]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Rapsys Git / youtubedl / blob
? search:


5075d131ec66debcdb0296b6e9e1c87598a12836
[youtubedl] / youtube_dl / extractor / generic.py
1 # encoding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 orderedSet,
24 sanitized_Request,
25 smuggle_url,
26 unescapeHTML,
27 unified_strdate,
28 unsmuggle_url,
29 UnsupportedError,
30 url_basename,
31 xpath_text,
32 )
33 from .brightcove import (
34 BrightcoveLegacyIE,
35 BrightcoveNewIE,
36 )
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .bliptv import BlipTVIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .snagfilms import SnagFilmsEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57
58
59 class GenericIE(InfoExtractor):
60 IE_DESC = 'Generic downloader that works on some sites'
61 _VALID_URL = r'.*'
62 IE_NAME = 'generic'
63 _TESTS = [
64 # Direct link to a video
65 {
66 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
67 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
68 'info_dict': {
69 'id': 'trailer',
70 'ext': 'mp4',
71 'title': 'trailer',
72 'upload_date': '20100513',
73 }
74 },
75 # Direct link to media delivered compressed (until Accept-Encoding is *)
76 {
77 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
78 'md5': '128c42e68b13950268b648275386fc74',
79 'info_dict': {
80 'id': 'FictionJunction-Parallel_Hearts',
81 'ext': 'flac',
82 'title': 'FictionJunction-Parallel_Hearts',
83 'upload_date': '20140522',
84 },
85 'expected_warnings': [
86 'URL could be a direct video link, returning it as such.'
87 ]
88 },
89 # Direct download with broken HEAD
90 {
91 'url': 'http://ai-radio.org:8000/radio.opus',
92 'info_dict': {
93 'id': 'radio',
94 'ext': 'opus',
95 'title': 'radio',
96 },
97 'params': {
98 'skip_download': True, # infinite live stream
99 },
100 'expected_warnings': [
101 r'501.*Not Implemented'
102 ],
103 },
104 # Direct link with incorrect MIME type
105 {
106 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
107 'md5': '4ccbebe5f36706d85221f204d7eb5913',
108 'info_dict': {
109 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
110 'id': '5_Lennart_Poettering_-_Systemd',
111 'ext': 'webm',
112 'title': '5_Lennart_Poettering_-_Systemd',
113 'upload_date': '20141120',
114 },
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
117 ]
118 },
119 # RSS feed
120 {
121 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
122 'info_dict': {
123 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
124 'title': 'Zero Punctuation',
125 'description': 're:.*groundbreaking video review series.*'
126 },
127 'playlist_mincount': 11,
128 },
129 # RSS feed with enclosure
130 {
131 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
132 'info_dict': {
133 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
134 'ext': 'm4v',
135 'upload_date': '20150228',
136 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
137 }
138 },
139 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
140 {
141 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
142 'info_dict': {
143 'id': 'smil',
144 'ext': 'mp4',
145 'title': 'Automatics, robotics and biocybernetics',
146 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
147 'upload_date': '20130627',
148 'formats': 'mincount:16',
149 'subtitles': 'mincount:1',
150 },
151 'params': {
152 'force_generic_extractor': True,
153 'skip_download': True,
154 },
155 },
156 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
157 {
158 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
159 'info_dict': {
160 'id': 'hds',
161 'ext': 'flv',
162 'title': 'hds',
163 'formats': 'mincount:1',
164 },
165 'params': {
166 'skip_download': True,
167 },
168 },
169 # SMIL from https://www.restudy.dk/video/play/id/1637
170 {
171 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
172 'info_dict': {
173 'id': 'video_1637',
174 'ext': 'flv',
175 'title': 'video_1637',
176 'formats': 'mincount:3',
177 },
178 'params': {
179 'skip_download': True,
180 },
181 },
182 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
183 {
184 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
185 'info_dict': {
186 'id': 'smil-service',
187 'ext': 'flv',
188 'title': 'smil-service',
189 'formats': 'mincount:1',
190 },
191 'params': {
192 'skip_download': True,
193 },
194 },
195 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
196 {
197 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
198 'info_dict': {
199 'id': '4719370',
200 'ext': 'mp4',
201 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
202 'formats': 'mincount:3',
203 },
204 'params': {
205 'skip_download': True,
206 },
207 },
208 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
209 {
210 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
211 'info_dict': {
212 'id': 'mZlp2ctYIUEB',
213 'ext': 'mp4',
214 'title': 'Tikibad ontruimd wegens brand',
215 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
216 'thumbnail': 're:^https?://.*\.jpg$',
217 'duration': 33,
218 },
219 'params': {
220 'skip_download': True,
221 },
222 },
223 # google redirect
224 {
225 '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',
226 'info_dict': {
227 'id': 'cmQHVoWB5FY',
228 'ext': 'mp4',
229 'upload_date': '20130224',
230 'uploader_id': 'TheVerge',
231 'description': 're:^Chris Ziegler takes a look at the\.*',
232 'uploader': 'The Verge',
233 'title': 'First Firefox OS phones side-by-side',
234 },
235 'params': {
236 'skip_download': False,
237 }
238 },
239 {
240 # redirect in Refresh HTTP header
241 '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',
242 'info_dict': {
243 'id': 'pO8h3EaFRdo',
244 'ext': 'mp4',
245 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
246 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
247 'upload_date': '20150917',
248 'uploader_id': 'brtvofficial',
249 'uploader': 'Boiler Room',
250 },
251 'params': {
252 'skip_download': False,
253 },
254 },
255 {
256 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
257 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
258 'info_dict': {
259 'id': '13601338388002',
260 'ext': 'mp4',
261 'uploader': 'www.hodiho.fr',
262 'title': 'R\u00e9gis plante sa Jeep',
263 }
264 },
265 # bandcamp page with custom domain
266 {
267 'add_ie': ['Bandcamp'],
268 'url': 'http://bronyrock.com/track/the-pony-mash',
269 'info_dict': {
270 'id': '3235767654',
271 'ext': 'mp3',
272 'title': 'The Pony Mash',
273 'uploader': 'M_Pallante',
274 },
275 'skip': 'There is a limit of 200 free downloads / month for the test song',
276 },
277 # embedded brightcove video
278 # it also tests brightcove videos that need to set the 'Referer' in the
279 # http requests
280 {
281 'add_ie': ['BrightcoveLegacy'],
282 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
283 'info_dict': {
284 'id': '2765128793001',
285 'ext': 'mp4',
286 'title': 'Le cours de bourse : lā€™analyse technique',
287 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
288 'uploader': 'BFM BUSINESS',
289 },
290 'params': {
291 'skip_download': True,
292 },
293 },
294 {
295 # https://github.com/rg3/youtube-dl/issues/2253
296 'url': 'http://bcove.me/i6nfkrc3',
297 'md5': '0ba9446db037002366bab3b3eb30c88c',
298 'info_dict': {
299 'id': '3101154703001',
300 'ext': 'mp4',
301 'title': 'Still no power',
302 'uploader': 'thestar.com',
303 '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.',
304 },
305 'add_ie': ['BrightcoveLegacy'],
306 },
307 {
308 'url': 'http://www.championat.com/video/football/v/87/87499.html',
309 'md5': 'fb973ecf6e4a78a67453647444222983',
310 'info_dict': {
311 'id': '3414141473001',
312 'ext': 'mp4',
313 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
314 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
315 'uploader': 'Championat',
316 },
317 },
318 {
319 # https://github.com/rg3/youtube-dl/issues/3541
320 'add_ie': ['BrightcoveLegacy'],
321 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
322 'info_dict': {
323 'id': '3866516442001',
324 'ext': 'mp4',
325 'title': 'Leer mij vrouwen kennen: Aflevering 1',
326 'description': 'Leer mij vrouwen kennen: Aflevering 1',
327 'uploader': 'SBS Broadcasting',
328 },
329 'skip': 'Restricted to Netherlands',
330 'params': {
331 'skip_download': True, # m3u8 download
332 },
333 },
334 # ooyala video
335 {
336 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
337 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
338 'info_dict': {
339 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
340 'ext': 'mp4',
341 'title': '2cc213299525360.mov', # that's what we get
342 },
343 'add_ie': ['Ooyala'],
344 },
345 {
346 # ooyala video embedded with http://player.ooyala.com/iframe.js
347 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
348 'info_dict': {
349 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
350 'ext': 'mp4',
351 'title': '"Steve Jobs: Man in the Machine" trailer',
352 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
353 },
354 'params': {
355 'skip_download': True,
356 },
357 },
358 # multiple ooyala embeds on SBN network websites
359 {
360 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
361 'info_dict': {
362 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
363 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
364 },
365 'playlist_mincount': 3,
366 'params': {
367 'skip_download': True,
368 },
369 'add_ie': ['Ooyala'],
370 },
371 # embed.ly video
372 {
373 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
374 'info_dict': {
375 'id': '9ODmcdjQcHQ',
376 'ext': 'mp4',
377 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
378 'upload_date': '20140225',
379 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
380 'uploader': 'Tested',
381 'uploader_id': 'testedcom',
382 },
383 # No need to test YoutubeIE here
384 'params': {
385 'skip_download': True,
386 },
387 },
388 # funnyordie embed
389 {
390 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
391 'info_dict': {
392 'id': '18e820ec3f',
393 'ext': 'mp4',
394 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
395 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
396 },
397 },
398 # RUTV embed
399 {
400 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
401 'info_dict': {
402 'id': '776940',
403 'ext': 'mp4',
404 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
405 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
406 },
407 'params': {
408 # m3u8 download
409 'skip_download': True,
410 },
411 },
412 # TVC embed
413 {
414 '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/',
415 'info_dict': {
416 'id': '55304',
417 'ext': 'mp4',
418 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
419 },
420 },
421 # SportBox embed
422 {
423 'url': 'http://www.vestifinance.ru/articles/25753',
424 'info_dict': {
425 'id': '25753',
426 'title': 'Š’ŠµŃŃ‚Šø Š­ŠŗŠ¾Š½Š¾Š¼ŠøŠŗŠ° ā€• ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
427 },
428 'playlist': [{
429 'info_dict': {
430 'id': '370908',
431 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
432 'ext': 'mp4',
433 }
434 }, {
435 'info_dict': {
436 'id': '370905',
437 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
438 'ext': 'mp4',
439 }
440 }, {
441 'info_dict': {
442 'id': '370902',
443 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
444 'ext': 'mp4',
445 }
446 }],
447 'params': {
448 # m3u8 download
449 'skip_download': True,
450 },
451 },
452 # Myvi.ru embed
453 {
454 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
455 'info_dict': {
456 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
457 'ext': 'mp4',
458 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
459 'thumbnail': 're:^https?://.*\.jpg$',
460 'duration': 153,
461 }
462 },
463 # XHamster embed
464 {
465 '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',
466 'info_dict': {
467 'id': 'showthread',
468 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
469 },
470 'playlist_mincount': 7,
471 },
472 # Embedded TED video
473 {
474 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
475 'md5': '65fdff94098e4a607385a60c5177c638',
476 'info_dict': {
477 'id': '1969',
478 'ext': 'mp4',
479 'title': 'Hidden miracles of the natural world',
480 'uploader': 'Louie Schwartzberg',
481 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
482 }
483 },
484 # Embeded Ustream video
485 {
486 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
487 'md5': '27b99cdb639c9b12a79bca876a073417',
488 'info_dict': {
489 'id': '45734260',
490 'ext': 'flv',
491 'uploader': 'AU SPA: The NSA and Privacy',
492 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
493 }
494 },
495 # nowvideo embed hidden behind percent encoding
496 {
497 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
498 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
499 'info_dict': {
500 'id': '06e53103ca9aa',
501 'ext': 'flv',
502 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
503 'description': 'No description',
504 },
505 },
506 # arte embed
507 {
508 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
509 'md5': '7653032cbb25bf6c80d80f217055fa43',
510 'info_dict': {
511 'id': '048195-004_PLUS7-F',
512 'ext': 'flv',
513 'title': 'X:enius',
514 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
515 'upload_date': '20140320',
516 },
517 'params': {
518 'skip_download': 'Requires rtmpdump'
519 }
520 },
521 # francetv embed
522 {
523 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
524 'info_dict': {
525 'id': 'EV_30231',
526 'ext': 'mp4',
527 'title': 'Alcaline, le concert avec Calogero',
528 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
529 'upload_date': '20150226',
530 'timestamp': 1424989860,
531 'duration': 5400,
532 },
533 'params': {
534 # m3u8 downloads
535 'skip_download': True,
536 },
537 'expected_warnings': [
538 'Forbidden'
539 ]
540 },
541 # CondƩ Nast embed
542 {
543 'url': 'http://www.wired.com/2014/04/honda-asimo/',
544 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
545 'info_dict': {
546 'id': '53501be369702d3275860000',
547 'ext': 'mp4',
548 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
549 }
550 },
551 # Dailymotion embed
552 {
553 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
554 'md5': '441aeeb82eb72c422c7f14ec533999cd',
555 'info_dict': {
556 'id': 'k2mm4bCdJ6CQ2i7c8o2',
557 'ext': 'mp4',
558 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
559 'uploader': 'Spi0n',
560 },
561 'add_ie': ['Dailymotion'],
562 },
563 # YouTube embed
564 {
565 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
566 'info_dict': {
567 'id': 'FXRb4ykk4S0',
568 'ext': 'mp4',
569 'title': 'The NBL Auction 2014',
570 'uploader': 'BADMINTON England',
571 'uploader_id': 'BADMINTONEvents',
572 'upload_date': '20140603',
573 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
574 },
575 'add_ie': ['Youtube'],
576 'params': {
577 'skip_download': True,
578 }
579 },
580 # MTVSercices embed
581 {
582 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
583 'md5': '35727f82f58c76d996fc188f9755b0d5',
584 'info_dict': {
585 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
586 'ext': 'mp4',
587 'title': 'Review',
588 'description': 'Mario\'s life in the fast lane has never looked so good.',
589 },
590 },
591 # YouTube embed via <data-embed-url="">
592 {
593 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
594 'info_dict': {
595 'id': '4vAffPZIT44',
596 'ext': 'mp4',
597 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
598 'uploader': 'Gameloft',
599 'uploader_id': 'gameloft',
600 'upload_date': '20140828',
601 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
602 },
603 'params': {
604 'skip_download': True,
605 }
606 },
607 # Camtasia studio
608 {
609 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
610 'playlist': [{
611 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
612 'info_dict': {
613 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
614 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
615 'ext': 'flv',
616 'duration': 2235.90,
617 }
618 }, {
619 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
620 'info_dict': {
621 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
622 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
623 'ext': 'flv',
624 'duration': 2235.93,
625 }
626 }],
627 'info_dict': {
628 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
629 }
630 },
631 # Flowplayer
632 {
633 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
634 'md5': '9d65602bf31c6e20014319c7d07fba27',
635 'info_dict': {
636 'id': '5123ea6d5e5a7',
637 'ext': 'mp4',
638 'age_limit': 18,
639 'uploader': 'www.handjobhub.com',
640 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
641 }
642 },
643 # Multiple brightcove videos
644 # https://github.com/rg3/youtube-dl/issues/2283
645 {
646 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
647 'info_dict': {
648 'id': 'always-never',
649 'title': 'Always / Never - The New Yorker',
650 },
651 'playlist_count': 3,
652 'params': {
653 'extract_flat': False,
654 'skip_download': True,
655 }
656 },
657 # MLB embed
658 {
659 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
660 'md5': '96f09a37e44da40dd083e12d9a683327',
661 'info_dict': {
662 'id': '33322633',
663 'ext': 'mp4',
664 'title': 'Ump changes call to ball',
665 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
666 'duration': 48,
667 'timestamp': 1401537900,
668 'upload_date': '20140531',
669 'thumbnail': 're:^https?://.*\.jpg$',
670 },
671 },
672 # Wistia embed
673 {
674 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
675 'md5': '8788b683c777a5cf25621eaf286d0c23',
676 'info_dict': {
677 'id': '1cfaf6b7ea',
678 'ext': 'mov',
679 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
680 'duration': 643.0,
681 'filesize': 182808282,
682 'uploader': 'education-portal.com',
683 },
684 },
685 {
686 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
687 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
688 'info_dict': {
689 'id': 'uxjb0lwrcz',
690 'ext': 'mp4',
691 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
692 'duration': 1715.0,
693 'uploader': 'thoughtworks.wistia.com',
694 },
695 },
696 # Soundcloud embed
697 {
698 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
699 'info_dict': {
700 'id': '174391317',
701 'ext': 'mp3',
702 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
703 'uploader': 'Sophos Security',
704 'title': 'Chet Chat 171 - Oct 29, 2014',
705 'upload_date': '20141029',
706 }
707 },
708 # Livestream embed
709 {
710 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
711 'info_dict': {
712 'id': '67864563',
713 'ext': 'flv',
714 'upload_date': '20141112',
715 'title': 'Rosetta #CometLanding webcast HL 10',
716 }
717 },
718 # LazyYT
719 {
720 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
721 'info_dict': {
722 'id': '1986',
723 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
724 },
725 'playlist_mincount': 2,
726 },
727 # Cinchcast embed
728 {
729 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
730 'info_dict': {
731 'id': '7141703',
732 'ext': 'mp3',
733 'upload_date': '20141126',
734 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
735 }
736 },
737 # Cinerama player
738 {
739 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
740 'info_dict': {
741 'id': '730m_DandD_1901_512k',
742 'ext': 'mp4',
743 'uploader': 'www.abc.net.au',
744 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
745 }
746 },
747 # embedded viddler video
748 {
749 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
750 'info_dict': {
751 'id': '4d03aad9',
752 'ext': 'mp4',
753 'uploader': 'deadspin',
754 'title': 'WALL-TO-GORTAT',
755 'timestamp': 1422285291,
756 'upload_date': '20150126',
757 },
758 'add_ie': ['Viddler'],
759 },
760 # Libsyn embed
761 {
762 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
763 'info_dict': {
764 'id': '3377616',
765 'ext': 'mp3',
766 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
767 'description': 'md5:601cb790edd05908957dae8aaa866465',
768 'upload_date': '20150220',
769 },
770 },
771 # jwplayer YouTube
772 {
773 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
774 'info_dict': {
775 'id': 'Mrj4DVp2zeA',
776 'ext': 'mp4',
777 'upload_date': '20150212',
778 'uploader': 'The National Archives UK',
779 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
780 'uploader_id': 'NationalArchives08',
781 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
782 },
783 },
784 # rtl.nl embed
785 {
786 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
787 'playlist_mincount': 5,
788 'info_dict': {
789 'id': 'aanslagen-kopenhagen',
790 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
791 }
792 },
793 # Zapiks embed
794 {
795 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
796 'info_dict': {
797 'id': '118046',
798 'ext': 'mp4',
799 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
800 }
801 },
802 # Kaltura embed
803 {
804 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
805 'info_dict': {
806 'id': '1_eergr3h1',
807 'ext': 'mp4',
808 'upload_date': '20150226',
809 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
810 'timestamp': int,
811 'title': 'John Carlson Postgame 2/25/15',
812 },
813 },
814 # Kaltura embed (different embed code)
815 {
816 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
817 'info_dict': {
818 'id': '1_a52wc67y',
819 'ext': 'flv',
820 'upload_date': '20150127',
821 'uploader_id': 'PremierMedia',
822 'timestamp': int,
823 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
824 },
825 },
826 # Kaltura embed protected with referrer
827 {
828 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
829 'info_dict': {
830 'id': '1_g4fbemnq',
831 'ext': 'mp4',
832 'title': 'Violetta - Achter De Schermen - Ruggero',
833 'description': 'Achter de schermen met Ruggero',
834 'timestamp': 1435133761,
835 'upload_date': '20150624',
836 'uploader_id': 'echojecka',
837 },
838 },
839 # Eagle.Platform embed (generic URL)
840 {
841 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
842 'info_dict': {
843 'id': '227304',
844 'ext': 'mp4',
845 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
846 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
847 'thumbnail': 're:^https?://.*\.jpg$',
848 'duration': 87,
849 'view_count': int,
850 'age_limit': 0,
851 },
852 },
853 # ClipYou (Eagle.Platform) embed (custom URL)
854 {
855 'url': 'http://muz-tv.ru/play/7129/',
856 'info_dict': {
857 'id': '12820',
858 'ext': 'mp4',
859 'title': "'O Sole Mio",
860 'thumbnail': 're:^https?://.*\.jpg$',
861 'duration': 216,
862 'view_count': int,
863 },
864 },
865 # Pladform embed
866 {
867 'url': 'http://muz-tv.ru/kinozal/view/7400/',
868 'info_dict': {
869 'id': '100183293',
870 'ext': 'mp4',
871 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
872 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
873 'thumbnail': 're:^https?://.*\.jpg$',
874 'duration': 694,
875 'age_limit': 0,
876 },
877 },
878 # Playwire embed
879 {
880 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
881 'info_dict': {
882 'id': '3519514',
883 'ext': 'mp4',
884 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
885 'thumbnail': 're:^https?://.*\.png$',
886 'duration': 45.115,
887 },
888 },
889 # 5min embed
890 {
891 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
892 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
893 'info_dict': {
894 'id': '518726732',
895 'ext': 'mp4',
896 'title': 'Facebook Creates "On This Day" | Crunch Report',
897 },
898 },
899 # SVT embed
900 {
901 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
902 'info_dict': {
903 'id': '2900353',
904 'ext': 'flv',
905 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
906 'duration': 27,
907 'age_limit': 0,
908 },
909 },
910 # Crooks and Liars embed
911 {
912 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
913 'info_dict': {
914 'id': '8RUoRhRi',
915 'ext': 'mp4',
916 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
917 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
918 'timestamp': 1428207000,
919 'upload_date': '20150405',
920 'uploader': 'Heather',
921 },
922 },
923 # Crooks and Liars external embed
924 {
925 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
926 'info_dict': {
927 'id': 'MTE3MjUtMzQ2MzA',
928 'ext': 'mp4',
929 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
930 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
931 'timestamp': 1265032391,
932 'upload_date': '20100201',
933 'uploader': 'Heather',
934 },
935 },
936 # NBC Sports vplayer embed
937 {
938 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
939 'info_dict': {
940 'id': 'ln7x1qSThw4k',
941 'ext': 'flv',
942 'title': "PFT Live: New leader in the 'new-look' defense",
943 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
944 },
945 },
946 # UDN embed
947 {
948 'url': 'http://www.udn.com/news/story/7314/822787',
949 'md5': 'fd2060e988c326991037b9aff9df21a6',
950 'info_dict': {
951 'id': '300346',
952 'ext': 'mp4',
953 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
954 'thumbnail': 're:^https?://.*\.jpg$',
955 }
956 },
957 # Ooyala embed
958 {
959 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
960 'info_dict': {
961 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
962 'ext': 'mp4',
963 'description': 'VIDEO: Index/Match versus VLOOKUP.',
964 'title': 'This is what separates the Excel masters from the wannabes',
965 },
966 'params': {
967 # m3u8 downloads
968 'skip_download': True,
969 }
970 },
971 # Contains a SMIL manifest
972 {
973 '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',
974 'info_dict': {
975 'id': 'file',
976 'ext': 'flv',
977 'title': '+ Football: Lottery Champions League Europe',
978 'uploader': 'www.telewebion.com',
979 },
980 'params': {
981 # rtmpe downloads
982 'skip_download': True,
983 }
984 },
985 # Brightcove URL in single quotes
986 {
987 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
988 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
989 'info_dict': {
990 'id': '4255764656001',
991 'ext': 'mp4',
992 'title': 'SN Presents: Russell Martin, World Citizen',
993 'description': 'To understand why he was the Toronto Blue Jaysā€™ 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.',
994 'uploader': 'Rogers Sportsnet',
995 },
996 },
997 # Dailymotion Cloud video
998 {
999 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1000 'md5': '49444254273501a64675a7e68c502681',
1001 'info_dict': {
1002 'id': '5585de919473990de4bee11b',
1003 'ext': 'mp4',
1004 'title': 'Le dƩbat',
1005 'thumbnail': 're:^https?://.*\.jpe?g$',
1006 }
1007 },
1008 # OnionStudios embed
1009 {
1010 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1011 'info_dict': {
1012 'id': '2855',
1013 'ext': 'mp4',
1014 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1015 'thumbnail': 're:^https?://.*\.jpe?g$',
1016 'uploader': 'ClickHole',
1017 'uploader_id': 'clickhole',
1018 }
1019 },
1020 # SnagFilms embed
1021 {
1022 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1023 'info_dict': {
1024 'id': '74849a00-85a9-11e1-9660-123139220831',
1025 'ext': 'mp4',
1026 'title': '#whilewewatch',
1027 }
1028 },
1029 # AdobeTVVideo embed
1030 {
1031 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1032 'md5': '43662b577c018ad707a63766462b1e87',
1033 'info_dict': {
1034 'id': '2456',
1035 'ext': 'mp4',
1036 'title': 'New experience with Acrobat DC',
1037 'description': 'New experience with Acrobat DC',
1038 'duration': 248.667,
1039 },
1040 },
1041 # ScreenwaveMedia embed
1042 {
1043 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1044 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1045 'info_dict': {
1046 'id': 'cinemasnob-55d26273809dd',
1047 'ext': 'mp4',
1048 'title': 'cinemasnob',
1049 },
1050 },
1051 # BrightcoveInPageEmbed embed
1052 {
1053 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1054 'info_dict': {
1055 'id': '4238694884001',
1056 'ext': 'flv',
1057 'title': 'Tabletop: Dread, Last Thoughts',
1058 'description': 'Tabletop: Dread, Last Thoughts',
1059 'duration': 51690,
1060 },
1061 },
1062 # JWPlayer with M3U8
1063 {
1064 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1065 'info_dict': {
1066 'id': 'playlist',
1067 'ext': 'mp4',
1068 'title': 'Š”Š»ŃƒŃ‡Š°Š¹Š½Ń‹Š¹ ŠæрŠ¾Ń…Š¾Š¶ŠøŠ¹ ŠæŠ¾Š¹Š¼Š°Š» Š°Š²Ń‚Š¾ŃƒŠ³Š¾Š½Ń‰ŠøŠŗŠ° Š² ŠœŃƒŃ€Š¼Š°Š½ŃŠŗŠµ. Š’Š˜Š”Š•Šž | Š Š•Š Š¢Š’',
1069 'uploader': 'ren.tv',
1070 },
1071 'params': {
1072 # m3u8 downloads
1073 'skip_download': True,
1074 }
1075 }
1076 ]
1077
1078 def report_following_redirect(self, new_url):
1079 """Report information extraction."""
1080 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1081
1082 def _extract_rss(self, url, video_id, doc):
1083 playlist_title = doc.find('./channel/title').text
1084 playlist_desc_el = doc.find('./channel/description')
1085 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1086
1087 entries = []
1088 for it in doc.findall('./channel/item'):
1089 next_url = xpath_text(it, 'link', fatal=False)
1090 if not next_url:
1091 enclosure_nodes = it.findall('./enclosure')
1092 for e in enclosure_nodes:
1093 next_url = e.attrib.get('url')
1094 if next_url:
1095 break
1096
1097 if not next_url:
1098 continue
1099
1100 entries.append({
1101 '_type': 'url',
1102 'url': next_url,
1103 'title': it.find('title').text,
1104 })
1105
1106 return {
1107 '_type': 'playlist',
1108 'id': url,
1109 'title': playlist_title,
1110 'description': playlist_desc,
1111 'entries': entries,
1112 }
1113
1114 def _extract_camtasia(self, url, video_id, webpage):
1115 """ Returns None if no camtasia video can be found. """
1116
1117 camtasia_cfg = self._search_regex(
1118 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1119 webpage, 'camtasia configuration file', default=None)
1120 if camtasia_cfg is None:
1121 return None
1122
1123 title = self._html_search_meta('DC.title', webpage, fatal=True)
1124
1125 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1126 camtasia_cfg = self._download_xml(
1127 camtasia_url, video_id,
1128 note='Downloading camtasia configuration',
1129 errnote='Failed to download camtasia configuration')
1130 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1131
1132 entries = []
1133 for n in fileset_node.getchildren():
1134 url_n = n.find('./uri')
1135 if url_n is None:
1136 continue
1137
1138 entries.append({
1139 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1140 'title': '%s - %s' % (title, n.tag),
1141 'url': compat_urlparse.urljoin(url, url_n.text),
1142 'duration': float_or_none(n.find('./duration').text),
1143 })
1144
1145 return {
1146 '_type': 'playlist',
1147 'entries': entries,
1148 'title': title,
1149 }
1150
1151 def _real_extract(self, url):
1152 if url.startswith('//'):
1153 return {
1154 '_type': 'url',
1155 'url': self.http_scheme() + url,
1156 }
1157
1158 parsed_url = compat_urlparse.urlparse(url)
1159 if not parsed_url.scheme:
1160 default_search = self._downloader.params.get('default_search')
1161 if default_search is None:
1162 default_search = 'fixup_error'
1163
1164 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1165 if '/' in url:
1166 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1167 return self.url_result('http://' + url)
1168 elif default_search != 'fixup_error':
1169 if default_search == 'auto_warning':
1170 if re.match(r'^(?:url|URL)$', url):
1171 raise ExtractorError(
1172 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1173 expected=True)
1174 else:
1175 self._downloader.report_warning(
1176 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1177 return self.url_result('ytsearch:' + url)
1178
1179 if default_search in ('error', 'fixup_error'):
1180 raise ExtractorError(
1181 '%r is not a valid URL. '
1182 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1183 % (url, url), expected=True)
1184 else:
1185 if ':' not in default_search:
1186 default_search += ':'
1187 return self.url_result(default_search + url)
1188
1189 url, smuggled_data = unsmuggle_url(url)
1190 force_videoid = None
1191 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1192 if smuggled_data and 'force_videoid' in smuggled_data:
1193 force_videoid = smuggled_data['force_videoid']
1194 video_id = force_videoid
1195 else:
1196 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1197
1198 self.to_screen('%s: Requesting header' % video_id)
1199
1200 head_req = HEADRequest(url)
1201 head_response = self._request_webpage(
1202 head_req, video_id,
1203 note=False, errnote='Could not send HEAD request to %s' % url,
1204 fatal=False)
1205
1206 if head_response is not False:
1207 # Check for redirect
1208 new_url = head_response.geturl()
1209 if url != new_url:
1210 self.report_following_redirect(new_url)
1211 if force_videoid:
1212 new_url = smuggle_url(
1213 new_url, {'force_videoid': force_videoid})
1214 return self.url_result(new_url)
1215
1216 full_response = None
1217 if head_response is False:
1218 request = sanitized_Request(url)
1219 request.add_header('Accept-Encoding', '*')
1220 full_response = self._request_webpage(request, video_id)
1221 head_response = full_response
1222
1223 # Check for direct link to a video
1224 content_type = head_response.headers.get('Content-Type', '')
1225 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1226 if m:
1227 upload_date = unified_strdate(
1228 head_response.headers.get('Last-Modified'))
1229 return {
1230 'id': video_id,
1231 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1232 'direct': True,
1233 'formats': [{
1234 'format_id': m.group('format_id'),
1235 'url': url,
1236 'vcodec': 'none' if m.group('type') == 'audio' else None
1237 }],
1238 'upload_date': upload_date,
1239 }
1240
1241 if not self._downloader.params.get('test', False) and not is_intentional:
1242 force = self._downloader.params.get('force_generic_extractor', False)
1243 self._downloader.report_warning(
1244 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1245
1246 if not full_response:
1247 request = sanitized_Request(url)
1248 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1249 # making it impossible to download only chunk of the file (yet we need only 512kB to
1250 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1251 # that will always result in downloading the whole file that is not desirable.
1252 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1253 # to accept raw bytes and being able to download only a chunk.
1254 # It may probably better to solve this by checking Content-Type for application/octet-stream
1255 # after HEAD request finishes, but not sure if we can rely on this.
1256 request.add_header('Accept-Encoding', '*')
1257 full_response = self._request_webpage(request, video_id)
1258
1259 # Maybe it's a direct link to a video?
1260 # Be careful not to download the whole thing!
1261 first_bytes = full_response.read(512)
1262 if not is_html(first_bytes):
1263 self._downloader.report_warning(
1264 'URL could be a direct video link, returning it as such.')
1265 upload_date = unified_strdate(
1266 head_response.headers.get('Last-Modified'))
1267 return {
1268 'id': video_id,
1269 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1270 'direct': True,
1271 'url': url,
1272 'upload_date': upload_date,
1273 }
1274
1275 webpage = self._webpage_read_content(
1276 full_response, url, video_id, prefix=first_bytes)
1277
1278 self.report_extraction(video_id)
1279
1280 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1281 try:
1282 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1283 if doc.tag == 'rss':
1284 return self._extract_rss(url, video_id, doc)
1285 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1286 return self._parse_smil(doc, url, video_id)
1287 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1288 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1289 except compat_xml_parse_error:
1290 pass
1291
1292 # Is it a Camtasia project?
1293 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1294 if camtasia_res is not None:
1295 return camtasia_res
1296
1297 # Sometimes embedded video player is hidden behind percent encoding
1298 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1299 # Unescaping the whole page allows to handle those cases in a generic way
1300 webpage = compat_urllib_parse_unquote(webpage)
1301
1302 # it's tempting to parse this further, but you would
1303 # have to take into account all the variations like
1304 # Video Title - Site Name
1305 # Site Name | Video Title
1306 # Video Title - Tagline | Site Name
1307 # and so on and so forth; it's just not practical
1308 video_title = self._html_search_regex(
1309 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1310 default='video')
1311
1312 # Try to detect age limit automatically
1313 age_limit = self._rta_search(webpage)
1314 # And then there are the jokers who advertise that they use RTA,
1315 # but actually don't.
1316 AGE_LIMIT_MARKERS = [
1317 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1318 ]
1319 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1320 age_limit = 18
1321
1322 # video uploader is domain name
1323 video_uploader = self._search_regex(
1324 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1325
1326 # Helper method
1327 def _playlist_from_matches(matches, getter=None, ie=None):
1328 urlrs = orderedSet(
1329 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1330 for m in matches)
1331 return self.playlist_result(
1332 urlrs, playlist_id=video_id, playlist_title=video_title)
1333
1334 # Look for Brightcove Legacy Studio embeds
1335 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1336 if bc_urls:
1337 self.to_screen('Brightcove video detected.')
1338 entries = [{
1339 '_type': 'url',
1340 'url': smuggle_url(bc_url, {'Referer': url}),
1341 'ie_key': 'BrightcoveLegacy'
1342 } for bc_url in bc_urls]
1343
1344 return {
1345 '_type': 'playlist',
1346 'title': video_title,
1347 'id': video_id,
1348 'entries': entries,
1349 }
1350
1351 # Look for Brightcove New Studio embeds
1352 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1353 if bc_urls:
1354 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1355
1356 # Look for embedded rtl.nl player
1357 matches = re.findall(
1358 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1359 webpage)
1360 if matches:
1361 return _playlist_from_matches(matches, ie='RtlNl')
1362
1363 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1364 if vimeo_url is not None:
1365 return self.url_result(vimeo_url)
1366
1367 vid_me_embed_url = self._search_regex(
1368 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1369 webpage, 'vid.me embed', default=None)
1370 if vid_me_embed_url is not None:
1371 return self.url_result(vid_me_embed_url, 'Vidme')
1372
1373 # Look for embedded YouTube player
1374 matches = re.findall(r'''(?x)
1375 (?:
1376 <iframe[^>]+?src=|
1377 data-video-url=|
1378 <embed[^>]+?src=|
1379 embedSWF\(?:\s*|
1380 new\s+SWFObject\(
1381 )
1382 (["\'])
1383 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1384 (?:embed|v|p)/.+?)
1385 \1''', webpage)
1386 if matches:
1387 return _playlist_from_matches(
1388 matches, lambda m: unescapeHTML(m[1]))
1389
1390 # Look for lazyYT YouTube embed
1391 matches = re.findall(
1392 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1393 if matches:
1394 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1395
1396 # Look for embedded Dailymotion player
1397 matches = re.findall(
1398 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1399 if matches:
1400 return _playlist_from_matches(
1401 matches, lambda m: unescapeHTML(m[1]))
1402
1403 # Look for embedded Dailymotion playlist player (#3822)
1404 m = re.search(
1405 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1406 if m:
1407 playlists = re.findall(
1408 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1409 if playlists:
1410 return _playlist_from_matches(
1411 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1412
1413 # Look for embedded Wistia player
1414 match = re.search(
1415 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1416 if match:
1417 embed_url = self._proto_relative_url(
1418 unescapeHTML(match.group('url')))
1419 return {
1420 '_type': 'url_transparent',
1421 'url': embed_url,
1422 'ie_key': 'Wistia',
1423 'uploader': video_uploader,
1424 'title': video_title,
1425 'id': video_id,
1426 }
1427
1428 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1429 if match:
1430 return {
1431 '_type': 'url_transparent',
1432 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1433 'ie_key': 'Wistia',
1434 'uploader': video_uploader,
1435 'title': video_title,
1436 'id': match.group('id')
1437 }
1438
1439 # Look for embedded blip.tv player
1440 bliptv_url = BlipTVIE._extract_url(webpage)
1441 if bliptv_url:
1442 return self.url_result(bliptv_url, 'BlipTV')
1443
1444 # Look for SVT player
1445 svt_url = SVTIE._extract_url(webpage)
1446 if svt_url:
1447 return self.url_result(svt_url, 'SVT')
1448
1449 # Look for embedded condenast player
1450 matches = re.findall(
1451 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1452 webpage)
1453 if matches:
1454 return {
1455 '_type': 'playlist',
1456 'entries': [{
1457 '_type': 'url',
1458 'ie_key': 'CondeNast',
1459 'url': ma,
1460 } for ma in matches],
1461 'title': video_title,
1462 'id': video_id,
1463 }
1464
1465 # Look for Bandcamp pages with custom domain
1466 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1467 if mobj is not None:
1468 burl = unescapeHTML(mobj.group(1))
1469 # Don't set the extractor because it can be a track url or an album
1470 return self.url_result(burl)
1471
1472 # Look for embedded Vevo player
1473 mobj = re.search(
1474 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1475 if mobj is not None:
1476 return self.url_result(mobj.group('url'))
1477
1478 # Look for embedded Viddler player
1479 mobj = re.search(
1480 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1481 webpage)
1482 if mobj is not None:
1483 return self.url_result(mobj.group('url'))
1484
1485 # Look for NYTimes player
1486 mobj = re.search(
1487 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1488 webpage)
1489 if mobj is not None:
1490 return self.url_result(mobj.group('url'))
1491
1492 # Look for Libsyn player
1493 mobj = re.search(
1494 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1495 if mobj is not None:
1496 return self.url_result(mobj.group('url'))
1497
1498 # Look for Ooyala videos
1499 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1500 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1501 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1502 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1503 if mobj is not None:
1504 return OoyalaIE._build_url_result(mobj.group('ec'))
1505
1506 # Look for multiple Ooyala embeds on SBN network websites
1507 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1508 if mobj is not None:
1509 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1510 if embeds:
1511 return _playlist_from_matches(
1512 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1513
1514 # Look for Aparat videos
1515 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1516 if mobj is not None:
1517 return self.url_result(mobj.group(1), 'Aparat')
1518
1519 # Look for MPORA videos
1520 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1521 if mobj is not None:
1522 return self.url_result(mobj.group(1), 'Mpora')
1523
1524 # Look for embedded NovaMov-based player
1525 mobj = re.search(
1526 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1527 (?P<url>http://(?:(?:embed|www)\.)?
1528 (?:novamov\.com|
1529 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1530 videoweed\.(?:es|com)|
1531 movshare\.(?:net|sx|ag)|
1532 divxstage\.(?:eu|net|ch|co|at|ag))
1533 /embed\.php.+?)\1''', webpage)
1534 if mobj is not None:
1535 return self.url_result(mobj.group('url'))
1536
1537 # Look for embedded Facebook player
1538 mobj = re.search(
1539 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1540 if mobj is not None:
1541 return self.url_result(mobj.group('url'), 'Facebook')
1542
1543 # Look for embedded VK player
1544 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1545 if mobj is not None:
1546 return self.url_result(mobj.group('url'), 'VK')
1547
1548 # Look for embedded ivi player
1549 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1550 if mobj is not None:
1551 return self.url_result(mobj.group('url'), 'Ivi')
1552
1553 # Look for embedded Huffington Post player
1554 mobj = re.search(
1555 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1556 if mobj is not None:
1557 return self.url_result(mobj.group('url'), 'HuffPost')
1558
1559 # Look for embed.ly
1560 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1561 if mobj is not None:
1562 return self.url_result(mobj.group('url'))
1563 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1564 if mobj is not None:
1565 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1566
1567 # Look for funnyordie embed
1568 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1569 if matches:
1570 return _playlist_from_matches(
1571 matches, getter=unescapeHTML, ie='FunnyOrDie')
1572
1573 # Look for BBC iPlayer embed
1574 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1575 if matches:
1576 return _playlist_from_matches(matches, ie='BBCCoUk')
1577
1578 # Look for embedded RUTV player
1579 rutv_url = RUTVIE._extract_url(webpage)
1580 if rutv_url:
1581 return self.url_result(rutv_url, 'RUTV')
1582
1583 # Look for embedded TVC player
1584 tvc_url = TVCIE._extract_url(webpage)
1585 if tvc_url:
1586 return self.url_result(tvc_url, 'TVC')
1587
1588 # Look for embedded SportBox player
1589 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1590 if sportbox_urls:
1591 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1592
1593 # Look for embedded PornHub player
1594 pornhub_url = PornHubIE._extract_url(webpage)
1595 if pornhub_url:
1596 return self.url_result(pornhub_url, 'PornHub')
1597
1598 # Look for embedded XHamster player
1599 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1600 if xhamster_urls:
1601 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1602
1603 # Look for embedded Tvigle player
1604 mobj = re.search(
1605 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1606 if mobj is not None:
1607 return self.url_result(mobj.group('url'), 'Tvigle')
1608
1609 # Look for embedded TED player
1610 mobj = re.search(
1611 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1612 if mobj is not None:
1613 return self.url_result(mobj.group('url'), 'TED')
1614
1615 # Look for embedded Ustream videos
1616 mobj = re.search(
1617 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1618 if mobj is not None:
1619 return self.url_result(mobj.group('url'), 'Ustream')
1620
1621 # Look for embedded arte.tv player
1622 mobj = re.search(
1623 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1624 webpage)
1625 if mobj is not None:
1626 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1627
1628 # Look for embedded francetv player
1629 mobj = re.search(
1630 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1631 webpage)
1632 if mobj is not None:
1633 return self.url_result(mobj.group('url'))
1634
1635 # Look for embedded smotri.com player
1636 smotri_url = SmotriIE._extract_url(webpage)
1637 if smotri_url:
1638 return self.url_result(smotri_url, 'Smotri')
1639
1640 # Look for embedded Myvi.ru player
1641 myvi_url = MyviIE._extract_url(webpage)
1642 if myvi_url:
1643 return self.url_result(myvi_url)
1644
1645 # Look for embeded soundcloud player
1646 mobj = re.search(
1647 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1648 webpage)
1649 if mobj is not None:
1650 url = unescapeHTML(mobj.group('url'))
1651 return self.url_result(url)
1652
1653 # Look for embedded vulture.com player
1654 mobj = re.search(
1655 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1656 webpage)
1657 if mobj is not None:
1658 url = unescapeHTML(mobj.group('url'))
1659 return self.url_result(url, ie='Vulture')
1660
1661 # Look for embedded mtvservices player
1662 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1663 if mtvservices_url:
1664 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1665
1666 # Look for embedded yahoo player
1667 mobj = re.search(
1668 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1669 webpage)
1670 if mobj is not None:
1671 return self.url_result(mobj.group('url'), 'Yahoo')
1672
1673 # Look for embedded sbs.com.au player
1674 mobj = re.search(
1675 r'''(?x)
1676 (?:
1677 <meta\s+property="og:video"\s+content=|
1678 <iframe[^>]+?src=
1679 )
1680 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1681 webpage)
1682 if mobj is not None:
1683 return self.url_result(mobj.group('url'), 'SBS')
1684
1685 # Look for embedded Cinchcast player
1686 mobj = re.search(
1687 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1688 webpage)
1689 if mobj is not None:
1690 return self.url_result(mobj.group('url'), 'Cinchcast')
1691
1692 mobj = re.search(
1693 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1694 webpage)
1695 if not mobj:
1696 mobj = re.search(
1697 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1698 webpage)
1699 if mobj is not None:
1700 return self.url_result(mobj.group('url'), 'MLB')
1701
1702 mobj = re.search(
1703 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1704 webpage)
1705 if mobj is not None:
1706 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1707
1708 mobj = re.search(
1709 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1710 webpage)
1711 if mobj is not None:
1712 return self.url_result(mobj.group('url'), 'Livestream')
1713
1714 # Look for Zapiks embed
1715 mobj = re.search(
1716 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1717 if mobj is not None:
1718 return self.url_result(mobj.group('url'), 'Zapiks')
1719
1720 # Look for Kaltura embeds
1721 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1722 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))
1723 if mobj is not None:
1724 return self.url_result(smuggle_url(
1725 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1726 {'source_url': url}), 'Kaltura')
1727
1728 # Look for Eagle.Platform embeds
1729 mobj = re.search(
1730 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1731 if mobj is not None:
1732 return self.url_result(mobj.group('url'), 'EaglePlatform')
1733
1734 # Look for ClipYou (uses Eagle.Platform) embeds
1735 mobj = re.search(
1736 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1737 if mobj is not None:
1738 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1739
1740 # Look for Pladform embeds
1741 mobj = re.search(
1742 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1743 if mobj is not None:
1744 return self.url_result(mobj.group('url'), 'Pladform')
1745
1746 # Look for Playwire embeds
1747 mobj = re.search(
1748 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1749 if mobj is not None:
1750 return self.url_result(mobj.group('url'))
1751
1752 # Look for 5min embeds
1753 mobj = re.search(
1754 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1755 if mobj is not None:
1756 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1757
1758 # Look for Crooks and Liars embeds
1759 mobj = re.search(
1760 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1761 if mobj is not None:
1762 return self.url_result(mobj.group('url'))
1763
1764 # Look for NBC Sports VPlayer embeds
1765 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1766 if nbc_sports_url:
1767 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1768
1769 # Look for UDN embeds
1770 mobj = re.search(
1771 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1772 if mobj is not None:
1773 return self.url_result(
1774 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1775
1776 # Look for Senate ISVP iframe
1777 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1778 if senate_isvp_url:
1779 return self.url_result(senate_isvp_url, 'SenateISVP')
1780
1781 # Look for Dailymotion Cloud videos
1782 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1783 if dmcloud_url:
1784 return self.url_result(dmcloud_url, 'DailymotionCloud')
1785
1786 # Look for OnionStudios embeds
1787 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1788 if onionstudios_url:
1789 return self.url_result(onionstudios_url)
1790
1791 # Look for SnagFilms embeds
1792 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1793 if snagfilms_url:
1794 return self.url_result(snagfilms_url)
1795
1796 # Look for ScreenwaveMedia embeds
1797 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1798 if mobj is not None:
1799 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1800
1801 # Look for AdobeTVVideo embeds
1802 mobj = re.search(
1803 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1804 webpage)
1805 if mobj is not None:
1806 return self.url_result(
1807 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1808 'AdobeTVVideo')
1809
1810 def check_video(vurl):
1811 if YoutubeIE.suitable(vurl):
1812 return True
1813 vpath = compat_urlparse.urlparse(vurl).path
1814 vext = determine_ext(vpath)
1815 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1816
1817 def filter_video(urls):
1818 return list(filter(check_video, urls))
1819
1820 # Start with something easy: JW Player in SWFObject
1821 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1822 if not found:
1823 # Look for gorilla-vid style embedding
1824 found = filter_video(re.findall(r'''(?sx)
1825 (?:
1826 jw_plugins|
1827 JWPlayerOptions|
1828 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1829 )
1830 .*?
1831 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1832 if not found:
1833 # Broaden the search a little bit
1834 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1835 if not found:
1836 # Broaden the findall a little bit: JWPlayer JS loader
1837 found = filter_video(re.findall(
1838 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1839 if not found:
1840 # Flow player
1841 found = filter_video(re.findall(r'''(?xs)
1842 flowplayer\("[^"]+",\s*
1843 \{[^}]+?\}\s*,
1844 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1845 ["']?url["']?\s*:\s*["']([^"']+)["']
1846 ''', webpage))
1847 if not found:
1848 # Cinerama player
1849 found = re.findall(
1850 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1851 if not found:
1852 # Try to find twitter cards info
1853 found = filter_video(re.findall(
1854 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1855 if not found:
1856 # We look for Open Graph info:
1857 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1858 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1859 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1860 if m_video_type is not None:
1861 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1862 if not found:
1863 # HTML5 video
1864 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1865 if not found:
1866 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1867 found = re.search(
1868 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1869 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1870 webpage)
1871 if not found:
1872 # Look also in Refresh HTTP header
1873 refresh_header = head_response.headers.get('Refresh')
1874 if refresh_header:
1875 # In python 2 response HTTP headers are bytestrings
1876 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1877 refresh_header = refresh_header.decode('iso-8859-1')
1878 found = re.search(REDIRECT_REGEX, refresh_header)
1879 if found:
1880 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1881 self.report_following_redirect(new_url)
1882 return {
1883 '_type': 'url',
1884 'url': new_url,
1885 }
1886 if not found:
1887 raise UnsupportedError(url)
1888
1889 entries = []
1890 for video_url in found:
1891 video_url = video_url.replace('\\/', '/')
1892 video_url = compat_urlparse.urljoin(url, video_url)
1893 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1894
1895 # Sometimes, jwplayer extraction will result in a YouTube URL
1896 if YoutubeIE.suitable(video_url):
1897 entries.append(self.url_result(video_url, 'Youtube'))
1898 continue
1899
1900 # here's a fun little line of code for you:
1901 video_id = os.path.splitext(video_id)[0]
1902
1903 entry_info_dict = {
1904 'id': video_id,
1905 'uploader': video_uploader,
1906 'title': video_title,
1907 'age_limit': age_limit,
1908 }
1909
1910 ext = determine_ext(video_url)
1911 if ext == 'smil':
1912 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1913 elif ext == 'xspf':
1914 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1915 elif ext == 'm3u8':
1916 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1917 else:
1918 entry_info_dict['url'] = video_url
1919
1920 entries.append(entry_info_dict)
1921
1922 if len(entries) == 1:
1923 return entries[0]
1924 else:
1925 for num, e in enumerate(entries, start=1):
1926 # 'url' results don't have a title
1927 if e.get('title') is not None:
1928 e['title'] = '%s (%d)' % (e['title'], num)
1929 return {
1930 '_type': 'playlist',
1931 'entries': entries,
1932 }
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...