]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[generic] Support Wordpress "YouTube Video Importer" plugin
[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
48a5eabc 66from .vessel import VesselIE
c287f2bc 67from .kaltura import KalturaIE
06a96da1 68from .eagleplatform import EaglePlatformIE
fd6ca382 69from .facebook import FacebookIE
9b122384 70
0838239e 71
9b122384 72class GenericIE(InfoExtractor):
79649588 73 IE_DESC = 'Generic downloader that works on some sites'
9b122384 74 _VALID_URL = r'.*'
79649588 75 IE_NAME = 'generic'
cfe50f04 76 _TESTS = [
c5fa81fe
S
77 # Direct link to a video
78 {
79 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
80 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
81 'info_dict': {
82 'id': 'trailer',
83 'ext': 'mp4',
84 'title': 'trailer',
85 'upload_date': '20100513',
86 }
87 },
c5138a7c 88 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
89 {
90 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
91 'md5': '128c42e68b13950268b648275386fc74',
92 'info_dict': {
93 'id': 'FictionJunction-Parallel_Hearts',
94 'ext': 'flac',
95 'title': 'FictionJunction-Parallel_Hearts',
96 'upload_date': '20140522',
97 },
98 'expected_warnings': [
99 'URL could be a direct video link, returning it as such.'
100 ]
101 },
102 # Direct download with broken HEAD
103 {
104 'url': 'http://ai-radio.org:8000/radio.opus',
105 'info_dict': {
106 'id': 'radio',
107 'ext': 'opus',
108 'title': 'radio',
109 },
110 'params': {
111 'skip_download': True, # infinite live stream
112 },
113 'expected_warnings': [
ef0e4e7b
YCH
114 r'501.*Not Implemented',
115 r'400.*Bad Request',
c5fa81fe
S
116 ],
117 },
118 # Direct link with incorrect MIME type
119 {
120 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
121 'md5': '4ccbebe5f36706d85221f204d7eb5913',
122 'info_dict': {
123 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
124 'id': '5_Lennart_Poettering_-_Systemd',
125 'ext': 'webm',
126 'title': '5_Lennart_Poettering_-_Systemd',
127 'upload_date': '20141120',
128 },
129 'expected_warnings': [
130 'URL could be a direct video link, returning it as such.'
131 ]
132 },
133 # RSS feed
134 {
135 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
136 'info_dict': {
137 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
138 'title': 'Zero Punctuation',
139 'description': 're:.*groundbreaking video review series.*'
140 },
141 'playlist_mincount': 11,
142 },
143 # RSS feed with enclosure
144 {
145 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
146 'info_dict': {
147 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
148 'ext': 'm4v',
149 'upload_date': '20150228',
150 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
151 }
152 },
8765222d
S
153 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
154 {
155 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
156 'info_dict': {
157 'id': 'smil',
158 'ext': 'mp4',
159 'title': 'Automatics, robotics and biocybernetics',
160 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 161 'upload_date': '20130627',
8765222d
S
162 'formats': 'mincount:16',
163 'subtitles': 'mincount:1',
164 },
165 'params': {
166 'force_generic_extractor': True,
167 'skip_download': True,
168 },
169 },
170 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
171 {
172 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
173 'info_dict': {
174 'id': 'hds',
175 'ext': 'flv',
176 'title': 'hds',
177 'formats': 'mincount:1',
178 },
179 'params': {
180 'skip_download': True,
181 },
182 },
183 # SMIL from https://www.restudy.dk/video/play/id/1637
184 {
185 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
186 'info_dict': {
187 'id': 'video_1637',
188 'ext': 'flv',
189 'title': 'video_1637',
190 'formats': 'mincount:3',
191 },
192 'params': {
193 'skip_download': True,
194 },
195 },
196 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
197 {
198 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
199 'info_dict': {
200 'id': 'smil-service',
201 'ext': 'flv',
202 'title': 'smil-service',
203 'formats': 'mincount:1',
204 },
205 'params': {
206 'skip_download': True,
207 },
208 },
209 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
210 {
211 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
212 'info_dict': {
213 'id': '4719370',
214 'ext': 'mp4',
215 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
216 'formats': 'mincount:3',
217 },
218 'params': {
219 'skip_download': True,
220 },
221 },
1de5cd3b
S
222 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
223 {
224 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
225 'info_dict': {
226 'id': 'mZlp2ctYIUEB',
227 'ext': 'mp4',
228 'title': 'Tikibad ontruimd wegens brand',
229 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
230 'thumbnail': 're:^https?://.*\.jpg$',
231 'duration': 33,
232 },
233 'params': {
234 'skip_download': True,
235 },
236 },
9d939cec
S
237 # MPD from http://dash-mse-test.appspot.com/media.html
238 {
239 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
240 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
241 'info_dict': {
242 'id': 'car-20120827-manifest',
243 'ext': 'mp4',
244 'title': 'car-20120827-manifest',
245 'formats': 'mincount:9',
0738187f 246 'upload_date': '20130904',
9d939cec
S
247 },
248 'params': {
249 'format': 'bestvideo',
250 },
251 },
20938f76
S
252 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
253 {
254 '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',
255 'info_dict': {
256 'id': 'content',
257 'ext': 'mp4',
258 'title': 'content',
259 'formats': 'mincount:8',
260 },
261 'params': {
262 # m3u8 downloads
263 'skip_download': True,
264 }
265 },
edd9b71c
S
266 # m3u8 served with Content-Type: text/plain
267 {
268 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
269 'info_dict': {
270 'id': 'index',
271 'ext': 'mp4',
272 'title': 'index',
273 'upload_date': '20140720',
274 'formats': 'mincount:11',
275 },
276 'params': {
277 # m3u8 downloads
278 'skip_download': True,
279 }
280 },
c5fa81fe
S
281 # google redirect
282 {
283 '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',
284 'info_dict': {
285 'id': 'cmQHVoWB5FY',
286 'ext': 'mp4',
287 'upload_date': '20130224',
288 'uploader_id': 'TheVerge',
289 'description': 're:^Chris Ziegler takes a look at the\.*',
290 'uploader': 'The Verge',
291 'title': 'First Firefox OS phones side-by-side',
292 },
293 'params': {
294 'skip_download': False,
295 }
296 },
6c91a5a7
S
297 {
298 # redirect in Refresh HTTP header
299 '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',
300 'info_dict': {
301 'id': 'pO8h3EaFRdo',
302 'ext': 'mp4',
303 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
304 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
305 'upload_date': '20150917',
306 'uploader_id': 'brtvofficial',
307 'uploader': 'Boiler Room',
308 },
309 'params': {
310 'skip_download': False,
311 },
312 },
cfe50f04 313 {
79649588 314 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 315 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 316 'info_dict': {
d360a146
S
317 'id': '13601338388002',
318 'ext': 'mp4',
79649588
PH
319 'uploader': 'www.hodiho.fr',
320 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
321 }
322 },
c19f7764
JMF
323 # bandcamp page with custom domain
324 {
79649588
PH
325 'add_ie': ['Bandcamp'],
326 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 327 'info_dict': {
fd50bf62
S
328 'id': '3235767654',
329 'ext': 'mp3',
79649588
PH
330 'title': 'The Pony Mash',
331 'uploader': 'M_Pallante',
c19f7764 332 },
79649588 333 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 334 },
eeb165e6 335 # embedded brightcove video
dd5bcdc4
JMF
336 # it also tests brightcove videos that need to set the 'Referer' in the
337 # http requests
eeb165e6 338 {
3b7d9aa4 339 'add_ie': ['BrightcoveLegacy'],
79649588
PH
340 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
341 'info_dict': {
342 'id': '2765128793001',
343 'ext': 'mp4',
344 'title': 'Le cours de bourse : l’analyse technique',
345 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
346 'uploader': 'BFM BUSINESS',
eeb165e6 347 },
79649588
PH
348 'params': {
349 'skip_download': True,
eeb165e6
JMF
350 },
351 },
17ab4d3b
PH
352 {
353 # https://github.com/rg3/youtube-dl/issues/2253
354 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
355 'md5': '0ba9446db037002366bab3b3eb30c88c',
356 'info_dict': {
fd50bf62
S
357 'id': '3101154703001',
358 'ext': 'mp4',
17ab4d3b
PH
359 'title': 'Still no power',
360 'uploader': 'thestar.com',
361 '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.',
362 },
3b7d9aa4 363 'add_ie': ['BrightcoveLegacy'],
17ab4d3b 364 },
0479c625
S
365 {
366 'url': 'http://www.championat.com/video/football/v/87/87499.html',
367 'md5': 'fb973ecf6e4a78a67453647444222983',
368 'info_dict': {
369 'id': '3414141473001',
370 'ext': 'mp4',
371 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
372 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
373 'uploader': 'Championat',
374 },
375 },
bdf97017 376 {
37aab278 377 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 378 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
379 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
380 'info_dict': {
381 'id': '3866516442001',
37aab278 382 'ext': 'mp4',
bdf97017
NJ
383 'title': 'Leer mij vrouwen kennen: Aflevering 1',
384 'description': 'Leer mij vrouwen kennen: Aflevering 1',
385 'uploader': 'SBS Broadcasting',
386 },
37aab278 387 'skip': 'Restricted to Netherlands',
bdf97017 388 'params': {
37aab278 389 'skip_download': True, # m3u8 download
bdf97017
NJ
390 },
391 },
c0d0b01f
JMF
392 # ooyala video
393 {
79649588 394 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 395 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
396 'info_dict': {
397 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
398 'ext': 'mp4',
3486df38 399 'title': '2cc213299525360.mov', # that's what we get
53e06b25 400 'duration': 238.231,
c0d0b01f 401 },
87830900 402 'add_ie': ['Ooyala'],
c0d0b01f 403 },
bf94d763
S
404 {
405 # ooyala video embedded with http://player.ooyala.com/iframe.js
406 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
407 'info_dict': {
408 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
409 'ext': 'mp4',
410 'title': '"Steve Jobs: Man in the Machine" trailer',
411 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 412 'duration': 135.427,
bf94d763
S
413 },
414 'params': {
415 'skip_download': True,
416 },
417 },
1b86cc41 418 # embed.ly video
419 {
420 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
421 'info_dict': {
422 'id': '9ODmcdjQcHQ',
423 'ext': 'mp4',
0a5bce56
PH
424 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
425 'upload_date': '20140225',
426 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
427 'uploader': 'Tested',
428 'uploader_id': 'testedcom',
1b86cc41 429 },
430 # No need to test YoutubeIE here
431 'params': {
432 'skip_download': True,
433 },
434 },
60cc4dc4
PH
435 # funnyordie embed
436 {
437 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
438 'info_dict': {
439 'id': '18e820ec3f',
440 'ext': 'mp4',
441 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
442 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 443 },
60cc4dc4 444 },
93d020dd
S
445 # RUTV embed
446 {
447 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
448 'info_dict': {
449 'id': '776940',
450 'ext': 'mp4',
451 'title': 'Охотское море стало целиком российским',
452 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
453 },
454 'params': {
455 # m3u8 download
456 'skip_download': True,
457 },
aab74fa1 458 },
f37bdbe5
S
459 # TVC embed
460 {
461 '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/',
462 'info_dict': {
463 'id': '55304',
464 'ext': 'mp4',
465 'title': 'Дошкольное воспитание',
466 },
467 },
b827a601
S
468 # SportBox embed
469 {
470 'url': 'http://www.vestifinance.ru/articles/25753',
471 'info_dict': {
472 'id': '25753',
473 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
474 },
475 'playlist': [{
476 'info_dict': {
477 'id': '370908',
478 'title': 'Госзаказ. День 3',
479 'ext': 'mp4',
480 }
481 }, {
482 'info_dict': {
483 'id': '370905',
484 'title': 'Госзаказ. День 2',
485 'ext': 'mp4',
486 }
487 }, {
488 'info_dict': {
489 'id': '370902',
490 'title': 'Госзаказ. День 1',
491 'ext': 'mp4',
492 }
493 }],
494 'params': {
495 # m3u8 download
496 'skip_download': True,
497 },
498 },
bf20b9c5
S
499 # Myvi.ru embed
500 {
501 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
502 'info_dict': {
503 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
504 'ext': 'mp4',
505 'title': 'Ужастики, русский трейлер (2015)',
506 'thumbnail': 're:^https?://.*\.jpg$',
507 'duration': 153,
508 }
509 },
c76799c5
S
510 # XHamster embed
511 {
512 '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',
513 'info_dict': {
514 'id': 'showthread',
515 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
516 },
517 'playlist_mincount': 7,
518 },
aab74fa1
PH
519 # Embedded TED video
520 {
521 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 522 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 523 'info_dict': {
a8eb5a8e 524 'id': '1969',
aab74fa1 525 'ext': 'mp4',
a8eb5a8e
PH
526 'title': 'Hidden miracles of the natural world',
527 'uploader': 'Louie Schwartzberg',
528 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 529 }
60cc4dc4 530 },
dfb1b146 531 # Embedded Ustream video
5c386252 532 {
533 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
534 'md5': '27b99cdb639c9b12a79bca876a073417',
535 'info_dict': {
ca6aada4 536 'id': '45734260',
537 'ext': 'flv',
538 'uploader': 'AU SPA: The NSA and Privacy',
5c386252 539 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
540 }
541 },
d95e35d6
S
542 # nowvideo embed hidden behind percent encoding
543 {
544 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
545 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
546 'info_dict': {
547 'id': '06e53103ca9aa',
548 'ext': 'flv',
549 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
550 'description': 'No description',
551 },
0f2a2ba1 552 },
893f8832
PH
553 # arte embed
554 {
555 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
556 'md5': '7653032cbb25bf6c80d80f217055fa43',
557 'info_dict': {
558 'id': '048195-004_PLUS7-F',
559 'ext': 'flv',
560 'title': 'X:enius',
561 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
562 'upload_date': '20140320',
563 },
564 'params': {
565 'skip_download': 'Requires rtmpdump'
566 }
567 },
cbd55ade
S
568 # francetv embed
569 {
570 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
571 'info_dict': {
572 'id': 'EV_30231',
573 'ext': 'mp4',
574 'title': 'Alcaline, le concert avec Calogero',
575 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
576 'upload_date': '20150226',
577 'timestamp': 1424989860,
578 'duration': 5400,
579 },
580 'params': {
581 # m3u8 downloads
582 'skip_download': True,
583 },
584 'expected_warnings': [
585 'Forbidden'
586 ]
587 },
fa35cdad
PH
588 # Condé Nast embed
589 {
590 'url': 'http://www.wired.com/2014/04/honda-asimo/',
591 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
592 'info_dict': {
593 'id': '53501be369702d3275860000',
594 'ext': 'mp4',
595 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
596 }
ebd3c7b3
PH
597 },
598 # Dailymotion embed
599 {
600 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
601 'md5': '441aeeb82eb72c422c7f14ec533999cd',
602 'info_dict': {
603 'id': 'k2mm4bCdJ6CQ2i7c8o2',
604 'ext': 'mp4',
605 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 606 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 607 'uploader': 'Spi0n',
0738187f
YCH
608 'uploader_id': 'xgditw',
609 'upload_date': '20140425',
610 'timestamp': 1398441542,
ebd3c7b3
PH
611 },
612 'add_ie': ['Dailymotion'],
2b88feed
PH
613 },
614 # YouTube embed
615 {
616 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
617 'info_dict': {
618 'id': 'FXRb4ykk4S0',
619 'ext': 'mp4',
620 'title': 'The NBL Auction 2014',
621 'uploader': 'BADMINTON England',
622 'uploader_id': 'BADMINTONEvents',
623 'upload_date': '20140603',
624 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
625 },
626 'add_ie': ['Youtube'],
627 'params': {
628 'skip_download': True,
629 }
630 },
c5cd249e
JMF
631 # MTVSercices embed
632 {
1fa309da
YCH
633 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
634 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 635 'info_dict': {
1fa309da 636 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 637 'ext': 'mp4',
1fa309da
YCH
638 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
639 'description': 'Two valets share their love for movie star Liam Neesons.',
c5cd249e
JMF
640 },
641 },
61013473 642 # YouTube embed via <data-embed-url="">
643 {
644 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 645 'info_dict': {
a8eb5a8e 646 'id': '4vAffPZIT44',
61013473 647 'ext': 'mp4',
a8eb5a8e 648 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
649 'uploader': 'Gameloft',
650 'uploader_id': 'gameloft',
a8eb5a8e
PH
651 'upload_date': '20140828',
652 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
653 },
654 'params': {
655 'skip_download': True,
61013473 656 }
c8e9a235
PH
657 },
658 # Camtasia studio
659 {
660 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
661 'playlist': [{
662 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
663 'info_dict': {
664 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
665 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
666 'ext': 'flv',
667 'duration': 2235.90,
668 }
669 }, {
670 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
671 'info_dict': {
672 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
673 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
674 'ext': 'flv',
675 'duration': 2235.93,
676 }
677 }],
678 'info_dict': {
679 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
680 }
4d805e06
PH
681 },
682 # Flowplayer
683 {
684 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
685 'md5': '9d65602bf31c6e20014319c7d07fba27',
686 'info_dict': {
687 'id': '5123ea6d5e5a7',
688 'ext': 'mp4',
689 'age_limit': 18,
690 'uploader': 'www.handjobhub.com',
d6d9186f 691 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 692 }
0990305d 693 },
22a6f150
PH
694 # Multiple brightcove videos
695 # https://github.com/rg3/youtube-dl/issues/2283
696 {
697 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
698 'info_dict': {
699 'id': 'always-never',
700 'title': 'Always / Never - The New Yorker',
701 },
702 'playlist_count': 3,
703 'params': {
704 'extract_flat': False,
705 'skip_download': True,
706 }
1a94ff68
S
707 },
708 # MLB embed
709 {
710 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
711 'md5': '96f09a37e44da40dd083e12d9a683327',
712 'info_dict': {
713 'id': '33322633',
714 'ext': 'mp4',
715 'title': 'Ump changes call to ball',
716 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
717 'duration': 48,
718 'timestamp': 1401537900,
719 'upload_date': '20140531',
720 'thumbnail': 're:^https?://.*\.jpg$',
721 },
722 },
746c67d7
NJ
723 # Wistia embed
724 {
6c114b12
S
725 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
726 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 727 'info_dict': {
6c114b12 728 'id': '6e2wtrbdaf',
746c67d7 729 'ext': 'mov',
6c114b12
S
730 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
731 'description': 'a Paywall Videos video from Remilon',
732 'duration': 644.072,
733 'uploader': 'study.com',
734 'timestamp': 1459678540,
735 'upload_date': '20160403',
736 'filesize': 24687186,
746c67d7
NJ
737 },
738 },
52cffcb1 739 {
740 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
741 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
742 'info_dict': {
743 'id': 'uxjb0lwrcz',
744 'ext': 'mp4',
6c114b12 745 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 746 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 747 'duration': 1715.0,
85d7b765 748 'uploader': 'thoughtworks.wistia.com',
0738187f 749 'timestamp': 1401832161,
6c114b12 750 'upload_date': '20140603',
70b7e3fb 751 },
52cffcb1 752 },
7ded6545
S
753 # Wistia standard embed (async)
754 {
755 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
756 'info_dict': {
757 'id': '807fafadvk',
758 'ext': 'mp4',
759 'title': 'Drip Brennan Dunn Workshop',
760 'description': 'a JV Webinars video from getdrip-1',
761 'duration': 4986.95,
7ded6545 762 'timestamp': 1463607249,
6c114b12 763 'upload_date': '20160518',
7ded6545
S
764 },
765 'params': {
766 'skip_download': True,
767 }
768 },
ac645ac7
PH
769 # Soundcloud embed
770 {
771 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
772 'info_dict': {
773 'id': '174391317',
774 'ext': 'mp3',
775 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
776 'uploader': 'Sophos Security',
777 'title': 'Chet Chat 171 - Oct 29, 2014',
778 'upload_date': '20141029',
779 }
af63fed7
PH
780 },
781 # Livestream embed
782 {
783 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
784 'info_dict': {
785 'id': '67864563',
786 'ext': 'flv',
787 'upload_date': '20141112',
788 'title': 'Rosetta #CometLanding webcast HL 10',
789 }
790 },
78d3b3e2
YCH
791 # Another Livestream embed, without 'new.' in URL
792 {
793 'url': 'https://www.freespeech.org/',
794 'info_dict': {
795 'id': '123537347',
796 'ext': 'mp4',
797 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
798 },
799 'params': {
800 # Live stream
801 'skip_download': True,
802 },
803 },
65f3a228
PH
804 # LazyYT
805 {
806 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
807 'info_dict': {
11e611a7 808 'id': '1986',
65f3a228
PH
809 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
810 },
811 'playlist_mincount': 2,
4e262a88 812 },
42bdd9d0
PH
813 # Cinchcast embed
814 {
815 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
816 'info_dict': {
817 'id': '7141703',
818 'ext': 'mp3',
819 'upload_date': '20141126',
820 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
821 }
822 },
501f13fb
PH
823 # Cinerama player
824 {
825 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
826 'info_dict': {
827 'id': '730m_DandD_1901_512k',
828 'ext': 'mp4',
829 'uploader': 'www.abc.net.au',
830 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
831 }
796df3c6
S
832 },
833 # embedded viddler video
834 {
835 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
836 'info_dict': {
837 'id': '4d03aad9',
838 'ext': 'mp4',
839 'uploader': 'deadspin',
840 'title': 'WALL-TO-GORTAT',
841 'timestamp': 1422285291,
842 'upload_date': '20150126',
843 },
844 'add_ie': ['Viddler'],
a0f71985 845 },
2051acde
S
846 # Libsyn embed
847 {
848 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
849 'info_dict': {
850 'id': '3377616',
851 'ext': 'mp3',
852 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
853 'description': 'md5:601cb790edd05908957dae8aaa866465',
854 'upload_date': '20150220',
855 },
856 },
a0f71985
PH
857 # jwplayer YouTube
858 {
859 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
860 'info_dict': {
861 'id': 'Mrj4DVp2zeA',
862 'ext': 'mp4',
f37e3f99 863 'upload_date': '20150212',
a0f71985
PH
864 'uploader': 'The National Archives UK',
865 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
866 'uploader_id': 'NationalArchives08',
867 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
868 },
59b8ab58
PH
869 },
870 # rtl.nl embed
871 {
872 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
873 'playlist_mincount': 5,
874 'info_dict': {
875 'id': 'aanslagen-kopenhagen',
876 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
877 }
255fca5e
S
878 },
879 # Zapiks embed
880 {
881 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
882 'info_dict': {
883 'id': '118046',
884 'ext': 'mp4',
885 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
886 }
887 },
66e568de
S
888 # Kaltura embed (different embed code)
889 {
890 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
891 'info_dict': {
892 'id': '1_a52wc67y',
893 'ext': 'flv',
894 'upload_date': '20150127',
895 'uploader_id': 'PremierMedia',
896 'timestamp': int,
897 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
898 },
899 },
6da620de
S
900 # Kaltura embed protected with referrer
901 {
902 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
903 'info_dict': {
904 'id': '1_g4fbemnq',
905 'ext': 'mp4',
906 'title': 'Violetta - Achter De Schermen - Ruggero',
907 'description': 'Achter de schermen met Ruggero',
908 'timestamp': 1435133761,
909 'upload_date': '20150624',
910 'uploader_id': 'echojecka',
911 },
912 },
87703231
YCH
913 # Kaltura embed with single quotes
914 {
915 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
916 'info_dict': {
917 'id': '0_izeg5utt',
918 'ext': 'mp4',
919 'title': '35871',
920 'timestamp': 1355743100,
921 'upload_date': '20121217',
922 'uploader_id': 'batchUser',
923 },
924 'add_ie': ['Kaltura'],
925 },
427cd050
S
926 {
927 # Kaltura embedded via quoted entry_id
928 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
929 'info_dict': {
930 'id': '0_utuok90b',
931 'ext': 'mp4',
932 'title': '06_matthew_brender_raj_dutt',
933 'timestamp': 1466638791,
934 'upload_date': '20160622',
935 },
936 'add_ie': ['Kaltura'],
937 'expected_warnings': [
938 'Could not send HEAD request'
939 ],
940 'params': {
941 'skip_download': True,
942 }
943 },
135c9c42
S
944 # Eagle.Platform embed (generic URL)
945 {
946 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
4645432d 947 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
135c9c42
S
948 'info_dict': {
949 'id': '227304',
950 'ext': 'mp4',
951 'title': 'Навальный вышел на свободу',
952 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
953 'thumbnail': 're:^https?://.*\.jpg$',
954 'duration': 87,
955 'view_count': int,
956 'age_limit': 0,
957 },
958 },
d47ae7f6
S
959 # ClipYou (Eagle.Platform) embed (custom URL)
960 {
961 'url': 'http://muz-tv.ru/play/7129/',
4645432d 962 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
963 'info_dict': {
964 'id': '12820',
965 'ext': 'mp4',
966 'title': "'O Sole Mio",
967 'thumbnail': 're:^https?://.*\.jpg$',
968 'duration': 216,
969 'view_count': int,
970 },
971 },
f8388757
S
972 # Pladform embed
973 {
974 'url': 'http://muz-tv.ru/kinozal/view/7400/',
975 'info_dict': {
976 'id': '100183293',
977 'ext': 'mp4',
62259846 978 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757
S
979 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
980 'thumbnail': 're:^https?://.*\.jpg$',
981 'duration': 694,
982 'age_limit': 0,
983 },
984 },
c798f15b
S
985 # Playwire embed
986 {
987 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
988 'info_dict': {
989 'id': '3519514',
990 'ext': 'mp4',
991 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
992 'thumbnail': 're:^https?://.*\.png$',
993 'duration': 45.115,
994 },
995 },
ad320e9b
NJ
996 # 5min embed
997 {
998 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
999 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1000 'info_dict': {
1001 'id': '518726732',
1002 'ext': 'mp4',
1003 'title': 'Facebook Creates "On This Day" | Crunch Report',
1004 },
1005 },
dc455a5f
S
1006 # SVT embed
1007 {
1008 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1009 'info_dict': {
1010 'id': '2900353',
1011 'ext': 'flv',
1012 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1013 'duration': 27,
1014 'age_limit': 0,
1015 },
1016 },
a4257017
S
1017 # Crooks and Liars embed
1018 {
1019 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1020 'info_dict': {
1021 'id': '8RUoRhRi',
1022 'ext': 'mp4',
1023 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1024 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1025 'timestamp': 1428207000,
1026 'upload_date': '20150405',
1027 'uploader': 'Heather',
1028 },
1029 },
1030 # Crooks and Liars external embed
1031 {
1032 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1033 'info_dict': {
1034 'id': 'MTE3MjUtMzQ2MzA',
1035 'ext': 'mp4',
1036 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1037 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1038 'timestamp': 1265032391,
1039 'upload_date': '20100201',
1040 'uploader': 'Heather',
1041 },
1042 },
facecb84 1043 # NBC Sports vplayer embed
a2edf2e7 1044 {
facecb84 1045 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1046 'info_dict': {
facecb84
S
1047 'id': 'ln7x1qSThw4k',
1048 'ext': 'flv',
1049 'title': "PFT Live: New leader in the 'new-look' defense",
1050 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1051 'uploader': 'NBCU-SPORTS',
1052 'upload_date': '20140107',
1053 'timestamp': 1389118457,
a2edf2e7 1054 },
418c5cc3 1055 },
de3eb07e
YCH
1056 # NBC News embed
1057 {
1058 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1059 'md5': '1aa589c675898ae6d37a17913cf68d66',
1060 'info_dict': {
1061 'id': '701714499682',
1062 'ext': 'mp4',
1063 'title': 'PREVIEW: On Assignment: David Letterman',
1064 '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.',
1065 },
1066 },
418c5cc3
YCH
1067 # UDN embed
1068 {
811586eb 1069 'url': 'https://video.udn.com/news/300346',
01c58f84 1070 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1071 'info_dict': {
01c58f84 1072 'id': '300346',
418c5cc3 1073 'ext': 'mp4',
01c58f84 1074 'title': '中一中男師變性 全校師生力挺',
418c5cc3 1075 'thumbnail': 're:^https?://.*\.jpg$',
811586eb
YCH
1076 },
1077 'params': {
1078 # m3u8 download
1079 'skip_download': True,
1080 },
edfcf7ab
YCH
1081 },
1082 # Ooyala embed
1083 {
1084 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1085 'info_dict': {
1086 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1087 'ext': 'mp4',
cce9d15d 1088 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
edfcf7ab 1089 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1090 'duration': 191.933,
edfcf7ab
YCH
1091 },
1092 'params': {
1093 # m3u8 downloads
1094 'skip_download': True,
1095 }
d6fd958c 1096 },
b26733ba
YCH
1097 # Brightcove URL in single quotes
1098 {
1099 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1100 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1101 'info_dict': {
1102 'id': '4255764656001',
1103 'ext': 'mp4',
1104 'title': 'SN Presents: Russell Martin, World Citizen',
1105 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1106 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1107 'uploader_id': '1704050871',
1108 'upload_date': '20150525',
1109 'timestamp': 1432570283,
b26733ba 1110 },
756f574e
YCH
1111 },
1112 # Dailymotion Cloud video
1113 {
1114 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
7d52c052 1115 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
756f574e 1116 'info_dict': {
7d52c052 1117 'id': 'x2uy8t3',
756f574e 1118 'ext': 'mp4',
7d52c052
YCH
1119 'title': 'Sauvons les abeilles ! - Le débat',
1120 'description': 'md5:d9082128b1c5277987825d684939ca26',
756f574e 1121 'thumbnail': 're:^https?://.*\.jpe?g$',
7d52c052
YCH
1122 'timestamp': 1434970506,
1123 'upload_date': '20150622',
1124 'uploader': 'Public Sénat',
1125 'uploader_id': 'xa9gza',
756f574e 1126 }
a5158f38 1127 },
8084be78
S
1128 # OnionStudios embed
1129 {
1130 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1131 'info_dict': {
1132 'id': '2855',
1133 'ext': 'mp4',
1134 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1135 'thumbnail': 're:^https?://.*\.jpe?g$',
1136 'uploader': 'ClickHole',
1137 'uploader_id': 'clickhole',
1138 }
1139 },
b8c1cc1a
S
1140 # SnagFilms embed
1141 {
1142 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1143 'info_dict': {
1144 'id': '74849a00-85a9-11e1-9660-123139220831',
1145 'ext': 'mp4',
1146 'title': '#whilewewatch',
1147 }
1148 },
a5158f38
YCH
1149 # AdobeTVVideo embed
1150 {
1151 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1152 'md5': '43662b577c018ad707a63766462b1e87',
1153 'info_dict': {
1154 'id': '2456',
1155 'ext': 'mp4',
1156 'title': 'New experience with Acrobat DC',
1157 'description': 'New experience with Acrobat DC',
1158 'duration': 248.667,
1159 },
1f812580
S
1160 },
1161 # ScreenwaveMedia embed
1162 {
1163 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1164 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1165 'info_dict': {
1166 'id': 'cinemasnob-55d26273809dd',
1167 'ext': 'mp4',
1168 'title': 'cinemasnob',
1169 },
ed126900 1170 },
1171 # BrightcoveInPageEmbed embed
1172 {
1173 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1174 'info_dict': {
1175 'id': '4238694884001',
1176 'ext': 'flv',
1177 'title': 'Tabletop: Dread, Last Thoughts',
1178 'description': 'Tabletop: Dread, Last Thoughts',
1179 'duration': 51690,
1180 },
750b9ff0
YCH
1181 },
1182 # JWPlayer with M3U8
1183 {
1184 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1185 'info_dict': {
1186 'id': 'playlist',
1187 'ext': 'mp4',
1188 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1189 'uploader': 'ren.tv',
1190 },
1191 'params': {
1192 # m3u8 downloads
1193 'skip_download': True,
1194 }
d10fe835
YCH
1195 },
1196 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1197 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1198 {
1199 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1200 'info_dict': {
1201 'id': '4785848093001',
1202 'ext': 'mp4',
1203 'title': 'The Cardinal Pell Interview',
1204 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1205 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1206 'uploader_id': '2733773828001',
1207 'upload_date': '20160304',
1208 'timestamp': 1457083087,
d10fe835
YCH
1209 },
1210 'params': {
1211 # m3u8 downloads
1212 'skip_download': True,
1213 },
1214 },
134c207e
YCH
1215 # Another form of arte.tv embed
1216 {
1217 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1218 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1219 'info_dict': {
1220 'id': '030273-562_PLUS7-F',
1221 'ext': 'mp4',
1222 'title': 'ARTE Reportage - Nulle part, en France',
1223 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1224 'upload_date': '20160409',
1225 },
1226 },
b8f67449
KM
1227 # LiveLeak embed
1228 {
1229 'url': 'http://www.wykop.pl/link/3088787/',
1230 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1231 'info_dict': {
1232 'id': '874_1459135191',
1233 'ext': 'mp4',
1234 'title': 'Man shows poor quality of new apartment building',
1235 'description': 'The wall is like a sand pile.',
1236 'uploader': 'Lake8737',
1237 }
1238 },
4a120778
YCH
1239 # Duplicated embedded video URLs
1240 {
1241 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1242 'info_dict': {
1243 'id': '149298443_480_16c25b74_2',
1244 'ext': 'mp4',
1245 'title': 'vs. Blue Orange Spring Game',
1246 'uploader': 'www.hudl.com',
1247 },
1248 },
32917907
RA
1249 # twitter:player embed
1250 {
1251 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1252 'md5': 'a3e0df96369831de324f0778e126653c',
1253 'info_dict': {
1254 'id': '4909620399001',
1255 'ext': 'mp4',
1256 'title': 'What Do Black Holes Sound Like?',
1257 'description': 'what do black holes sound like',
1258 'upload_date': '20160524',
1259 'uploader_id': '29913724001',
1260 'timestamp': 1464107587,
1261 'uploader': 'TheAtlantic',
1262 },
1263 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1264 },
1265 # Facebook <iframe> embed
1266 {
1267 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1268 'info_dict': {
1269 'id': '599637780109885',
1270 'ext': 'mp4',
1271 'title': 'Facebook video #599637780109885',
1272 },
1273 },
1274 # Facebook API embed
1275 {
1276 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1277 'info_dict': {
1278 'id': '10153467542406923',
1279 'ext': 'mp4',
1280 'title': 'Facebook video #10153467542406923',
1281 },
7deef1ba
YCH
1282 },
1283 # Wordpress "YouTube Video Importer" plugin
1284 {
1285 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1286 'info_dict': {
1287 'id': 'HNTXWDXV9Is',
1288 'ext': 'mp4',
1289 'title': 'Blue Devils Drumline Stanford lot 2016',
1290 'upload_date': '20160627',
1291 'uploader_id': 'GENOCIDE8GENERAL10',
1292 'uploader': 'cylus cyrus',
1293 },
1294 },
cfe50f04 1295 ]
9b122384 1296
9b122384
PH
1297 def report_following_redirect(self, new_url):
1298 """Report information extraction."""
79649588 1299 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1300
4fc946b5
PH
1301 def _extract_rss(self, url, video_id, doc):
1302 playlist_title = doc.find('./channel/title').text
1303 playlist_desc_el = doc.find('./channel/description')
1304 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1305
76c73715
PH
1306 entries = []
1307 for it in doc.findall('./channel/item'):
1308 next_url = xpath_text(it, 'link', fatal=False)
1309 if not next_url:
1310 enclosure_nodes = it.findall('./enclosure')
1311 for e in enclosure_nodes:
1312 next_url = e.attrib.get('url')
1313 if next_url:
1314 break
1315
1316 if not next_url:
1317 continue
1318
1319 entries.append({
1320 '_type': 'url',
1321 'url': next_url,
1322 'title': it.find('title').text,
1323 })
4fc946b5
PH
1324
1325 return {
1326 '_type': 'playlist',
1327 'id': url,
1328 'title': playlist_title,
1329 'description': playlist_desc,
1330 'entries': entries,
1331 }
1332
c8e9a235
PH
1333 def _extract_camtasia(self, url, video_id, webpage):
1334 """ Returns None if no camtasia video can be found. """
1335
1336 camtasia_cfg = self._search_regex(
1337 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1338 webpage, 'camtasia configuration file', default=None)
1339 if camtasia_cfg is None:
1340 return None
1341
1342 title = self._html_search_meta('DC.title', webpage, fatal=True)
1343
1344 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1345 camtasia_cfg = self._download_xml(
1346 camtasia_url, video_id,
1347 note='Downloading camtasia configuration',
1348 errnote='Failed to download camtasia configuration')
1349 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1350
1351 entries = []
1352 for n in fileset_node.getchildren():
1353 url_n = n.find('./uri')
1354 if url_n is None:
1355 continue
1356
1357 entries.append({
1358 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1359 'title': '%s - %s' % (title, n.tag),
1360 'url': compat_urlparse.urljoin(url, url_n.text),
1361 'duration': float_or_none(n.find('./duration').text),
1362 })
1363
1364 return {
1365 '_type': 'playlist',
1366 'entries': entries,
1367 'title': title,
1368 }
1369
9b122384 1370 def _real_extract(self, url):
ebd3c7b3
PH
1371 if url.startswith('//'):
1372 return {
1373 '_type': 'url',
20991253 1374 'url': self.http_scheme() + url,
ebd3c7b3
PH
1375 }
1376
a7130543
JMF
1377 parsed_url = compat_urlparse.urlparse(url)
1378 if not parsed_url.scheme:
04b4d394
PH
1379 default_search = self._downloader.params.get('default_search')
1380 if default_search is None:
1f7ccb90 1381 default_search = 'fixup_error'
04b4d394 1382
1f7ccb90 1383 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
1384 if '/' in url:
1385 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1386 return self.url_result('http://' + url)
1f7ccb90 1387 elif default_search != 'fixup_error':
9c1fc022 1388 if default_search == 'auto_warning':
0e67ab0d
PH
1389 if re.match(r'^(?:url|URL)$', url):
1390 raise ExtractorError(
1391 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1392 expected=True)
1393 else:
1394 self._downloader.report_warning(
7571c02c 1395 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 1396 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
1397
1398 if default_search in ('error', 'fixup_error'):
7571c02c 1399 raise ExtractorError(
b74e86f4
PH
1400 '%r is not a valid URL. '
1401 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1402 % (url, url), expected=True)
04b4d394 1403 else:
f2f2c0c2
PH
1404 if ':' not in default_search:
1405 default_search += ':'
04b4d394 1406 return self.url_result(default_search + url)
4d54ef20
PH
1407
1408 url, smuggled_data = unsmuggle_url(url)
1409 force_videoid = None
d6e6a422 1410 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
1411 if smuggled_data and 'force_videoid' in smuggled_data:
1412 force_videoid = smuggled_data['force_videoid']
1413 video_id = force_videoid
1414 else:
1ddb9456 1415 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
a7130543 1416
79649588 1417 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 1418
ebab4520 1419 head_req = HEADRequest(url)
23be51d8 1420 head_response = self._request_webpage(
ebab4520
PH
1421 head_req, video_id,
1422 note=False, errnote='Could not send HEAD request to %s' % url,
1423 fatal=False)
42393ce2 1424
23be51d8 1425 if head_response is not False:
42393ce2 1426 # Check for redirect
23be51d8 1427 new_url = head_response.geturl()
42393ce2
PH
1428 if url != new_url:
1429 self.report_following_redirect(new_url)
4d54ef20
PH
1430 if force_videoid:
1431 new_url = smuggle_url(
1432 new_url, {'force_videoid': force_videoid})
cecaaf3f 1433 return self.url_result(new_url)
42393ce2 1434
23be51d8
PH
1435 full_response = None
1436 if head_response is False:
5c2266df 1437 request = sanitized_Request(url)
58bde34a
S
1438 request.add_header('Accept-Encoding', '*')
1439 full_response = self._request_webpage(request, video_id)
23be51d8
PH
1440 head_response = full_response
1441
f930e0c7
S
1442 info_dict = {
1443 'id': video_id,
1444 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
303dcdb9 1445 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
1446 }
1447
23be51d8 1448 # Check for direct link to a video
955737b2 1449 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 1450 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 1451 if m:
f930e0c7
S
1452 format_id = m.group('format_id')
1453 if format_id.endswith('mpegurl'):
eadc3ccd 1454 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
1455 elif format_id == 'f4m':
1456 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 1457 else:
1458 formats = [{
1459 'format_id': m.group('format_id'),
1460 'url': url,
1461 'vcodec': 'none' if m.group('type') == 'audio' else None
1462 }]
de6c51e8 1463 info_dict['direct'] = True
19dbaeec 1464 self._sort_formats(formats)
de6c51e8 1465 info_dict['formats'] = formats
f930e0c7 1466 return info_dict
42393ce2 1467
d6e6a422 1468 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
1469 force = self._downloader.params.get('force_generic_extractor', False)
1470 self._downloader.report_warning(
1471 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 1472
4e262a88 1473 if not full_response:
5c2266df 1474 request = sanitized_Request(url)
58bde34a
S
1475 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1476 # making it impossible to download only chunk of the file (yet we need only 512kB to
1477 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1478 # that will always result in downloading the whole file that is not desirable.
1479 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1480 # to accept raw bytes and being able to download only a chunk.
1481 # It may probably better to solve this by checking Content-Type for application/octet-stream
1482 # after HEAD request finishes, but not sure if we can rely on this.
1483 request.add_header('Accept-Encoding', '*')
1484 full_response = self._request_webpage(request, video_id)
4e262a88 1485
5940862d
S
1486 first_bytes = full_response.read(512)
1487
1488 # Is it an M3U playlist?
0d769bcb 1489 if first_bytes.startswith(b'#EXTM3U'):
5940862d 1490 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 1491 self._sort_formats(info_dict['formats'])
5940862d
S
1492 return info_dict
1493
4e262a88
PH
1494 # Maybe it's a direct link to a video?
1495 # Be careful not to download the whole thing!
61ca9a80 1496 if not is_html(first_bytes):
4e262a88
PH
1497 self._downloader.report_warning(
1498 'URL could be a direct video link, returning it as such.')
f930e0c7 1499 info_dict.update({
4e262a88
PH
1500 'direct': True,
1501 'url': url,
f930e0c7
S
1502 })
1503 return info_dict
4e262a88
PH
1504
1505 webpage = self._webpage_read_content(
1506 full_response, url, video_id, prefix=first_bytes)
1507
9b122384 1508 self.report_extraction(video_id)
887c6acd 1509
1b840245 1510 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 1511 try:
f7854627 1512 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
1513 if doc.tag == 'rss':
1514 return self._extract_rss(url, video_id, doc)
e5e8d20a 1515 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
1516 smil = self._parse_smil(doc, url, video_id)
1517 self._sort_formats(smil['formats'])
1518 return smil
729accb4
S
1519 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1520 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245 1521 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7
S
1522 info_dict['formats'] = self._parse_mpd_formats(
1523 doc, video_id, mpd_base_url=url.rpartition('/')[0])
19dbaeec 1524 self._sort_formats(info_dict['formats'])
f930e0c7
S
1525 return info_dict
1526 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1527 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 1528 self._sort_formats(info_dict['formats'])
f930e0c7 1529 return info_dict
f7300c5c 1530 except compat_xml_parse_error:
4fc946b5
PH
1531 pass
1532
c8e9a235
PH
1533 # Is it a Camtasia project?
1534 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1535 if camtasia_res is not None:
1536 return camtasia_res
1537
14390730
S
1538 # Sometimes embedded video player is hidden behind percent encoding
1539 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1540 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 1541 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 1542
887c6acd
PH
1543 # it's tempting to parse this further, but you would
1544 # have to take into account all the variations like
1545 # Video Title - Site Name
1546 # Site Name | Video Title
1547 # Video Title - Tagline | Site Name
1548 # and so on and so forth; it's just not practical
6f41b2bc
S
1549 video_title = self._og_search_title(
1550 webpage, default=None) or self._html_search_regex(
79649588
PH
1551 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1552 default='video')
ef4fd848 1553
4d805e06
PH
1554 # Try to detect age limit automatically
1555 age_limit = self._rta_search(webpage)
1556 # And then there are the jokers who advertise that they use RTA,
1557 # but actually don't.
1558 AGE_LIMIT_MARKERS = [
1559 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1560 ]
1561 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1562 age_limit = 18
1563
ef4fd848
PH
1564 # video uploader is domain name
1565 video_uploader = self._search_regex(
79649588 1566 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 1567
6f41b2bc
S
1568 video_description = self._og_search_description(webpage, default=None)
1569 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1570
ed2d6a19 1571 # Helper method
83992676 1572 def _playlist_from_matches(matches, getter=None, ie=None):
3b2f933b 1573 urlrs = orderedSet(
83992676 1574 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
3b2f933b 1575 for m in matches)
ed2d6a19
PH
1576 return self.playlist_result(
1577 urlrs, playlist_id=video_id, playlist_title=video_title)
1578
1f4b722b 1579 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 1580 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 1581 if bc_urls:
79649588 1582 self.to_screen('Brightcove video detected.')
99877772
PH
1583 entries = [{
1584 '_type': 'url',
1585 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 1586 'ie_key': 'BrightcoveLegacy'
99877772
PH
1587 } for bc_url in bc_urls]
1588
1589 return {
1590 '_type': 'playlist',
1591 'title': video_title,
1592 'id': video_id,
1593 'entries': entries,
1594 }
cfe50f04 1595
f6519f89
S
1596 # Look for Brightcove New Studio embeds
1597 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1598 if bc_urls:
1599 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
ed126900 1600
4d8819d2
S
1601 # Look for ThePlatform embeds
1602 tp_urls = ThePlatformIE._extract_urls(webpage)
1603 if tp_urls:
1604 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1605
48a5eabc
S
1606 # Look for Vessel embeds
1607 vessel_urls = VesselIE._extract_urls(webpage)
1608 if vessel_urls:
1609 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1610
59b8ab58
PH
1611 # Look for embedded rtl.nl player
1612 matches = re.findall(
97b570a9 1613 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
59b8ab58
PH
1614 webpage)
1615 if matches:
1616 return _playlist_from_matches(matches, ie='RtlNl')
1617
b407e173
YCH
1618 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1619 if vimeo_url is not None:
1620 return self.url_result(vimeo_url)
7115ca84 1621
a1b85269
YCH
1622 vid_me_embed_url = self._search_regex(
1623 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1624 webpage, 'vid.me embed', default=None)
1625 if vid_me_embed_url is not None:
1626 return self.url_result(vid_me_embed_url, 'Vidme')
1627
53c1d3ef 1628 # Look for embedded YouTube player
1f9da904 1629 matches = re.findall(r'''(?x)
2b88feed
PH
1630 (?:
1631 <iframe[^>]+?src=|
c71dfccc 1632 data-video-url=|
2b88feed 1633 <embed[^>]+?src=|
a7e97f6d
PH
1634 embedSWF\(?:\s*|
1635 new\s+SWFObject\(
2b88feed
PH
1636 )
1637 (["\'])
1bf5423e 1638 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
6b08cdf6 1639 (?:embed|v|p)/.+?)
1f9da904 1640 \1''', webpage)
887c6acd 1641 if matches:
ed2d6a19 1642 return _playlist_from_matches(
3b2f933b 1643 matches, lambda m: unescapeHTML(m[1]))
53c1d3ef 1644
65f3a228
PH
1645 # Look for lazyYT YouTube embed
1646 matches = re.findall(
1647 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1648 if matches:
1649 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1650
7deef1ba
YCH
1651 # Look for Wordpress "YouTube Video Importer" plugin
1652 matches = re.findall(r'''(?x)<div[^>]+
1653 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1654 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1655 if matches:
1656 return _playlist_from_matches(matches, lambda m: m[-1])
1657
355e4fd0
PH
1658 # Look for embedded Dailymotion player
1659 matches = re.findall(
5a490592 1660 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
355e4fd0 1661 if matches:
ed2d6a19
PH
1662 return _playlist_from_matches(
1663 matches, lambda m: unescapeHTML(m[1]))
355e4fd0 1664
8489578d
NJ
1665 # Look for embedded Dailymotion playlist player (#3822)
1666 m = re.search(
1667 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1668 if m:
1669 playlists = re.findall(
1670 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1671 if playlists:
1672 return _playlist_from_matches(
1673 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1674
ef4fd848
PH
1675 # Look for embedded Wistia player
1676 match = re.search(
281d3f1d 1677 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
ef4fd848 1678 if match:
9471c444
NJ
1679 embed_url = self._proto_relative_url(
1680 unescapeHTML(match.group('url')))
ef4fd848
PH
1681 return {
1682 '_type': 'url_transparent',
9471c444 1683 'url': embed_url,
ef4fd848
PH
1684 'ie_key': 'Wistia',
1685 'uploader': video_uploader,
ef4fd848 1686 }
5f6a1245 1687
9471c444 1688 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
746c67d7
NJ
1689 if match:
1690 return {
1691 '_type': 'url_transparent',
6c114b12 1692 'url': 'wistia:%s' % match.group('id'),
746c67d7
NJ
1693 'ie_key': 'Wistia',
1694 'uploader': video_uploader,
746c67d7 1695 }
ef4fd848 1696
aa5957ac
S
1697 match = re.search(
1698 r'''(?sx)
1699 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1700 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1701 ''', webpage)
1702 if match:
1703 return self.url_result(self._proto_relative_url(
1704 'wistia:%s' % match.group('id')), 'Wistia')
1705
bab19a8e
S
1706 # Look for SVT player
1707 svt_url = SVTIE._extract_url(webpage)
1708 if svt_url:
1709 return self.url_result(svt_url, 'SVT')
1710
fa35cdad
PH
1711 # Look for embedded condenast player
1712 matches = re.findall(
1713 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1714 webpage)
1715 if matches:
1716 return {
1717 '_type': 'playlist',
1718 'entries': [{
1719 '_type': 'url',
1720 'ie_key': 'CondeNast',
1721 'url': ma,
1722 } for ma in matches],
1723 'title': video_title,
1724 'id': video_id,
1725 }
1726
c19f7764
JMF
1727 # Look for Bandcamp pages with custom domain
1728 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1729 if mobj is not None:
1730 burl = unescapeHTML(mobj.group(1))
09804265
JMF
1731 # Don't set the extractor because it can be a track url or an album
1732 return self.url_result(burl)
c19f7764 1733
f25571ff
PH
1734 # Look for embedded Vevo player
1735 mobj = re.search(
1736 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1737 if mobj is not None:
1738 return self.url_result(mobj.group('url'))
796df3c6
S
1739
1740 # Look for embedded Viddler player
cb454b33
S
1741 mobj = re.search(
1742 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1743 webpage)
796df3c6
S
1744 if mobj is not None:
1745 return self.url_result(mobj.group('url'))
f25571ff 1746
3378d67a
S
1747 # Look for NYTimes player
1748 mobj = re.search(
1749 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1750 webpage)
1751 if mobj is not None:
1752 return self.url_result(mobj.group('url'))
1753
cefdf970
S
1754 # Look for Libsyn player
1755 mobj = re.search(
1756 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1757 if mobj is not None:
1758 return self.url_result(mobj.group('url'))
1759
c0d0b01f 1760 # Look for Ooyala videos
8a37aa15 1761 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 1762 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
1763 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1764 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 1765 if mobj is not None:
cce9d15d 1766 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
c0d0b01f 1767
f076b638 1768 # Look for multiple Ooyala embeds on SBN network websites
1769 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1770 if mobj is not None:
1771 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1772 if embeds:
1773 return _playlist_from_matches(
cce9d15d 1774 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 1775
aa94a6d3 1776 # Look for Aparat videos
48099643 1777 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
1778 if mobj is not None:
1779 return self.url_result(mobj.group(1), 'Aparat')
1780
c93c2ab1 1781 # Look for MPORA videos
c3f51436 1782 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
1783 if mobj is not None:
1784 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 1785
15c0e8e7 1786 # Look for embedded NovaMov-based player
8f89e687 1787 mobj = re.search(
8dfa187b 1788 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
1789 (?P<url>http://(?:(?:embed|www)\.)?
1790 (?:novamov\.com|
1791 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1792 videoweed\.(?:es|com)|
1793 movshare\.(?:net|sx|ag)|
1794 divxstage\.(?:eu|net|ch|co|at|ag))
1795 /embed\.php.+?)\1''', webpage)
8f89e687 1796 if mobj is not None:
15c0e8e7 1797 return self.url_result(mobj.group('url'))
50f56607 1798
9834872b 1799 # Look for embedded Facebook player
fd6ca382
YCH
1800 facebook_url = FacebookIE._extract_url(webpage)
1801 if facebook_url is not None:
1802 return self.url_result(facebook_url, 'Facebook')
9834872b 1803
ca97a56e
S
1804 # Look for embedded VK player
1805 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1806 if mobj is not None:
1807 return self.url_result(mobj.group('url'), 'VK')
1808
33d4fdab
S
1809 # Look for embedded Odnoklassniki player
1810 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1811 if mobj is not None:
1812 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1813
0364fa8b
S
1814 # Look for embedded ivi player
1815 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1816 if mobj is not None:
1817 return self.url_result(mobj.group('url'), 'Ivi')
1818
db1f3888
PH
1819 # Look for embedded Huffington Post player
1820 mobj = re.search(
c3f51436 1821 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
1822 if mobj is not None:
1823 return self.url_result(mobj.group('url'), 'HuffPost')
1824
1b86cc41 1825 # Look for embed.ly
1826 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1827 if mobj is not None:
1828 return self.url_result(mobj.group('url'))
1829 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1830 if mobj is not None:
f7e6f7fa 1831 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 1832
60cc4dc4
PH
1833 # Look for funnyordie embed
1834 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1835 if matches:
ed2d6a19
PH
1836 return _playlist_from_matches(
1837 matches, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 1838
db546cf8
S
1839 # Look for BBC iPlayer embed
1840 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1841 if matches:
476eae0c 1842 return _playlist_from_matches(matches, ie='BBCCoUk')
db546cf8 1843
93d020dd
S
1844 # Look for embedded RUTV player
1845 rutv_url = RUTVIE._extract_url(webpage)
1846 if rutv_url:
1847 return self.url_result(rutv_url, 'RUTV')
1848
494f20cb 1849 # Look for embedded TVC player
b8599718
S
1850 tvc_url = TVCIE._extract_url(webpage)
1851 if tvc_url:
1852 return self.url_result(tvc_url, 'TVC')
494f20cb 1853
d40a3b5b
S
1854 # Look for embedded SportBox player
1855 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1856 if sportbox_urls:
1857 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1858
78e2b74b 1859 # Look for embedded PornHub player
65d161c4
S
1860 pornhub_url = PornHubIE._extract_url(webpage)
1861 if pornhub_url:
1862 return self.url_result(pornhub_url, 'PornHub')
1863
2bb5b6d0
S
1864 # Look for embedded XHamster player
1865 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1866 if xhamster_urls:
1867 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1868
2c9ca782
S
1869 # Look for embedded TNAFlixNetwork player
1870 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1871 if tnaflix_urls:
1872 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1873
9872d311
S
1874 # Look for embedded Tvigle player
1875 mobj = re.search(
1876 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1877 if mobj is not None:
1878 return self.url_result(mobj.group('url'), 'Tvigle')
1879
7e2ede98
JMF
1880 # Look for embedded TED player
1881 mobj = re.search(
d7cc31b6 1882 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
1883 if mobj is not None:
1884 return self.url_result(mobj.group('url'), 'TED')
1885
5c386252 1886 # Look for embedded Ustream videos
1887 mobj = re.search(
1888 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1889 if mobj is not None:
1890 return self.url_result(mobj.group('url'), 'Ustream')
1891
893f8832
PH
1892 # Look for embedded arte.tv player
1893 mobj = re.search(
134c207e 1894 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
1895 webpage)
1896 if mobj is not None:
1897 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1898
cbd55ade
S
1899 # Look for embedded francetv player
1900 mobj = re.search(
1901 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1902 webpage)
1903 if mobj is not None:
1904 return self.url_result(mobj.group('url'))
1905
cb3ac1c6
S
1906 # Look for embedded smotri.com player
1907 smotri_url = SmotriIE._extract_url(webpage)
1908 if smotri_url:
1909 return self.url_result(smotri_url, 'Smotri')
1910
e6c2d9ad 1911 # Look for embedded Myvi.ru player
6dd94d3a 1912 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
1913 if myvi_url:
1914 return self.url_result(myvi_url)
1915
dfb1b146 1916 # Look for embedded soundcloud player
20991253 1917 mobj = re.search(
ac645ac7 1918 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
20991253
PH
1919 webpage)
1920 if mobj is not None:
1921 url = unescapeHTML(mobj.group('url'))
1922 return self.url_result(url)
1923
c5cd249e 1924 # Look for embedded mtvservices player
46fde8a1
S
1925 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1926 if mtvservices_url:
1927 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 1928
49807b4a
S
1929 # Look for embedded yahoo player
1930 mobj = re.search(
1931 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1932 webpage)
1933 if mobj is not None:
1934 return self.url_result(mobj.group('url'), 'Yahoo')
1935
2ef6fcb5
PH
1936 # Look for embedded sbs.com.au player
1937 mobj = re.search(
e98b8e79
PH
1938 r'''(?x)
1939 (?:
1940 <meta\s+property="og:video"\s+content=|
1941 <iframe[^>]+?src=
1942 )
1943 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
1944 webpage)
1945 if mobj is not None:
1946 return self.url_result(mobj.group('url'), 'SBS')
1947
42bdd9d0
PH
1948 # Look for embedded Cinchcast player
1949 mobj = re.search(
1950 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1951 webpage)
1952 if mobj is not None:
1953 return self.url_result(mobj.group('url'), 'Cinchcast')
1954
1a94ff68 1955 mobj = re.search(
5263cdfc 1956 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 1957 webpage)
8001607e
YCH
1958 if not mobj:
1959 mobj = re.search(
1960 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1961 webpage)
1a94ff68
S
1962 if mobj is not None:
1963 return self.url_result(mobj.group('url'), 'MLB')
1964
1419fafd 1965 mobj = re.search(
dd467d33 1966 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
1967 webpage)
1968 if mobj is not None:
1969 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1970
af63fed7 1971 mobj = re.search(
78d3b3e2 1972 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
1973 webpage)
1974 if mobj is not None:
1975 return self.url_result(mobj.group('url'), 'Livestream')
1976
255fca5e
S
1977 # Look for Zapiks embed
1978 mobj = re.search(
1979 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1980 if mobj is not None:
1981 return self.url_result(mobj.group('url'), 'Zapiks')
1982
e3216b82 1983 # Look for Kaltura embeds
c287f2bc
S
1984 kaltura_url = KalturaIE._extract_url(webpage)
1985 if kaltura_url:
1986 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 1987
135c9c42 1988 # Look for Eagle.Platform embeds
06a96da1
S
1989 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
1990 if eagleplatform_url:
1991 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
135c9c42 1992
d47ae7f6
S
1993 # Look for ClipYou (uses Eagle.Platform) embeds
1994 mobj = re.search(
1995 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1996 if mobj is not None:
1997 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1998
f8388757 1999 # Look for Pladform embeds
45dad7ba
S
2000 pladform_url = PladformIE._extract_url(webpage)
2001 if pladform_url:
2002 return self.url_result(pladform_url)
f8388757 2003
ff18735c
S
2004 # Look for Videomore embeds
2005 videomore_url = VideomoreIE._extract_url(webpage)
2006 if videomore_url:
2007 return self.url_result(videomore_url)
2008
2dcc114f
S
2009 # Look for Playwire embeds
2010 mobj = re.search(
2011 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2012 if mobj is not None:
2013 return self.url_result(mobj.group('url'))
2014
ad320e9b
NJ
2015 # Look for 5min embeds
2016 mobj = re.search(
2017 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2018 if mobj is not None:
2019 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2020
18153f1b
S
2021 # Look for Crooks and Liars embeds
2022 mobj = re.search(
2023 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2024 if mobj is not None:
2025 return self.url_result(mobj.group('url'))
2026
a2edf2e7
YCH
2027 # Look for NBC Sports VPlayer embeds
2028 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2029 if nbc_sports_url:
2030 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2031
de3eb07e
YCH
2032 # Look for NBC News embeds
2033 nbc_news_embed_url = re.search(
2034 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2035 if nbc_news_embed_url:
2036 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2037
653789af 2038 # Look for Google Drive embeds
5b251628 2039 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2040 if google_drive_url:
2041 return self.url_result(google_drive_url, 'GoogleDrive')
2042
418c5cc3
YCH
2043 # Look for UDN embeds
2044 mobj = re.search(
c39fd7b1 2045 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2046 if mobj is not None:
2047 return self.url_result(
0a160363 2048 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2049
2fe1b5bd
YCH
2050 # Look for Senate ISVP iframe
2051 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2052 if senate_isvp_url:
25c3a734 2053 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2054
756f574e
YCH
2055 # Look for Dailymotion Cloud videos
2056 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2057 if dmcloud_url:
2058 return self.url_result(dmcloud_url, 'DailymotionCloud')
2059
1ac1c4c2
S
2060 # Look for OnionStudios embeds
2061 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2062 if onionstudios_url:
2063 return self.url_result(onionstudios_url)
2064
67167920 2065 # Look for ViewLift embeds
2066 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2067 if viewlift_url:
2068 return self.url_result(viewlift_url)
eedd20ef 2069
7cb09524 2070 # Look for JWPlatform embeds
2071 jwplatform_url = JWPlatformIE._extract_url(webpage)
2072 if jwplatform_url:
2073 return self.url_result(jwplatform_url, 'JWPlatform')
2074
8ca31a0e 2075 # Look for ScreenwaveMedia embeds
efd712c6 2076 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
8ca31a0e 2077 if mobj is not None:
efd712c6 2078 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
8ca31a0e 2079
aecfcd4e
S
2080 # Look for Digiteka embeds
2081 digiteka_url = DigitekaIE._extract_url(webpage)
2082 if digiteka_url:
2083 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2084
1bf996fa 2085 # Look for Limelight embeds
2086 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2087 if mobj:
2088 lm = {
2089 'Media': 'media',
2090 'Channel': 'channel',
2091 'ChannelList': 'channel_list',
2092 }
2093 return self.url_result('limelight:%s:%s' % (
2094 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2095
a5158f38
YCH
2096 # Look for AdobeTVVideo embeds
2097 mobj = re.search(
2098 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2099 webpage)
2100 if mobj is not None:
2101 return self.url_result(
2102 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2103 'AdobeTVVideo')
2104
088e1aac
YCH
2105 # Look for Vine embeds
2106 mobj = re.search(
2107 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2108 webpage)
2109 if mobj is not None:
2110 return self.url_result(
2111 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2112
5a51775a
YCH
2113 # Look for Instagram embeds
2114 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2115 if instagram_embed_url is not None:
11e60fca
S
2116 return self.url_result(
2117 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2118
b8f67449
KM
2119 # Look for LiveLeak embeds
2120 liveleak_url = LiveLeakIE._extract_url(webpage)
2121 if liveleak_url:
2122 return self.url_result(liveleak_url, 'LiveLeak')
2123
5d39176f
S
2124 # Look for 3Q SDN embeds
2125 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2126 if threeqsdn_url:
6f41b2bc
S
2127 return {
2128 '_type': 'url_transparent',
2129 'ie_key': ThreeQSDNIE.ie_key(),
2130 'url': self._proto_relative_url(threeqsdn_url),
2131 'title': video_title,
2132 'description': video_description,
2133 'thumbnail': video_thumbnail,
2134 'uploader': video_uploader,
2135 }
5d39176f 2136
32917907 2137 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
7dbeee7e 2138 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
32917907
RA
2139 if embed_url:
2140 return self.url_result(embed_url)
2141
ced659bb 2142 def check_video(vurl):
a0f71985
PH
2143 if YoutubeIE.suitable(vurl):
2144 return True
ced659bb
S
2145 vpath = compat_urlparse.urlparse(vurl).path
2146 vext = determine_ext(vpath)
2147 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2148
2149 def filter_video(urls):
2150 return list(filter(check_video, urls))
2151
9b122384 2152 # Start with something easy: JW Player in SWFObject
ced659bb 2153 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 2154 if not found:
d981cef6 2155 # Look for gorilla-vid style embedding
ced659bb 2156 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
2157 (?:
2158 jw_plugins|
2159 JWPlayerOptions|
2160 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2161 )
a0f71985
PH
2162 .*?
2163 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 2164 if not found:
9b122384 2165 # Broaden the search a little bit
ced659bb 2166 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
2167 if not found:
2168 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 2169 found = filter_video(re.findall(
54a9328b 2170 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
2171 if not found:
2172 # Flow player
ced659bb 2173 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
2174 flowplayer\("[^"]+",\s*
2175 \{[^}]+?\}\s*,
52585fd6 2176 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 2177 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 2178 ''', webpage))
501f13fb
PH
2179 if not found:
2180 # Cinerama player
2181 found = re.findall(
2182 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 2183 if not found:
9b122384 2184 # Try to find twitter cards info
ced659bb
S
2185 found = filter_video(re.findall(
2186 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 2187 if not found:
9b122384
PH
2188 # We look for Open Graph info:
2189 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 2190 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
2191 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2192 if m_video_type is not None:
ced659bb 2193 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 2194 if not found:
7fea7156 2195 # HTML5 video
12439dd5 2196 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
b30b8698 2197 if not found:
ed9a25dd 2198 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 2199 found = re.search(
89ef304b 2200 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 2201 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 2202 webpage)
84f81016
S
2203 if not found:
2204 # Look also in Refresh HTTP header
2205 refresh_header = head_response.headers.get('Refresh')
2206 if refresh_header:
6c91a5a7
S
2207 # In python 2 response HTTP headers are bytestrings
2208 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2209 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 2210 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 2211 if found:
b37317d8 2212 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
89ef304b
PH
2213 self.report_following_redirect(new_url)
2214 return {
2215 '_type': 'url',
2216 'url': new_url,
2217 }
b30b8698 2218 if not found:
416c7fcb 2219 raise UnsupportedError(url)
9b122384 2220
b30b8698 2221 entries = []
4a120778 2222 for video_url in orderedSet(found):
949b6497 2223 video_url = unescapeHTML(video_url)
6cc37c69 2224 video_url = video_url.replace('\\/', '/')
b30b8698 2225 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 2226 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 2227
b30b8698
PH
2228 # Sometimes, jwplayer extraction will result in a YouTube URL
2229 if YoutubeIE.suitable(video_url):
2230 entries.append(self.url_result(video_url, 'Youtube'))
2231 continue
9b122384 2232
b30b8698
PH
2233 # here's a fun little line of code for you:
2234 video_id = os.path.splitext(video_id)[0]
fc9713a1 2235
28602e74
YCH
2236 entry_info_dict = {
2237 'id': video_id,
2238 'uploader': video_uploader,
2239 'title': video_title,
2240 'age_limit': age_limit,
2241 }
2242
729accb4
S
2243 ext = determine_ext(video_url)
2244 if ext == 'smil':
28602e74 2245 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
2246 elif ext == 'xspf':
2247 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
2248 elif ext == 'm3u8':
2249 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
2250 elif ext == 'mpd':
2251 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
2252 elif ext == 'f4m':
2253 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
d6fd958c 2254 else:
28602e74
YCH
2255 entry_info_dict['url'] = video_url
2256
19dbaeec
S
2257 if entry_info_dict.get('formats'):
2258 self._sort_formats(entry_info_dict['formats'])
2259
28602e74 2260 entries.append(entry_info_dict)
b30b8698
PH
2261
2262 if len(entries) == 1:
669f0e7c 2263 return entries[0]
b30b8698
PH
2264 else:
2265 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
2266 # 'url' results don't have a title
2267 if e.get('title') is not None:
2268 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
2269 return {
2270 '_type': 'playlist',
2271 'entries': entries,
2272 }