1731 if mobj is not None:
f7e6f7fa 1732 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 1733
60cc4dc4
PH
1734 # Look for funnyordie embed
1735 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1736 if matches:
ed2d6a19
PH
1737 return _playlist_from_matches(
1738 matches, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 1739
db546cf8
S
1740 # Look for BBC iPlayer embed
1741 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1742 if matches:
476eae0c 1743 return _playlist_from_matches(matches, ie='BBCCoUk')
db546cf8 1744
93d020dd
S
1745 # Look for embedded RUTV player
1746 rutv_url = RUTVIE._extract_url(webpage)
1747 if rutv_url:
1748 return self.url_result(rutv_url, 'RUTV')
1749
494f20cb 1750 # Look for embedded TVC player
b8599718
S
1751 tvc_url = TVCIE._extract_url(webpage)
1752 if tvc_url:
1753 return self.url_result(tvc_url, 'TVC')
494f20cb 1754
d40a3b5b
S
1755 # Look for embedded SportBox player
1756 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1757 if sportbox_urls:
1758 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1759
78e2b74b 1760 # Look for embedded PornHub player
65d161c4
S
1761 pornhub_url = PornHubIE._extract_url(webpage)
1762 if pornhub_url:
1763 return self.url_result(pornhub_url, 'PornHub')
1764
2bb5b6d0
S
1765 # Look for embedded XHamster player
1766 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1767 if xhamster_urls:
1768 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1769
2c9ca782
S
1770 # Look for embedded TNAFlixNetwork player
1771 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1772 if tnaflix_urls:
1773 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1774
9872d311
S
1775 # Look for embedded Tvigle player
1776 mobj = re.search(
1777 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1778 if mobj is not None:
1779 return self.url_result(mobj.group('url'), 'Tvigle')
1780
7e2ede98
JMF
1781 # Look for embedded TED player
1782 mobj = re.search(
d7cc31b6 1783 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
1784 if mobj is not None:
1785 return self.url_result(mobj.group('url'), 'TED')
1786
5c386252 1787 # Look for embedded Ustream videos
1788 mobj = re.search(
1789 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1790 if mobj is not None:
1791 return self.url_result(mobj.group('url'), 'Ustream')
1792
893f8832
PH
1793 # Look for embedded arte.tv player
1794 mobj = re.search(
134c207e 1795 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
1796 webpage)
1797 if mobj is not None:
1798 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1799
cbd55ade
S
1800 # Look for embedded francetv player
1801 mobj = re.search(
1802 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1803 webpage)
1804 if mobj is not None:
1805 return self.url_result(mobj.group('url'))
1806
cb3ac1c6
S
1807 # Look for embedded smotri.com player
1808 smotri_url = SmotriIE._extract_url(webpage)
1809 if smotri_url:
1810 return self.url_result(smotri_url, 'Smotri')
1811
e6c2d9ad 1812 # Look for embedded Myvi.ru player
6dd94d3a 1813 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
1814 if myvi_url:
1815 return self.url_result(myvi_url)
1816
dfb1b146 1817 # Look for embedded soundcloud player
20991253 1818 mobj = re.search(
ac645ac7 1819 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
20991253
PH
1820 webpage)
1821 if mobj is not None:
1822 url = unescapeHTML(mobj.group('url'))
1823 return self.url_result(url)
1824
826ec77f
PH
1825 # Look for embedded vulture.com player
1826 mobj = re.search(
1827 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1828 webpage)
1829 if mobj is not None:
1830 url = unescapeHTML(mobj.group('url'))
1831 return self.url_result(url, ie='Vulture')
1832
c5cd249e 1833 # Look for embedded mtvservices player
46fde8a1
S
1834 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1835 if mtvservices_url:
1836 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 1837
49807b4a
S
1838 # Look for embedded yahoo player
1839 mobj = re.search(
1840 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1841 webpage)
1842 if mobj is not None:
1843 return self.url_result(mobj.group('url'), 'Yahoo')
1844
2ef6fcb5
PH
1845 # Look for embedded sbs.com.au player
1846 mobj = re.search(
e98b8e79
PH
1847 r'''(?x)
1848 (?:
1849 <meta\s+property="og:video"\s+content=|
1850 <iframe[^>]+?src=
1851 )
1852 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
1853 webpage)
1854 if mobj is not None:
1855 return self.url_result(mobj.group('url'), 'SBS')
1856
42bdd9d0
PH
1857 # Look for embedded Cinchcast player
1858 mobj = re.search(
1859 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1860 webpage)
1861 if mobj is not None:
1862 return self.url_result(mobj.group('url'), 'Cinchcast')
1863
1a94ff68 1864 mobj = re.search(
5263cdfc 1865 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 1866 webpage)
8001607e
YCH
1867 if not mobj:
1868 mobj = re.search(
1869 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1870 webpage)
1a94ff68
S
1871 if mobj is not None:
1872 return self.url_result(mobj.group('url'), 'MLB')
1873
1419fafd 1874 mobj = re.search(
dd467d33 1875 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
1876 webpage)
1877 if mobj is not None:
1878 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1879
af63fed7
PH
1880 mobj = re.search(
1881 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1882 webpage)
1883 if mobj is not None:
1884 return self.url_result(mobj.group('url'), 'Livestream')
1885
255fca5e
S
1886 # Look for Zapiks embed
1887 mobj = re.search(
1888 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1889 if mobj is not None:
1890 return self.url_result(mobj.group('url'), 'Zapiks')
1891
e3216b82 1892 # Look for Kaltura embeds
6a5d6de1 1893 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1c31a5b0 1894 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
e3216b82 1895 if mobj is not None:
5b5fae5f
S
1896 return self.url_result(smuggle_url(
1897 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1898 {'source_url': url}), 'Kaltura')
e3216b82 1899
135c9c42
S
1900 # Look for Eagle.Platform embeds
1901 mobj = re.search(
1902 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1903 if mobj is not None:
1904 return self.url_result(mobj.group('url'), 'EaglePlatform')
1905
d47ae7f6
S
1906 # Look for ClipYou (uses Eagle.Platform) embeds
1907 mobj = re.search(
1908 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1909 if mobj is not None:
1910 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1911
f8388757 1912 # Look for Pladform embeds
45dad7ba
S
1913 pladform_url = PladformIE._extract_url(webpage)
1914 if pladform_url:
1915 return self.url_result(pladform_url)
f8388757 1916
ff18735c
S
1917 # Look for Videomore embeds
1918 videomore_url = VideomoreIE._extract_url(webpage)
1919 if videomore_url:
1920 return self.url_result(videomore_url)
1921
2dcc114f
S
1922 # Look for Playwire embeds
1923 mobj = re.search(
1924 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1925 if mobj is not None:
1926 return self.url_result(mobj.group('url'))
1927
ad320e9b
NJ
1928 # Look for 5min embeds
1929 mobj = re.search(
1930 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1931 if mobj is not None:
1932 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1933
18153f1b
S
1934 # Look for Crooks and Liars embeds
1935 mobj = re.search(
1936 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1937 if mobj is not None:
1938 return self.url_result(mobj.group('url'))
1939
a2edf2e7
YCH
1940 # Look for NBC Sports VPlayer embeds
1941 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1942 if nbc_sports_url:
1943 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1944
653789af 1945 # Look for Google Drive embeds
5b251628 1946 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 1947 if google_drive_url:
1948 return self.url_result(google_drive_url, 'GoogleDrive')
1949
418c5cc3
YCH
1950 # Look for UDN embeds
1951 mobj = re.search(
c39fd7b1 1952 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
1953 if mobj is not None:
1954 return self.url_result(
0a160363 1955 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 1956
2fe1b5bd
YCH
1957 # Look for Senate ISVP iframe
1958 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1959 if senate_isvp_url:
25c3a734 1960 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 1961
756f574e
YCH
1962 # Look for Dailymotion Cloud videos
1963 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1964 if dmcloud_url:
1965 return self.url_result(dmcloud_url, 'DailymotionCloud')
1966
1ac1c4c2
S
1967 # Look for OnionStudios embeds
1968 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1969 if onionstudios_url:
1970 return self.url_result(onionstudios_url)
1971
67167920 1972 # Look for ViewLift embeds
1973 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1974 if viewlift_url:
1975 return self.url_result(viewlift_url)
eedd20ef 1976
7cb09524 1977 # Look for JWPlatform embeds
1978 jwplatform_url = JWPlatformIE._extract_url(webpage)
1979 if jwplatform_url:
1980 return self.url_result(jwplatform_url, 'JWPlatform')
1981
8ca31a0e 1982 # Look for ScreenwaveMedia embeds
efd712c6 1983 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
8ca31a0e 1984 if mobj is not None:
efd712c6 1985 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
8ca31a0e 1986
aecfcd4e
S
1987 # Look for Digiteka embeds
1988 digiteka_url = DigitekaIE._extract_url(webpage)
1989 if digiteka_url:
1990 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 1991
1bf996fa 1992 # Look for Limelight embeds
1993 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1994 if mobj:
1995 lm = {
1996 'Media': 'media',
1997 'Channel': 'channel',
1998 'ChannelList': 'channel_list',
1999 }
2000 return self.url_result('limelight:%s:%s' % (
2001 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2002
a5158f38
YCH
2003 # Look for AdobeTVVideo embeds
2004 mobj = re.search(
2005 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2006 webpage)
2007 if mobj is not None:
2008 return self.url_result(
2009 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2010 'AdobeTVVideo')
2011
088e1aac
YCH
2012 # Look for Vine embeds
2013 mobj = re.search(
2014 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2015 webpage)
2016 if mobj is not None:
2017 return self.url_result(
2018 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2019
5a51775a
YCH
2020 # Look for Instagram embeds
2021 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2022 if instagram_embed_url is not None:
11e60fca
S
2023 return self.url_result(
2024 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2025
b8f67449
KM
2026 # Look for LiveLeak embeds
2027 liveleak_url = LiveLeakIE._extract_url(webpage)
2028 if liveleak_url:
2029 return self.url_result(liveleak_url, 'LiveLeak')
2030
5d39176f
S
2031 # Look for 3Q SDN embeds
2032 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2033 if threeqsdn_url:
6f41b2bc
S
2034 return {
2035 '_type': 'url_transparent',
2036 'ie_key': ThreeQSDNIE.ie_key(),
2037 'url': self._proto_relative_url(threeqsdn_url),
2038 'title': video_title,
2039 'description': video_description,
2040 'thumbnail': video_thumbnail,
2041 'uploader': video_uploader,
2042 }
5d39176f 2043
ced659bb 2044 def check_video(vurl):
a0f71985
PH
2045 if YoutubeIE.suitable(vurl):
2046 return True
ced659bb
S
2047 vpath = compat_urlparse.urlparse(vurl).path
2048 vext = determine_ext(vpath)
2049 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2050
2051 def filter_video(urls):
2052 return list(filter(check_video, urls))
2053
9b122384 2054 # Start with something easy: JW Player in SWFObject
ced659bb 2055 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 2056 if not found:
d981cef6 2057 # Look for gorilla-vid style embedding
ced659bb 2058 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
2059 (?:
2060 jw_plugins|
2061 JWPlayerOptions|
2062 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2063 )
a0f71985
PH
2064 .*?
2065 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 2066 if not found:
9b122384 2067 # Broaden the search a little bit
ced659bb 2068 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
2069 if not found:
2070 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 2071 found = filter_video(re.findall(
54a9328b 2072 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
2073 if not found:
2074 # Flow player
ced659bb 2075 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
2076 flowplayer\("[^"]+",\s*
2077 \{[^}]+?\}\s*,
52585fd6 2078 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 2079 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 2080 ''', webpage))
501f13fb
PH
2081 if not found:
2082 # Cinerama player
2083 found = re.findall(
2084 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 2085 if not found:
9b122384 2086 # Try to find twitter cards info
ced659bb
S
2087 found = filter_video(re.findall(
2088 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 2089 if not found:
9b122384
PH
2090 # We look for Open Graph info:
2091 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 2092 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
2093 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2094 if m_video_type is not None:
ced659bb 2095 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 2096 if not found:
7fea7156 2097 # HTML5 video
12439dd5 2098 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
b30b8698 2099 if not found:
ed9a25dd 2100 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 2101 found = re.search(
89ef304b 2102 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 2103 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 2104 webpage)
84f81016
S
2105 if not found:
2106 # Look also in Refresh HTTP header
2107 refresh_header = head_response.headers.get('Refresh')
2108 if refresh_header:
6c91a5a7
S
2109 # In python 2 response HTTP headers are bytestrings
2110 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2111 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 2112 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 2113 if found:
b37317d8 2114 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
89ef304b
PH
2115 self.report_following_redirect(new_url)
2116 return {
2117 '_type': 'url',
2118 'url': new_url,
2119 }
b30b8698 2120 if not found:
416c7fcb 2121 raise UnsupportedError(url)
9b122384 2122
b30b8698 2123 entries = []
4a120778 2124 for video_url in orderedSet(found):
949b6497 2125 video_url = unescapeHTML(video_url)
6cc37c69 2126 video_url = video_url.replace('\\/', '/')
b30b8698 2127 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 2128 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 2129
b30b8698
PH
2130 # Sometimes, jwplayer extraction will result in a YouTube URL
2131 if YoutubeIE.suitable(video_url):
2132 entries.append(self.url_result(video_url, 'Youtube'))
2133 continue
9b122384 2134
b30b8698
PH
2135 # here's a fun little line of code for you:
2136 video_id = os.path.splitext(video_id)[0]
fc9713a1 2137
28602e74
YCH
2138 entry_info_dict = {
2139 'id': video_id,
2140 'uploader': video_uploader,
2141 'title': video_title,
2142 'age_limit': age_limit,
2143 }
2144
729accb4
S
2145 ext = determine_ext(video_url)
2146 if ext == 'smil':
28602e74 2147 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
2148 elif ext == 'xspf':
2149 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
2150 elif ext == 'm3u8':
2151 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
2152 elif ext == 'mpd':
2153 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
2154 elif ext == 'f4m':
2155 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
d6fd958c 2156 else:
28602e74
YCH
2157 entry_info_dict['url'] = video_url
2158
19dbaeec
S
2159 if entry_info_dict.get('formats'):
2160 self._sort_formats(entry_info_dict['formats'])
2161
28602e74 2162 entries.append(entry_info_dict)
b30b8698
PH
2163
2164 if len(entries) == 1:
669f0e7c 2165 return entries[0]
b30b8698
PH
2166 else:
2167 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
2168 # 'url' results don't have a title
2169 if e.get('title') is not None:
2170 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
2171 return {
2172 '_type': 'playlist',
2173 'entries': entries,
2174 }