_ Git - youtube-dl/blob - 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     smuggle_url,
  13     update_url_query,
  14     int_or_none,
  15 )
  16
  17
  18 class NBCIE(AdobePassIE):
  19     _VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
  20
  21     _TESTS = [
  22         {
  23             'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
  24             'info_dict': {
  25                 'id': '2848237',
  26                 'ext': 'mp4',
  27                 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
  28                 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
  29                 'timestamp': 1424246400,
  30                 'upload_date': '20150218',
  31                 'uploader': 'NBCU-COM',
  32             },
  33             'params': {
  34                 # m3u8 download
  35                 'skip_download': True,
  36             },
  37         },
  38         {
  39             'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
  40             'info_dict': {
  41                 'id': '2832821',
  42                 'ext': 'mp4',
  43                 'title': 'Star Wars Teaser',
  44                 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
  45                 'timestamp': 1417852800,
  46                 'upload_date': '20141206',
  47                 'uploader': 'NBCU-COM',
  48             },
  49             'params': {
  50                 # m3u8 download
  51                 'skip_download': True,
  52             },
  53             'skip': 'Only works from US',
  54         },
  55         {
  56             # HLS streams requires the 'hdnea3' cookie
  57             'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
  58             'info_dict': {
  59                 'id': '101528f5a9e8127b107e98c5e6ce4638',
  60                 'ext': 'mp4',
  61                 'title': 'Goliath',
  62                 '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.',
  63                 'timestamp': 1237100400,
  64                 'upload_date': '20090315',
  65                 'uploader': 'NBCU-COM',
  66             },
  67             'params': {
  68                 'skip_download': True,
  69             },
  70             'skip': 'Only works from US',
  71         },
  72         {
  73             'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
  74             'only_matching': True,
  75         },
  76         {
  77             # Percent escaped url
  78             'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
  79             'only_matching': True,
  80         }
  81     ]
  82
  83     def _real_extract(self, url):
  84         permalink, video_id = re.match(self._VALID_URL, url).groups()
  85         permalink = 'http' + compat_urllib_parse_unquote(permalink)
  86         response = self._download_json(
  87             'https://friendship.nbc.co/v2/graphql', video_id, query={
  88                 'query': '''{
  89   page(name: "%s", platform: web, type: VIDEO, userId: "0") {
  90     data {
  91       ... on VideoPageData {
  92         description
  93         episodeNumber
  94         keywords
  95         locked
  96         mpxAccountId
  97         mpxGuid
  98         rating
  99         seasonNumber
 100         secondaryTitle
 101         seriesShortTitle
 102       }
 103     }
 104   }
 105 }''' % permalink,
 106             })
 107         video_data = response['data']['page']['data']
 108         query = {
 109             'mbr': 'true',
 110             'manifest': 'm3u',
 111         }
 112         video_id = video_data['mpxGuid']
 113         title = video_data['secondaryTitle']
 114         if video_data.get('locked'):
 115             resource = self._get_mvpd_resource(
 116                 'nbcentertainment', title, video_id,
 117                 video_data.get('rating'))
 118             query['auth'] = self._extract_mvpd_auth(
 119                 url, video_id, 'nbcentertainment', resource)
 120         theplatform_url = smuggle_url(update_url_query(
 121             'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id),
 122             query), {'force_smil_url': True})
 123         return {
 124             '_type': 'url_transparent',
 125             'id': video_id,
 126             'title': title,
 127             'url': theplatform_url,
 128             'description': video_data.get('description'),
 129             'tags': video_data.get('keywords'),
 130             'season_number': int_or_none(video_data.get('seasonNumber')),
 131             'episode_number': int_or_none(video_data.get('episodeNumber')),
 132             'episode': title,
 133             'series': video_data.get('seriesShortTitle'),
 134             'ie_key': 'ThePlatform',
 135         }
 136
 137
 138 class NBCSportsVPlayerIE(InfoExtractor):
 139     _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
 140
 141     _TESTS = [{
 142         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
 143         'info_dict': {
 144             'id': '9CsDKds0kvHI',
 145             'ext': 'mp4',
 146             'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
 147             'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
 148             'timestamp': 1426270238,
 149             'upload_date': '20150313',
 150             'uploader': 'NBCU-SPORTS',
 151         }
 152     }, {
 153         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z',
 154         'only_matching': True,
 155     }]
 156
 157     @staticmethod
 158     def _extract_url(webpage):
 159         iframe_m = re.search(
 160             r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
 161         if iframe_m:
 162             return iframe_m.group('url')
 163
 164     def _real_extract(self, url):
 165         video_id = self._match_id(url)
 166         webpage = self._download_webpage(url, video_id)
 167         theplatform_url = self._og_search_video_url(webpage).replace(
 168             'vplayer.nbcsports.com', 'player.theplatform.com')
 169         return self.url_result(theplatform_url, 'ThePlatform')
 170
 171
 172 class NBCSportsIE(InfoExtractor):
 173     # Does not include https because its certificate is invalid
 174     _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 175
 176     _TEST = {
 177         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
 178         'info_dict': {
 179             'id': 'PHJSaFWbrTY9',
 180             'ext': 'flv',
 181             'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
 182             'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
 183             'uploader': 'NBCU-SPORTS',
 184             'upload_date': '20150330',
 185             'timestamp': 1427726529,
 186         }
 187     }
 188
 189     def _real_extract(self, url):
 190         video_id = self._match_id(url)
 191         webpage = self._download_webpage(url, video_id)
 192         return self.url_result(
 193             NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
 194
 195
 196 class NBCSportsStreamIE(AdobePassIE):
 197     _VALID_URL = r'https?://stream\.nbcsports\.com/.+?\bpid=(?P<id>\d+)'
 198     _TEST = {
 199         'url': 'http://stream.nbcsports.com/nbcsn/generic?pid=206559',
 200         'info_dict': {
 201             'id': '206559',
 202             'ext': 'mp4',
 203             'title': 'Amgen Tour of California Women\'s Recap',
 204             'description': 'md5:66520066b3b5281ada7698d0ea2aa894',
 205         },
 206         'params': {
 207             # m3u8 download
 208             'skip_download': True,
 209         },
 210         'skip': 'Requires Adobe Pass Authentication',
 211     }
 212
 213     def _real_extract(self, url):
 214         video_id = self._match_id(url)
 215         live_source = self._download_json(
 216             'http://stream.nbcsports.com/data/live_sources_%s.json' % video_id,
 217             video_id)
 218         video_source = live_source['videoSources'][0]
 219         title = video_source['title']
 220         source_url = None
 221         for k in ('source', 'msl4source', 'iossource', 'hlsv4'):
 222             sk = k + 'Url'
 223             source_url = video_source.get(sk) or video_source.get(sk + 'Alt')
 224             if source_url:
 225                 break
 226         else:
 227             source_url = video_source['ottStreamUrl']
 228         is_live = video_source.get('type') == 'live' or video_source.get('status') == 'Live'
 229         resource = self._get_mvpd_resource('nbcsports', title, video_id, '')
 230         token = self._extract_mvpd_auth(url, video_id, 'nbcsports', resource)
 231         tokenized_url = self._download_json(
 232             'https://token.playmakerservices.com/cdn',
 233             video_id, data=json.dumps({
 234                 'requestorId': 'nbcsports',
 235                 'pid': video_id,
 236                 'application': 'NBCSports',
 237                 'version': 'v1',
 238                 'platform': 'desktop',
 239                 'cdn': 'akamai',
 240                 'url': video_source['sourceUrl'],
 241                 'token': base64.b64encode(token.encode()).decode(),
 242                 'resourceId': base64.b64encode(resource.encode()).decode(),
 243             }).encode())['tokenizedUrl']
 244         formats = self._extract_m3u8_formats(tokenized_url, video_id, 'mp4')
 245         self._sort_formats(formats)
 246         return {
 247             'id': video_id,
 248             'title': self._live_title(title) if is_live else title,
 249             'description': live_source.get('description'),
 250             'formats': formats,
 251             'is_live': is_live,
 252         }
 253
 254
 255 class CSNNEIE(InfoExtractor):
 256     _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
 257
 258     _TEST = {
 259         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
 260         'info_dict': {
 261             'id': 'yvBLLUgQ8WU0',
 262             'ext': 'mp4',
 263             'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
 264             'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
 265             'timestamp': 1459369979,
 266             'upload_date': '20160330',
 267             'uploader': 'NBCU-SPORTS',
 268         }
 269     }
 270
 271     def _real_extract(self, url):
 272         display_id = self._match_id(url)
 273         webpage = self._download_webpage(url, display_id)
 274         return {
 275             '_type': 'url_transparent',
 276             'ie_key': 'ThePlatform',
 277             'url': self._html_search_meta('twitter:player:stream', webpage),
 278             'display_id': display_id,
 279         }
 280
 281
 282 class NBCNewsIE(ThePlatformIE):
 283     _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
 284
 285     _TESTS = [
 286         {
 287             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
 288             'md5': 'af1adfa51312291a017720403826bb64',
 289             'info_dict': {
 290                 'id': '269389891880',
 291                 'ext': 'mp4',
 292                 'title': 'How Twitter Reacted To The Snowden Interview',
 293                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
 294                 'uploader': 'NBCU-NEWS',
 295                 'timestamp': 1401363060,
 296                 'upload_date': '20140529',
 297             },
 298         },
 299         {
 300             'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
 301             'md5': 'fdbf39ab73a72df5896b6234ff98518a',
 302             'info_dict': {
 303                 'id': '529953347624',
 304                 'ext': 'mp4',
 305                 'title': 'FULL EPISODE: Family Business',
 306                 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
 307             },
 308             'skip': 'This page is unavailable.',
 309         },
 310         {
 311             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
 312             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
 313             'info_dict': {
 314                 'id': '394064451844',
 315                 'ext': 'mp4',
 316                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
 317                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
 318                 'timestamp': 1423104900,
 319                 'uploader': 'NBCU-NEWS',
 320                 'upload_date': '20150205',
 321             },
 322         },
 323         {
 324             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
 325             'md5': 'a49e173825e5fcd15c13fc297fced39d',
 326             'info_dict': {
 327                 'id': '529953347624',
 328                 'ext': 'mp4',
 329                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
 330                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
 331                 'upload_date': '20150922',
 332                 'timestamp': 1442917800,
 333                 'uploader': 'NBCU-NEWS',
 334             },
 335         },
 336         {
 337             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
 338             'md5': '118d7ca3f0bea6534f119c68ef539f71',
 339             'info_dict': {
 340                 'id': '669831235788',
 341                 'ext': 'mp4',
 342                 'title': 'See the aurora borealis from space in stunning new NASA video',
 343                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
 344                 'upload_date': '20160420',
 345                 'timestamp': 1461152093,
 346                 'uploader': 'NBCU-NEWS',
 347             },
 348         },
 349         {
 350             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
 351             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
 352             'info_dict': {
 353                 'id': '314487875924',
 354                 'ext': 'mp4',
 355                 'title': 'The chaotic GOP immigration vote',
 356                 '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.',
 357                 'thumbnail': r're:^https?://.*\.jpg$',
 358                 'timestamp': 1406937606,
 359                 'upload_date': '20140802',
 360                 'uploader': 'NBCU-NEWS',
 361             },
 362         },
 363         {
 364             'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
 365             'only_matching': True,
 366         },
 367         {
 368             # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
 369             'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
 370             'only_matching': True,
 371         },
 372     ]
 373
 374     def _real_extract(self, url):
 375         video_id = self._match_id(url)
 376         if not video_id.isdigit():
 377             webpage = self._download_webpage(url, video_id)
 378
 379             data = self._parse_json(self._search_regex(
 380                 r'window\.__data\s*=\s*({.+});', webpage,
 381                 'bootstrap json'), video_id)
 382             video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id']
 383
 384         return {
 385             '_type': 'url_transparent',
 386             'id': video_id,
 387             # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
 388             'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}),
 389             'ie_key': 'ThePlatformFeed',
 390         }
 391
 392
 393 class NBCOlympicsIE(InfoExtractor):
 394     IE_NAME = 'nbcolympics'
 395     _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
 396
 397     _TEST = {
 398         # Geo-restricted to US
 399         'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 400         'md5': '54fecf846d05429fbaa18af557ee523a',
 401         'info_dict': {
 402             'id': 'WjTBzDXx5AUq',
 403             'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 404             'ext': 'mp4',
 405             'title': 'Rose\'s son Leo was in tears after his dad won gold',
 406             'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
 407             'timestamp': 1471274964,
 408             'upload_date': '20160815',
 409             'uploader': 'NBCU-SPORTS',
 410         },
 411     }
 412
 413     def _real_extract(self, url):
 414         display_id = self._match_id(url)
 415
 416         webpage = self._download_webpage(url, display_id)
 417
 418         drupal_settings = self._parse_json(self._search_regex(
 419             r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
 420             webpage, 'drupal settings'), display_id)
 421
 422         iframe_url = drupal_settings['vod']['iframe_url']
 423         theplatform_url = iframe_url.replace(
 424             'vplayer.nbcolympics.com', 'player.theplatform.com')
 425
 426         return {
 427             '_type': 'url_transparent',
 428             'url': theplatform_url,
 429             'ie_key': ThePlatformIE.ie_key(),
 430             'display_id': display_id,
 431         }
 432
 433
 434 class NBCOlympicsStreamIE(AdobePassIE):
 435     IE_NAME = 'nbcolympics:stream'
 436     _VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
 437     _TEST = {
 438         'url': 'http://stream.nbcolympics.com/2018-winter-olympics-nbcsn-evening-feb-8',
 439         'info_dict': {
 440             'id': '203493',
 441             'ext': 'mp4',
 442             'title': 're:Curling, Alpine, Luge [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 443         },
 444         'params': {
 445             # m3u8 download
 446             'skip_download': True,
 447         },
 448     }
 449     _DATA_URL_TEMPLATE = 'http://stream.nbcolympics.com/data/%s_%s.json'
 450
 451     def _real_extract(self, url):
 452         display_id = self._match_id(url)
 453         webpage = self._download_webpage(url, display_id)
 454         pid = self._search_regex(r'pid\s*=\s*(\d+);', webpage, 'pid')
 455         resource = self._search_regex(
 456             r"resource\s*=\s*'(.+)';", webpage,
 457             'resource').replace("' + pid + '", pid)
 458         event_config = self._download_json(
 459             self._DATA_URL_TEMPLATE % ('event_config', pid),
 460             pid)['eventConfig']
 461         title = self._live_title(event_config['eventTitle'])
 462         source_url = self._download_json(
 463             self._DATA_URL_TEMPLATE % ('live_sources', pid),
 464             pid)['videoSources'][0]['sourceUrl']
 465         media_token = self._extract_mvpd_auth(
 466             url, pid, event_config.get('requestorId', 'NBCOlympics'), resource)
 467         formats = self._extract_m3u8_formats(self._download_webpage(
 468             'http://sp.auth.adobe.com/tvs/v1/sign', pid, query={
 469                 'cdn': 'akamai',
 470                 'mediaToken': base64.b64encode(media_token.encode()),
 471                 'resource': base64.b64encode(resource.encode()),
 472                 'url': source_url,
 473             }), pid, 'mp4')
 474         self._sort_formats(formats)
 475
 476         return {
 477             'id': pid,
 478             'display_id': display_id,
 479             'title': title,
 480             'formats': formats,
 481             'is_live': True,
 482         }