]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nbc.py
Update changelog.
[youtubedl] / youtube_dl / extractor / nbc.py
1 from __future__ import unicode_literals
2
3 import base64
4 import json
5 import re
6
7 from .common import InfoExtractor
8 from .theplatform import ThePlatformIE
9 from .adobepass import AdobePassIE
10 from ..compat import compat_urllib_parse_unquote
11 from ..utils import (
12 find_xpath_attr,
13 smuggle_url,
14 try_get,
15 unescapeHTML,
16 update_url_query,
17 int_or_none,
18 )
19
20
21 class NBCIE(AdobePassIE):
22 _VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
23
24 _TESTS = [
25 {
26 'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
27 'info_dict': {
28 'id': '2848237',
29 'ext': 'mp4',
30 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
31 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
32 'timestamp': 1424246400,
33 'upload_date': '20150218',
34 'uploader': 'NBCU-COM',
35 },
36 'params': {
37 # m3u8 download
38 'skip_download': True,
39 },
40 },
41 {
42 'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
43 'info_dict': {
44 'id': '2832821',
45 'ext': 'mp4',
46 'title': 'Star Wars Teaser',
47 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
48 'timestamp': 1417852800,
49 'upload_date': '20141206',
50 'uploader': 'NBCU-COM',
51 },
52 'params': {
53 # m3u8 download
54 'skip_download': True,
55 },
56 'skip': 'Only works from US',
57 },
58 {
59 # HLS streams requires the 'hdnea3' cookie
60 'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
61 'info_dict': {
62 'id': '101528f5a9e8127b107e98c5e6ce4638',
63 'ext': 'mp4',
64 'title': 'Goliath',
65 'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
66 'timestamp': 1237100400,
67 'upload_date': '20090315',
68 'uploader': 'NBCU-COM',
69 },
70 'params': {
71 'skip_download': True,
72 },
73 'skip': 'Only works from US',
74 },
75 {
76 'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
77 'only_matching': True,
78 },
79 {
80 # Percent escaped url
81 'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
82 'only_matching': True,
83 }
84 ]
85
86 def _real_extract(self, url):
87 permalink, video_id = re.match(self._VALID_URL, url).groups()
88 permalink = 'http' + compat_urllib_parse_unquote(permalink)
89 response = self._download_json(
90 'https://api.nbc.com/v3/videos', video_id, query={
91 'filter[permalink]': permalink,
92 'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating',
93 'fields[shows]': 'shortTitle',
94 'include': 'show.shortTitle',
95 })
96 video_data = response['data'][0]['attributes']
97 query = {
98 'mbr': 'true',
99 'manifest': 'm3u',
100 }
101 video_id = video_data['guid']
102 title = video_data['title']
103 if video_data.get('entitlement') == 'auth':
104 resource = self._get_mvpd_resource(
105 'nbcentertainment', title, video_id,
106 video_data.get('vChipRating'))
107 query['auth'] = self._extract_mvpd_auth(
108 url, video_id, 'nbcentertainment', resource)
109 theplatform_url = smuggle_url(update_url_query(
110 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
111 query), {'force_smil_url': True})
112 return {
113 '_type': 'url_transparent',
114 'id': video_id,
115 'title': title,
116 'url': theplatform_url,
117 'description': video_data.get('description'),
118 'tags': video_data.get('keywords'),
119 'season_number': int_or_none(video_data.get('seasonNumber')),
120 'episode_number': int_or_none(video_data.get('episodeNumber')),
121 'episode': title,
122 'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']),
123 'ie_key': 'ThePlatform',
124 }
125
126
127 class NBCSportsVPlayerIE(InfoExtractor):
128 _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
129
130 _TESTS = [{
131 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
132 'info_dict': {
133 'id': '9CsDKds0kvHI',
134 'ext': 'mp4',
135 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
136 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
137 'timestamp': 1426270238,
138 'upload_date': '20150313',
139 'uploader': 'NBCU-SPORTS',
140 }
141 }, {
142 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z',
143 'only_matching': True,
144 }]
145
146 @staticmethod
147 def _extract_url(webpage):
148 iframe_m = re.search(
149 r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
150 if iframe_m:
151 return iframe_m.group('url')
152
153 def _real_extract(self, url):
154 video_id = self._match_id(url)
155 webpage = self._download_webpage(url, video_id)
156 theplatform_url = self._og_search_video_url(webpage).replace(
157 'vplayer.nbcsports.com', 'player.theplatform.com')
158 return self.url_result(theplatform_url, 'ThePlatform')
159
160
161 class NBCSportsIE(InfoExtractor):
162 # Does not include https because its certificate is invalid
163 _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
164
165 _TEST = {
166 'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
167 'info_dict': {
168 'id': 'PHJSaFWbrTY9',
169 'ext': 'flv',
170 'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
171 'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
172 'uploader': 'NBCU-SPORTS',
173 'upload_date': '20150330',
174 'timestamp': 1427726529,
175 }
176 }
177
178 def _real_extract(self, url):
179 video_id = self._match_id(url)
180 webpage = self._download_webpage(url, video_id)
181 return self.url_result(
182 NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
183
184
185 class NBCSportsStreamIE(AdobePassIE):
186 _VALID_URL = r'https?://stream\.nbcsports\.com/.+?\bpid=(?P<id>\d+)'
187 _TEST = {
188 'url': 'http://stream.nbcsports.com/nbcsn/generic?pid=206559',
189 'info_dict': {
190 'id': '206559',
191 'ext': 'mp4',
192 'title': 'Amgen Tour of California Women\'s Recap',
193 'description': 'md5:66520066b3b5281ada7698d0ea2aa894',
194 },
195 'params': {
196 # m3u8 download
197 'skip_download': True,
198 },
199 'skip': 'Requires Adobe Pass Authentication',
200 }
201
202 def _real_extract(self, url):
203 video_id = self._match_id(url)
204 live_source = self._download_json(
205 'http://stream.nbcsports.com/data/live_sources_%s.json' % video_id,
206 video_id)
207 video_source = live_source['videoSources'][0]
208 title = video_source['title']
209 source_url = None
210 for k in ('source', 'msl4source', 'iossource', 'hlsv4'):
211 sk = k + 'Url'
212 source_url = video_source.get(sk) or video_source.get(sk + 'Alt')
213 if source_url:
214 break
215 else:
216 source_url = video_source['ottStreamUrl']
217 is_live = video_source.get('type') == 'live' or video_source.get('status') == 'Live'
218 resource = self._get_mvpd_resource('nbcsports', title, video_id, '')
219 token = self._extract_mvpd_auth(url, video_id, 'nbcsports', resource)
220 tokenized_url = self._download_json(
221 'https://token.playmakerservices.com/cdn',
222 video_id, data=json.dumps({
223 'requestorId': 'nbcsports',
224 'pid': video_id,
225 'application': 'NBCSports',
226 'version': 'v1',
227 'platform': 'desktop',
228 'cdn': 'akamai',
229 'url': video_source['sourceUrl'],
230 'token': base64.b64encode(token.encode()).decode(),
231 'resourceId': base64.b64encode(resource.encode()).decode(),
232 }).encode())['tokenizedUrl']
233 formats = self._extract_m3u8_formats(tokenized_url, video_id, 'mp4')
234 self._sort_formats(formats)
235 return {
236 'id': video_id,
237 'title': self._live_title(title) if is_live else title,
238 'description': live_source.get('description'),
239 'formats': formats,
240 'is_live': is_live,
241 }
242
243
244 class CSNNEIE(InfoExtractor):
245 _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
246
247 _TEST = {
248 'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
249 'info_dict': {
250 'id': 'yvBLLUgQ8WU0',
251 'ext': 'mp4',
252 'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
253 'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
254 'timestamp': 1459369979,
255 'upload_date': '20160330',
256 'uploader': 'NBCU-SPORTS',
257 }
258 }
259
260 def _real_extract(self, url):
261 display_id = self._match_id(url)
262 webpage = self._download_webpage(url, display_id)
263 return {
264 '_type': 'url_transparent',
265 'ie_key': 'ThePlatform',
266 'url': self._html_search_meta('twitter:player:stream', webpage),
267 'display_id': display_id,
268 }
269
270
271 class NBCNewsIE(ThePlatformIE):
272 _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
273 (?:video/.+?/(?P<id>\d+)|
274 ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
275 '''
276
277 _TESTS = [
278 {
279 'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
280 'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
281 'info_dict': {
282 'id': '52753292',
283 'ext': 'flv',
284 'title': 'Crew emerges after four-month Mars food study',
285 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
286 },
287 },
288 {
289 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
290 'md5': 'af1adfa51312291a017720403826bb64',
291 'info_dict': {
292 'id': 'p_tweet_snow_140529',
293 'ext': 'mp4',
294 'title': 'How Twitter Reacted To The Snowden Interview',
295 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
296 'uploader': 'NBCU-NEWS',
297 'timestamp': 1401363060,
298 'upload_date': '20140529',
299 },
300 },
301 {
302 'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
303 'md5': 'fdbf39ab73a72df5896b6234ff98518a',
304 'info_dict': {
305 'id': '529953347624',
306 'ext': 'mp4',
307 'title': 'FULL EPISODE: Family Business',
308 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
309 },
310 'skip': 'This page is unavailable.',
311 },
312 {
313 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
314 'md5': '73135a2e0ef819107bbb55a5a9b2a802',
315 'info_dict': {
316 'id': 'nn_netcast_150204',
317 'ext': 'mp4',
318 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
319 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
320 'timestamp': 1423104900,
321 'uploader': 'NBCU-NEWS',
322 'upload_date': '20150205',
323 },
324 },
325 {
326 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
327 'md5': 'a49e173825e5fcd15c13fc297fced39d',
328 'info_dict': {
329 'id': 'x_lon_vwhorn_150922',
330 'ext': 'mp4',
331 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
332 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
333 'upload_date': '20150922',
334 'timestamp': 1442917800,
335 'uploader': 'NBCU-NEWS',
336 },
337 },
338 {
339 'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
340 'md5': '118d7ca3f0bea6534f119c68ef539f71',
341 'info_dict': {
342 'id': 'tdy_al_space_160420',
343 'ext': 'mp4',
344 'title': 'See the aurora borealis from space in stunning new NASA video',
345 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
346 'upload_date': '20160420',
347 'timestamp': 1461152093,
348 'uploader': 'NBCU-NEWS',
349 },
350 },
351 {
352 'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
353 'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
354 'info_dict': {
355 'id': 'n_hayes_Aimm_140801_272214',
356 'ext': 'mp4',
357 'title': 'The chaotic GOP immigration vote',
358 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
359 'thumbnail': r're:^https?://.*\.jpg$',
360 'timestamp': 1406937606,
361 'upload_date': '20140802',
362 'uploader': 'NBCU-NEWS',
363 },
364 },
365 {
366 'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
367 'only_matching': True,
368 },
369 {
370 # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
371 'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
372 'only_matching': True,
373 },
374 ]
375
376 def _real_extract(self, url):
377 mobj = re.match(self._VALID_URL, url)
378 video_id = mobj.group('id')
379 if video_id is not None:
380 all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
381 info = all_info.find('video')
382
383 return {
384 'id': video_id,
385 'title': info.find('headline').text,
386 'ext': 'flv',
387 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
388 'description': info.find('caption').text,
389 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
390 }
391 else:
392 # "feature" and "nightly-news" pages use theplatform.com
393 video_id = mobj.group('mpx_id')
394 webpage = self._download_webpage(url, video_id)
395
396 filter_param = 'byId'
397 bootstrap_json = self._search_regex(
398 [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
399 r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
400 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
401 webpage, 'bootstrap json', default=None)
402 if bootstrap_json:
403 bootstrap = self._parse_json(
404 bootstrap_json, video_id, transform_source=unescapeHTML)
405
406 info = None
407 if 'results' in bootstrap:
408 info = bootstrap['results'][0]['video']
409 elif 'video' in bootstrap:
410 info = bootstrap['video']
411 elif 'msnbcVideoInfo' in bootstrap:
412 info = bootstrap['msnbcVideoInfo']['meta']
413 elif 'msnbcThePlatform' in bootstrap:
414 info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
415 else:
416 info = bootstrap
417
418 if 'guid' in info:
419 video_id = info['guid']
420 filter_param = 'byGuid'
421 elif 'mpxId' in info:
422 video_id = info['mpxId']
423
424 return {
425 '_type': 'url_transparent',
426 'id': video_id,
427 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
428 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
429 'ie_key': 'ThePlatformFeed',
430 }
431
432
433 class NBCOlympicsIE(InfoExtractor):
434 IE_NAME = 'nbcolympics'
435 _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
436
437 _TEST = {
438 # Geo-restricted to US
439 'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
440 'md5': '54fecf846d05429fbaa18af557ee523a',
441 'info_dict': {
442 'id': 'WjTBzDXx5AUq',
443 'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
444 'ext': 'mp4',
445 'title': 'Rose\'s son Leo was in tears after his dad won gold',
446 'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
447 'timestamp': 1471274964,
448 'upload_date': '20160815',
449 'uploader': 'NBCU-SPORTS',
450 },
451 }
452
453 def _real_extract(self, url):
454 display_id = self._match_id(url)
455
456 webpage = self._download_webpage(url, display_id)
457
458 drupal_settings = self._parse_json(self._search_regex(
459 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
460 webpage, 'drupal settings'), display_id)
461
462 iframe_url = drupal_settings['vod']['iframe_url']
463 theplatform_url = iframe_url.replace(
464 'vplayer.nbcolympics.com', 'player.theplatform.com')
465
466 return {
467 '_type': 'url_transparent',
468 'url': theplatform_url,
469 'ie_key': ThePlatformIE.ie_key(),
470 'display_id': display_id,
471 }
472
473
474 class NBCOlympicsStreamIE(AdobePassIE):
475 IE_NAME = 'nbcolympics:stream'
476 _VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
477 _TEST = {
478 'url': 'http://stream.nbcolympics.com/2018-winter-olympics-nbcsn-evening-feb-8',
479 'info_dict': {
480 'id': '203493',
481 'ext': 'mp4',
482 'title': 're:Curling, Alpine, Luge [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
483 },
484 'params': {
485 # m3u8 download
486 'skip_download': True,
487 },
488 }
489 _DATA_URL_TEMPLATE = 'http://stream.nbcolympics.com/data/%s_%s.json'
490
491 def _real_extract(self, url):
492 display_id = self._match_id(url)
493 webpage = self._download_webpage(url, display_id)
494 pid = self._search_regex(r'pid\s*=\s*(\d+);', webpage, 'pid')
495 resource = self._search_regex(
496 r"resource\s*=\s*'(.+)';", webpage,
497 'resource').replace("' + pid + '", pid)
498 event_config = self._download_json(
499 self._DATA_URL_TEMPLATE % ('event_config', pid),
500 pid)['eventConfig']
501 title = self._live_title(event_config['eventTitle'])
502 source_url = self._download_json(
503 self._DATA_URL_TEMPLATE % ('live_sources', pid),
504 pid)['videoSources'][0]['sourceUrl']
505 media_token = self._extract_mvpd_auth(
506 url, pid, event_config.get('requestorId', 'NBCOlympics'), resource)
507 formats = self._extract_m3u8_formats(self._download_webpage(
508 'http://sp.auth.adobe.com/tvs/v1/sign', pid, query={
509 'cdn': 'akamai',
510 'mediaToken': base64.b64encode(media_token.encode()),
511 'resource': base64.b64encode(resource.encode()),
512 'url': source_url,
513 }), pid, 'mp4')
514 self._sort_formats(formats)
515
516 return {
517 'id': pid,
518 'display_id': display_id,
519 'title': title,
520 'formats': formats,
521 'is_live': True,
522 }