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