]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
New upstream version 2017.03.07
[youtubedl] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 js_to_json,
24 orderedSet,
25 sanitized_Request,
26 smuggle_url,
27 unescapeHTML,
28 unified_strdate,
29 unsmuggle_url,
30 UnsupportedError,
31 xpath_text,
32 )
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
35 BrightcoveLegacyIE,
36 BrightcoveNewIE,
37 )
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
56 DailymotionIE,
57 DailymotionCloudIE,
58 )
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87 from .rutube import RutubeIE
88
89
90 class GenericIE(InfoExtractor):
91 IE_DESC = 'Generic downloader that works on some sites'
92 _VALID_URL = r'.*'
93 IE_NAME = 'generic'
94 _TESTS = [
95 # Direct link to a video
96 {
97 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
98 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
99 'info_dict': {
100 'id': 'trailer',
101 'ext': 'mp4',
102 'title': 'trailer',
103 'upload_date': '20100513',
104 }
105 },
106 # Direct link to media delivered compressed (until Accept-Encoding is *)
107 {
108 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
109 'md5': '128c42e68b13950268b648275386fc74',
110 'info_dict': {
111 'id': 'FictionJunction-Parallel_Hearts',
112 'ext': 'flac',
113 'title': 'FictionJunction-Parallel_Hearts',
114 'upload_date': '20140522',
115 },
116 'expected_warnings': [
117 'URL could be a direct video link, returning it as such.'
118 ],
119 'skip': 'URL invalid',
120 },
121 # Direct download with broken HEAD
122 {
123 'url': 'http://ai-radio.org:8000/radio.opus',
124 'info_dict': {
125 'id': 'radio',
126 'ext': 'opus',
127 'title': 'radio',
128 },
129 'params': {
130 'skip_download': True, # infinite live stream
131 },
132 'expected_warnings': [
133 r'501.*Not Implemented',
134 r'400.*Bad Request',
135 ],
136 },
137 # Direct link with incorrect MIME type
138 {
139 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
140 'md5': '4ccbebe5f36706d85221f204d7eb5913',
141 'info_dict': {
142 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
143 'id': '5_Lennart_Poettering_-_Systemd',
144 'ext': 'webm',
145 'title': '5_Lennart_Poettering_-_Systemd',
146 'upload_date': '20141120',
147 },
148 'expected_warnings': [
149 'URL could be a direct video link, returning it as such.'
150 ]
151 },
152 # RSS feed
153 {
154 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
155 'info_dict': {
156 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'title': 'Zero Punctuation',
158 'description': 're:.*groundbreaking video review series.*'
159 },
160 'playlist_mincount': 11,
161 },
162 # RSS feed with enclosure
163 {
164 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
165 'info_dict': {
166 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
167 'ext': 'm4v',
168 'upload_date': '20150228',
169 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
170 }
171 },
172 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
173 {
174 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
175 'info_dict': {
176 'id': 'smil',
177 'ext': 'mp4',
178 'title': 'Automatics, robotics and biocybernetics',
179 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
180 'upload_date': '20130627',
181 'formats': 'mincount:16',
182 'subtitles': 'mincount:1',
183 },
184 'params': {
185 'force_generic_extractor': True,
186 'skip_download': True,
187 },
188 },
189 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
190 {
191 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
192 'info_dict': {
193 'id': 'hds',
194 'ext': 'flv',
195 'title': 'hds',
196 'formats': 'mincount:1',
197 },
198 'params': {
199 'skip_download': True,
200 },
201 },
202 # SMIL from https://www.restudy.dk/video/play/id/1637
203 {
204 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
205 'info_dict': {
206 'id': 'video_1637',
207 'ext': 'flv',
208 'title': 'video_1637',
209 'formats': 'mincount:3',
210 },
211 'params': {
212 'skip_download': True,
213 },
214 },
215 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
216 {
217 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
218 'info_dict': {
219 'id': 'smil-service',
220 'ext': 'flv',
221 'title': 'smil-service',
222 'formats': 'mincount:1',
223 },
224 'params': {
225 'skip_download': True,
226 },
227 },
228 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
229 {
230 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
231 'info_dict': {
232 'id': '4719370',
233 'ext': 'mp4',
234 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
235 'formats': 'mincount:3',
236 },
237 'params': {
238 'skip_download': True,
239 },
240 },
241 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
242 {
243 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
244 'info_dict': {
245 'id': 'mZlp2ctYIUEB',
246 'ext': 'mp4',
247 'title': 'Tikibad ontruimd wegens brand',
248 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
249 'thumbnail': r're:^https?://.*\.jpg$',
250 'duration': 33,
251 },
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # MPD from http://dash-mse-test.appspot.com/media.html
257 {
258 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
259 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
260 'info_dict': {
261 'id': 'car-20120827-manifest',
262 'ext': 'mp4',
263 'title': 'car-20120827-manifest',
264 'formats': 'mincount:9',
265 'upload_date': '20130904',
266 },
267 'params': {
268 'format': 'bestvideo',
269 },
270 },
271 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
272 {
273 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
274 'info_dict': {
275 'id': 'content',
276 'ext': 'mp4',
277 'title': 'content',
278 'formats': 'mincount:8',
279 },
280 'params': {
281 # m3u8 downloads
282 'skip_download': True,
283 },
284 'skip': 'video gone',
285 },
286 # m3u8 served with Content-Type: text/plain
287 {
288 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
289 'info_dict': {
290 'id': 'index',
291 'ext': 'mp4',
292 'title': 'index',
293 'upload_date': '20140720',
294 'formats': 'mincount:11',
295 },
296 'params': {
297 # m3u8 downloads
298 'skip_download': True,
299 },
300 'skip': 'video gone',
301 },
302 # google redirect
303 {
304 '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',
305 'info_dict': {
306 'id': 'cmQHVoWB5FY',
307 'ext': 'mp4',
308 'upload_date': '20130224',
309 'uploader_id': 'TheVerge',
310 'description': r're:^Chris Ziegler takes a look at the\.*',
311 'uploader': 'The Verge',
312 'title': 'First Firefox OS phones side-by-side',
313 },
314 'params': {
315 'skip_download': False,
316 }
317 },
318 {
319 # redirect in Refresh HTTP header
320 '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',
321 'info_dict': {
322 'id': 'pO8h3EaFRdo',
323 'ext': 'mp4',
324 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
325 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
326 'upload_date': '20150917',
327 'uploader_id': 'brtvofficial',
328 'uploader': 'Boiler Room',
329 },
330 'params': {
331 'skip_download': False,
332 },
333 },
334 {
335 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
336 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
337 'info_dict': {
338 'id': '13601338388002',
339 'ext': 'mp4',
340 'uploader': 'www.hodiho.fr',
341 'title': 'R\u00e9gis plante sa Jeep',
342 }
343 },
344 # bandcamp page with custom domain
345 {
346 'add_ie': ['Bandcamp'],
347 'url': 'http://bronyrock.com/track/the-pony-mash',
348 'info_dict': {
349 'id': '3235767654',
350 'ext': 'mp3',
351 'title': 'The Pony Mash',
352 'uploader': 'M_Pallante',
353 },
354 'skip': 'There is a limit of 200 free downloads / month for the test song',
355 },
356 {
357 # embedded brightcove video
358 # it also tests brightcove videos that need to set the 'Referer'
359 # in the http requests
360 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
362 'info_dict': {
363 'id': '2765128793001',
364 'ext': 'mp4',
365 'title': 'Le cours de bourse : lā€™analyse technique',
366 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
367 'uploader': 'BFM BUSINESS',
368 },
369 'params': {
370 'skip_download': True,
371 },
372 },
373 {
374 # embedded with itemprop embedURL and video id spelled as `idVideo`
375 'add_id': ['BrightcoveLegacy'],
376 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
377 'info_dict': {
378 'id': '5255628253001',
379 'ext': 'mp4',
380 'title': 'md5:37c519b1128915607601e75a87995fc0',
381 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
382 'uploader': 'BFM BUSINESS',
383 'uploader_id': '876450612001',
384 'timestamp': 1482255315,
385 'upload_date': '20161220',
386 },
387 'params': {
388 'skip_download': True,
389 },
390 },
391 {
392 # https://github.com/rg3/youtube-dl/issues/2253
393 'url': 'http://bcove.me/i6nfkrc3',
394 'md5': '0ba9446db037002366bab3b3eb30c88c',
395 'info_dict': {
396 'id': '3101154703001',
397 'ext': 'mp4',
398 'title': 'Still no power',
399 'uploader': 'thestar.com',
400 '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.',
401 },
402 'add_ie': ['BrightcoveLegacy'],
403 'skip': 'video gone',
404 },
405 {
406 'url': 'http://www.championat.com/video/football/v/87/87499.html',
407 'md5': 'fb973ecf6e4a78a67453647444222983',
408 'info_dict': {
409 'id': '3414141473001',
410 'ext': 'mp4',
411 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
412 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
413 'uploader': 'Championat',
414 },
415 },
416 {
417 # https://github.com/rg3/youtube-dl/issues/3541
418 'add_ie': ['BrightcoveLegacy'],
419 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
420 'info_dict': {
421 'id': '3866516442001',
422 'ext': 'mp4',
423 'title': 'Leer mij vrouwen kennen: Aflevering 1',
424 'description': 'Leer mij vrouwen kennen: Aflevering 1',
425 'uploader': 'SBS Broadcasting',
426 },
427 'skip': 'Restricted to Netherlands',
428 'params': {
429 'skip_download': True, # m3u8 download
430 },
431 },
432 {
433 # Brightcove with alternative playerID key
434 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
435 'info_dict': {
436 'id': 'nmeth.2062_SV1',
437 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
438 },
439 'playlist': [{
440 'info_dict': {
441 'id': '2228375078001',
442 'ext': 'mp4',
443 'title': 'nmeth.2062-sv1',
444 'description': 'nmeth.2062-sv1',
445 'timestamp': 1363357591,
446 'upload_date': '20130315',
447 'uploader': 'Nature Publishing Group',
448 'uploader_id': '1964492299001',
449 },
450 }],
451 },
452 # ooyala video
453 {
454 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
455 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
456 'info_dict': {
457 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
458 'ext': 'mp4',
459 'title': '2cc213299525360.mov', # that's what we get
460 'duration': 238.231,
461 },
462 'add_ie': ['Ooyala'],
463 },
464 {
465 # ooyala video embedded with http://player.ooyala.com/iframe.js
466 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
467 'info_dict': {
468 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
469 'ext': 'mp4',
470 'title': '"Steve Jobs: Man in the Machine" trailer',
471 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
472 'duration': 135.427,
473 },
474 'params': {
475 'skip_download': True,
476 },
477 'skip': 'movie expired',
478 },
479 # embed.ly video
480 {
481 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
482 'info_dict': {
483 'id': '9ODmcdjQcHQ',
484 'ext': 'mp4',
485 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
486 'upload_date': '20140225',
487 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
488 'uploader': 'Tested',
489 'uploader_id': 'testedcom',
490 },
491 # No need to test YoutubeIE here
492 'params': {
493 'skip_download': True,
494 },
495 },
496 # funnyordie embed
497 {
498 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
499 'info_dict': {
500 'id': '18e820ec3f',
501 'ext': 'mp4',
502 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
503 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
504 },
505 # HEAD requests lead to endless 301, while GET is OK
506 'expected_warnings': ['301'],
507 },
508 # RUTV embed
509 {
510 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
511 'info_dict': {
512 'id': '776940',
513 'ext': 'mp4',
514 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
515 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
516 },
517 'params': {
518 # m3u8 download
519 'skip_download': True,
520 },
521 },
522 # TVC embed
523 {
524 '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/',
525 'info_dict': {
526 'id': '55304',
527 'ext': 'mp4',
528 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
529 },
530 },
531 # SportBox embed
532 {
533 'url': 'http://www.vestifinance.ru/articles/25753',
534 'info_dict': {
535 'id': '25753',
536 'title': '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"',
537 },
538 'playlist': [{
539 'info_dict': {
540 'id': '370908',
541 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
542 'ext': 'mp4',
543 }
544 }, {
545 'info_dict': {
546 'id': '370905',
547 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
548 'ext': 'mp4',
549 }
550 }, {
551 'info_dict': {
552 'id': '370902',
553 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
554 'ext': 'mp4',
555 }
556 }],
557 'params': {
558 # m3u8 download
559 'skip_download': True,
560 },
561 },
562 # Myvi.ru embed
563 {
564 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
565 'info_dict': {
566 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
567 'ext': 'mp4',
568 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
569 'thumbnail': r're:^https?://.*\.jpg$',
570 'duration': 153,
571 }
572 },
573 # XHamster embed
574 {
575 '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',
576 'info_dict': {
577 'id': 'showthread',
578 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
579 },
580 'playlist_mincount': 7,
581 # This forum does not allow <iframe> syntaxes anymore
582 # Now HTML tags are displayed as-is
583 'skip': 'No videos on this page',
584 },
585 # Embedded TED video
586 {
587 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
588 'md5': '65fdff94098e4a607385a60c5177c638',
589 'info_dict': {
590 'id': '1969',
591 'ext': 'mp4',
592 'title': 'Hidden miracles of the natural world',
593 'uploader': 'Louie Schwartzberg',
594 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
595 }
596 },
597 # nowvideo embed hidden behind percent encoding
598 {
599 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
600 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
601 'info_dict': {
602 'id': '06e53103ca9aa',
603 'ext': 'flv',
604 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
605 'description': 'No description',
606 },
607 },
608 # arte embed
609 {
610 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
611 'md5': '7653032cbb25bf6c80d80f217055fa43',
612 'info_dict': {
613 'id': '048195-004_PLUS7-F',
614 'ext': 'flv',
615 'title': 'X:enius',
616 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
617 'upload_date': '20140320',
618 },
619 'params': {
620 'skip_download': 'Requires rtmpdump'
621 },
622 'skip': 'video gone',
623 },
624 # francetv embed
625 {
626 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
627 'info_dict': {
628 'id': 'EV_30231',
629 'ext': 'mp4',
630 'title': 'Alcaline, le concert avec Calogero',
631 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
632 'upload_date': '20150226',
633 'timestamp': 1424989860,
634 'duration': 5400,
635 },
636 'params': {
637 # m3u8 downloads
638 'skip_download': True,
639 },
640 'expected_warnings': [
641 'Forbidden'
642 ]
643 },
644 # CondƩ Nast embed
645 {
646 'url': 'http://www.wired.com/2014/04/honda-asimo/',
647 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
648 'info_dict': {
649 'id': '53501be369702d3275860000',
650 'ext': 'mp4',
651 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
652 }
653 },
654 # Dailymotion embed
655 {
656 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
657 'md5': '441aeeb82eb72c422c7f14ec533999cd',
658 'info_dict': {
659 'id': 'k2mm4bCdJ6CQ2i7c8o2',
660 'ext': 'mp4',
661 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
662 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
663 'uploader': 'Spi0n',
664 'uploader_id': 'xgditw',
665 'upload_date': '20140425',
666 'timestamp': 1398441542,
667 },
668 'add_ie': ['Dailymotion'],
669 },
670 # YouTube embed
671 {
672 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
673 'info_dict': {
674 'id': 'FXRb4ykk4S0',
675 'ext': 'mp4',
676 'title': 'The NBL Auction 2014',
677 'uploader': 'BADMINTON England',
678 'uploader_id': 'BADMINTONEvents',
679 'upload_date': '20140603',
680 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
681 },
682 'add_ie': ['Youtube'],
683 'params': {
684 'skip_download': True,
685 }
686 },
687 # MTVSercices embed
688 {
689 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
690 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
691 'info_dict': {
692 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
693 'ext': 'mp4',
694 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
695 'description': 'Two valets share their love for movie star Liam Neesons.',
696 'timestamp': 1349922600,
697 'upload_date': '20121011',
698 },
699 },
700 # YouTube embed via <data-embed-url="">
701 {
702 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
703 'info_dict': {
704 'id': '4vAffPZIT44',
705 'ext': 'mp4',
706 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
707 'uploader': 'Gameloft',
708 'uploader_id': 'gameloft',
709 'upload_date': '20140828',
710 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
711 },
712 'params': {
713 'skip_download': True,
714 }
715 },
716 # Camtasia studio
717 {
718 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
719 'playlist': [{
720 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
721 'info_dict': {
722 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
723 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
724 'ext': 'flv',
725 'duration': 2235.90,
726 }
727 }, {
728 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
729 'info_dict': {
730 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
731 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
732 'ext': 'flv',
733 'duration': 2235.93,
734 }
735 }],
736 'info_dict': {
737 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
738 }
739 },
740 # Flowplayer
741 {
742 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
743 'md5': '9d65602bf31c6e20014319c7d07fba27',
744 'info_dict': {
745 'id': '5123ea6d5e5a7',
746 'ext': 'mp4',
747 'age_limit': 18,
748 'uploader': 'www.handjobhub.com',
749 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
750 }
751 },
752 # Multiple brightcove videos
753 # https://github.com/rg3/youtube-dl/issues/2283
754 {
755 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
756 'info_dict': {
757 'id': 'always-never',
758 'title': 'Always / Never - The New Yorker',
759 },
760 'playlist_count': 3,
761 'params': {
762 'extract_flat': False,
763 'skip_download': True,
764 }
765 },
766 # MLB embed
767 {
768 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
769 'md5': '96f09a37e44da40dd083e12d9a683327',
770 'info_dict': {
771 'id': '33322633',
772 'ext': 'mp4',
773 'title': 'Ump changes call to ball',
774 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
775 'duration': 48,
776 'timestamp': 1401537900,
777 'upload_date': '20140531',
778 'thumbnail': r're:^https?://.*\.jpg$',
779 },
780 },
781 # Wistia embed
782 {
783 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
784 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
785 'info_dict': {
786 'id': '6e2wtrbdaf',
787 'ext': 'mov',
788 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
789 'description': 'a Paywall Videos video from Remilon',
790 'duration': 644.072,
791 'uploader': 'study.com',
792 'timestamp': 1459678540,
793 'upload_date': '20160403',
794 'filesize': 24687186,
795 },
796 },
797 {
798 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
799 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
800 'info_dict': {
801 'id': 'uxjb0lwrcz',
802 'ext': 'mp4',
803 'title': 'Conversation about Hexagonal Rails Part 1',
804 'description': 'a Martin Fowler video from ThoughtWorks',
805 'duration': 1715.0,
806 'uploader': 'thoughtworks.wistia.com',
807 'timestamp': 1401832161,
808 'upload_date': '20140603',
809 },
810 },
811 # Wistia standard embed (async)
812 {
813 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
814 'info_dict': {
815 'id': '807fafadvk',
816 'ext': 'mp4',
817 'title': 'Drip Brennan Dunn Workshop',
818 'description': 'a JV Webinars video from getdrip-1',
819 'duration': 4986.95,
820 'timestamp': 1463607249,
821 'upload_date': '20160518',
822 },
823 'params': {
824 'skip_download': True,
825 }
826 },
827 # Soundcloud embed
828 {
829 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
830 'info_dict': {
831 'id': '174391317',
832 'ext': 'mp3',
833 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
834 'uploader': 'Sophos Security',
835 'title': 'Chet Chat 171 - Oct 29, 2014',
836 'upload_date': '20141029',
837 }
838 },
839 # Soundcloud multiple embeds
840 {
841 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
842 'info_dict': {
843 'id': '52809',
844 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
845 },
846 'playlist_mincount': 7,
847 },
848 # TuneIn station embed
849 {
850 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
851 'info_dict': {
852 'id': '204146',
853 'ext': 'mp3',
854 'title': 'CNRV',
855 'location': 'Paris, France',
856 'is_live': True,
857 },
858 'params': {
859 # Live stream
860 'skip_download': True,
861 },
862 },
863 # Livestream embed
864 {
865 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
866 'info_dict': {
867 'id': '67864563',
868 'ext': 'flv',
869 'upload_date': '20141112',
870 'title': 'Rosetta #CometLanding webcast HL 10',
871 }
872 },
873 # Another Livestream embed, without 'new.' in URL
874 {
875 'url': 'https://www.freespeech.org/',
876 'info_dict': {
877 'id': '123537347',
878 'ext': 'mp4',
879 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
880 },
881 'params': {
882 # Live stream
883 'skip_download': True,
884 },
885 },
886 # LazyYT
887 {
888 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
889 'info_dict': {
890 'id': '1986',
891 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
892 },
893 'playlist_mincount': 2,
894 },
895 # Cinchcast embed
896 {
897 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
898 'info_dict': {
899 'id': '7141703',
900 'ext': 'mp3',
901 'upload_date': '20141126',
902 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
903 }
904 },
905 # Cinerama player
906 {
907 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
908 'info_dict': {
909 'id': '730m_DandD_1901_512k',
910 'ext': 'mp4',
911 'uploader': 'www.abc.net.au',
912 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
913 }
914 },
915 # embedded viddler video
916 {
917 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
918 'info_dict': {
919 'id': '4d03aad9',
920 'ext': 'mp4',
921 'uploader': 'deadspin',
922 'title': 'WALL-TO-GORTAT',
923 'timestamp': 1422285291,
924 'upload_date': '20150126',
925 },
926 'add_ie': ['Viddler'],
927 },
928 # Libsyn embed
929 {
930 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
931 'info_dict': {
932 'id': '3377616',
933 'ext': 'mp3',
934 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
935 'description': 'md5:601cb790edd05908957dae8aaa866465',
936 'upload_date': '20150220',
937 },
938 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
939 },
940 # jwplayer YouTube
941 {
942 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
943 'info_dict': {
944 'id': 'Mrj4DVp2zeA',
945 'ext': 'mp4',
946 'upload_date': '20150212',
947 'uploader': 'The National Archives UK',
948 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
949 'uploader_id': 'NationalArchives08',
950 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
951 },
952 },
953 # jwplayer rtmp
954 {
955 'url': 'http://www.suffolk.edu/sjc/',
956 'info_dict': {
957 'id': 'sjclive',
958 'ext': 'flv',
959 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
960 'uploader': 'www.suffolk.edu',
961 },
962 'params': {
963 'skip_download': True,
964 }
965 },
966 # Complex jwplayer
967 {
968 'url': 'http://www.indiedb.com/games/king-machine/videos',
969 'info_dict': {
970 'id': 'videos',
971 'ext': 'mp4',
972 'title': 'king machine trailer 1',
973 'thumbnail': r're:^https?://.*\.jpg$',
974 },
975 },
976 # rtl.nl embed
977 {
978 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
979 'playlist_mincount': 5,
980 'info_dict': {
981 'id': 'aanslagen-kopenhagen',
982 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
983 }
984 },
985 # Zapiks embed
986 {
987 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
988 'info_dict': {
989 'id': '118046',
990 'ext': 'mp4',
991 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
992 }
993 },
994 # Kaltura embed (different embed code)
995 {
996 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
997 'info_dict': {
998 'id': '1_a52wc67y',
999 'ext': 'flv',
1000 'upload_date': '20150127',
1001 'uploader_id': 'PremierMedia',
1002 'timestamp': int,
1003 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1004 },
1005 },
1006 # Kaltura embed with single quotes
1007 {
1008 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1009 'info_dict': {
1010 'id': '0_izeg5utt',
1011 'ext': 'mp4',
1012 'title': '35871',
1013 'timestamp': 1355743100,
1014 'upload_date': '20121217',
1015 'uploader_id': 'batchUser',
1016 },
1017 'add_ie': ['Kaltura'],
1018 },
1019 {
1020 # Kaltura embedded via quoted entry_id
1021 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1022 'info_dict': {
1023 'id': '0_utuok90b',
1024 'ext': 'mp4',
1025 'title': '06_matthew_brender_raj_dutt',
1026 'timestamp': 1466638791,
1027 'upload_date': '20160622',
1028 },
1029 'add_ie': ['Kaltura'],
1030 'expected_warnings': [
1031 'Could not send HEAD request'
1032 ],
1033 'params': {
1034 'skip_download': True,
1035 }
1036 },
1037 {
1038 # Kaltura embedded, some fileExt broken (#11480)
1039 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1040 'info_dict': {
1041 'id': '1_sgtvehim',
1042 'ext': 'mp4',
1043 'title': 'Our "Standard Models" of particle physics and cosmology',
1044 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1045 'timestamp': 1321158993,
1046 'upload_date': '20111113',
1047 'uploader_id': 'kps1',
1048 },
1049 'add_ie': ['Kaltura'],
1050 },
1051 # Eagle.Platform embed (generic URL)
1052 {
1053 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1054 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1055 'info_dict': {
1056 'id': '227304',
1057 'ext': 'mp4',
1058 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1059 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1060 'thumbnail': r're:^https?://.*\.jpg$',
1061 'duration': 87,
1062 'view_count': int,
1063 'age_limit': 0,
1064 },
1065 },
1066 # ClipYou (Eagle.Platform) embed (custom URL)
1067 {
1068 'url': 'http://muz-tv.ru/play/7129/',
1069 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1070 'info_dict': {
1071 'id': '12820',
1072 'ext': 'mp4',
1073 'title': "'O Sole Mio",
1074 'thumbnail': r're:^https?://.*\.jpg$',
1075 'duration': 216,
1076 'view_count': int,
1077 },
1078 },
1079 # Pladform embed
1080 {
1081 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1082 'info_dict': {
1083 'id': '100183293',
1084 'ext': 'mp4',
1085 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1086 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1087 'thumbnail': r're:^https?://.*\.jpg$',
1088 'duration': 694,
1089 'age_limit': 0,
1090 },
1091 },
1092 # Playwire embed
1093 {
1094 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1095 'info_dict': {
1096 'id': '3519514',
1097 'ext': 'mp4',
1098 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1099 'thumbnail': r're:^https?://.*\.png$',
1100 'duration': 45.115,
1101 },
1102 },
1103 # 5min embed
1104 {
1105 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1106 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1107 'info_dict': {
1108 'id': '518726732',
1109 'ext': 'mp4',
1110 'title': 'Facebook Creates "On This Day" | Crunch Report',
1111 },
1112 },
1113 # SVT embed
1114 {
1115 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1116 'info_dict': {
1117 'id': '2900353',
1118 'ext': 'flv',
1119 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1120 'duration': 27,
1121 'age_limit': 0,
1122 },
1123 },
1124 # Crooks and Liars embed
1125 {
1126 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1127 'info_dict': {
1128 'id': '8RUoRhRi',
1129 'ext': 'mp4',
1130 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1131 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1132 'timestamp': 1428207000,
1133 'upload_date': '20150405',
1134 'uploader': 'Heather',
1135 },
1136 },
1137 # Crooks and Liars external embed
1138 {
1139 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1140 'info_dict': {
1141 'id': 'MTE3MjUtMzQ2MzA',
1142 'ext': 'mp4',
1143 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1144 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1145 'timestamp': 1265032391,
1146 'upload_date': '20100201',
1147 'uploader': 'Heather',
1148 },
1149 },
1150 # NBC Sports vplayer embed
1151 {
1152 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1153 'info_dict': {
1154 'id': 'ln7x1qSThw4k',
1155 'ext': 'flv',
1156 'title': "PFT Live: New leader in the 'new-look' defense",
1157 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1158 'uploader': 'NBCU-SPORTS',
1159 'upload_date': '20140107',
1160 'timestamp': 1389118457,
1161 },
1162 },
1163 # NBC News embed
1164 {
1165 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1166 'md5': '1aa589c675898ae6d37a17913cf68d66',
1167 'info_dict': {
1168 'id': '701714499682',
1169 'ext': 'mp4',
1170 'title': 'PREVIEW: On Assignment: David Letterman',
1171 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1172 },
1173 },
1174 # UDN embed
1175 {
1176 'url': 'https://video.udn.com/news/300346',
1177 'md5': 'fd2060e988c326991037b9aff9df21a6',
1178 'info_dict': {
1179 'id': '300346',
1180 'ext': 'mp4',
1181 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1182 'thumbnail': r're:^https?://.*\.jpg$',
1183 },
1184 'params': {
1185 # m3u8 download
1186 'skip_download': True,
1187 },
1188 },
1189 # Ooyala embed
1190 {
1191 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1192 'info_dict': {
1193 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1194 'ext': 'mp4',
1195 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1196 'title': 'This is what separates the Excel masters from the wannabes',
1197 'duration': 191.933,
1198 },
1199 'params': {
1200 # m3u8 downloads
1201 'skip_download': True,
1202 }
1203 },
1204 # Brightcove URL in single quotes
1205 {
1206 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1207 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1208 'info_dict': {
1209 'id': '4255764656001',
1210 'ext': 'mp4',
1211 'title': 'SN Presents: Russell Martin, World Citizen',
1212 '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.',
1213 'uploader': 'Rogers Sportsnet',
1214 'uploader_id': '1704050871',
1215 'upload_date': '20150525',
1216 'timestamp': 1432570283,
1217 },
1218 },
1219 # Dailymotion Cloud video
1220 {
1221 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1222 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1223 'info_dict': {
1224 'id': 'x2uy8t3',
1225 'ext': 'mp4',
1226 'title': 'Sauvons les abeilles ! - Le dƩbat',
1227 'description': 'md5:d9082128b1c5277987825d684939ca26',
1228 'thumbnail': r're:^https?://.*\.jpe?g$',
1229 'timestamp': 1434970506,
1230 'upload_date': '20150622',
1231 'uploader': 'Public SĆ©nat',
1232 'uploader_id': 'xa9gza',
1233 }
1234 },
1235 # OnionStudios embed
1236 {
1237 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1238 'info_dict': {
1239 'id': '2855',
1240 'ext': 'mp4',
1241 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1242 'thumbnail': r're:^https?://.*\.jpe?g$',
1243 'uploader': 'ClickHole',
1244 'uploader_id': 'clickhole',
1245 }
1246 },
1247 # SnagFilms embed
1248 {
1249 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1250 'info_dict': {
1251 'id': '74849a00-85a9-11e1-9660-123139220831',
1252 'ext': 'mp4',
1253 'title': '#whilewewatch',
1254 }
1255 },
1256 # AdobeTVVideo embed
1257 {
1258 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1259 'md5': '43662b577c018ad707a63766462b1e87',
1260 'info_dict': {
1261 'id': '2456',
1262 'ext': 'mp4',
1263 'title': 'New experience with Acrobat DC',
1264 'description': 'New experience with Acrobat DC',
1265 'duration': 248.667,
1266 },
1267 },
1268 # BrightcoveInPageEmbed embed
1269 {
1270 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1271 'info_dict': {
1272 'id': '4238694884001',
1273 'ext': 'flv',
1274 'title': 'Tabletop: Dread, Last Thoughts',
1275 'description': 'Tabletop: Dread, Last Thoughts',
1276 'duration': 51690,
1277 },
1278 },
1279 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1280 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1281 {
1282 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1283 'info_dict': {
1284 'id': '4785848093001',
1285 'ext': 'mp4',
1286 'title': 'The Cardinal Pell Interview',
1287 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1288 'uploader': 'GlobeCast Australia - GlobeStream',
1289 'uploader_id': '2733773828001',
1290 'upload_date': '20160304',
1291 'timestamp': 1457083087,
1292 },
1293 'params': {
1294 # m3u8 downloads
1295 'skip_download': True,
1296 },
1297 },
1298 # Another form of arte.tv embed
1299 {
1300 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1301 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1302 'info_dict': {
1303 'id': '030273-562_PLUS7-F',
1304 'ext': 'mp4',
1305 'title': 'ARTE Reportage - Nulle part, en France',
1306 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1307 'upload_date': '20160409',
1308 },
1309 },
1310 # LiveLeak embed
1311 {
1312 'url': 'http://www.wykop.pl/link/3088787/',
1313 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1314 'info_dict': {
1315 'id': '874_1459135191',
1316 'ext': 'mp4',
1317 'title': 'Man shows poor quality of new apartment building',
1318 'description': 'The wall is like a sand pile.',
1319 'uploader': 'Lake8737',
1320 }
1321 },
1322 # Duplicated embedded video URLs
1323 {
1324 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1325 'info_dict': {
1326 'id': '149298443_480_16c25b74_2',
1327 'ext': 'mp4',
1328 'title': 'vs. Blue Orange Spring Game',
1329 'uploader': 'www.hudl.com',
1330 },
1331 },
1332 # twitter:player:stream embed
1333 {
1334 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1335 'info_dict': {
1336 'id': 'master',
1337 'ext': 'mp4',
1338 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1339 'uploader': 'www.rtl.be',
1340 },
1341 'params': {
1342 # m3u8 downloads
1343 'skip_download': True,
1344 },
1345 },
1346 # twitter:player embed
1347 {
1348 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1349 'md5': 'a3e0df96369831de324f0778e126653c',
1350 'info_dict': {
1351 'id': '4909620399001',
1352 'ext': 'mp4',
1353 'title': 'What Do Black Holes Sound Like?',
1354 'description': 'what do black holes sound like',
1355 'upload_date': '20160524',
1356 'uploader_id': '29913724001',
1357 'timestamp': 1464107587,
1358 'uploader': 'TheAtlantic',
1359 },
1360 'add_ie': ['BrightcoveLegacy'],
1361 },
1362 # Facebook <iframe> embed
1363 {
1364 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1365 'md5': 'fbcde74f534176ecb015849146dd3aee',
1366 'info_dict': {
1367 'id': '599637780109885',
1368 'ext': 'mp4',
1369 'title': 'Facebook video #599637780109885',
1370 },
1371 },
1372 # Facebook API embed
1373 {
1374 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1375 'md5': 'a47372ee61b39a7b90287094d447d94e',
1376 'info_dict': {
1377 'id': '10153467542406923',
1378 'ext': 'mp4',
1379 'title': 'Facebook video #10153467542406923',
1380 },
1381 },
1382 # Wordpress "YouTube Video Importer" plugin
1383 {
1384 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1385 'md5': 'd16797741b560b485194eddda8121b48',
1386 'info_dict': {
1387 'id': 'HNTXWDXV9Is',
1388 'ext': 'mp4',
1389 'title': 'Blue Devils Drumline Stanford lot 2016',
1390 'upload_date': '20160627',
1391 'uploader_id': 'GENOCIDE8GENERAL10',
1392 'uploader': 'cylus cyrus',
1393 },
1394 },
1395 {
1396 # video stored on custom kaltura server
1397 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1398 'md5': '537617d06e64dfed891fa1593c4b30cc',
1399 'info_dict': {
1400 'id': '0_1iotm5bh',
1401 'ext': 'mp4',
1402 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1403 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1404 'uploader_id': 'videos.expansion@el-mundo.net',
1405 'upload_date': '20150429',
1406 'timestamp': 1430303472,
1407 },
1408 'add_ie': ['Kaltura'],
1409 },
1410 {
1411 # Non-standard Vimeo embed
1412 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1413 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1414 'info_dict': {
1415 'id': '148867247',
1416 'ext': 'mp4',
1417 'title': 'Understanding the web - Teaser',
1418 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1419 'upload_date': '20151214',
1420 'uploader': 'OpenClassrooms',
1421 'uploader_id': 'openclassrooms',
1422 },
1423 'add_ie': ['Vimeo'],
1424 },
1425 {
1426 # generic vimeo embed that requires original URL passed as Referer
1427 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1428 'only_matching': True,
1429 },
1430 {
1431 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1432 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1433 'info_dict': {
1434 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1435 'ext': 'mp4',
1436 'title': 'Big Buck Bunny',
1437 'description': 'Royalty free test video',
1438 'timestamp': 1432816365,
1439 'upload_date': '20150528',
1440 'is_live': False,
1441 },
1442 'params': {
1443 'skip_download': True,
1444 },
1445 'add_ie': [ArkenaIE.ie_key()],
1446 },
1447 {
1448 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1449 'info_dict': {
1450 'id': '1c7141f46c',
1451 'ext': 'mp4',
1452 'title': 'ŠŠ ŠšŠžŠ”ŠŖŠœ ŠžŠ¢ Š’Š—Š Š˜Š’: Š˜Š·Ń‚ŠøчŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃ‚Š°Š½Ń†Šøя Š² ŠŸŠ»Š¾Š²Š“ŠøŠ²',
1453 },
1454 'params': {
1455 'skip_download': True,
1456 },
1457 'add_ie': [Vbox7IE.ie_key()],
1458 },
1459 {
1460 # DBTV embeds
1461 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1462 'info_dict': {
1463 'id': '43254897',
1464 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1465 },
1466 'playlist_mincount': 3,
1467 },
1468 {
1469 # Videa embeds
1470 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1471 'info_dict': {
1472 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1473 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1474 },
1475 'playlist_mincount': 2,
1476 },
1477 {
1478 # 20 minuten embed
1479 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1480 'info_dict': {
1481 'id': '523629',
1482 'ext': 'mp4',
1483 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1484 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1485 },
1486 'params': {
1487 'skip_download': True,
1488 },
1489 'add_ie': [TwentyMinutenIE.ie_key()],
1490 },
1491 {
1492 # VideoPress embed
1493 'url': 'https://en.support.wordpress.com/videopress/',
1494 'info_dict': {
1495 'id': 'OcobLTqC',
1496 'ext': 'm4v',
1497 'title': 'IMG_5786',
1498 'timestamp': 1435711927,
1499 'upload_date': '20150701',
1500 },
1501 'params': {
1502 'skip_download': True,
1503 },
1504 'add_ie': [VideoPressIE.ie_key()],
1505 },
1506 {
1507 # Rutube embed
1508 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1509 'info_dict': {
1510 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1511 'ext': 'flv',
1512 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1513 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1514 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1515 'upload_date': '20170228',
1516 'uploader_id': '996642',
1517 },
1518 'params': {
1519 'skip_download': True,
1520 },
1521 'add_ie': [RutubeIE.ie_key()],
1522 },
1523 {
1524 # ThePlatform embedded with whitespaces in URLs
1525 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1526 'only_matching': True,
1527 },
1528 # {
1529 # # TODO: find another test
1530 # # http://schema.org/VideoObject
1531 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1532 # 'md5': '888dcf08b7ea671381f00fab74692755',
1533 # 'info_dict': {
1534 # 'id': 'nyvTSJMKId',
1535 # 'ext': 'mp4',
1536 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1537 # 'description': '#love for cats.',
1538 # 'timestamp': 1461244995,
1539 # 'upload_date': '20160421',
1540 # },
1541 # 'params': {
1542 # 'force_generic_extractor': True,
1543 # },
1544 # }
1545 ]
1546
1547 def report_following_redirect(self, new_url):
1548 """Report information extraction."""
1549 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1550
1551 def _extract_rss(self, url, video_id, doc):
1552 playlist_title = doc.find('./channel/title').text
1553 playlist_desc_el = doc.find('./channel/description')
1554 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1555
1556 entries = []
1557 for it in doc.findall('./channel/item'):
1558 next_url = xpath_text(it, 'link', fatal=False)
1559 if not next_url:
1560 enclosure_nodes = it.findall('./enclosure')
1561 for e in enclosure_nodes:
1562 next_url = e.attrib.get('url')
1563 if next_url:
1564 break
1565
1566 if not next_url:
1567 continue
1568
1569 entries.append({
1570 '_type': 'url',
1571 'url': next_url,
1572 'title': it.find('title').text,
1573 })
1574
1575 return {
1576 '_type': 'playlist',
1577 'id': url,
1578 'title': playlist_title,
1579 'description': playlist_desc,
1580 'entries': entries,
1581 }
1582
1583 def _extract_camtasia(self, url, video_id, webpage):
1584 """ Returns None if no camtasia video can be found. """
1585
1586 camtasia_cfg = self._search_regex(
1587 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1588 webpage, 'camtasia configuration file', default=None)
1589 if camtasia_cfg is None:
1590 return None
1591
1592 title = self._html_search_meta('DC.title', webpage, fatal=True)
1593
1594 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1595 camtasia_cfg = self._download_xml(
1596 camtasia_url, video_id,
1597 note='Downloading camtasia configuration',
1598 errnote='Failed to download camtasia configuration')
1599 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1600
1601 entries = []
1602 for n in fileset_node.getchildren():
1603 url_n = n.find('./uri')
1604 if url_n is None:
1605 continue
1606
1607 entries.append({
1608 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1609 'title': '%s - %s' % (title, n.tag),
1610 'url': compat_urlparse.urljoin(url, url_n.text),
1611 'duration': float_or_none(n.find('./duration').text),
1612 })
1613
1614 return {
1615 '_type': 'playlist',
1616 'entries': entries,
1617 'title': title,
1618 }
1619
1620 def _real_extract(self, url):
1621 if url.startswith('//'):
1622 return {
1623 '_type': 'url',
1624 'url': self.http_scheme() + url,
1625 }
1626
1627 parsed_url = compat_urlparse.urlparse(url)
1628 if not parsed_url.scheme:
1629 default_search = self._downloader.params.get('default_search')
1630 if default_search is None:
1631 default_search = 'fixup_error'
1632
1633 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1634 if '/' in url:
1635 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1636 return self.url_result('http://' + url)
1637 elif default_search != 'fixup_error':
1638 if default_search == 'auto_warning':
1639 if re.match(r'^(?:url|URL)$', url):
1640 raise ExtractorError(
1641 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1642 expected=True)
1643 else:
1644 self._downloader.report_warning(
1645 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1646 return self.url_result('ytsearch:' + url)
1647
1648 if default_search in ('error', 'fixup_error'):
1649 raise ExtractorError(
1650 '%r is not a valid URL. '
1651 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1652 % (url, url), expected=True)
1653 else:
1654 if ':' not in default_search:
1655 default_search += ':'
1656 return self.url_result(default_search + url)
1657
1658 url, smuggled_data = unsmuggle_url(url)
1659 force_videoid = None
1660 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1661 if smuggled_data and 'force_videoid' in smuggled_data:
1662 force_videoid = smuggled_data['force_videoid']
1663 video_id = force_videoid
1664 else:
1665 video_id = self._generic_id(url)
1666
1667 self.to_screen('%s: Requesting header' % video_id)
1668
1669 head_req = HEADRequest(url)
1670 head_response = self._request_webpage(
1671 head_req, video_id,
1672 note=False, errnote='Could not send HEAD request to %s' % url,
1673 fatal=False)
1674
1675 if head_response is not False:
1676 # Check for redirect
1677 new_url = head_response.geturl()
1678 if url != new_url:
1679 self.report_following_redirect(new_url)
1680 if force_videoid:
1681 new_url = smuggle_url(
1682 new_url, {'force_videoid': force_videoid})
1683 return self.url_result(new_url)
1684
1685 full_response = None
1686 if head_response is False:
1687 request = sanitized_Request(url)
1688 request.add_header('Accept-Encoding', '*')
1689 full_response = self._request_webpage(request, video_id)
1690 head_response = full_response
1691
1692 info_dict = {
1693 'id': video_id,
1694 'title': self._generic_title(url),
1695 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1696 }
1697
1698 # Check for direct link to a video
1699 content_type = head_response.headers.get('Content-Type', '').lower()
1700 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1701 if m:
1702 format_id = m.group('format_id')
1703 if format_id.endswith('mpegurl'):
1704 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1705 elif format_id == 'f4m':
1706 formats = self._extract_f4m_formats(url, video_id)
1707 else:
1708 formats = [{
1709 'format_id': m.group('format_id'),
1710 'url': url,
1711 'vcodec': 'none' if m.group('type') == 'audio' else None
1712 }]
1713 info_dict['direct'] = True
1714 self._sort_formats(formats)
1715 info_dict['formats'] = formats
1716 return info_dict
1717
1718 if not self._downloader.params.get('test', False) and not is_intentional:
1719 force = self._downloader.params.get('force_generic_extractor', False)
1720 self._downloader.report_warning(
1721 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1722
1723 if not full_response:
1724 request = sanitized_Request(url)
1725 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1726 # making it impossible to download only chunk of the file (yet we need only 512kB to
1727 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1728 # that will always result in downloading the whole file that is not desirable.
1729 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1730 # to accept raw bytes and being able to download only a chunk.
1731 # It may probably better to solve this by checking Content-Type for application/octet-stream
1732 # after HEAD request finishes, but not sure if we can rely on this.
1733 request.add_header('Accept-Encoding', '*')
1734 full_response = self._request_webpage(request, video_id)
1735
1736 first_bytes = full_response.read(512)
1737
1738 # Is it an M3U playlist?
1739 if first_bytes.startswith(b'#EXTM3U'):
1740 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1741 self._sort_formats(info_dict['formats'])
1742 return info_dict
1743
1744 # Maybe it's a direct link to a video?
1745 # Be careful not to download the whole thing!
1746 if not is_html(first_bytes):
1747 self._downloader.report_warning(
1748 'URL could be a direct video link, returning it as such.')
1749 info_dict.update({
1750 'direct': True,
1751 'url': url,
1752 })
1753 return info_dict
1754
1755 webpage = self._webpage_read_content(
1756 full_response, url, video_id, prefix=first_bytes)
1757
1758 self.report_extraction(video_id)
1759
1760 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1761 try:
1762 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1763 if doc.tag == 'rss':
1764 return self._extract_rss(url, video_id, doc)
1765 elif doc.tag == 'SmoothStreamingMedia':
1766 info_dict['formats'] = self._parse_ism_formats(doc, url)
1767 self._sort_formats(info_dict['formats'])
1768 return info_dict
1769 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1770 smil = self._parse_smil(doc, url, video_id)
1771 self._sort_formats(smil['formats'])
1772 return smil
1773 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1774 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1775 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1776 info_dict['formats'] = self._parse_mpd_formats(
1777 doc, video_id,
1778 mpd_base_url=full_response.geturl().rpartition('/')[0],
1779 mpd_url=url)
1780 self._sort_formats(info_dict['formats'])
1781 return info_dict
1782 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1783 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1784 self._sort_formats(info_dict['formats'])
1785 return info_dict
1786 except compat_xml_parse_error:
1787 pass
1788
1789 # Is it a Camtasia project?
1790 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1791 if camtasia_res is not None:
1792 return camtasia_res
1793
1794 # Sometimes embedded video player is hidden behind percent encoding
1795 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1796 # Unescaping the whole page allows to handle those cases in a generic way
1797 webpage = compat_urllib_parse_unquote(webpage)
1798
1799 # it's tempting to parse this further, but you would
1800 # have to take into account all the variations like
1801 # Video Title - Site Name
1802 # Site Name | Video Title
1803 # Video Title - Tagline | Site Name
1804 # and so on and so forth; it's just not practical
1805 video_title = self._og_search_title(
1806 webpage, default=None) or self._html_search_regex(
1807 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1808 default='video')
1809
1810 # Try to detect age limit automatically
1811 age_limit = self._rta_search(webpage)
1812 # And then there are the jokers who advertise that they use RTA,
1813 # but actually don't.
1814 AGE_LIMIT_MARKERS = [
1815 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1816 ]
1817 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1818 age_limit = 18
1819
1820 # video uploader is domain name
1821 video_uploader = self._search_regex(
1822 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1823
1824 video_description = self._og_search_description(webpage, default=None)
1825 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1826
1827 # Helper method
1828 def _playlist_from_matches(matches, getter=None, ie=None):
1829 urlrs = orderedSet(
1830 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1831 for m in matches)
1832 return self.playlist_result(
1833 urlrs, playlist_id=video_id, playlist_title=video_title)
1834
1835 # Look for Brightcove Legacy Studio embeds
1836 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1837 if bc_urls:
1838 self.to_screen('Brightcove video detected.')
1839 entries = [{
1840 '_type': 'url',
1841 'url': smuggle_url(bc_url, {'Referer': url}),
1842 'ie_key': 'BrightcoveLegacy'
1843 } for bc_url in bc_urls]
1844
1845 return {
1846 '_type': 'playlist',
1847 'title': video_title,
1848 'id': video_id,
1849 'entries': entries,
1850 }
1851
1852 # Look for Brightcove New Studio embeds
1853 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1854 if bc_urls:
1855 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1856
1857 # Look for ThePlatform embeds
1858 tp_urls = ThePlatformIE._extract_urls(webpage)
1859 if tp_urls:
1860 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1861
1862 # Look for Vessel embeds
1863 vessel_urls = VesselIE._extract_urls(webpage)
1864 if vessel_urls:
1865 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1866
1867 # Look for embedded rtl.nl player
1868 matches = re.findall(
1869 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1870 webpage)
1871 if matches:
1872 return _playlist_from_matches(matches, ie='RtlNl')
1873
1874 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1875 if vimeo_urls:
1876 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1877
1878 vid_me_embed_url = self._search_regex(
1879 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1880 webpage, 'vid.me embed', default=None)
1881 if vid_me_embed_url is not None:
1882 return self.url_result(vid_me_embed_url, 'Vidme')
1883
1884 # Look for embedded YouTube player
1885 matches = re.findall(r'''(?x)
1886 (?:
1887 <iframe[^>]+?src=|
1888 data-video-url=|
1889 <embed[^>]+?src=|
1890 embedSWF\(?:\s*|
1891 new\s+SWFObject\(
1892 )
1893 (["\'])
1894 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1895 (?:embed|v|p)/.+?)
1896 \1''', webpage)
1897 if matches:
1898 return _playlist_from_matches(
1899 matches, lambda m: unescapeHTML(m[1]))
1900
1901 # Look for lazyYT YouTube embed
1902 matches = re.findall(
1903 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1904 if matches:
1905 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1906
1907 # Look for Wordpress "YouTube Video Importer" plugin
1908 matches = re.findall(r'''(?x)<div[^>]+
1909 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1910 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1911 if matches:
1912 return _playlist_from_matches(matches, lambda m: m[-1])
1913
1914 matches = DailymotionIE._extract_urls(webpage)
1915 if matches:
1916 return _playlist_from_matches(matches)
1917
1918 # Look for embedded Dailymotion playlist player (#3822)
1919 m = re.search(
1920 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1921 if m:
1922 playlists = re.findall(
1923 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1924 if playlists:
1925 return _playlist_from_matches(
1926 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1927
1928 # Look for embedded Wistia player
1929 match = re.search(
1930 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1931 if match:
1932 embed_url = self._proto_relative_url(
1933 unescapeHTML(match.group('url')))
1934 return {
1935 '_type': 'url_transparent',
1936 'url': embed_url,
1937 'ie_key': 'Wistia',
1938 'uploader': video_uploader,
1939 }
1940
1941 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1942 if match:
1943 return {
1944 '_type': 'url_transparent',
1945 'url': 'wistia:%s' % match.group('id'),
1946 'ie_key': 'Wistia',
1947 'uploader': video_uploader,
1948 }
1949
1950 match = re.search(
1951 r'''(?sx)
1952 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1953 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1954 ''', webpage)
1955 if match:
1956 return self.url_result(self._proto_relative_url(
1957 'wistia:%s' % match.group('id')), 'Wistia')
1958
1959 # Look for SVT player
1960 svt_url = SVTIE._extract_url(webpage)
1961 if svt_url:
1962 return self.url_result(svt_url, 'SVT')
1963
1964 # Look for embedded condenast player
1965 matches = re.findall(
1966 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1967 webpage)
1968 if matches:
1969 return {
1970 '_type': 'playlist',
1971 'entries': [{
1972 '_type': 'url',
1973 'ie_key': 'CondeNast',
1974 'url': ma,
1975 } for ma in matches],
1976 'title': video_title,
1977 'id': video_id,
1978 }
1979
1980 # Look for Bandcamp pages with custom domain
1981 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1982 if mobj is not None:
1983 burl = unescapeHTML(mobj.group(1))
1984 # Don't set the extractor because it can be a track url or an album
1985 return self.url_result(burl)
1986
1987 # Look for embedded Vevo player
1988 mobj = re.search(
1989 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1990 if mobj is not None:
1991 return self.url_result(mobj.group('url'))
1992
1993 # Look for embedded Viddler player
1994 mobj = re.search(
1995 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1996 webpage)
1997 if mobj is not None:
1998 return self.url_result(mobj.group('url'))
1999
2000 # Look for NYTimes player
2001 mobj = re.search(
2002 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2003 webpage)
2004 if mobj is not None:
2005 return self.url_result(mobj.group('url'))
2006
2007 # Look for Libsyn player
2008 mobj = re.search(
2009 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2010 if mobj is not None:
2011 return self.url_result(mobj.group('url'))
2012
2013 # Look for Ooyala videos
2014 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2015 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2016 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2017 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2018 if mobj is not None:
2019 embed_token = self._search_regex(
2020 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2021 webpage, 'ooyala embed token', default=None)
2022 return OoyalaIE._build_url_result(smuggle_url(
2023 mobj.group('ec'), {
2024 'domain': url,
2025 'embed_token': embed_token,
2026 }))
2027
2028 # Look for multiple Ooyala embeds on SBN network websites
2029 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2030 if mobj is not None:
2031 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2032 if embeds:
2033 return _playlist_from_matches(
2034 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2035
2036 # Look for Aparat videos
2037 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2038 if mobj is not None:
2039 return self.url_result(mobj.group(1), 'Aparat')
2040
2041 # Look for MPORA videos
2042 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2043 if mobj is not None:
2044 return self.url_result(mobj.group(1), 'Mpora')
2045
2046 # Look for embedded NovaMov-based player
2047 mobj = re.search(
2048 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2049 (?P<url>http://(?:(?:embed|www)\.)?
2050 (?:novamov\.com|
2051 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2052 videoweed\.(?:es|com)|
2053 movshare\.(?:net|sx|ag)|
2054 divxstage\.(?:eu|net|ch|co|at|ag))
2055 /embed\.php.+?)\1''', webpage)
2056 if mobj is not None:
2057 return self.url_result(mobj.group('url'))
2058
2059 # Look for embedded Facebook player
2060 facebook_url = FacebookIE._extract_url(webpage)
2061 if facebook_url is not None:
2062 return self.url_result(facebook_url, 'Facebook')
2063
2064 # Look for embedded VK player
2065 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2066 if mobj is not None:
2067 return self.url_result(mobj.group('url'), 'VK')
2068
2069 # Look for embedded Odnoklassniki player
2070 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2071 if mobj is not None:
2072 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2073
2074 # Look for embedded ivi player
2075 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2076 if mobj is not None:
2077 return self.url_result(mobj.group('url'), 'Ivi')
2078
2079 # Look for embedded Huffington Post player
2080 mobj = re.search(
2081 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2082 if mobj is not None:
2083 return self.url_result(mobj.group('url'), 'HuffPost')
2084
2085 # Look for embed.ly
2086 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2087 if mobj is not None:
2088 return self.url_result(mobj.group('url'))
2089 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2090 if mobj is not None:
2091 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2092
2093 # Look for funnyordie embed
2094 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2095 if matches:
2096 return _playlist_from_matches(
2097 matches, getter=unescapeHTML, ie='FunnyOrDie')
2098
2099 # Look for BBC iPlayer embed
2100 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2101 if matches:
2102 return _playlist_from_matches(matches, ie='BBCCoUk')
2103
2104 # Look for embedded RUTV player
2105 rutv_url = RUTVIE._extract_url(webpage)
2106 if rutv_url:
2107 return self.url_result(rutv_url, 'RUTV')
2108
2109 # Look for embedded TVC player
2110 tvc_url = TVCIE._extract_url(webpage)
2111 if tvc_url:
2112 return self.url_result(tvc_url, 'TVC')
2113
2114 # Look for embedded SportBox player
2115 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2116 if sportbox_urls:
2117 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2118
2119 # Look for embedded XHamster player
2120 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2121 if xhamster_urls:
2122 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2123
2124 # Look for embedded TNAFlixNetwork player
2125 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2126 if tnaflix_urls:
2127 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2128
2129 # Look for embedded PornHub player
2130 pornhub_urls = PornHubIE._extract_urls(webpage)
2131 if pornhub_urls:
2132 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2133
2134 # Look for embedded DrTuber player
2135 drtuber_urls = DrTuberIE._extract_urls(webpage)
2136 if drtuber_urls:
2137 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2138
2139 # Look for embedded RedTube player
2140 redtube_urls = RedTubeIE._extract_urls(webpage)
2141 if redtube_urls:
2142 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2143
2144 # Look for embedded Tvigle player
2145 mobj = re.search(
2146 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2147 if mobj is not None:
2148 return self.url_result(mobj.group('url'), 'Tvigle')
2149
2150 # Look for embedded TED player
2151 mobj = re.search(
2152 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2153 if mobj is not None:
2154 return self.url_result(mobj.group('url'), 'TED')
2155
2156 # Look for embedded Ustream videos
2157 ustream_url = UstreamIE._extract_url(webpage)
2158 if ustream_url:
2159 return self.url_result(ustream_url, UstreamIE.ie_key())
2160
2161 # Look for embedded arte.tv player
2162 mobj = re.search(
2163 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2164 webpage)
2165 if mobj is not None:
2166 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2167
2168 # Look for embedded francetv player
2169 mobj = re.search(
2170 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2171 webpage)
2172 if mobj is not None:
2173 return self.url_result(mobj.group('url'))
2174
2175 # Look for embedded smotri.com player
2176 smotri_url = SmotriIE._extract_url(webpage)
2177 if smotri_url:
2178 return self.url_result(smotri_url, 'Smotri')
2179
2180 # Look for embedded Myvi.ru player
2181 myvi_url = MyviIE._extract_url(webpage)
2182 if myvi_url:
2183 return self.url_result(myvi_url)
2184
2185 # Look for embedded soundcloud player
2186 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2187 if soundcloud_urls:
2188 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2189
2190 # Look for tunein player
2191 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2192 if tunein_urls:
2193 return _playlist_from_matches(tunein_urls)
2194
2195 # Look for embedded mtvservices player
2196 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2197 if mtvservices_url:
2198 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2199
2200 # Look for embedded yahoo player
2201 mobj = re.search(
2202 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2203 webpage)
2204 if mobj is not None:
2205 return self.url_result(mobj.group('url'), 'Yahoo')
2206
2207 # Look for embedded sbs.com.au player
2208 mobj = re.search(
2209 r'''(?x)
2210 (?:
2211 <meta\s+property="og:video"\s+content=|
2212 <iframe[^>]+?src=
2213 )
2214 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2215 webpage)
2216 if mobj is not None:
2217 return self.url_result(mobj.group('url'), 'SBS')
2218
2219 # Look for embedded Cinchcast player
2220 mobj = re.search(
2221 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2222 webpage)
2223 if mobj is not None:
2224 return self.url_result(mobj.group('url'), 'Cinchcast')
2225
2226 mobj = re.search(
2227 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2228 webpage)
2229 if not mobj:
2230 mobj = re.search(
2231 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2232 webpage)
2233 if mobj is not None:
2234 return self.url_result(mobj.group('url'), 'MLB')
2235
2236 mobj = re.search(
2237 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2238 webpage)
2239 if mobj is not None:
2240 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2241
2242 mobj = re.search(
2243 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2244 webpage)
2245 if mobj is not None:
2246 return self.url_result(mobj.group('url'), 'Livestream')
2247
2248 # Look for Zapiks embed
2249 mobj = re.search(
2250 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2251 if mobj is not None:
2252 return self.url_result(mobj.group('url'), 'Zapiks')
2253
2254 # Look for Kaltura embeds
2255 kaltura_url = KalturaIE._extract_url(webpage)
2256 if kaltura_url:
2257 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2258
2259 # Look for Eagle.Platform embeds
2260 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2261 if eagleplatform_url:
2262 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2263
2264 # Look for ClipYou (uses Eagle.Platform) embeds
2265 mobj = re.search(
2266 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2267 if mobj is not None:
2268 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2269
2270 # Look for Pladform embeds
2271 pladform_url = PladformIE._extract_url(webpage)
2272 if pladform_url:
2273 return self.url_result(pladform_url)
2274
2275 # Look for Videomore embeds
2276 videomore_url = VideomoreIE._extract_url(webpage)
2277 if videomore_url:
2278 return self.url_result(videomore_url)
2279
2280 # Look for Webcaster embeds
2281 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2282 if webcaster_url:
2283 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2284
2285 # Look for Playwire embeds
2286 mobj = re.search(
2287 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2288 if mobj is not None:
2289 return self.url_result(mobj.group('url'))
2290
2291 # Look for 5min embeds
2292 mobj = re.search(
2293 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2294 if mobj is not None:
2295 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2296
2297 # Look for Crooks and Liars embeds
2298 mobj = re.search(
2299 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2300 if mobj is not None:
2301 return self.url_result(mobj.group('url'))
2302
2303 # Look for NBC Sports VPlayer embeds
2304 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2305 if nbc_sports_url:
2306 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2307
2308 # Look for NBC News embeds
2309 nbc_news_embed_url = re.search(
2310 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2311 if nbc_news_embed_url:
2312 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2313
2314 # Look for Google Drive embeds
2315 google_drive_url = GoogleDriveIE._extract_url(webpage)
2316 if google_drive_url:
2317 return self.url_result(google_drive_url, 'GoogleDrive')
2318
2319 # Look for UDN embeds
2320 mobj = re.search(
2321 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2322 if mobj is not None:
2323 return self.url_result(
2324 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2325
2326 # Look for Senate ISVP iframe
2327 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2328 if senate_isvp_url:
2329 return self.url_result(senate_isvp_url, 'SenateISVP')
2330
2331 # Look for Dailymotion Cloud videos
2332 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2333 if dmcloud_url:
2334 return self.url_result(dmcloud_url, 'DailymotionCloud')
2335
2336 # Look for OnionStudios embeds
2337 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2338 if onionstudios_url:
2339 return self.url_result(onionstudios_url)
2340
2341 # Look for ViewLift embeds
2342 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2343 if viewlift_url:
2344 return self.url_result(viewlift_url)
2345
2346 # Look for JWPlatform embeds
2347 jwplatform_url = JWPlatformIE._extract_url(webpage)
2348 if jwplatform_url:
2349 return self.url_result(jwplatform_url, 'JWPlatform')
2350
2351 # Look for Digiteka embeds
2352 digiteka_url = DigitekaIE._extract_url(webpage)
2353 if digiteka_url:
2354 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2355
2356 # Look for Arkena embeds
2357 arkena_url = ArkenaIE._extract_url(webpage)
2358 if arkena_url:
2359 return self.url_result(arkena_url, ArkenaIE.ie_key())
2360
2361 # Look for Piksel embeds
2362 piksel_url = PikselIE._extract_url(webpage)
2363 if piksel_url:
2364 return self.url_result(piksel_url, PikselIE.ie_key())
2365
2366 # Look for Limelight embeds
2367 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2368 if mobj:
2369 lm = {
2370 'Media': 'media',
2371 'Channel': 'channel',
2372 'ChannelList': 'channel_list',
2373 }
2374 return self.url_result(smuggle_url('limelight:%s:%s' % (
2375 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2376 'Limelight%s' % mobj.group(1), mobj.group(2))
2377
2378 mobj = re.search(
2379 r'''(?sx)
2380 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2381 <param[^>]+
2382 name=(["\'])flashVars\2[^>]+
2383 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2384 ''', webpage)
2385 if mobj:
2386 return self.url_result(smuggle_url(
2387 'limelight:media:%s' % mobj.group('id'),
2388 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2389
2390 # Look for AdobeTVVideo embeds
2391 mobj = re.search(
2392 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2393 webpage)
2394 if mobj is not None:
2395 return self.url_result(
2396 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2397 'AdobeTVVideo')
2398
2399 # Look for Vine embeds
2400 mobj = re.search(
2401 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2402 webpage)
2403 if mobj is not None:
2404 return self.url_result(
2405 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2406
2407 # Look for VODPlatform embeds
2408 mobj = re.search(
2409 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2410 webpage)
2411 if mobj is not None:
2412 return self.url_result(
2413 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2414
2415 # Look for Mangomolo embeds
2416 mobj = re.search(
2417 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2418 (?:
2419 video\?.*?\bid=(?P<video_id>\d+)|
2420 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2421 ).+?)\1''', webpage)
2422 if mobj is not None:
2423 info = {
2424 '_type': 'url_transparent',
2425 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2426 'title': video_title,
2427 'description': video_description,
2428 'thumbnail': video_thumbnail,
2429 'uploader': video_uploader,
2430 }
2431 video_id = mobj.group('video_id')
2432 if video_id:
2433 info.update({
2434 'ie_key': 'MangomoloVideo',
2435 'id': video_id,
2436 })
2437 else:
2438 info.update({
2439 'ie_key': 'MangomoloLive',
2440 'id': mobj.group('channel_id'),
2441 })
2442 return info
2443
2444 # Look for Instagram embeds
2445 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2446 if instagram_embed_url is not None:
2447 return self.url_result(
2448 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2449
2450 # Look for LiveLeak embeds
2451 liveleak_url = LiveLeakIE._extract_url(webpage)
2452 if liveleak_url:
2453 return self.url_result(liveleak_url, 'LiveLeak')
2454
2455 # Look for 3Q SDN embeds
2456 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2457 if threeqsdn_url:
2458 return {
2459 '_type': 'url_transparent',
2460 'ie_key': ThreeQSDNIE.ie_key(),
2461 'url': self._proto_relative_url(threeqsdn_url),
2462 'title': video_title,
2463 'description': video_description,
2464 'thumbnail': video_thumbnail,
2465 'uploader': video_uploader,
2466 }
2467
2468 # Look for VBOX7 embeds
2469 vbox7_url = Vbox7IE._extract_url(webpage)
2470 if vbox7_url:
2471 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2472
2473 # Look for DBTV embeds
2474 dbtv_urls = DBTVIE._extract_urls(webpage)
2475 if dbtv_urls:
2476 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2477
2478 # Look for Videa embeds
2479 videa_urls = VideaIE._extract_urls(webpage)
2480 if videa_urls:
2481 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2482
2483 # Look for 20 minuten embeds
2484 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2485 if twentymin_urls:
2486 return _playlist_from_matches(
2487 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2488
2489 # Look for Openload embeds
2490 openload_urls = OpenloadIE._extract_urls(webpage)
2491 if openload_urls:
2492 return _playlist_from_matches(
2493 openload_urls, ie=OpenloadIE.ie_key())
2494
2495 # Look for VideoPress embeds
2496 videopress_urls = VideoPressIE._extract_urls(webpage)
2497 if videopress_urls:
2498 return _playlist_from_matches(
2499 videopress_urls, ie=VideoPressIE.ie_key())
2500
2501 # Look for Rutube embeds
2502 rutube_urls = RutubeIE._extract_urls(webpage)
2503 if rutube_urls:
2504 return _playlist_from_matches(
2505 rutube_urls, ie=RutubeIE.ie_key())
2506
2507 # Looking for http://schema.org/VideoObject
2508 json_ld = self._search_json_ld(
2509 webpage, video_id, default={}, expected_type='VideoObject')
2510 if json_ld.get('url'):
2511 info_dict.update({
2512 'title': video_title or info_dict['title'],
2513 'description': video_description,
2514 'thumbnail': video_thumbnail,
2515 'age_limit': age_limit
2516 })
2517 info_dict.update(json_ld)
2518 return info_dict
2519
2520 # Look for HTML5 media
2521 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2522 if entries:
2523 for entry in entries:
2524 entry.update({
2525 'id': video_id,
2526 'title': video_title,
2527 })
2528 self._sort_formats(entry['formats'])
2529 return self.playlist_result(entries)
2530
2531 jwplayer_data_str = self._find_jwplayer_data(webpage)
2532 if jwplayer_data_str:
2533 try:
2534 jwplayer_data = self._parse_json(
2535 jwplayer_data_str, video_id, transform_source=js_to_json)
2536 return self._parse_jwplayer_data(jwplayer_data, video_id)
2537 except ExtractorError:
2538 pass
2539
2540 def check_video(vurl):
2541 if YoutubeIE.suitable(vurl):
2542 return True
2543 if RtmpIE.suitable(vurl):
2544 return True
2545 vpath = compat_urlparse.urlparse(vurl).path
2546 vext = determine_ext(vpath)
2547 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2548
2549 def filter_video(urls):
2550 return list(filter(check_video, urls))
2551
2552 # Start with something easy: JW Player in SWFObject
2553 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2554 if not found:
2555 # Look for gorilla-vid style embedding
2556 found = filter_video(re.findall(r'''(?sx)
2557 (?:
2558 jw_plugins|
2559 JWPlayerOptions|
2560 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2561 )
2562 .*?
2563 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2564 if not found:
2565 # Broaden the search a little bit
2566 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2567 if not found:
2568 # Broaden the findall a little bit: JWPlayer JS loader
2569 found = filter_video(re.findall(
2570 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2571 if not found:
2572 # Flow player
2573 found = filter_video(re.findall(r'''(?xs)
2574 flowplayer\("[^"]+",\s*
2575 \{[^}]+?\}\s*,
2576 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2577 ["']?url["']?\s*:\s*["']([^"']+)["']
2578 ''', webpage))
2579 if not found:
2580 # Cinerama player
2581 found = re.findall(
2582 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2583 if not found:
2584 # Try to find twitter cards info
2585 # twitter:player:stream should be checked before twitter:player since
2586 # it is expected to contain a raw stream (see
2587 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2588 found = filter_video(re.findall(
2589 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2590 if not found:
2591 # We look for Open Graph info:
2592 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2593 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2594 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2595 if m_video_type is not None:
2596 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2597 if not found:
2598 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2599 found = re.search(
2600 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2601 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2602 webpage)
2603 if not found:
2604 # Look also in Refresh HTTP header
2605 refresh_header = head_response.headers.get('Refresh')
2606 if refresh_header:
2607 # In python 2 response HTTP headers are bytestrings
2608 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2609 refresh_header = refresh_header.decode('iso-8859-1')
2610 found = re.search(REDIRECT_REGEX, refresh_header)
2611 if found:
2612 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2613 self.report_following_redirect(new_url)
2614 return {
2615 '_type': 'url',
2616 'url': new_url,
2617 }
2618
2619 if not found:
2620 # twitter:player is a https URL to iframe player that may or may not
2621 # be supported by youtube-dl thus this is checked the very last (see
2622 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2623 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2624 if embed_url:
2625 return self.url_result(embed_url)
2626
2627 if not found:
2628 raise UnsupportedError(url)
2629
2630 entries = []
2631 for video_url in orderedSet(found):
2632 video_url = unescapeHTML(video_url)
2633 video_url = video_url.replace('\\/', '/')
2634 video_url = compat_urlparse.urljoin(url, video_url)
2635 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2636
2637 # Sometimes, jwplayer extraction will result in a YouTube URL
2638 if YoutubeIE.suitable(video_url):
2639 entries.append(self.url_result(video_url, 'Youtube'))
2640 continue
2641
2642 # here's a fun little line of code for you:
2643 video_id = os.path.splitext(video_id)[0]
2644
2645 entry_info_dict = {
2646 'id': video_id,
2647 'uploader': video_uploader,
2648 'title': video_title,
2649 'age_limit': age_limit,
2650 }
2651
2652 if RtmpIE.suitable(video_url):
2653 entry_info_dict.update({
2654 '_type': 'url_transparent',
2655 'ie_key': RtmpIE.ie_key(),
2656 'url': video_url,
2657 })
2658 entries.append(entry_info_dict)
2659 continue
2660
2661 ext = determine_ext(video_url)
2662 if ext == 'smil':
2663 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2664 elif ext == 'xspf':
2665 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2666 elif ext == 'm3u8':
2667 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2668 elif ext == 'mpd':
2669 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2670 elif ext == 'f4m':
2671 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2672 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2673 # Just matching .ism/manifest is not enough to be reliably sure
2674 # whether it's actually an ISM manifest or some other streaming
2675 # manifest since there are various streaming URL formats
2676 # possible (see [1]) as well as some other shenanigans like
2677 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2678 # so on.
2679 # Thus the most reasonable way to solve this is to delegate
2680 # to generic extractor in order to look into the contents of
2681 # the manifest itself.
2682 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2683 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2684 entry_info_dict = self.url_result(
2685 smuggle_url(video_url, {'to_generic': True}),
2686 GenericIE.ie_key())
2687 else:
2688 entry_info_dict['url'] = video_url
2689
2690 if entry_info_dict.get('formats'):
2691 self._sort_formats(entry_info_dict['formats'])
2692
2693 entries.append(entry_info_dict)
2694
2695 if len(entries) == 1:
2696 return entries[0]
2697 else:
2698 for num, e in enumerate(entries, start=1):
2699 # 'url' results don't have a title
2700 if e.get('title') is not None:
2701 e['title'] = '%s (%d)' % (e['title'], num)
2702 return {
2703 '_type': 'playlist',
2704 'entries': entries,
2705 }