5 from .common
import InfoExtractor
6 from .theplatform
import ThePlatformIE
7 from .adobepass
import AdobePassIE
8 from ..compat
import compat_urllib_parse_unquote
21 class NBCIE(ThePlatformIE
):
22 _VALID_URL
= r
'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
26 'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
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',
38 'skip_download': True,
42 'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
46 'title': 'Star Wars Teaser',
47 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
48 'timestamp': 1417852800,
49 'upload_date': '20141206',
50 'uploader': 'NBCU-COM',
54 'skip_download': True,
56 'skip': 'Only works from US',
59 # HLS streams requires the 'hdnea3' cookie
60 'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
62 'id': '101528f5a9e8127b107e98c5e6ce4638',
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',
71 'skip_download': True,
73 'skip': 'Only works from US',
76 'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
77 'only_matching': True,
81 'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
82 'only_matching': True,
86 def _real_extract(self
, url
):
87 permalink
, video_id
= self
._match
_valid
_url
(url
).groups()
88 permalink
= 'http' + compat_urllib_parse_unquote(permalink
)
89 video_data
= self
._download
_json
(
90 'https://friendship.nbc.co/v2/graphql', video_id
, query
={
91 'query': '''query bonanzaPage(
92 $app: NBCUBrands! = nbc
95 $platform: SupportedPlatforms! = web
96 $type: EntityPageType! = VIDEO
108 ... on VideoPageData {
124 'variables': json
.dumps({
129 })['data']['bonanzaPage']['metadata']
134 video_id
= video_data
['mpxGuid']
135 tp_path
= 'NnzsPC/media/guid/%s/%s' % (video_data
.get('mpxAccountId') or '2410887629', video_id
)
136 tpm
= self
._download
_theplatform
_metadata
(tp_path
, video_id
)
137 title
= tpm
.get('title') or video_data
.get('secondaryTitle')
138 if video_data
.get('locked'):
139 resource
= self
._get
_mvpd
_resource
(
140 video_data
.get('resourceId') or 'nbcentertainment',
141 title
, video_id
, video_data
.get('rating'))
142 query
['auth'] = self
._extract
_mvpd
_auth
(
143 url
, video_id
, 'nbcentertainment', resource
)
144 theplatform_url
= smuggle_url(update_url_query(
145 'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data
.get('mpxAccountId') or '2410887629', video_id
),
146 query
), {'force_smil_url': True}
)
148 # Empty string or 0 can be valid values for these. So the check must be `is None`
149 description
= video_data
.get('description')
150 if description
is None:
151 description
= tpm
.get('description')
152 episode_number
= int_or_none(video_data
.get('episodeNumber'))
153 if episode_number
is None:
154 episode_number
= int_or_none(tpm
.get('nbcu$airOrder'))
155 rating
= video_data
.get('rating')
157 try_get(tpm
, lambda x
: x
['ratings'][0]['rating'])
158 season_number
= int_or_none(video_data
.get('seasonNumber'))
159 if season_number
is None:
160 season_number
= int_or_none(tpm
.get('nbcu$seasonNumber'))
161 series
= video_data
.get('seriesShortTitle')
163 series
= tpm
.get('nbcu$seriesShortTitle')
164 tags
= video_data
.get('keywords')
165 if tags
is None or len(tags
) == 0:
166 tags
= tpm
.get('keywords')
169 '_type': 'url_transparent',
170 'age_limit': parse_age_limit(rating
),
171 'description': description
,
173 'episode_number': episode_number
,
175 'ie_key': 'ThePlatform',
176 'season_number': season_number
,
180 'url': theplatform_url
,
184 class NBCSportsVPlayerIE(InfoExtractor
):
185 _VALID_URL_BASE
= r
'https?://(?:vplayer\.nbcsports\.com|(?:www\.)?nbcsports\.com/vplayer)/'
186 _VALID_URL
= _VALID_URL_BASE
+ r
'(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
187 _EMBED_REGEX
= [r
'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>%s[^\"]+)' % _VALID_URL_BASE
]
190 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
192 'id': '9CsDKds0kvHI',
194 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
195 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
196 'timestamp': 1426270238,
197 'upload_date': '20150313',
198 'uploader': 'NBCU-SPORTS',
201 'thumbnail': r
're:^https?://.*\.jpg$'
204 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/PEgOtlNcC_y2',
205 'only_matching': True,
207 'url': 'https://www.nbcsports.com/vplayer/p/BxmELC/nbcsports/select/PHJSaFWbrTY9?form=html&autoPlay=true',
208 'only_matching': True,
211 def _real_extract(self
, url
):
212 video_id
= self
._match
_id
(url
)
213 webpage
= self
._download
_webpage
(url
, video_id
)
214 theplatform_url
= self
._html
_search
_regex
(r
'tp:releaseUrl="(.+?)"', webpage
, 'url')
215 return self
.url_result(theplatform_url
, 'ThePlatform')
218 class NBCSportsIE(InfoExtractor
):
219 _VALID_URL
= r
'https?://(?:www\.)?nbcsports\.com//?(?!vplayer/)(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
223 'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
225 'id': 'PHJSaFWbrTY9',
227 'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
228 'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
229 'uploader': 'NBCU-SPORTS',
230 'upload_date': '20150330',
231 'timestamp': 1427726529,
233 'thumbnail': 'https://hdliveextra-a.akamaihd.net/HD/image_sports/NBCU_Sports_Group_-_nbcsports/253/303/izzodps.jpg',
238 'url': 'https://www.nbcsports.com/philadelphia/philadelphia-phillies/bruce-bochy-hector-neris-hes-idiot',
239 'only_matching': True,
242 'url': 'https://www.nbcsports.com/boston/video/report-card-pats-secondary-no-match-josh-allen',
243 'only_matching': True,
246 def _real_extract(self
, url
):
247 video_id
= self
._match
_id
(url
)
248 webpage
= self
._download
_webpage
(url
, video_id
)
249 return self
.url_result(
250 NBCSportsVPlayerIE
._extract
_url
(webpage
), 'NBCSportsVPlayer')
253 class NBCSportsStreamIE(AdobePassIE
):
254 _VALID_URL
= r
'https?://stream\.nbcsports\.com/.+?\bpid=(?P<id>\d+)'
256 'url': 'http://stream.nbcsports.com/nbcsn/generic?pid=206559',
260 'title': 'Amgen Tour of California Women\'s Recap',
261 'description': 'md5:66520066b3b5281ada7698d0ea2aa894',
265 'skip_download': True,
267 'skip': 'Requires Adobe Pass Authentication',
270 def _real_extract(self
, url
):
271 video_id
= self
._match
_id
(url
)
272 live_source
= self
._download
_json
(
273 'http://stream.nbcsports.com/data/live_sources_%s.json' % video_id
,
275 video_source
= live_source
['videoSources'][0]
276 title
= video_source
['title']
278 for k
in ('source', 'msl4source', 'iossource', 'hlsv4'):
280 source_url
= video_source
.get(sk
) or video_source
.get(sk
+ 'Alt')
284 source_url
= video_source
['ottStreamUrl']
285 is_live
= video_source
.get('type') == 'live' or video_source
.get('status') == 'Live'
286 resource
= self
._get
_mvpd
_resource
('nbcsports', title
, video_id
, '')
287 token
= self
._extract
_mvpd
_auth
(url
, video_id
, 'nbcsports', resource
)
288 tokenized_url
= self
._download
_json
(
289 'https://token.playmakerservices.com/cdn',
290 video_id
, data
=json
.dumps({
291 'requestorId': 'nbcsports',
293 'application': 'NBCSports',
295 'platform': 'desktop',
297 'url': video_source
['sourceUrl'],
298 'token': base64
.b64encode(token
.encode()).decode(),
299 'resourceId': base64
.b64encode(resource
.encode()).decode(),
300 }).encode())['tokenizedUrl']
301 formats
= self
._extract
_m
3u8_formats
(tokenized_url
, video_id
, 'mp4')
302 self
._sort
_formats
(formats
)
306 'description': live_source
.get('description'),
312 class NBCNewsIE(ThePlatformIE
):
313 _VALID_URL
= r
'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
314 _EMBED_REGEX
= [r
'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//www\
.nbcnews\
.com
/widget
/video
-embed
/[^
"\']+)\1']
318 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
319 'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf',
321 'id': '269389891880',
323 'title': 'How Twitter Reacted To The Snowden Interview',
324 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
325 'timestamp': 1401363060,
326 'upload_date': '20140529',
330 'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
331 'md5': 'fdbf39ab73a72df5896b6234ff98518a',
333 'id': '529953347624',
335 'title': 'FULL EPISODE: Family Business',
336 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
338 'skip': 'This page is unavailable.',
341 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
342 'md5': '8eb831eca25bfa7d25ddd83e85946548',
344 'id': '394064451844',
346 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
347 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
348 'timestamp': 1423104900,
349 'upload_date': '20150205',
353 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
354 'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0',
358 'title': "Volkswagen U
.S
. Chief
: We
'Totally Screwed Up'",
359 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301',
360 'upload_date': '20150922',
361 'timestamp': 1442917800,
365 'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
366 'md5': '118d7ca3f0bea6534f119c68ef539f71',
368 'id': '669831235788',
370 'title': 'See the aurora borealis from space in stunning new NASA video',
371 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
372 'upload_date': '20160420',
373 'timestamp': 1461152093,
377 'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
378 'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
380 'id': '314487875924',
382 'title': 'The chaotic GOP immigration vote',
383 '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.',
384 'thumbnail': r're:^https?://.*\.jpg$',
385 'timestamp': 1406937606,
386 'upload_date': '20140802',
390 'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
391 'only_matching': True,
394 # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
395 'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
396 'only_matching': True,
400 def _real_extract(self, url):
401 video_id = self._match_id(url)
402 webpage = self._download_webpage(url, video_id)
404 data = self._search_nextjs_data(webpage, video_id)['props']['initialState']
405 video_data = try_get(data, lambda x: x['video']['current'], dict)
407 video_data = data['article']['content'][0]['primaryMedia']['video']
408 title = video_data['headline']['primary']
411 for va in video_data.get('videoAssets', []):
412 public_url = va.get('publicUrl')
415 if '://link.theplatform.com/' in public_url:
416 public_url = update_url_query(public_url, {'format': 'redirect'})
417 format_id = va.get('format')
418 if format_id == 'M3U':
419 formats.extend(self._extract_m3u8_formats(
420 public_url, video_id, 'mp4', 'm3u8_native',
421 m3u8_id=format_id, fatal=False))
423 tbr = int_or_none(va.get('bitrate'), 1000)
425 format_id += '-%d' % tbr
427 'format_id': format_id,
429 'width': int_or_none(va.get('width')),
430 'height': int_or_none(va.get('height')),
434 self._sort_formats(formats)
437 closed_captioning = video_data.get('closedCaptioning')
438 if closed_captioning:
439 for cc_url in closed_captioning.values():
442 subtitles.setdefault('en', []).append({
449 'description': try_get(video_data, lambda x: x['description']['primary']),
450 'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']),
451 'duration': parse_duration(video_data.get('duration')),
452 'timestamp': unified_timestamp(video_data.get('datePublished')),
454 'subtitles': subtitles,
458 class NBCOlympicsIE(InfoExtractor):
459 IE_NAME = 'nbcolympics'
460 _VALID_URL = r'https?://www\.nbcolympics\.com/videos?/(?P<id>[0-9a-z-]+)'
463 # Geo-restricted to US
464 'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
465 'md5': '54fecf846d05429fbaa18af557ee523a',
467 'id': 'WjTBzDXx5AUq',
468 'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
470 'title': 'Rose\'s son Leo was in tears after his dad won gold',
471 'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
472 'timestamp': 1471274964,
473 'upload_date': '20160815',
474 'uploader': 'NBCU-SPORTS',
478 def _real_extract(self, url):
479 display_id = self._match_id(url)
481 webpage = self._download_webpage(url, display_id)
484 drupal_settings = self._parse_json(self._search_regex(
485 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
486 webpage, 'drupal settings'), display_id)
488 iframe_url = drupal_settings['vod']['iframe_url']
489 theplatform_url = iframe_url.replace(
490 'vplayer.nbcolympics.com', 'player.theplatform.com')
491 except RegexNotFoundError:
492 theplatform_url = self._search_regex(
493 r"([\"'])embedUrl\1: *([\"'])(?P
<embedUrl
>.+)\
2",
494 webpage, 'embedding URL', group="embedUrl
")
497 '_type': 'url_transparent',
498 'url': theplatform_url,
499 'ie_key': ThePlatformIE.ie_key(),
500 'display_id': display_id,
504 class NBCOlympicsStreamIE(AdobePassIE):
505 IE_NAME = 'nbcolympics:stream'
506 _VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
509 'note': 'Tokenized m3u8 source URL',
510 'url': 'https://stream.nbcolympics.com/womens-soccer-group-round-11',
514 'title': r"re
:Women
's Group Stage - Netherlands vs\. Brazil [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$",
517 'skip_download
': 'm3u8
',
520 'note
': 'Plain m3u8 source URL
',
521 'url
': 'https
://stream
.nbcolympics
.com
/gymnastics
-event
-finals
-mens
-floor
-pommel
-horse
-womens
-vault
-bars
',
525 'title
': r're
:Event Finals
: M Floor
, W Vault
, M Pommel
, W Uneven Bars
[0-9]{4}
-[0-9]{2}
-[0-9]{2}
[0-9]{2}
:[0-9]{2}$
',
528 'skip_download
': 'm3u8
',
533 def _real_extract(self, url):
534 display_id = self._match_id(url)
535 webpage = self._download_webpage(url, display_id)
536 pid = self._search_regex(r'pid\s
*=\s
*(\d
+);', webpage, 'pid
')
538 event_config = self._download_json(
539 f'http
://stream
.nbcolympics
.com
/data
/event_config_{pid}
.json
',
540 pid, 'Downloading event config
')['eventConfig
']
542 title = event_config['eventTitle
']
543 is_live = {'live': True, 'replay': False}.get(event_config.get('eventStatus
'))
545 source_url = self._download_json(
546 f'https
://api
-leap
.nbcsports
.com
/feeds
/assets
/{pid}?application
=NBCOlympics
&platform
=desktop
&format
=nbc
-player
&env
=staging
',
547 pid, 'Downloading leap config
'
548 )['videoSources
'][0]['cdnSources
']['primary
'][0]['sourceUrl
']
550 if event_config.get('cdnToken
'):
551 ap_resource = self._get_mvpd_resource(
552 event_config.get('resourceId
', 'NBCOlympics
'),
553 re.sub(r'[^\w\d
]+', '', event_config['eventTitle
']), pid,
554 event_config.get('ratingId
', 'NO VALUE
'))
555 media_token = self._extract_mvpd_auth(url, pid, event_config.get('requestorId
', 'NBCOlympics
'), ap_resource)
557 source_url = self._download_json(
558 'https
://tokens
.playmakerservices
.com
/', pid, 'Retrieving tokenized URL
',
560 'application
': 'NBCSports
',
561 'authentication
-type': 'adobe
-pass',
564 'platform
': 'desktop
',
565 'requestorId
': 'NBCOlympics
',
566 'resourceId
': base64.b64encode(ap_resource.encode()).decode(),
567 'token
': base64.b64encode(media_token.encode()).decode(),
571 )['akamai
'][0]['tokenizedUrl
']
573 formats = self._extract_m3u8_formats(source_url, pid, 'mp4
', live=is_live)
575 # -http_seekable requires ffmpeg 4.3+ but it doesnt seem possible to
576 # download with ffmpeg without this option
577 f['downloader_options
'] = {'ffmpeg_args': ['-seekable', '0', '-http_seekable', '0', '-icy', '0']}
578 self._sort_formats(formats)
582 'display_id
': display_id,