5 from .common
import InfoExtractor
6 from .theplatform
import ThePlatformIE
7 from .adobepass
import AdobePassIE
8 from ..compat
import compat_urllib_parse_unquote
27 class NBCIE(ThePlatformIE
): # XXX: Do not subclass from concrete IE
28 _VALID_URL
= r
'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
32 'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
36 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
37 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
38 'timestamp': 1424246400,
39 'upload_date': '20150218',
40 'uploader': 'NBCU-COM',
44 'skip_download': True,
48 'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
52 'title': 'Star Wars Teaser',
53 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
54 'timestamp': 1417852800,
55 'upload_date': '20141206',
56 'uploader': 'NBCU-COM',
60 'skip_download': True,
62 'skip': 'Only works from US',
65 # HLS streams requires the 'hdnea3' cookie
66 'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
68 'id': '101528f5a9e8127b107e98c5e6ce4638',
71 '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.',
72 'timestamp': 1237100400,
73 'upload_date': '20090315',
74 'uploader': 'NBCU-COM',
77 'skip_download': True,
79 'skip': 'Only works from US',
82 'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
83 'only_matching': True,
87 'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
88 'only_matching': True,
92 def _real_extract(self
, url
):
93 permalink
, video_id
= self
._match
_valid
_url
(url
).groups()
94 permalink
= 'http' + compat_urllib_parse_unquote(permalink
)
95 video_data
= self
._download
_json
(
96 'https://friendship.nbc.co/v2/graphql', video_id
, query
={
97 'query': '''query bonanzaPage(
98 $app: NBCUBrands! = nbc
101 $platform: SupportedPlatforms! = web
102 $type: EntityPageType! = VIDEO
114 ... on VideoPageData {
130 'variables': json
.dumps({
135 })['data']['bonanzaPage']['metadata']
140 video_id
= video_data
['mpxGuid']
141 tp_path
= 'NnzsPC/media/guid/%s/%s' % (video_data
.get('mpxAccountId') or '2410887629', video_id
)
142 tpm
= self
._download
_theplatform
_metadata
(tp_path
, video_id
)
143 title
= tpm
.get('title') or video_data
.get('secondaryTitle')
144 if video_data
.get('locked'):
145 resource
= self
._get
_mvpd
_resource
(
146 video_data
.get('resourceId') or 'nbcentertainment',
147 title
, video_id
, video_data
.get('rating'))
148 query
['auth'] = self
._extract
_mvpd
_auth
(
149 url
, video_id
, 'nbcentertainment', resource
)
150 theplatform_url
= smuggle_url(update_url_query(
151 'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data
.get('mpxAccountId') or '2410887629', video_id
),
152 query
), {'force_smil_url': True}
)
154 # Empty string or 0 can be valid values for these. So the check must be `is None`
155 description
= video_data
.get('description')
156 if description
is None:
157 description
= tpm
.get('description')
158 episode_number
= int_or_none(video_data
.get('episodeNumber'))
159 if episode_number
is None:
160 episode_number
= int_or_none(tpm
.get('nbcu$airOrder'))
161 rating
= video_data
.get('rating')
163 try_get(tpm
, lambda x
: x
['ratings'][0]['rating'])
164 season_number
= int_or_none(video_data
.get('seasonNumber'))
165 if season_number
is None:
166 season_number
= int_or_none(tpm
.get('nbcu$seasonNumber'))
167 series
= video_data
.get('seriesShortTitle')
169 series
= tpm
.get('nbcu$seriesShortTitle')
170 tags
= video_data
.get('keywords')
171 if tags
is None or len(tags
) == 0:
172 tags
= tpm
.get('keywords')
175 '_type': 'url_transparent',
176 'age_limit': parse_age_limit(rating
),
177 'description': description
,
179 'episode_number': episode_number
,
181 'ie_key': 'ThePlatform',
182 'season_number': season_number
,
186 'url': theplatform_url
,
190 class NBCSportsVPlayerIE(InfoExtractor
):
191 _VALID_URL_BASE
= r
'https?://(?:vplayer\.nbcsports\.com|(?:www\.)?nbcsports\.com/vplayer)/'
192 _VALID_URL
= _VALID_URL_BASE
+ r
'(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
193 _EMBED_REGEX
= [r
'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>%s[^\"]+)' % _VALID_URL_BASE
]
196 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
198 'id': '9CsDKds0kvHI',
200 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
201 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
202 'timestamp': 1426270238,
203 'upload_date': '20150313',
204 'uploader': 'NBCU-SPORTS',
207 'thumbnail': r
're:^https?://.*\.jpg$'
210 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/PEgOtlNcC_y2',
211 'only_matching': True,
213 'url': 'https://www.nbcsports.com/vplayer/p/BxmELC/nbcsports/select/PHJSaFWbrTY9?form=html&autoPlay=true',
214 'only_matching': True,
217 def _real_extract(self
, url
):
218 video_id
= self
._match
_id
(url
)
219 webpage
= self
._download
_webpage
(url
, video_id
)
220 theplatform_url
= self
._html
_search
_regex
(r
'tp:releaseUrl="(.+?)"', webpage
, 'url')
221 return self
.url_result(theplatform_url
, 'ThePlatform')
224 class NBCSportsIE(InfoExtractor
):
225 _VALID_URL
= r
'https?://(?:www\.)?nbcsports\.com//?(?!vplayer/)(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
229 'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
231 'id': 'PHJSaFWbrTY9',
233 'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
234 'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
235 'uploader': 'NBCU-SPORTS',
236 'upload_date': '20150330',
237 'timestamp': 1427726529,
239 'thumbnail': 'https://hdliveextra-a.akamaihd.net/HD/image_sports/NBCU_Sports_Group_-_nbcsports/253/303/izzodps.jpg',
244 'url': 'https://www.nbcsports.com/philadelphia/philadelphia-phillies/bruce-bochy-hector-neris-hes-idiot',
245 'only_matching': True,
248 'url': 'https://www.nbcsports.com/boston/video/report-card-pats-secondary-no-match-josh-allen',
249 'only_matching': True,
252 def _real_extract(self
, url
):
253 video_id
= self
._match
_id
(url
)
254 webpage
= self
._download
_webpage
(url
, video_id
)
255 return self
.url_result(
256 NBCSportsVPlayerIE
._extract
_url
(webpage
), 'NBCSportsVPlayer')
259 class NBCSportsStreamIE(AdobePassIE
):
260 _VALID_URL
= r
'https?://stream\.nbcsports\.com/.+?\bpid=(?P<id>\d+)'
262 'url': 'http://stream.nbcsports.com/nbcsn/generic?pid=206559',
266 'title': 'Amgen Tour of California Women\'s Recap',
267 'description': 'md5:66520066b3b5281ada7698d0ea2aa894',
271 'skip_download': True,
273 'skip': 'Requires Adobe Pass Authentication',
276 def _real_extract(self
, url
):
277 video_id
= self
._match
_id
(url
)
278 live_source
= self
._download
_json
(
279 'http://stream.nbcsports.com/data/live_sources_%s.json' % video_id
,
281 video_source
= live_source
['videoSources'][0]
282 title
= video_source
['title']
284 for k
in ('source', 'msl4source', 'iossource', 'hlsv4'):
286 source_url
= video_source
.get(sk
) or video_source
.get(sk
+ 'Alt')
290 source_url
= video_source
['ottStreamUrl']
291 is_live
= video_source
.get('type') == 'live' or video_source
.get('status') == 'Live'
292 resource
= self
._get
_mvpd
_resource
('nbcsports', title
, video_id
, '')
293 token
= self
._extract
_mvpd
_auth
(url
, video_id
, 'nbcsports', resource
)
294 tokenized_url
= self
._download
_json
(
295 'https://token.playmakerservices.com/cdn',
296 video_id
, data
=json
.dumps({
297 'requestorId': 'nbcsports',
299 'application': 'NBCSports',
301 'platform': 'desktop',
303 'url': video_source
['sourceUrl'],
304 'token': base64
.b64encode(token
.encode()).decode(),
305 'resourceId': base64
.b64encode(resource
.encode()).decode(),
306 }).encode())['tokenizedUrl']
307 formats
= self
._extract
_m
3u8_formats
(tokenized_url
, video_id
, 'mp4')
311 'description': live_source
.get('description'),
317 class NBCNewsIE(ThePlatformIE
): # XXX: Do not subclass from concrete IE
318 _VALID_URL
= r
'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
319 _EMBED_REGEX
= [r
'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//www\
.nbcnews\
.com
/widget
/video
-embed
/[^
"\']+)\1']
323 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
324 'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf',
326 'id': '269389891880',
328 'title': 'How Twitter Reacted To The Snowden Interview',
329 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
330 'timestamp': 1401363060,
331 'upload_date': '20140529',
335 'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
336 'md5': 'fdbf39ab73a72df5896b6234ff98518a',
338 'id': '529953347624',
340 'title': 'FULL EPISODE: Family Business',
341 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
343 'skip': 'This page is unavailable.',
346 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
347 'md5': '8eb831eca25bfa7d25ddd83e85946548',
349 'id': '394064451844',
351 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
352 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
353 'timestamp': 1423104900,
354 'upload_date': '20150205',
358 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
359 'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0',
363 'title': "Volkswagen U
.S
. Chief
: We
'Totally Screwed Up'",
364 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301',
365 'upload_date': '20150922',
366 'timestamp': 1442917800,
370 'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
371 'md5': '118d7ca3f0bea6534f119c68ef539f71',
373 'id': '669831235788',
375 'title': 'See the aurora borealis from space in stunning new NASA video',
376 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
377 'upload_date': '20160420',
378 'timestamp': 1461152093,
382 'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
383 'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
385 'id': '314487875924',
387 'title': 'The chaotic GOP immigration vote',
388 '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.',
389 'thumbnail': r're:^https?://.*\.jpg$',
390 'timestamp': 1406937606,
391 'upload_date': '20140802',
395 'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
396 'only_matching': True,
399 # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
400 'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
401 'only_matching': True,
405 def _real_extract(self, url):
406 video_id = self._match_id(url)
407 webpage = self._download_webpage(url, video_id)
409 data = self._search_nextjs_data(webpage, video_id)['props']['initialState']
410 video_data = try_get(data, lambda x: x['video']['current'], dict)
412 video_data = data['article']['content'][0]['primaryMedia']['video']
413 title = video_data['headline']['primary']
416 for va in video_data.get('videoAssets', []):
417 public_url = va.get('publicUrl')
420 if '://link.theplatform.com/' in public_url:
421 public_url = update_url_query(public_url, {'format': 'redirect'})
422 format_id = va.get('format')
423 if format_id == 'M3U':
424 formats.extend(self._extract_m3u8_formats(
425 public_url, video_id, 'mp4', 'm3u8_native',
426 m3u8_id=format_id, fatal=False))
428 tbr = int_or_none(va.get('bitrate'), 1000)
430 format_id += '-%d' % tbr
432 'format_id': format_id,
434 'width': int_or_none(va.get('width')),
435 'height': int_or_none(va.get('height')),
441 closed_captioning = video_data.get('closedCaptioning')
442 if closed_captioning:
443 for cc_url in closed_captioning.values():
446 subtitles.setdefault('en', []).append({
453 'description': try_get(video_data, lambda x: x['description']['primary']),
454 'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']),
455 'duration': parse_duration(video_data.get('duration')),
456 'timestamp': unified_timestamp(video_data.get('datePublished')),
458 'subtitles': subtitles,
462 class NBCOlympicsIE(InfoExtractor):
463 IE_NAME = 'nbcolympics'
464 _VALID_URL = r'https?://www\.nbcolympics\.com/videos?/(?P<id>[0-9a-z-]+)'
467 # Geo-restricted to US
468 'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
469 'md5': '54fecf846d05429fbaa18af557ee523a',
471 'id': 'WjTBzDXx5AUq',
472 'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
474 'title': 'Rose\'s son Leo was in tears after his dad won gold',
475 'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
476 'timestamp': 1471274964,
477 'upload_date': '20160815',
478 'uploader': 'NBCU-SPORTS',
482 def _real_extract(self, url):
483 display_id = self._match_id(url)
485 webpage = self._download_webpage(url, display_id)
488 drupal_settings = self._parse_json(self._search_regex(
489 r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
490 webpage, 'drupal settings'), display_id)
492 iframe_url = drupal_settings['vod']['iframe_url']
493 theplatform_url = iframe_url.replace(
494 'vplayer.nbcolympics.com', 'player.theplatform.com')
495 except RegexNotFoundError:
496 theplatform_url = self._search_regex(
497 r"([\"'])embedUrl\1: *([\"'])(?P
<embedUrl
>.+)\
2",
498 webpage, 'embedding URL', group="embedUrl
")
501 '_type': 'url_transparent',
502 'url': theplatform_url,
503 'ie_key': ThePlatformIE.ie_key(),
504 'display_id': display_id,
508 class NBCOlympicsStreamIE(AdobePassIE):
509 IE_NAME = 'nbcolympics:stream'
510 _VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
513 'note': 'Tokenized m3u8 source URL',
514 'url': 'https://stream.nbcolympics.com/womens-soccer-group-round-11',
518 '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}$",
521 'skip_download
': 'm3u8
',
524 'note
': 'Plain m3u8 source URL
',
525 'url
': 'https
://stream
.nbcolympics
.com
/gymnastics
-event
-finals
-mens
-floor
-pommel
-horse
-womens
-vault
-bars
',
529 'title
': r're
:Event Finals
: M Floor
, W Vault
, M Pommel
, W Uneven Bars
[0-9]{4}
-[0-9]{2}
-[0-9]{2}
[0-9]{2}
:[0-9]{2}$
',
532 'skip_download
': 'm3u8
',
537 def _real_extract(self, url):
538 display_id = self._match_id(url)
539 webpage = self._download_webpage(url, display_id)
540 pid = self._search_regex(r'pid\s
*=\s
*(\d
+);', webpage, 'pid
')
542 event_config = self._download_json(
543 f'http
://stream
.nbcolympics
.com
/data
/event_config_{pid}
.json
',
544 pid, 'Downloading event config
')['eventConfig
']
546 title = event_config['eventTitle
']
547 is_live = {'live': True, 'replay': False}.get(event_config.get('eventStatus
'))
549 source_url = self._download_json(
550 f'https
://api
-leap
.nbcsports
.com
/feeds
/assets
/{pid}?application
=NBCOlympics
&platform
=desktop
&format
=nbc
-player
&env
=staging
',
551 pid, 'Downloading leap config
'
552 )['videoSources
'][0]['cdnSources
']['primary
'][0]['sourceUrl
']
554 if event_config.get('cdnToken
'):
555 ap_resource = self._get_mvpd_resource(
556 event_config.get('resourceId
', 'NBCOlympics
'),
557 re.sub(r'[^\w\d
]+', '', event_config['eventTitle
']), pid,
558 event_config.get('ratingId
', 'NO VALUE
'))
559 media_token = self._extract_mvpd_auth(url, pid, event_config.get('requestorId
', 'NBCOlympics
'), ap_resource)
561 source_url = self._download_json(
562 'https
://tokens
.playmakerservices
.com
/', pid, 'Retrieving tokenized URL
',
564 'application
': 'NBCSports
',
565 'authentication
-type': 'adobe
-pass',
568 'platform
': 'desktop
',
569 'requestorId
': 'NBCOlympics
',
570 'resourceId
': base64.b64encode(ap_resource.encode()).decode(),
571 'token
': base64.b64encode(media_token.encode()).decode(),
575 )['akamai
'][0]['tokenizedUrl
']
577 formats = self._extract_m3u8_formats(source_url, pid, 'mp4
', live=is_live)
579 # -http_seekable requires ffmpeg 4.3+ but it doesnt seem possible to
580 # download with ffmpeg without this option
581 f['downloader_options
'] = {'ffmpeg_args': ['-seekable', '0', '-http_seekable', '0', '-icy', '0']}
585 'display_id
': display_id,
592 class NBCStationsIE(InfoExtractor):
593 _DOMAIN_RE = '|
'.join(map(re.escape, (
594 'nbcbayarea
', 'nbcboston
', 'nbcchicago
', 'nbcconnecticut
', 'nbcdfw
', 'nbclosangeles
',
595 'nbcmiami
', 'nbcnewyork
', 'nbcphiladelphia
', 'nbcsandiego
', 'nbcwashington
',
596 'necn
', 'telemundo52
', 'telemundoarizona
', 'telemundochicago
', 'telemundonuevainglaterra
',
598 _VALID_URL = rf'https?
://(?
:www\
.)?
(?P
<site
>{_DOMAIN_RE}
)\
.com
/(?
:[^
/?
#]+/)*(?P<id>[^/?#]+)/?(?:$|[#?])'
601 'url': 'https://www.nbclosangeles.com/news/local/large-structure-fire-in-downtown-la-prompts-smoke-odor-advisory/2968618/',
602 'md5': '462041d91bd762ef5a38b7d85d6dc18f',
606 'title': 'Large Structure Fire in Downtown LA Prompts Smoke Odor Advisory',
608 'timestamp': 1661135892,
609 'upload_date': '20220821',
611 'uploader_id': 'KNBC',
612 'channel': 'nbclosangeles',
615 'url': 'https://www.telemundoarizona.com/responde/huracan-complica-reembolso-para-televidente-de-tucson/2247002/',
616 'md5': '0917dcf7885be1023a9220630d415f67',
620 'title': 'Huracán complica que televidente de Tucson reciba reembolso',
621 'description': 'md5:af298dc73aab74d4fca6abfb12acb6cf',
622 'timestamp': 1660886507,
623 'upload_date': '20220819',
624 'uploader': 'Telemundo Arizona',
625 'uploader_id': 'KTAZ',
626 'channel': 'telemundoarizona',
638 def _real_extract(self
, url
):
639 channel
, video_id
= self
._match
_valid
_url
(url
).group('site', 'id')
640 webpage
= self
._download
_webpage
(url
, video_id
)
642 nbc_data
= self
._search
_json
(
643 r
'<script>var\s*nbc\s*=', webpage
, 'NBC JSON data', video_id
)
644 pdk_acct
= nbc_data
.get('pdkAcct') or 'Yh1nAC'
645 fw_ssid
= traverse_obj(nbc_data
, ('video', 'fwSSID'))
646 fw_network_id
= traverse_obj(nbc_data
, ('video', 'fwNetworkID'), default
='382114')
648 video_data
= self
._parse
_json
(self
._html
_search
_regex
(
649 r
'data-videos="([^"]*)"', webpage
, 'video data', default
='{}'), video_id
)
650 video_data
= variadic(video_data
)[0]
651 video_data
.update(self
._parse
_json
(self
._html
_search
_regex
(
652 r
'data-meta="([^"]*)"', webpage
, 'metadata', default
='{}'), video_id
))
656 if video_data
.get('mpx_is_livestream') == '1':
658 player_id
= traverse_obj(
659 video_data
, 'mpx_m3upid', ('video', 'meta', 'mpx_m3upid'), 'mpx_pid',
660 ('video', 'meta', 'mpx_pid'), 'pid_streaming_web_medium')
663 'assetTypes': 'LegacyRelease',
664 'fwsitesection': fw_ssid
,
665 'fwNetworkID': fw_network_id
,
666 'pprofile': 'ots_desktop_html',
667 'sensitive': 'false',
674 'formats': 'M3U+none,MPEG-DASH+none,MPEG4,MP3',
680 'title': f
'{channel} livestream',
685 player_id
= traverse_obj(
686 video_data
, ('video', 'meta', 'pid_streaming_web_high'), 'pid_streaming_web_high',
687 ('video', 'meta', 'mpx_pid'), 'mpx_pid')
689 date_string
= traverse_obj(video_data
, 'date_string', 'date_gmt')
691 date_string
= self
._search
_regex
(
692 r
'datetime="([^"]+)"', date_string
, 'date string', fatal
=False)
694 date_string
= traverse_obj(
695 nbc_data
, ('dataLayer', 'adobe', 'prop70'), ('dataLayer', 'adobe', 'eVar70'),
696 ('dataLayer', 'adobe', 'eVar59'))
698 video_url
= traverse_obj(video_data
, ('video', 'meta', 'mp4_url'), 'mp4_url')
700 height
= url_basename(video_url
).split('-')[1].split('p')[0]
704 'width': int_or_none(self
._RESOLUTIONS
.get(height
)),
705 'height': int_or_none(height
),
706 'format_id': f
'http-{height}',
711 'assetTypes': 'LegacyRelease',
712 'fwsitesection': fw_ssid
,
713 'fwNetworkID': fw_network_id
,
714 'format': 'redirect',
721 'title': video_data
.get('title') or traverse_obj(
722 nbc_data
, ('dataLayer', 'contenttitle'), ('dataLayer', 'title'),
723 ('dataLayer', 'adobe', 'prop22'), ('dataLayer', 'id')),
724 'description': traverse_obj(video_data
, 'summary', 'excerpt', 'video_hero_text'),
725 'upload_date': str_or_none(unified_strdate(date_string
)),
726 'timestamp': int_or_none(unified_timestamp(date_string
)),
730 raise ExtractorError(
731 'No video player ID or livestream player ID found in webpage', expected
=True)
733 headers
= {'Origin': f'https://www.{channel}
.com
'}
734 manifest, urlh = self._download_webpage_handle(
735 f'https
://link
.theplatform
.com
/s
/{pdk_acct}
/{player_id}
', video_id,
736 headers=headers, query=query, note='Downloading manifest
')
738 manifest_url = self._search_regex(r'<video src
="([^"]*)', manifest, 'manifest URL
')
740 manifest_url = urlh.geturl()
742 formats.extend(self._extract_m3u8_formats(
743 manifest_url, video_id, 'mp4
', headers=headers, m3u8_id='hls
',
744 fatal=live, live=live, errnote='No HLS formats found
'))
747 'id': str_or_none(video_id),
749 'uploader
': str_or_none(nbc_data.get('on_air_name
')),
750 'uploader_id
': str_or_none(nbc_data.get('callLetters
')),