_ Git - youtube-dl/blob - youtube_dl/extractor/nbc.py

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