]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[extractor/generic] Detect DASH manifests and extract mpd formats
[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
b407e173 50from .vimeo import VimeoIE
756f574e 51from .dailymotion import DailymotionCloudIE
1ac1c4c2 52from .onionstudios import OnionStudiosIE
eedd20ef 53from .snagfilms import SnagFilmsEmbedIE
efd712c6 54from .screenwavemedia import ScreenwaveMediaIE
46fde8a1 55from .mtv import MTVServicesEmbeddedIE
45dad7ba 56from .pladform import PladformIE
ff18735c 57from .videomore import VideomoreIE
5b251628 58from .googledrive import GoogleDriveIE
7cb09524 59from .jwplatform import JWPlatformIE
aecfcd4e 60from .digiteka import DigitekaIE
9b122384 61
0838239e 62
9b122384 63class GenericIE(InfoExtractor):
79649588 64 IE_DESC = 'Generic downloader that works on some sites'
9b122384 65 _VALID_URL = r'.*'
79649588 66 IE_NAME = 'generic'
cfe50f04 67 _TESTS = [
c5fa81fe
S
68 # Direct link to a video
69 {
70 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
71 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
72 'info_dict': {
73 'id': 'trailer',
74 'ext': 'mp4',
75 'title': 'trailer',
76 'upload_date': '20100513',
77 }
78 },
c5138a7c 79 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
80 {
81 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
82 'md5': '128c42e68b13950268b648275386fc74',
83 'info_dict': {
84 'id': 'FictionJunction-Parallel_Hearts',
85 'ext': 'flac',
86 'title': 'FictionJunction-Parallel_Hearts',
87 'upload_date': '20140522',
88 },
89 'expected_warnings': [
90 'URL could be a direct video link, returning it as such.'
91 ]
92 },
93 # Direct download with broken HEAD
94 {
95 'url': 'http://ai-radio.org:8000/radio.opus',
96 'info_dict': {
97 'id': 'radio',
98 'ext': 'opus',
99 'title': 'radio',
100 },
101 'params': {
102 'skip_download': True, # infinite live stream
103 },
104 'expected_warnings': [
105 r'501.*Not Implemented'
106 ],
107 },
108 # Direct link with incorrect MIME type
109 {
110 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
111 'md5': '4ccbebe5f36706d85221f204d7eb5913',
112 'info_dict': {
113 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
114 'id': '5_Lennart_Poettering_-_Systemd',
115 'ext': 'webm',
116 'title': '5_Lennart_Poettering_-_Systemd',
117 'upload_date': '20141120',
118 },
119 'expected_warnings': [
120 'URL could be a direct video link, returning it as such.'
121 ]
122 },
123 # RSS feed
124 {
125 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
126 'info_dict': {
127 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
128 'title': 'Zero Punctuation',
129 'description': 're:.*groundbreaking video review series.*'
130 },
131 'playlist_mincount': 11,
132 },
133 # RSS feed with enclosure
134 {
135 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
136 'info_dict': {
137 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
138 'ext': 'm4v',
139 'upload_date': '20150228',
140 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
141 }
142 },
8765222d
S
143 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
144 {
145 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
146 'info_dict': {
147 'id': 'smil',
148 'ext': 'mp4',
149 'title': 'Automatics, robotics and biocybernetics',
150 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 151 'upload_date': '20130627',
8765222d
S
152 'formats': 'mincount:16',
153 'subtitles': 'mincount:1',
154 },
155 'params': {
156 'force_generic_extractor': True,
157 'skip_download': True,
158 },
159 },
160 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
161 {
162 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
163 'info_dict': {
164 'id': 'hds',
165 'ext': 'flv',
166 'title': 'hds',
167 'formats': 'mincount:1',
168 },
169 'params': {
170 'skip_download': True,
171 },
172 },
173 # SMIL from https://www.restudy.dk/video/play/id/1637
174 {
175 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
176 'info_dict': {
177 'id': 'video_1637',
178 'ext': 'flv',
179 'title': 'video_1637',
180 'formats': 'mincount:3',
181 },
182 'params': {
183 'skip_download': True,
184 },
185 },
186 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
187 {
188 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
189 'info_dict': {
190 'id': 'smil-service',
191 'ext': 'flv',
192 'title': 'smil-service',
193 'formats': 'mincount:1',
194 },
195 'params': {
196 'skip_download': True,
197 },
198 },
199 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
200 {
201 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
202 'info_dict': {
203 'id': '4719370',
204 'ext': 'mp4',
205 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
206 'formats': 'mincount:3',
207 },
208 'params': {
209 'skip_download': True,
210 },
211 },
1de5cd3b
S
212 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
213 {
214 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
215 'info_dict': {
216 'id': 'mZlp2ctYIUEB',
217 'ext': 'mp4',
218 'title': 'Tikibad ontruimd wegens brand',
219 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
220 'thumbnail': 're:^https?://.*\.jpg$',
221 'duration': 33,
222 },
223 'params': {
224 'skip_download': True,
225 },
226 },
c5fa81fe
S
227 # google redirect
228 {
229 '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',
230 'info_dict': {
231 'id': 'cmQHVoWB5FY',
232 'ext': 'mp4',
233 'upload_date': '20130224',
234 'uploader_id': 'TheVerge',
235 'description': 're:^Chris Ziegler takes a look at the\.*',
236 'uploader': 'The Verge',
237 'title': 'First Firefox OS phones side-by-side',
238 },
239 'params': {
240 'skip_download': False,
241 }
242 },
6c91a5a7
S
243 {
244 # redirect in Refresh HTTP header
245 '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',
246 'info_dict': {
247 'id': 'pO8h3EaFRdo',
248 'ext': 'mp4',
249 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
250 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
251 'upload_date': '20150917',
252 'uploader_id': 'brtvofficial',
253 'uploader': 'Boiler Room',
254 },
255 'params': {
256 'skip_download': False,
257 },
258 },
cfe50f04 259 {
79649588 260 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 261 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 262 'info_dict': {
d360a146
S
263 'id': '13601338388002',
264 'ext': 'mp4',
79649588
PH
265 'uploader': 'www.hodiho.fr',
266 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
267 }
268 },
c19f7764
JMF
269 # bandcamp page with custom domain
270 {
79649588
PH
271 'add_ie': ['Bandcamp'],
272 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 273 'info_dict': {
fd50bf62
S
274 'id': '3235767654',
275 'ext': 'mp3',
79649588
PH
276 'title': 'The Pony Mash',
277 'uploader': 'M_Pallante',
c19f7764 278 },
79649588 279 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 280 },
eeb165e6 281 # embedded brightcove video
dd5bcdc4
JMF
282 # it also tests brightcove videos that need to set the 'Referer' in the
283 # http requests
eeb165e6 284 {
3b7d9aa4 285 'add_ie': ['BrightcoveLegacy'],
79649588
PH
286 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
287 'info_dict': {
288 'id': '2765128793001',
289 'ext': 'mp4',
290 'title': 'Le cours de bourse : l’analyse technique',
291 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
292 'uploader': 'BFM BUSINESS',
eeb165e6 293 },
79649588
PH
294 'params': {
295 'skip_download': True,
eeb165e6
JMF
296 },
297 },
17ab4d3b
PH
298 {
299 # https://github.com/rg3/youtube-dl/issues/2253
300 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
301 'md5': '0ba9446db037002366bab3b3eb30c88c',
302 'info_dict': {
fd50bf62
S
303 'id': '3101154703001',
304 'ext': 'mp4',
17ab4d3b
PH
305 'title': 'Still no power',
306 'uploader': 'thestar.com',
307 '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.',
308 },
3b7d9aa4 309 'add_ie': ['BrightcoveLegacy'],
17ab4d3b 310 },
0479c625
S
311 {
312 'url': 'http://www.championat.com/video/football/v/87/87499.html',
313 'md5': 'fb973ecf6e4a78a67453647444222983',
314 'info_dict': {
315 'id': '3414141473001',
316 'ext': 'mp4',
317 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
318 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
319 'uploader': 'Championat',
320 },
321 },
bdf97017 322 {
37aab278 323 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 324 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
325 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
326 'info_dict': {
327 'id': '3866516442001',
37aab278 328 'ext': 'mp4',
bdf97017
NJ
329 'title': 'Leer mij vrouwen kennen: Aflevering 1',
330 'description': 'Leer mij vrouwen kennen: Aflevering 1',
331 'uploader': 'SBS Broadcasting',
332 },
37aab278 333 'skip': 'Restricted to Netherlands',
bdf97017 334 'params': {
37aab278 335 'skip_download': True, # m3u8 download
bdf97017
NJ
336 },
337 },
c0d0b01f
JMF
338 # ooyala video
339 {
79649588 340 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 341 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
342 'info_dict': {
343 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
344 'ext': 'mp4',
3486df38 345 'title': '2cc213299525360.mov', # that's what we get
53e06b25 346 'duration': 238.231,
c0d0b01f 347 },
87830900 348 'add_ie': ['Ooyala'],
c0d0b01f 349 },
bf94d763
S
350 {
351 # ooyala video embedded with http://player.ooyala.com/iframe.js
352 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
353 'info_dict': {
354 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
355 'ext': 'mp4',
356 'title': '"Steve Jobs: Man in the Machine" trailer',
357 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 358 'duration': 135.427,
bf94d763
S
359 },
360 'params': {
361 'skip_download': True,
362 },
363 },
f076b638 364 # multiple ooyala embeds on SBN network websites
365 {
366 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
367 'info_dict': {
368 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
369 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
370 },
371 'playlist_mincount': 3,
372 'params': {
373 'skip_download': True,
374 },
375 'add_ie': ['Ooyala'],
376 },
1b86cc41 377 # embed.ly video
378 {
379 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
380 'info_dict': {
381 'id': '9ODmcdjQcHQ',
382 'ext': 'mp4',
0a5bce56
PH
383 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
384 'upload_date': '20140225',
385 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
386 'uploader': 'Tested',
387 'uploader_id': 'testedcom',
1b86cc41 388 },
389 # No need to test YoutubeIE here
390 'params': {
391 'skip_download': True,
392 },
393 },
60cc4dc4
PH
394 # funnyordie embed
395 {
396 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
397 'info_dict': {
398 'id': '18e820ec3f',
399 'ext': 'mp4',
400 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
401 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 402 },
60cc4dc4 403 },
93d020dd
S
404 # RUTV embed
405 {
406 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
407 'info_dict': {
408 'id': '776940',
409 'ext': 'mp4',
410 'title': 'Охотское море стало целиком российским',
411 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
412 },
413 'params': {
414 # m3u8 download
415 'skip_download': True,
416 },
aab74fa1 417 },
f37bdbe5
S
418 # TVC embed
419 {
420 '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/',
421 'info_dict': {
422 'id': '55304',
423 'ext': 'mp4',
424 'title': 'Дошкольное воспитание',
425 },
426 },
b827a601
S
427 # SportBox embed
428 {
429 'url': 'http://www.vestifinance.ru/articles/25753',
430 'info_dict': {
431 'id': '25753',
432 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
433 },
434 'playlist': [{
435 'info_dict': {
436 'id': '370908',
437 'title': 'Госзаказ. День 3',
438 'ext': 'mp4',
439 }
440 }, {
441 'info_dict': {
442 'id': '370905',
443 'title': 'Госзаказ. День 2',
444 'ext': 'mp4',
445 }
446 }, {
447 'info_dict': {
448 'id': '370902',
449 'title': 'Госзаказ. День 1',
450 'ext': 'mp4',
451 }
452 }],
453 'params': {
454 # m3u8 download
455 'skip_download': True,
456 },
457 },
bf20b9c5
S
458 # Myvi.ru embed
459 {
460 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
461 'info_dict': {
462 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
463 'ext': 'mp4',
464 'title': 'Ужастики, русский трейлер (2015)',
465 'thumbnail': 're:^https?://.*\.jpg$',
466 'duration': 153,
467 }
468 },
c76799c5
S
469 # XHamster embed
470 {
471 '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',
472 'info_dict': {
473 'id': 'showthread',
474 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
475 },
476 'playlist_mincount': 7,
477 },
aab74fa1
PH
478 # Embedded TED video
479 {
480 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 481 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 482 'info_dict': {
a8eb5a8e 483 'id': '1969',
aab74fa1 484 'ext': 'mp4',
a8eb5a8e
PH
485 'title': 'Hidden miracles of the natural world',
486 'uploader': 'Louie Schwartzberg',
487 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 488 }
60cc4dc4 489 },
dfb1b146 490 # Embedded Ustream video
5c386252 491 {
492 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
493 'md5': '27b99cdb639c9b12a79bca876a073417',
494 'info_dict': {
ca6aada4 495 'id': '45734260',
496 'ext': 'flv',
497 'uploader': 'AU SPA: The NSA and Privacy',
5c386252 498 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
499 }
500 },
d95e35d6
S
501 # nowvideo embed hidden behind percent encoding
502 {
503 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
504 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
505 'info_dict': {
506 'id': '06e53103ca9aa',
507 'ext': 'flv',
508 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
509 'description': 'No description',
510 },
0f2a2ba1 511 },
893f8832
PH
512 # arte embed
513 {
514 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
515 'md5': '7653032cbb25bf6c80d80f217055fa43',
516 'info_dict': {
517 'id': '048195-004_PLUS7-F',
518 'ext': 'flv',
519 'title': 'X:enius',
520 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
521 'upload_date': '20140320',
522 },
523 'params': {
524 'skip_download': 'Requires rtmpdump'
525 }
526 },
cbd55ade
S
527 # francetv embed
528 {
529 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
530 'info_dict': {
531 'id': 'EV_30231',
532 'ext': 'mp4',
533 'title': 'Alcaline, le concert avec Calogero',
534 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
535 'upload_date': '20150226',
536 'timestamp': 1424989860,
537 'duration': 5400,
538 },
539 'params': {
540 # m3u8 downloads
541 'skip_download': True,
542 },
543 'expected_warnings': [
544 'Forbidden'
545 ]
546 },
fa35cdad
PH
547 # Condé Nast embed
548 {
549 'url': 'http://www.wired.com/2014/04/honda-asimo/',
550 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
551 'info_dict': {
552 'id': '53501be369702d3275860000',
553 'ext': 'mp4',
554 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
555 }
ebd3c7b3
PH
556 },
557 # Dailymotion embed
558 {
559 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
560 'md5': '441aeeb82eb72c422c7f14ec533999cd',
561 'info_dict': {
562 'id': 'k2mm4bCdJ6CQ2i7c8o2',
563 'ext': 'mp4',
564 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
565 'uploader': 'Spi0n',
566 },
567 'add_ie': ['Dailymotion'],
2b88feed
PH
568 },
569 # YouTube embed
570 {
571 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
572 'info_dict': {
573 'id': 'FXRb4ykk4S0',
574 'ext': 'mp4',
575 'title': 'The NBL Auction 2014',
576 'uploader': 'BADMINTON England',
577 'uploader_id': 'BADMINTONEvents',
578 'upload_date': '20140603',
579 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
580 },
581 'add_ie': ['Youtube'],
582 'params': {
583 'skip_download': True,
584 }
585 },
c5cd249e
JMF
586 # MTVSercices embed
587 {
588 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
589 'md5': '35727f82f58c76d996fc188f9755b0d5',
590 'info_dict': {
591 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
592 'ext': 'mp4',
593 'title': 'Review',
594 'description': 'Mario\'s life in the fast lane has never looked so good.',
595 },
596 },
61013473 597 # YouTube embed via <data-embed-url="">
598 {
599 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 600 'info_dict': {
a8eb5a8e 601 'id': '4vAffPZIT44',
61013473 602 'ext': 'mp4',
a8eb5a8e 603 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
604 'uploader': 'Gameloft',
605 'uploader_id': 'gameloft',
a8eb5a8e
PH
606 'upload_date': '20140828',
607 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
608 },
609 'params': {
610 'skip_download': True,
61013473 611 }
c8e9a235
PH
612 },
613 # Camtasia studio
614 {
615 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
616 'playlist': [{
617 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
618 'info_dict': {
619 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
620 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
621 'ext': 'flv',
622 'duration': 2235.90,
623 }
624 }, {
625 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
626 'info_dict': {
627 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
628 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
629 'ext': 'flv',
630 'duration': 2235.93,
631 }
632 }],
633 'info_dict': {
634 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
635 }
4d805e06
PH
636 },
637 # Flowplayer
638 {
639 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
640 'md5': '9d65602bf31c6e20014319c7d07fba27',
641 'info_dict': {
642 'id': '5123ea6d5e5a7',
643 'ext': 'mp4',
644 'age_limit': 18,
645 'uploader': 'www.handjobhub.com',
d6d9186f 646 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 647 }
0990305d 648 },
22a6f150
PH
649 # Multiple brightcove videos
650 # https://github.com/rg3/youtube-dl/issues/2283
651 {
652 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
653 'info_dict': {
654 'id': 'always-never',
655 'title': 'Always / Never - The New Yorker',
656 },
657 'playlist_count': 3,
658 'params': {
659 'extract_flat': False,
660 'skip_download': True,
661 }
1a94ff68
S
662 },
663 # MLB embed
664 {
665 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
666 'md5': '96f09a37e44da40dd083e12d9a683327',
667 'info_dict': {
668 'id': '33322633',
669 'ext': 'mp4',
670 'title': 'Ump changes call to ball',
671 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
672 'duration': 48,
673 'timestamp': 1401537900,
674 'upload_date': '20140531',
675 'thumbnail': 're:^https?://.*\.jpg$',
676 },
677 },
746c67d7
NJ
678 # Wistia embed
679 {
680 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
681 'md5': '8788b683c777a5cf25621eaf286d0c23',
682 'info_dict': {
683 'id': '1cfaf6b7ea',
684 'ext': 'mov',
685 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
686 'duration': 643.0,
687 'filesize': 182808282,
688 'uploader': 'education-portal.com',
689 },
690 },
52cffcb1 691 {
692 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
693 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
694 'info_dict': {
695 'id': 'uxjb0lwrcz',
696 'ext': 'mp4',
85d7b765 697 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
52cffcb1 698 'duration': 1715.0,
85d7b765 699 'uploader': 'thoughtworks.wistia.com',
70b7e3fb 700 },
52cffcb1 701 },
ac645ac7
PH
702 # Soundcloud embed
703 {
704 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
705 'info_dict': {
706 'id': '174391317',
707 'ext': 'mp3',
708 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
709 'uploader': 'Sophos Security',
710 'title': 'Chet Chat 171 - Oct 29, 2014',
711 'upload_date': '20141029',
712 }
af63fed7
PH
713 },
714 # Livestream embed
715 {
716 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
717 'info_dict': {
718 'id': '67864563',
719 'ext': 'flv',
720 'upload_date': '20141112',
721 'title': 'Rosetta #CometLanding webcast HL 10',
722 }
723 },
65f3a228
PH
724 # LazyYT
725 {
726 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
727 'info_dict': {
11e611a7 728 'id': '1986',
65f3a228
PH
729 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
730 },
731 'playlist_mincount': 2,
4e262a88 732 },
42bdd9d0
PH
733 # Cinchcast embed
734 {
735 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
736 'info_dict': {
737 'id': '7141703',
738 'ext': 'mp3',
739 'upload_date': '20141126',
740 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
741 }
742 },
501f13fb
PH
743 # Cinerama player
744 {
745 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
746 'info_dict': {
747 'id': '730m_DandD_1901_512k',
748 'ext': 'mp4',
749 'uploader': 'www.abc.net.au',
750 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
751 }
796df3c6
S
752 },
753 # embedded viddler video
754 {
755 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
756 'info_dict': {
757 'id': '4d03aad9',
758 'ext': 'mp4',
759 'uploader': 'deadspin',
760 'title': 'WALL-TO-GORTAT',
761 'timestamp': 1422285291,
762 'upload_date': '20150126',
763 },
764 'add_ie': ['Viddler'],
a0f71985 765 },
2051acde
S
766 # Libsyn embed
767 {
768 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
769 'info_dict': {
770 'id': '3377616',
771 'ext': 'mp3',
772 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
773 'description': 'md5:601cb790edd05908957dae8aaa866465',
774 'upload_date': '20150220',
775 },
776 },
a0f71985
PH
777 # jwplayer YouTube
778 {
779 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
780 'info_dict': {
781 'id': 'Mrj4DVp2zeA',
782 'ext': 'mp4',
f37e3f99 783 'upload_date': '20150212',
a0f71985
PH
784 'uploader': 'The National Archives UK',
785 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
786 'uploader_id': 'NationalArchives08',
787 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
788 },
59b8ab58
PH
789 },
790 # rtl.nl embed
791 {
792 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
793 'playlist_mincount': 5,
794 'info_dict': {
795 'id': 'aanslagen-kopenhagen',
796 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
797 }
255fca5e
S
798 },
799 # Zapiks embed
800 {
801 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
802 'info_dict': {
803 'id': '118046',
804 'ext': 'mp4',
805 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
806 }
807 },
e3216b82
NJ
808 # Kaltura embed
809 {
810 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
811 'info_dict': {
812 'id': '1_eergr3h1',
813 'ext': 'mp4',
814 'upload_date': '20150226',
815 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
816 'timestamp': int,
817 'title': 'John Carlson Postgame 2/25/15',
818 },
819 },
66e568de
S
820 # Kaltura embed (different embed code)
821 {
822 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
823 'info_dict': {
824 'id': '1_a52wc67y',
825 'ext': 'flv',
826 'upload_date': '20150127',
827 'uploader_id': 'PremierMedia',
828 'timestamp': int,
829 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
830 },
831 },
6da620de
S
832 # Kaltura embed protected with referrer
833 {
834 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
835 'info_dict': {
836 'id': '1_g4fbemnq',
837 'ext': 'mp4',
838 'title': 'Violetta - Achter De Schermen - Ruggero',
839 'description': 'Achter de schermen met Ruggero',
840 'timestamp': 1435133761,
841 'upload_date': '20150624',
842 'uploader_id': 'echojecka',
843 },
844 },
135c9c42
S
845 # Eagle.Platform embed (generic URL)
846 {
847 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
848 'info_dict': {
849 'id': '227304',
850 'ext': 'mp4',
851 'title': 'Навальный вышел на свободу',
852 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
853 'thumbnail': 're:^https?://.*\.jpg$',
854 'duration': 87,
855 'view_count': int,
856 'age_limit': 0,
857 },
858 },
d47ae7f6
S
859 # ClipYou (Eagle.Platform) embed (custom URL)
860 {
861 'url': 'http://muz-tv.ru/play/7129/',
862 'info_dict': {
863 'id': '12820',
864 'ext': 'mp4',
865 'title': "'O Sole Mio",
866 'thumbnail': 're:^https?://.*\.jpg$',
867 'duration': 216,
868 'view_count': int,
869 },
870 },
f8388757
S
871 # Pladform embed
872 {
873 'url': 'http://muz-tv.ru/kinozal/view/7400/',
874 'info_dict': {
875 'id': '100183293',
876 'ext': 'mp4',
62259846 877 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757
S
878 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
879 'thumbnail': 're:^https?://.*\.jpg$',
880 'duration': 694,
881 'age_limit': 0,
882 },
883 },
c798f15b
S
884 # Playwire embed
885 {
886 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
887 'info_dict': {
888 'id': '3519514',
889 'ext': 'mp4',
890 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
891 'thumbnail': 're:^https?://.*\.png$',
892 'duration': 45.115,
893 },
894 },
ad320e9b
NJ
895 # 5min embed
896 {
897 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
898 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
899 'info_dict': {
900 'id': '518726732',
901 'ext': 'mp4',
902 'title': 'Facebook Creates "On This Day" | Crunch Report',
903 },
904 },
dc455a5f
S
905 # SVT embed
906 {
907 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
908 'info_dict': {
909 'id': '2900353',
910 'ext': 'flv',
911 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
912 'duration': 27,
913 'age_limit': 0,
914 },
915 },
a4257017
S
916 # Crooks and Liars embed
917 {
918 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
919 'info_dict': {
920 'id': '8RUoRhRi',
921 'ext': 'mp4',
922 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
923 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
924 'timestamp': 1428207000,
925 'upload_date': '20150405',
926 'uploader': 'Heather',
927 },
928 },
929 # Crooks and Liars external embed
930 {
931 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
932 'info_dict': {
933 'id': 'MTE3MjUtMzQ2MzA',
934 'ext': 'mp4',
935 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
936 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
937 'timestamp': 1265032391,
938 'upload_date': '20100201',
939 'uploader': 'Heather',
940 },
941 },
facecb84 942 # NBC Sports vplayer embed
a2edf2e7 943 {
facecb84 944 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 945 'info_dict': {
facecb84
S
946 'id': 'ln7x1qSThw4k',
947 'ext': 'flv',
948 'title': "PFT Live: New leader in the 'new-look' defense",
949 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
a2edf2e7 950 },
418c5cc3
YCH
951 },
952 # UDN embed
953 {
954 'url': 'http://www.udn.com/news/story/7314/822787',
01c58f84 955 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 956 'info_dict': {
01c58f84 957 'id': '300346',
418c5cc3 958 'ext': 'mp4',
01c58f84 959 'title': '中一中男師變性 全校師生力挺',
418c5cc3
YCH
960 'thumbnail': 're:^https?://.*\.jpg$',
961 }
edfcf7ab
YCH
962 },
963 # Ooyala embed
964 {
965 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
966 'info_dict': {
967 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
968 'ext': 'mp4',
cce9d15d 969 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
edfcf7ab 970 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 971 'duration': 191.933,
edfcf7ab
YCH
972 },
973 'params': {
974 # m3u8 downloads
975 'skip_download': True,
976 }
d6fd958c
YCH
977 },
978 # Contains a SMIL manifest
979 {
980 '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',
981 'info_dict': {
982 'id': 'file',
983 'ext': 'flv',
984 'title': '+ Football: Lottery Champions League Europe',
985 'uploader': 'www.telewebion.com',
986 },
987 'params': {
988 # rtmpe downloads
989 'skip_download': True,
990 }
b26733ba
YCH
991 },
992 # Brightcove URL in single quotes
993 {
994 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
995 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
996 'info_dict': {
997 'id': '4255764656001',
998 'ext': 'mp4',
999 'title': 'SN Presents: Russell Martin, World Citizen',
1000 '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.',
1001 'uploader': 'Rogers Sportsnet',
1002 },
756f574e
YCH
1003 },
1004 # Dailymotion Cloud video
1005 {
1006 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1007 'md5': '49444254273501a64675a7e68c502681',
1008 'info_dict': {
1009 'id': '5585de919473990de4bee11b',
1010 'ext': 'mp4',
1011 'title': 'Le débat',
1012 'thumbnail': 're:^https?://.*\.jpe?g$',
1013 }
a5158f38 1014 },
8084be78
S
1015 # OnionStudios embed
1016 {
1017 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1018 'info_dict': {
1019 'id': '2855',
1020 'ext': 'mp4',
1021 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1022 'thumbnail': 're:^https?://.*\.jpe?g$',
1023 'uploader': 'ClickHole',
1024 'uploader_id': 'clickhole',
1025 }
1026 },
b8c1cc1a
S
1027 # SnagFilms embed
1028 {
1029 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1030 'info_dict': {
1031 'id': '74849a00-85a9-11e1-9660-123139220831',
1032 'ext': 'mp4',
1033 'title': '#whilewewatch',
1034 }
1035 },
a5158f38
YCH
1036 # AdobeTVVideo embed
1037 {
1038 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1039 'md5': '43662b577c018ad707a63766462b1e87',
1040 'info_dict': {
1041 'id': '2456',
1042 'ext': 'mp4',
1043 'title': 'New experience with Acrobat DC',
1044 'description': 'New experience with Acrobat DC',
1045 'duration': 248.667,
1046 },
1f812580
S
1047 },
1048 # ScreenwaveMedia embed
1049 {
1050 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1051 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1052 'info_dict': {
1053 'id': 'cinemasnob-55d26273809dd',
1054 'ext': 'mp4',
1055 'title': 'cinemasnob',
1056 },
ed126900 1057 },
1058 # BrightcoveInPageEmbed embed
1059 {
1060 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1061 'info_dict': {
1062 'id': '4238694884001',
1063 'ext': 'flv',
1064 'title': 'Tabletop: Dread, Last Thoughts',
1065 'description': 'Tabletop: Dread, Last Thoughts',
1066 'duration': 51690,
1067 },
750b9ff0
YCH
1068 },
1069 # JWPlayer with M3U8
1070 {
1071 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1072 'info_dict': {
1073 'id': 'playlist',
1074 'ext': 'mp4',
1075 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1076 'uploader': 'ren.tv',
1077 },
1078 'params': {
1079 # m3u8 downloads
1080 'skip_download': True,
1081 }
76c73715 1082 }
cfe50f04 1083 ]
9b122384 1084
9b122384
PH
1085 def report_following_redirect(self, new_url):
1086 """Report information extraction."""
79649588 1087 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1088
4fc946b5
PH
1089 def _extract_rss(self, url, video_id, doc):
1090 playlist_title = doc.find('./channel/title').text
1091 playlist_desc_el = doc.find('./channel/description')
1092 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1093
76c73715
PH
1094 entries = []
1095 for it in doc.findall('./channel/item'):
1096 next_url = xpath_text(it, 'link', fatal=False)
1097 if not next_url:
1098 enclosure_nodes = it.findall('./enclosure')
1099 for e in enclosure_nodes:
1100 next_url = e.attrib.get('url')
1101 if next_url:
1102 break
1103
1104 if not next_url:
1105 continue
1106
1107 entries.append({
1108 '_type': 'url',
1109 'url': next_url,
1110 'title': it.find('title').text,
1111 })
4fc946b5
PH
1112
1113 return {
1114 '_type': 'playlist',
1115 'id': url,
1116 'title': playlist_title,
1117 'description': playlist_desc,
1118 'entries': entries,
1119 }
1120
c8e9a235
PH
1121 def _extract_camtasia(self, url, video_id, webpage):
1122 """ Returns None if no camtasia video can be found. """
1123
1124 camtasia_cfg = self._search_regex(
1125 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1126 webpage, 'camtasia configuration file', default=None)
1127 if camtasia_cfg is None:
1128 return None
1129
1130 title = self._html_search_meta('DC.title', webpage, fatal=True)
1131
1132 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1133 camtasia_cfg = self._download_xml(
1134 camtasia_url, video_id,
1135 note='Downloading camtasia configuration',
1136 errnote='Failed to download camtasia configuration')
1137 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1138
1139 entries = []
1140 for n in fileset_node.getchildren():
1141 url_n = n.find('./uri')
1142 if url_n is None:
1143 continue
1144
1145 entries.append({
1146 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1147 'title': '%s - %s' % (title, n.tag),
1148 'url': compat_urlparse.urljoin(url, url_n.text),
1149 'duration': float_or_none(n.find('./duration').text),
1150 })
1151
1152 return {
1153 '_type': 'playlist',
1154 'entries': entries,
1155 'title': title,
1156 }
1157
9b122384 1158 def _real_extract(self, url):
ebd3c7b3
PH
1159 if url.startswith('//'):
1160 return {
1161 '_type': 'url',
20991253 1162 'url': self.http_scheme() + url,
ebd3c7b3
PH
1163 }
1164
a7130543
JMF
1165 parsed_url = compat_urlparse.urlparse(url)
1166 if not parsed_url.scheme:
04b4d394
PH
1167 default_search = self._downloader.params.get('default_search')
1168 if default_search is None:
1f7ccb90 1169 default_search = 'fixup_error'
04b4d394 1170
1f7ccb90 1171 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
1172 if '/' in url:
1173 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1174 return self.url_result('http://' + url)
1f7ccb90 1175 elif default_search != 'fixup_error':
9c1fc022 1176 if default_search == 'auto_warning':
0e67ab0d
PH
1177 if re.match(r'^(?:url|URL)$', url):
1178 raise ExtractorError(
1179 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1180 expected=True)
1181 else:
1182 self._downloader.report_warning(
7571c02c 1183 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 1184 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
1185
1186 if default_search in ('error', 'fixup_error'):
7571c02c 1187 raise ExtractorError(
b74e86f4
PH
1188 '%r is not a valid URL. '
1189 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1190 % (url, url), expected=True)
04b4d394 1191 else:
f2f2c0c2
PH
1192 if ':' not in default_search:
1193 default_search += ':'
04b4d394 1194 return self.url_result(default_search + url)
4d54ef20
PH
1195
1196 url, smuggled_data = unsmuggle_url(url)
1197 force_videoid = None
d6e6a422 1198 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
1199 if smuggled_data and 'force_videoid' in smuggled_data:
1200 force_videoid = smuggled_data['force_videoid']
1201 video_id = force_videoid
1202 else:
1ddb9456 1203 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
a7130543 1204
79649588 1205 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 1206
ebab4520 1207 head_req = HEADRequest(url)
23be51d8 1208 head_response = self._request_webpage(
ebab4520
PH
1209 head_req, video_id,
1210 note=False, errnote='Could not send HEAD request to %s' % url,
1211 fatal=False)
42393ce2 1212
23be51d8 1213 if head_response is not False:
42393ce2 1214 # Check for redirect
23be51d8 1215 new_url = head_response.geturl()
42393ce2
PH
1216 if url != new_url:
1217 self.report_following_redirect(new_url)
4d54ef20
PH
1218 if force_videoid:
1219 new_url = smuggle_url(
1220 new_url, {'force_videoid': force_videoid})
cecaaf3f 1221 return self.url_result(new_url)
42393ce2 1222
23be51d8
PH
1223 full_response = None
1224 if head_response is False:
5c2266df 1225 request = sanitized_Request(url)
58bde34a
S
1226 request.add_header('Accept-Encoding', '*')
1227 full_response = self._request_webpage(request, video_id)
23be51d8
PH
1228 head_response = full_response
1229
1230 # Check for direct link to a video
1231 content_type = head_response.headers.get('Content-Type', '')
bcbbb98b 1232 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|dash\+xml|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
23be51d8
PH
1233 if m:
1234 upload_date = unified_strdate(
1235 head_response.headers.get('Last-Modified'))
eadc3ccd 1236 formats = []
1237 if m.group('format_id').endswith('mpegurl'):
1238 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
bcbbb98b 1239 elif m.group('format_id').startswith('dash+xml'):
1240 formats = self._extract_mpd_formats(url, video_id)
eadc3ccd 1241 else:
1242 formats = [{
1243 'format_id': m.group('format_id'),
1244 'url': url,
1245 'vcodec': 'none' if m.group('type') == 'audio' else None
1246 }]
23be51d8
PH
1247 return {
1248 'id': video_id,
1ddb9456 1249 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
ccdd0ffb 1250 'direct': True,
eadc3ccd 1251 'formats': formats,
23be51d8
PH
1252 'upload_date': upload_date,
1253 }
42393ce2 1254
d6e6a422 1255 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
1256 force = self._downloader.params.get('force_generic_extractor', False)
1257 self._downloader.report_warning(
1258 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 1259
4e262a88 1260 if not full_response:
5c2266df 1261 request = sanitized_Request(url)
58bde34a
S
1262 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1263 # making it impossible to download only chunk of the file (yet we need only 512kB to
1264 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1265 # that will always result in downloading the whole file that is not desirable.
1266 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1267 # to accept raw bytes and being able to download only a chunk.
1268 # It may probably better to solve this by checking Content-Type for application/octet-stream
1269 # after HEAD request finishes, but not sure if we can rely on this.
1270 request.add_header('Accept-Encoding', '*')
1271 full_response = self._request_webpage(request, video_id)
4e262a88
PH
1272
1273 # Maybe it's a direct link to a video?
1274 # Be careful not to download the whole thing!
1275 first_bytes = full_response.read(512)
61ca9a80 1276 if not is_html(first_bytes):
4e262a88
PH
1277 self._downloader.report_warning(
1278 'URL could be a direct video link, returning it as such.')
1279 upload_date = unified_strdate(
1280 head_response.headers.get('Last-Modified'))
1281 return {
1282 'id': video_id,
1ddb9456 1283 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
4e262a88
PH
1284 'direct': True,
1285 'url': url,
1286 'upload_date': upload_date,
1287 }
1288
1289 webpage = self._webpage_read_content(
1290 full_response, url, video_id, prefix=first_bytes)
1291
9b122384 1292 self.report_extraction(video_id)
887c6acd 1293
1b840245 1294 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 1295 try:
f7854627 1296 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
1297 if doc.tag == 'rss':
1298 return self._extract_rss(url, video_id, doc)
e5e8d20a
S
1299 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1300 return self._parse_smil(doc, url, video_id)
729accb4
S
1301 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1302 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245
S
1303 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1304 return {
1305 'id': video_id,
1306 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1307 'formats': self._parse_mpd_formats(doc, video_id),
1308 }
f7300c5c 1309 except compat_xml_parse_error:
4fc946b5
PH
1310 pass
1311
c8e9a235
PH
1312 # Is it a Camtasia project?
1313 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1314 if camtasia_res is not None:
1315 return camtasia_res
1316
14390730
S
1317 # Sometimes embedded video player is hidden behind percent encoding
1318 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1319 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 1320 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 1321
887c6acd
PH
1322 # it's tempting to parse this further, but you would
1323 # have to take into account all the variations like
1324 # Video Title - Site Name
1325 # Site Name | Video Title
1326 # Video Title - Tagline | Site Name
1327 # and so on and so forth; it's just not practical
ef4fd848 1328 video_title = self._html_search_regex(
79649588
PH
1329 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1330 default='video')
ef4fd848 1331
4d805e06
PH
1332 # Try to detect age limit automatically
1333 age_limit = self._rta_search(webpage)
1334 # And then there are the jokers who advertise that they use RTA,
1335 # but actually don't.
1336 AGE_LIMIT_MARKERS = [
1337 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1338 ]
1339 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1340 age_limit = 18
1341
ef4fd848
PH
1342 # video uploader is domain name
1343 video_uploader = self._search_regex(
79649588 1344 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 1345
ed2d6a19 1346 # Helper method
83992676 1347 def _playlist_from_matches(matches, getter=None, ie=None):
3b2f933b 1348 urlrs = orderedSet(
83992676 1349 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
3b2f933b 1350 for m in matches)
ed2d6a19
PH
1351 return self.playlist_result(
1352 urlrs, playlist_id=video_id, playlist_title=video_title)
1353
1f4b722b 1354 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 1355 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 1356 if bc_urls:
79649588 1357 self.to_screen('Brightcove video detected.')
99877772
PH
1358 entries = [{
1359 '_type': 'url',
1360 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 1361 'ie_key': 'BrightcoveLegacy'
99877772
PH
1362 } for bc_url in bc_urls]
1363
1364 return {
1365 '_type': 'playlist',
1366 'title': video_title,
1367 'id': video_id,
1368 'entries': entries,
1369 }
cfe50f04 1370
f6519f89
S
1371 # Look for Brightcove New Studio embeds
1372 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1373 if bc_urls:
1374 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
ed126900 1375
59b8ab58
PH
1376 # Look for embedded rtl.nl player
1377 matches = re.findall(
97b570a9 1378 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
59b8ab58
PH
1379 webpage)
1380 if matches:
1381 return _playlist_from_matches(matches, ie='RtlNl')
1382
b407e173
YCH
1383 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1384 if vimeo_url is not None:
1385 return self.url_result(vimeo_url)
7115ca84 1386
a1b85269
YCH
1387 vid_me_embed_url = self._search_regex(
1388 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1389 webpage, 'vid.me embed', default=None)
1390 if vid_me_embed_url is not None:
1391 return self.url_result(vid_me_embed_url, 'Vidme')
1392
53c1d3ef 1393 # Look for embedded YouTube player
1f9da904 1394 matches = re.findall(r'''(?x)
2b88feed
PH
1395 (?:
1396 <iframe[^>]+?src=|
c71dfccc 1397 data-video-url=|
2b88feed 1398 <embed[^>]+?src=|
a7e97f6d
PH
1399 embedSWF\(?:\s*|
1400 new\s+SWFObject\(
2b88feed
PH
1401 )
1402 (["\'])
1bf5423e 1403 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
6b08cdf6 1404 (?:embed|v|p)/.+?)
1f9da904 1405 \1''', webpage)
887c6acd 1406 if matches:
ed2d6a19 1407 return _playlist_from_matches(
3b2f933b 1408 matches, lambda m: unescapeHTML(m[1]))
53c1d3ef 1409
65f3a228
PH
1410 # Look for lazyYT YouTube embed
1411 matches = re.findall(
1412 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1413 if matches:
1414 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1415
355e4fd0
PH
1416 # Look for embedded Dailymotion player
1417 matches = re.findall(
1fa2b984 1418 r'<(?:embed|iframe)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
355e4fd0 1419 if matches:
ed2d6a19
PH
1420 return _playlist_from_matches(
1421 matches, lambda m: unescapeHTML(m[1]))
355e4fd0 1422
8489578d
NJ
1423 # Look for embedded Dailymotion playlist player (#3822)
1424 m = re.search(
1425 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1426 if m:
1427 playlists = re.findall(
1428 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1429 if playlists:
1430 return _playlist_from_matches(
1431 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1432
ef4fd848
PH
1433 # Look for embedded Wistia player
1434 match = re.search(
281d3f1d 1435 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
ef4fd848 1436 if match:
9471c444
NJ
1437 embed_url = self._proto_relative_url(
1438 unescapeHTML(match.group('url')))
ef4fd848
PH
1439 return {
1440 '_type': 'url_transparent',
9471c444 1441 'url': embed_url,
ef4fd848
PH
1442 'ie_key': 'Wistia',
1443 'uploader': video_uploader,
1444 'title': video_title,
1445 'id': video_id,
1446 }
5f6a1245 1447
9471c444 1448 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
746c67d7
NJ
1449 if match:
1450 return {
1451 '_type': 'url_transparent',
1452 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1453 'ie_key': 'Wistia',
1454 'uploader': video_uploader,
1455 'title': video_title,
1456 'id': match.group('id')
1457 }
ef4fd848 1458
bab19a8e
S
1459 # Look for SVT player
1460 svt_url = SVTIE._extract_url(webpage)
1461 if svt_url:
1462 return self.url_result(svt_url, 'SVT')
1463
fa35cdad
PH
1464 # Look for embedded condenast player
1465 matches = re.findall(
1466 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1467 webpage)
1468 if matches:
1469 return {
1470 '_type': 'playlist',
1471 'entries': [{
1472 '_type': 'url',
1473 'ie_key': 'CondeNast',
1474 'url': ma,
1475 } for ma in matches],
1476 'title': video_title,
1477 'id': video_id,
1478 }
1479
c19f7764
JMF
1480 # Look for Bandcamp pages with custom domain
1481 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1482 if mobj is not None:
1483 burl = unescapeHTML(mobj.group(1))
09804265
JMF
1484 # Don't set the extractor because it can be a track url or an album
1485 return self.url_result(burl)
c19f7764 1486
f25571ff
PH
1487 # Look for embedded Vevo player
1488 mobj = re.search(
1489 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1490 if mobj is not None:
1491 return self.url_result(mobj.group('url'))
796df3c6
S
1492
1493 # Look for embedded Viddler player
cb454b33
S
1494 mobj = re.search(
1495 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1496 webpage)
796df3c6
S
1497 if mobj is not None:
1498 return self.url_result(mobj.group('url'))
f25571ff 1499
3378d67a
S
1500 # Look for NYTimes player
1501 mobj = re.search(
1502 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1503 webpage)
1504 if mobj is not None:
1505 return self.url_result(mobj.group('url'))
1506
cefdf970
S
1507 # Look for Libsyn player
1508 mobj = re.search(
1509 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1510 if mobj is not None:
1511 return self.url_result(mobj.group('url'))
1512
c0d0b01f 1513 # Look for Ooyala videos
8a37aa15 1514 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 1515 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
1516 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1517 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 1518 if mobj is not None:
cce9d15d 1519 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
c0d0b01f 1520
f076b638 1521 # Look for multiple Ooyala embeds on SBN network websites
1522 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1523 if mobj is not None:
1524 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1525 if embeds:
1526 return _playlist_from_matches(
cce9d15d 1527 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 1528
aa94a6d3 1529 # Look for Aparat videos
48099643 1530 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
1531 if mobj is not None:
1532 return self.url_result(mobj.group(1), 'Aparat')
1533
c93c2ab1 1534 # Look for MPORA videos
c3f51436 1535 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
1536 if mobj is not None:
1537 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 1538
15c0e8e7 1539 # Look for embedded NovaMov-based player
8f89e687 1540 mobj = re.search(
8dfa187b 1541 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
1542 (?P<url>http://(?:(?:embed|www)\.)?
1543 (?:novamov\.com|
1544 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1545 videoweed\.(?:es|com)|
1546 movshare\.(?:net|sx|ag)|
1547 divxstage\.(?:eu|net|ch|co|at|ag))
1548 /embed\.php.+?)\1''', webpage)
8f89e687 1549 if mobj is not None:
15c0e8e7 1550 return self.url_result(mobj.group('url'))
50f56607 1551
9834872b
PH
1552 # Look for embedded Facebook player
1553 mobj = re.search(
db1f3888 1554 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
9834872b
PH
1555 if mobj is not None:
1556 return self.url_result(mobj.group('url'), 'Facebook')
1557
ca97a56e
S
1558 # Look for embedded VK player
1559 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1560 if mobj is not None:
1561 return self.url_result(mobj.group('url'), 'VK')
1562
0364fa8b
S
1563 # Look for embedded ivi player
1564 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1565 if mobj is not None:
1566 return self.url_result(mobj.group('url'), 'Ivi')
1567
db1f3888
PH
1568 # Look for embedded Huffington Post player
1569 mobj = re.search(
c3f51436 1570 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
1571 if mobj is not None:
1572 return self.url_result(mobj.group('url'), 'HuffPost')
1573
1b86cc41 1574 # Look for embed.ly
1575 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1576 if mobj is not None:
1577 return self.url_result(mobj.group('url'))
1578 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1579 if mobj is not None:
f7e6f7fa 1580 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 1581
60cc4dc4
PH
1582 # Look for funnyordie embed
1583 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1584 if matches:
ed2d6a19
PH
1585 return _playlist_from_matches(
1586 matches, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 1587
db546cf8
S
1588 # Look for BBC iPlayer embed
1589 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1590 if matches:
476eae0c 1591 return _playlist_from_matches(matches, ie='BBCCoUk')
db546cf8 1592
93d020dd
S
1593 # Look for embedded RUTV player
1594 rutv_url = RUTVIE._extract_url(webpage)
1595 if rutv_url:
1596 return self.url_result(rutv_url, 'RUTV')
1597
494f20cb 1598 # Look for embedded TVC player
b8599718
S
1599 tvc_url = TVCIE._extract_url(webpage)
1600 if tvc_url:
1601 return self.url_result(tvc_url, 'TVC')
494f20cb 1602
d40a3b5b
S
1603 # Look for embedded SportBox player
1604 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1605 if sportbox_urls:
1606 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1607
78e2b74b 1608 # Look for embedded PornHub player
65d161c4
S
1609 pornhub_url = PornHubIE._extract_url(webpage)
1610 if pornhub_url:
1611 return self.url_result(pornhub_url, 'PornHub')
1612
2bb5b6d0
S
1613 # Look for embedded XHamster player
1614 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1615 if xhamster_urls:
1616 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1617
9872d311
S
1618 # Look for embedded Tvigle player
1619 mobj = re.search(
1620 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1621 if mobj is not None:
1622 return self.url_result(mobj.group('url'), 'Tvigle')
1623
7e2ede98
JMF
1624 # Look for embedded TED player
1625 mobj = re.search(
d7cc31b6 1626 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'), 'TED')
1629
5c386252 1630 # Look for embedded Ustream videos
1631 mobj = re.search(
1632 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1633 if mobj is not None:
1634 return self.url_result(mobj.group('url'), 'Ustream')
1635
893f8832
PH
1636 # Look for embedded arte.tv player
1637 mobj = re.search(
1638 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1639 webpage)
1640 if mobj is not None:
1641 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1642
cbd55ade
S
1643 # Look for embedded francetv player
1644 mobj = re.search(
1645 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1646 webpage)
1647 if mobj is not None:
1648 return self.url_result(mobj.group('url'))
1649
cb3ac1c6
S
1650 # Look for embedded smotri.com player
1651 smotri_url = SmotriIE._extract_url(webpage)
1652 if smotri_url:
1653 return self.url_result(smotri_url, 'Smotri')
1654
e6c2d9ad 1655 # Look for embedded Myvi.ru player
6dd94d3a 1656 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
1657 if myvi_url:
1658 return self.url_result(myvi_url)
1659
dfb1b146 1660 # Look for embedded soundcloud player
20991253 1661 mobj = re.search(
ac645ac7 1662 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
20991253
PH
1663 webpage)
1664 if mobj is not None:
1665 url = unescapeHTML(mobj.group('url'))
1666 return self.url_result(url)
1667
826ec77f
PH
1668 # Look for embedded vulture.com player
1669 mobj = re.search(
1670 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1671 webpage)
1672 if mobj is not None:
1673 url = unescapeHTML(mobj.group('url'))
1674 return self.url_result(url, ie='Vulture')
1675
c5cd249e 1676 # Look for embedded mtvservices player
46fde8a1
S
1677 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1678 if mtvservices_url:
1679 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 1680
49807b4a
S
1681 # Look for embedded yahoo player
1682 mobj = re.search(
1683 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1684 webpage)
1685 if mobj is not None:
1686 return self.url_result(mobj.group('url'), 'Yahoo')
1687
2ef6fcb5
PH
1688 # Look for embedded sbs.com.au player
1689 mobj = re.search(
e98b8e79
PH
1690 r'''(?x)
1691 (?:
1692 <meta\s+property="og:video"\s+content=|
1693 <iframe[^>]+?src=
1694 )
1695 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
1696 webpage)
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'SBS')
1699
42bdd9d0
PH
1700 # Look for embedded Cinchcast player
1701 mobj = re.search(
1702 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1703 webpage)
1704 if mobj is not None:
1705 return self.url_result(mobj.group('url'), 'Cinchcast')
1706
1a94ff68 1707 mobj = re.search(
5263cdfc 1708 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 1709 webpage)
8001607e
YCH
1710 if not mobj:
1711 mobj = re.search(
1712 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1713 webpage)
1a94ff68
S
1714 if mobj is not None:
1715 return self.url_result(mobj.group('url'), 'MLB')
1716
1419fafd 1717 mobj = re.search(
dd467d33 1718 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
1719 webpage)
1720 if mobj is not None:
1721 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1722
af63fed7
PH
1723 mobj = re.search(
1724 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1725 webpage)
1726 if mobj is not None:
1727 return self.url_result(mobj.group('url'), 'Livestream')
1728
255fca5e
S
1729 # Look for Zapiks embed
1730 mobj = re.search(
1731 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1732 if mobj is not None:
1733 return self.url_result(mobj.group('url'), 'Zapiks')
1734
e3216b82 1735 # Look for Kaltura embeds
6a5d6de1 1736 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 1737 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 1738 if mobj is not None:
5b5fae5f
S
1739 return self.url_result(smuggle_url(
1740 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1741 {'source_url': url}), 'Kaltura')
e3216b82 1742
135c9c42
S
1743 # Look for Eagle.Platform embeds
1744 mobj = re.search(
1745 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1746 if mobj is not None:
1747 return self.url_result(mobj.group('url'), 'EaglePlatform')
1748
d47ae7f6
S
1749 # Look for ClipYou (uses Eagle.Platform) embeds
1750 mobj = re.search(
1751 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1752 if mobj is not None:
1753 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1754
f8388757 1755 # Look for Pladform embeds
45dad7ba
S
1756 pladform_url = PladformIE._extract_url(webpage)
1757 if pladform_url:
1758 return self.url_result(pladform_url)
f8388757 1759
ff18735c
S
1760 # Look for Videomore embeds
1761 videomore_url = VideomoreIE._extract_url(webpage)
1762 if videomore_url:
1763 return self.url_result(videomore_url)
1764
2dcc114f
S
1765 # Look for Playwire embeds
1766 mobj = re.search(
1767 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'))
1770
ad320e9b
NJ
1771 # Look for 5min embeds
1772 mobj = re.search(
1773 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1774 if mobj is not None:
1775 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1776
18153f1b
S
1777 # Look for Crooks and Liars embeds
1778 mobj = re.search(
1779 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1780 if mobj is not None:
1781 return self.url_result(mobj.group('url'))
1782
a2edf2e7
YCH
1783 # Look for NBC Sports VPlayer embeds
1784 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1785 if nbc_sports_url:
1786 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1787
653789af 1788 # Look for Google Drive embeds
5b251628 1789 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 1790 if google_drive_url:
1791 return self.url_result(google_drive_url, 'GoogleDrive')
1792
418c5cc3
YCH
1793 # Look for UDN embeds
1794 mobj = re.search(
c39fd7b1 1795 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
1796 if mobj is not None:
1797 return self.url_result(
0a160363 1798 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 1799
2fe1b5bd
YCH
1800 # Look for Senate ISVP iframe
1801 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1802 if senate_isvp_url:
25c3a734 1803 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 1804
756f574e
YCH
1805 # Look for Dailymotion Cloud videos
1806 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1807 if dmcloud_url:
1808 return self.url_result(dmcloud_url, 'DailymotionCloud')
1809
1ac1c4c2
S
1810 # Look for OnionStudios embeds
1811 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1812 if onionstudios_url:
1813 return self.url_result(onionstudios_url)
1814
eedd20ef
S
1815 # Look for SnagFilms embeds
1816 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1817 if snagfilms_url:
1818 return self.url_result(snagfilms_url)
1819
7cb09524 1820 # Look for JWPlatform embeds
1821 jwplatform_url = JWPlatformIE._extract_url(webpage)
1822 if jwplatform_url:
1823 return self.url_result(jwplatform_url, 'JWPlatform')
1824
8ca31a0e 1825 # Look for ScreenwaveMedia embeds
efd712c6 1826 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
8ca31a0e 1827 if mobj is not None:
efd712c6 1828 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
8ca31a0e 1829
aecfcd4e
S
1830 # Look for Digiteka embeds
1831 digiteka_url = DigitekaIE._extract_url(webpage)
1832 if digiteka_url:
1833 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 1834
1bf996fa 1835 # Look for Limelight embeds
1836 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1837 if mobj:
1838 lm = {
1839 'Media': 'media',
1840 'Channel': 'channel',
1841 'ChannelList': 'channel_list',
1842 }
1843 return self.url_result('limelight:%s:%s' % (
1844 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1845
a5158f38
YCH
1846 # Look for AdobeTVVideo embeds
1847 mobj = re.search(
1848 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1849 webpage)
1850 if mobj is not None:
1851 return self.url_result(
1852 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1853 'AdobeTVVideo')
1854
ced659bb 1855 def check_video(vurl):
a0f71985
PH
1856 if YoutubeIE.suitable(vurl):
1857 return True
ced659bb
S
1858 vpath = compat_urlparse.urlparse(vurl).path
1859 vext = determine_ext(vpath)
1860 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1861
1862 def filter_video(urls):
1863 return list(filter(check_video, urls))
1864
9b122384 1865 # Start with something easy: JW Player in SWFObject
ced659bb 1866 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 1867 if not found:
d981cef6 1868 # Look for gorilla-vid style embedding
ced659bb 1869 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
1870 (?:
1871 jw_plugins|
1872 JWPlayerOptions|
1873 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1874 )
a0f71985
PH
1875 .*?
1876 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 1877 if not found:
9b122384 1878 # Broaden the search a little bit
ced659bb 1879 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
1880 if not found:
1881 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 1882 found = filter_video(re.findall(
54a9328b 1883 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
1884 if not found:
1885 # Flow player
ced659bb 1886 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
1887 flowplayer\("[^"]+",\s*
1888 \{[^}]+?\}\s*,
52585fd6 1889 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 1890 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 1891 ''', webpage))
501f13fb
PH
1892 if not found:
1893 # Cinerama player
1894 found = re.findall(
1895 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 1896 if not found:
9b122384 1897 # Try to find twitter cards info
ced659bb
S
1898 found = filter_video(re.findall(
1899 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 1900 if not found:
9b122384
PH
1901 # We look for Open Graph info:
1902 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 1903 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
1904 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1905 if m_video_type is not None:
ced659bb 1906 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 1907 if not found:
7fea7156 1908 # HTML5 video
12439dd5 1909 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
b30b8698 1910 if not found:
ed9a25dd 1911 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 1912 found = re.search(
89ef304b 1913 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 1914 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 1915 webpage)
84f81016
S
1916 if not found:
1917 # Look also in Refresh HTTP header
1918 refresh_header = head_response.headers.get('Refresh')
1919 if refresh_header:
6c91a5a7
S
1920 # In python 2 response HTTP headers are bytestrings
1921 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1922 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 1923 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 1924 if found:
b37317d8 1925 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
89ef304b
PH
1926 self.report_following_redirect(new_url)
1927 return {
1928 '_type': 'url',
1929 'url': new_url,
1930 }
b30b8698 1931 if not found:
416c7fcb 1932 raise UnsupportedError(url)
9b122384 1933
b30b8698
PH
1934 entries = []
1935 for video_url in found:
6cc37c69 1936 video_url = video_url.replace('\\/', '/')
b30b8698 1937 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 1938 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 1939
b30b8698
PH
1940 # Sometimes, jwplayer extraction will result in a YouTube URL
1941 if YoutubeIE.suitable(video_url):
1942 entries.append(self.url_result(video_url, 'Youtube'))
1943 continue
9b122384 1944
b30b8698
PH
1945 # here's a fun little line of code for you:
1946 video_id = os.path.splitext(video_id)[0]
fc9713a1 1947
28602e74
YCH
1948 entry_info_dict = {
1949 'id': video_id,
1950 'uploader': video_uploader,
1951 'title': video_title,
1952 'age_limit': age_limit,
1953 }
1954
729accb4
S
1955 ext = determine_ext(video_url)
1956 if ext == 'smil':
28602e74 1957 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
1958 elif ext == 'xspf':
1959 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
1960 elif ext == 'm3u8':
1961 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
d6fd958c 1962 else:
28602e74
YCH
1963 entry_info_dict['url'] = video_url
1964
1965 entries.append(entry_info_dict)
b30b8698
PH
1966
1967 if len(entries) == 1:
669f0e7c 1968 return entries[0]
b30b8698
PH
1969 else:
1970 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
1971 # 'url' results don't have a title
1972 if e.get('title') is not None:
1973 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
1974 return {
1975 '_type': 'playlist',
1976 'entries': entries,
1977 }