Raphaël G. Git Repositories - youtubedl/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 ..utils import (
  11     find_xpath_attr,
  12     smuggle_url,
  13     try_get,
  14     unescapeHTML,
  15     update_url_query,
  16     int_or_none,
  17 )
  18
  19
  20 class NBCIE(AdobePassIE):
  21     _VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
  22
  23     _TESTS = [
  24         {
  25             'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
  26             'info_dict': {
  27                 'id': '2848237',
  28                 'ext': 'mp4',
  29                 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
  30                 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
  31                 'timestamp': 1424246400,
  32                 'upload_date': '20150218',
  33                 'uploader': 'NBCU-COM',
  34             },
  35             'params': {
  36                 # m3u8 download
  37                 'skip_download': True,
  38             },
  39         },
  40         {
  41             'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
  42             'info_dict': {
  43                 'id': '2832821',
  44                 'ext': 'mp4',
  45                 'title': 'Star Wars Teaser',
  46                 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
  47                 'timestamp': 1417852800,
  48                 'upload_date': '20141206',
  49                 'uploader': 'NBCU-COM',
  50             },
  51             'params': {
  52                 # m3u8 download
  53                 'skip_download': True,
  54             },
  55             'skip': 'Only works from US',
  56         },
  57         {
  58             # HLS streams requires the 'hdnea3' cookie
  59             'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
  60             'info_dict': {
  61                 'id': '101528f5a9e8127b107e98c5e6ce4638',
  62                 'ext': 'mp4',
  63                 'title': 'Goliath',
  64                 '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.',
  65                 'timestamp': 1237100400,
  66                 'upload_date': '20090315',
  67                 'uploader': 'NBCU-COM',
  68             },
  69             'params': {
  70                 'skip_download': True,
  71             },
  72             'skip': 'Only works from US',
  73         },
  74         {
  75             'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
  76             'only_matching': True,
  77         },
  78     ]
  79
  80     def _real_extract(self, url):
  81         permalink, video_id = re.match(self._VALID_URL, url).groups()
  82         permalink = 'http' + permalink
  83         response = self._download_json(
  84             'https://api.nbc.com/v3/videos', video_id, query={
  85                 'filter[permalink]': permalink,
  86                 'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating',
  87                 'fields[shows]': 'shortTitle',
  88                 'include': 'show.shortTitle',
  89             })
  90         video_data = response['data'][0]['attributes']
  91         query = {
  92             'mbr': 'true',
  93             'manifest': 'm3u',
  94         }
  95         video_id = video_data['guid']
  96         title = video_data['title']
  97         if video_data.get('entitlement') == 'auth':
  98             resource = self._get_mvpd_resource(
  99                 'nbcentertainment', title, video_id,
 100                 video_data.get('vChipRating'))
 101             query['auth'] = self._extract_mvpd_auth(
 102                 url, video_id, 'nbcentertainment', resource)
 103         theplatform_url = smuggle_url(update_url_query(
 104             'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
 105             query), {'force_smil_url': True})
 106         return {
 107             '_type': 'url_transparent',
 108             'id': video_id,
 109             'title': title,
 110             'url': theplatform_url,
 111             'description': video_data.get('description'),
 112             'tags': video_data.get('keywords'),
 113             'season_number': int_or_none(video_data.get('seasonNumber')),
 114             'episode_number': int_or_none(video_data.get('episodeNumber')),
 115             'episode': title,
 116             'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']),
 117             'ie_key': 'ThePlatform',
 118         }
 119
 120
 121 class NBCSportsVPlayerIE(InfoExtractor):
 122     _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
 123
 124     _TESTS = [{
 125         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
 126         'info_dict': {
 127             'id': '9CsDKds0kvHI',
 128             'ext': 'mp4',
 129             'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
 130             'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
 131             'timestamp': 1426270238,
 132             'upload_date': '20150313',
 133             'uploader': 'NBCU-SPORTS',
 134         }
 135     }, {
 136         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z',
 137         'only_matching': True,
 138     }]
 139
 140     @staticmethod
 141     def _extract_url(webpage):
 142         iframe_m = re.search(
 143             r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
 144         if iframe_m:
 145             return iframe_m.group('url')
 146
 147     def _real_extract(self, url):
 148         video_id = self._match_id(url)
 149         webpage = self._download_webpage(url, video_id)
 150         theplatform_url = self._og_search_video_url(webpage).replace(
 151             'vplayer.nbcsports.com', 'player.theplatform.com')
 152         return self.url_result(theplatform_url, 'ThePlatform')
 153
 154
 155 class NBCSportsIE(InfoExtractor):
 156     # Does not include https because its certificate is invalid
 157     _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 158
 159     _TEST = {
 160         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
 161         'info_dict': {
 162             'id': 'PHJSaFWbrTY9',
 163             'ext': 'flv',
 164             'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
 165             'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
 166             'uploader': 'NBCU-SPORTS',
 167             'upload_date': '20150330',
 168             'timestamp': 1427726529,
 169         }
 170     }
 171
 172     def _real_extract(self, url):
 173         video_id = self._match_id(url)
 174         webpage = self._download_webpage(url, video_id)
 175         return self.url_result(
 176             NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
 177
 178
 179 class NBCSportsStreamIE(AdobePassIE):
 180     _VALID_URL = r'https?://stream\.nbcsports\.com/.+?\bpid=(?P<id>\d+)'
 181     _TEST = {
 182         'url': 'http://stream.nbcsports.com/nbcsn/generic?pid=206559',
 183         'info_dict': {
 184             'id': '206559',
 185             'ext': 'mp4',
 186             'title': 'Amgen Tour of California Women\'s Recap',
 187             'description': 'md5:66520066b3b5281ada7698d0ea2aa894',
 188         },
 189         'params': {
 190             # m3u8 download
 191             'skip_download': True,
 192         },
 193         'skip': 'Requires Adobe Pass Authentication',
 194     }
 195
 196     def _real_extract(self, url):
 197         video_id = self._match_id(url)
 198         live_source = self._download_json(
 199             'http://stream.nbcsports.com/data/live_sources_%s.json' % video_id,
 200             video_id)
 201         video_source = live_source['videoSources'][0]
 202         title = video_source['title']
 203         source_url = None
 204         for k in ('source', 'msl4source', 'iossource', 'hlsv4'):
 205             sk = k + 'Url'
 206             source_url = video_source.get(sk) or video_source.get(sk + 'Alt')
 207             if source_url:
 208                 break
 209         else:
 210             source_url = video_source['ottStreamUrl']
 211         is_live = video_source.get('type') == 'live' or video_source.get('status') == 'Live'
 212         resource = self._get_mvpd_resource('nbcsports', title, video_id, '')
 213         token = self._extract_mvpd_auth(url, video_id, 'nbcsports', resource)
 214         tokenized_url = self._download_json(
 215             'https://token.playmakerservices.com/cdn',
 216             video_id, data=json.dumps({
 217                 'requestorId': 'nbcsports',
 218                 'pid': video_id,
 219                 'application': 'NBCSports',
 220                 'version': 'v1',
 221                 'platform': 'desktop',
 222                 'cdn': 'akamai',
 223                 'url': video_source['sourceUrl'],
 224                 'token': base64.b64encode(token.encode()).decode(),
 225                 'resourceId': base64.b64encode(resource.encode()).decode(),
 226             }).encode())['tokenizedUrl']
 227         formats = self._extract_m3u8_formats(tokenized_url, video_id, 'mp4')
 228         self._sort_formats(formats)
 229         return {
 230             'id': video_id,
 231             'title': self._live_title(title) if is_live else title,
 232             'description': live_source.get('description'),
 233             'formats': formats,
 234             'is_live': is_live,
 235         }
 236
 237
 238 class CSNNEIE(InfoExtractor):
 239     _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
 240
 241     _TEST = {
 242         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
 243         'info_dict': {
 244             'id': 'yvBLLUgQ8WU0',
 245             'ext': 'mp4',
 246             'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
 247             'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
 248             'timestamp': 1459369979,
 249             'upload_date': '20160330',
 250             'uploader': 'NBCU-SPORTS',
 251         }
 252     }
 253
 254     def _real_extract(self, url):
 255         display_id = self._match_id(url)
 256         webpage = self._download_webpage(url, display_id)
 257         return {
 258             '_type': 'url_transparent',
 259             'ie_key': 'ThePlatform',
 260             'url': self._html_search_meta('twitter:player:stream', webpage),
 261             'display_id': display_id,
 262         }
 263
 264
 265 class NBCNewsIE(ThePlatformIE):
 266     _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
 267         (?:video/.+?/(?P<id>\d+)|
 268         ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
 269         '''
 270
 271     _TESTS = [
 272         {
 273             'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
 274             'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
 275             'info_dict': {
 276                 'id': '52753292',
 277                 'ext': 'flv',
 278                 'title': 'Crew emerges after four-month Mars food study',
 279                 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
 280             },
 281         },
 282         {
 283             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
 284             'md5': 'af1adfa51312291a017720403826bb64',
 285             'info_dict': {
 286                 'id': 'p_tweet_snow_140529',
 287                 'ext': 'mp4',
 288                 'title': 'How Twitter Reacted To The Snowden Interview',
 289                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
 290                 'uploader': 'NBCU-NEWS',
 291                 'timestamp': 1401363060,
 292                 'upload_date': '20140529',
 293             },
 294         },
 295         {
 296             'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
 297             'md5': 'fdbf39ab73a72df5896b6234ff98518a',
 298             'info_dict': {
 299                 'id': '529953347624',
 300                 'ext': 'mp4',
 301                 'title': 'FULL EPISODE: Family Business',
 302                 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
 303             },
 304             'skip': 'This page is unavailable.',
 305         },
 306         {
 307             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
 308             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
 309             'info_dict': {
 310                 'id': 'nn_netcast_150204',
 311                 'ext': 'mp4',
 312                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
 313                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
 314                 'timestamp': 1423104900,
 315                 'uploader': 'NBCU-NEWS',
 316                 'upload_date': '20150205',
 317             },
 318         },
 319         {
 320             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
 321             'md5': 'a49e173825e5fcd15c13fc297fced39d',
 322             'info_dict': {
 323                 'id': 'x_lon_vwhorn_150922',
 324                 'ext': 'mp4',
 325                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
 326                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
 327                 'upload_date': '20150922',
 328                 'timestamp': 1442917800,
 329                 'uploader': 'NBCU-NEWS',
 330             },
 331         },
 332         {
 333             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
 334             'md5': '118d7ca3f0bea6534f119c68ef539f71',
 335             'info_dict': {
 336                 'id': 'tdy_al_space_160420',
 337                 'ext': 'mp4',
 338                 'title': 'See the aurora borealis from space in stunning new NASA video',
 339                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
 340                 'upload_date': '20160420',
 341                 'timestamp': 1461152093,
 342                 'uploader': 'NBCU-NEWS',
 343             },
 344         },
 345         {
 346             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
 347             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
 348             'info_dict': {
 349                 'id': 'n_hayes_Aimm_140801_272214',
 350                 'ext': 'mp4',
 351                 'title': 'The chaotic GOP immigration vote',
 352                 '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.',
 353                 'thumbnail': r're:^https?://.*\.jpg$',
 354                 'timestamp': 1406937606,
 355                 'upload_date': '20140802',
 356                 'uploader': 'NBCU-NEWS',
 357             },
 358         },
 359         {
 360             'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
 361             'only_matching': True,
 362         },
 363         {
 364             # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
 365             'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
 366             'only_matching': True,
 367         },
 368     ]
 369
 370     def _real_extract(self, url):
 371         mobj = re.match(self._VALID_URL, url)
 372         video_id = mobj.group('id')
 373         if video_id is not None:
 374             all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
 375             info = all_info.find('video')
 376
 377             return {
 378                 'id': video_id,
 379                 'title': info.find('headline').text,
 380                 'ext': 'flv',
 381                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
 382                 'description': info.find('caption').text,
 383                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
 384             }
 385         else:
 386             # "feature" and "nightly-news" pages use theplatform.com
 387             video_id = mobj.group('mpx_id')
 388             webpage = self._download_webpage(url, video_id)
 389
 390             filter_param = 'byId'
 391             bootstrap_json = self._search_regex(
 392                 [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
 393                  r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
 394                  r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
 395                 webpage, 'bootstrap json', default=None)
 396             if bootstrap_json:
 397                 bootstrap = self._parse_json(
 398                     bootstrap_json, video_id, transform_source=unescapeHTML)
 399
 400                 info = None
 401                 if 'results' in bootstrap:
 402                     info = bootstrap['results'][0]['video']
 403                 elif 'video' in bootstrap:
 404                     info = bootstrap['video']
 405                 elif 'msnbcVideoInfo' in bootstrap:
 406                     info = bootstrap['msnbcVideoInfo']['meta']
 407                 elif 'msnbcThePlatform' in bootstrap:
 408                     info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
 409                 else:
 410                     info = bootstrap
 411
 412                 if 'guid' in info:
 413                     video_id = info['guid']
 414                     filter_param = 'byGuid'
 415                 elif 'mpxId' in info:
 416                     video_id = info['mpxId']
 417
 418             return {
 419                 '_type': 'url_transparent',
 420                 'id': video_id,
 421                 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
 422                 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
 423                 'ie_key': 'ThePlatformFeed',
 424             }
 425
 426
 427 class NBCOlympicsIE(InfoExtractor):
 428     IE_NAME = 'nbcolympics'
 429     _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
 430
 431     _TEST = {
 432         # Geo-restricted to US
 433         'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 434         'md5': '54fecf846d05429fbaa18af557ee523a',
 435         'info_dict': {
 436             'id': 'WjTBzDXx5AUq',
 437             'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 438             'ext': 'mp4',
 439             'title': 'Rose\'s son Leo was in tears after his dad won gold',
 440             'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
 441             'timestamp': 1471274964,
 442             'upload_date': '20160815',
 443             'uploader': 'NBCU-SPORTS',
 444         },
 445     }
 446
 447     def _real_extract(self, url):
 448         display_id = self._match_id(url)
 449
 450         webpage = self._download_webpage(url, display_id)
 451
 452         drupal_settings = self._parse_json(self._search_regex(
 453             r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
 454             webpage, 'drupal settings'), display_id)
 455
 456         iframe_url = drupal_settings['vod']['iframe_url']
 457         theplatform_url = iframe_url.replace(
 458             'vplayer.nbcolympics.com', 'player.theplatform.com')
 459
 460         return {
 461             '_type': 'url_transparent',
 462             'url': theplatform_url,
 463             'ie_key': ThePlatformIE.ie_key(),
 464             'display_id': display_id,
 465         }
 466
 467
 468 class NBCOlympicsStreamIE(AdobePassIE):
 469     IE_NAME = 'nbcolympics:stream'
 470     _VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
 471     _TEST = {
 472         'url': 'http://stream.nbcolympics.com/2018-winter-olympics-nbcsn-evening-feb-8',
 473         'info_dict': {
 474             'id': '203493',
 475             'ext': 'mp4',
 476             'title': 're:Curling, Alpine, Luge [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 477         },
 478         'params': {
 479             # m3u8 download
 480             'skip_download': True,
 481         },
 482     }
 483     _DATA_URL_TEMPLATE = 'http://stream.nbcolympics.com/data/%s_%s.json'
 484
 485     def _real_extract(self, url):
 486         display_id = self._match_id(url)
 487         webpage = self._download_webpage(url, display_id)
 488         pid = self._search_regex(r'pid\s*=\s*(\d+);', webpage, 'pid')
 489         resource = self._search_regex(
 490             r"resource\s*=\s*'(.+)';", webpage,
 491             'resource').replace("' + pid + '", pid)
 492         event_config = self._download_json(
 493             self._DATA_URL_TEMPLATE % ('event_config', pid),
 494             pid)['eventConfig']
 495         title = self._live_title(event_config['eventTitle'])
 496         source_url = self._download_json(
 497             self._DATA_URL_TEMPLATE % ('live_sources', pid),
 498             pid)['videoSources'][0]['sourceUrl']
 499         media_token = self._extract_mvpd_auth(
 500             url, pid, event_config.get('requestorId', 'NBCOlympics'), resource)
 501         formats = self._extract_m3u8_formats(self._download_webpage(
 502             'http://sp.auth.adobe.com/tvs/v1/sign', pid, query={
 503                 'cdn': 'akamai',
 504                 'mediaToken': base64.b64encode(media_token.encode()),
 505                 'resource': base64.b64encode(resource.encode()),
 506                 'url': source_url,
 507             }), pid, 'mp4')
 508         self._sort_formats(formats)
 509
 510         return {
 511             'id': pid,
 512             'display_id': display_id,
 513             'title': title,
 514             'formats': formats,
 515             'is_live': True,
 516         }