Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nbc.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .theplatform import ThePlatformIE
   7 from .adobepass import AdobePassIE
   8 from ..compat import compat_urllib_parse_urlparse
   9 from ..utils import (
  10     find_xpath_attr,
  11     lowercase_escape,
  12     smuggle_url,
  13     unescapeHTML,
  14     update_url_query,
  15     int_or_none,
  16 )
  17
  18
  19 class NBCIE(AdobePassIE):
  20     _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?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/the-tonight-show/episodes/176',
  41             'info_dict': {
  42                 'id': '176',
  43                 'ext': 'flv',
  44                 'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen',
  45                 'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.',
  46             },
  47             'skip': '404 Not Found',
  48         },
  49         {
  50             'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
  51             'info_dict': {
  52                 'id': '2832821',
  53                 'ext': 'mp4',
  54                 'title': 'Star Wars Teaser',
  55                 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
  56                 'timestamp': 1417852800,
  57                 'upload_date': '20141206',
  58                 'uploader': 'NBCU-COM',
  59             },
  60             'params': {
  61                 # m3u8 download
  62                 'skip_download': True,
  63             },
  64             'skip': 'Only works from US',
  65         },
  66         {
  67             # This video has expired but with an escaped embedURL
  68             'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
  69             'only_matching': True,
  70         },
  71         {
  72             # HLS streams requires the 'hdnea3' cookie
  73             'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
  74             'info_dict': {
  75                 'id': '101528f5a9e8127b107e98c5e6ce4638',
  76                 'ext': 'mp4',
  77                 'title': 'Goliath',
  78                 '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.',
  79                 'timestamp': 1237100400,
  80                 'upload_date': '20090315',
  81                 'uploader': 'NBCU-COM',
  82             },
  83             'params': {
  84                 'skip_download': True,
  85             },
  86             'skip': 'Only works from US',
  87         }
  88     ]
  89
  90     def _real_extract(self, url):
  91         video_id = self._match_id(url)
  92         webpage = self._download_webpage(url, video_id)
  93         info = {
  94             '_type': 'url_transparent',
  95             'ie_key': 'ThePlatform',
  96             'id': video_id,
  97         }
  98         video_data = None
  99         preload = self._search_regex(
 100             r'PRELOAD\s*=\s*({.+})', webpage, 'preload data', default=None)
 101         if preload:
 102             preload_data = self._parse_json(preload, video_id)
 103             path = compat_urllib_parse_urlparse(url).path.rstrip('/')
 104             entity_id = preload_data.get('xref', {}).get(path)
 105             video_data = preload_data.get('entities', {}).get(entity_id)
 106         if video_data:
 107             query = {
 108                 'mbr': 'true',
 109                 'manifest': 'm3u',
 110             }
 111             video_id = video_data['guid']
 112             title = video_data['title']
 113             if video_data.get('entitlement') == 'auth':
 114                 resource = self._get_mvpd_resource(
 115                     'nbcentertainment', title, video_id,
 116                     video_data.get('vChipRating'))
 117                 query['auth'] = self._extract_mvpd_auth(
 118                     url, video_id, 'nbcentertainment', resource)
 119             theplatform_url = smuggle_url(update_url_query(
 120                 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
 121                 query), {'force_smil_url': True})
 122             info.update({
 123                 'id': video_id,
 124                 'title': title,
 125                 'url': theplatform_url,
 126                 'description': video_data.get('description'),
 127                 'keywords': video_data.get('keywords'),
 128                 'season_number': int_or_none(video_data.get('seasonNumber')),
 129                 'episode_number': int_or_none(video_data.get('episodeNumber')),
 130                 'series': video_data.get('showName'),
 131             })
 132         else:
 133             theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
 134                 [
 135                     r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
 136                     r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
 137                     r'"embedURL"\s*:\s*"([^"]+)"'
 138                 ],
 139                 webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
 140             if theplatform_url.startswith('//'):
 141                 theplatform_url = 'http:' + theplatform_url
 142             info['url'] = smuggle_url(theplatform_url, {'source_url': url})
 143         return info
 144
 145
 146 class NBCSportsVPlayerIE(InfoExtractor):
 147     _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
 148
 149     _TESTS = [{
 150         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
 151         'info_dict': {
 152             'id': '9CsDKds0kvHI',
 153             'ext': 'flv',
 154             'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
 155             'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
 156             'timestamp': 1426270238,
 157             'upload_date': '20150313',
 158             'uploader': 'NBCU-SPORTS',
 159         }
 160     }, {
 161         'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
 162         'only_matching': True,
 163     }]
 164
 165     @staticmethod
 166     def _extract_url(webpage):
 167         iframe_m = re.search(
 168             r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
 169         if iframe_m:
 170             return iframe_m.group('url')
 171
 172     def _real_extract(self, url):
 173         video_id = self._match_id(url)
 174         webpage = self._download_webpage(url, video_id)
 175         theplatform_url = self._og_search_video_url(webpage)
 176         return self.url_result(theplatform_url, 'ThePlatform')
 177
 178
 179 class NBCSportsIE(InfoExtractor):
 180     # Does not include https because its certificate is invalid
 181     _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 182
 183     _TEST = {
 184         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
 185         'info_dict': {
 186             'id': 'PHJSaFWbrTY9',
 187             'ext': 'flv',
 188             'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
 189             'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
 190             'uploader': 'NBCU-SPORTS',
 191             'upload_date': '20150330',
 192             'timestamp': 1427726529,
 193         }
 194     }
 195
 196     def _real_extract(self, url):
 197         video_id = self._match_id(url)
 198         webpage = self._download_webpage(url, video_id)
 199         return self.url_result(
 200             NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
 201
 202
 203 class CSNNEIE(InfoExtractor):
 204     _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
 205
 206     _TEST = {
 207         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
 208         'info_dict': {
 209             'id': 'yvBLLUgQ8WU0',
 210             'ext': 'mp4',
 211             'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
 212             'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
 213             'timestamp': 1459369979,
 214             'upload_date': '20160330',
 215             'uploader': 'NBCU-SPORTS',
 216         }
 217     }
 218
 219     def _real_extract(self, url):
 220         display_id = self._match_id(url)
 221         webpage = self._download_webpage(url, display_id)
 222         return {
 223             '_type': 'url_transparent',
 224             'ie_key': 'ThePlatform',
 225             'url': self._html_search_meta('twitter:player:stream', webpage),
 226             'display_id': display_id,
 227         }
 228
 229
 230 class NBCNewsIE(ThePlatformIE):
 231     _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
 232         (?:video/.+?/(?P<id>\d+)|
 233         ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
 234         '''
 235
 236     _TESTS = [
 237         {
 238             'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
 239             'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
 240             'info_dict': {
 241                 'id': '52753292',
 242                 'ext': 'flv',
 243                 'title': 'Crew emerges after four-month Mars food study',
 244                 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
 245             },
 246         },
 247         {
 248             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
 249             'md5': 'af1adfa51312291a017720403826bb64',
 250             'info_dict': {
 251                 'id': 'p_tweet_snow_140529',
 252                 'ext': 'mp4',
 253                 'title': 'How Twitter Reacted To The Snowden Interview',
 254                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
 255                 'uploader': 'NBCU-NEWS',
 256                 'timestamp': 1401363060,
 257                 'upload_date': '20140529',
 258             },
 259         },
 260         {
 261             'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
 262             'md5': 'fdbf39ab73a72df5896b6234ff98518a',
 263             'info_dict': {
 264                 'id': '529953347624',
 265                 'ext': 'mp4',
 266                 'title': 'FULL EPISODE: Family Business',
 267                 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
 268             },
 269             'skip': 'This page is unavailable.',
 270         },
 271         {
 272             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
 273             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
 274             'info_dict': {
 275                 'id': 'nn_netcast_150204',
 276                 'ext': 'mp4',
 277                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
 278                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
 279                 'timestamp': 1423104900,
 280                 'uploader': 'NBCU-NEWS',
 281                 'upload_date': '20150205',
 282             },
 283         },
 284         {
 285             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
 286             'md5': 'a49e173825e5fcd15c13fc297fced39d',
 287             'info_dict': {
 288                 'id': 'x_lon_vwhorn_150922',
 289                 'ext': 'mp4',
 290                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
 291                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
 292                 'upload_date': '20150922',
 293                 'timestamp': 1442917800,
 294                 'uploader': 'NBCU-NEWS',
 295             },
 296         },
 297         {
 298             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
 299             'md5': '118d7ca3f0bea6534f119c68ef539f71',
 300             'info_dict': {
 301                 'id': 'tdy_al_space_160420',
 302                 'ext': 'mp4',
 303                 'title': 'See the aurora borealis from space in stunning new NASA video',
 304                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
 305                 'upload_date': '20160420',
 306                 'timestamp': 1461152093,
 307                 'uploader': 'NBCU-NEWS',
 308             },
 309         },
 310         {
 311             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
 312             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
 313             'info_dict': {
 314                 'id': 'n_hayes_Aimm_140801_272214',
 315                 'ext': 'mp4',
 316                 'title': 'The chaotic GOP immigration vote',
 317                 '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.',
 318                 'thumbnail': r're:^https?://.*\.jpg$',
 319                 'timestamp': 1406937606,
 320                 'upload_date': '20140802',
 321                 'uploader': 'NBCU-NEWS',
 322             },
 323         },
 324         {
 325             'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
 326             'only_matching': True,
 327         },
 328         {
 329             # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
 330             'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
 331             'only_matching': True,
 332         },
 333     ]
 334
 335     def _real_extract(self, url):
 336         mobj = re.match(self._VALID_URL, url)
 337         video_id = mobj.group('id')
 338         if video_id is not None:
 339             all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
 340             info = all_info.find('video')
 341
 342             return {
 343                 'id': video_id,
 344                 'title': info.find('headline').text,
 345                 'ext': 'flv',
 346                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
 347                 'description': info.find('caption').text,
 348                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
 349             }
 350         else:
 351             # "feature" and "nightly-news" pages use theplatform.com
 352             video_id = mobj.group('mpx_id')
 353             webpage = self._download_webpage(url, video_id)
 354
 355             filter_param = 'byId'
 356             bootstrap_json = self._search_regex(
 357                 [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
 358                  r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
 359                  r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
 360                 webpage, 'bootstrap json', default=None)
 361             if bootstrap_json:
 362                 bootstrap = self._parse_json(
 363                     bootstrap_json, video_id, transform_source=unescapeHTML)
 364
 365                 info = None
 366                 if 'results' in bootstrap:
 367                     info = bootstrap['results'][0]['video']
 368                 elif 'video' in bootstrap:
 369                     info = bootstrap['video']
 370                 elif 'msnbcVideoInfo' in bootstrap:
 371                     info = bootstrap['msnbcVideoInfo']['meta']
 372                 elif 'msnbcThePlatform' in bootstrap:
 373                     info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
 374                 else:
 375                     info = bootstrap
 376
 377                 if 'guid' in info:
 378                     video_id = info['guid']
 379                     filter_param = 'byGuid'
 380                 elif 'mpxId' in info:
 381                     video_id = info['mpxId']
 382
 383             return {
 384                 '_type': 'url_transparent',
 385                 'id': video_id,
 386                 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
 387                 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
 388                 'ie_key': 'ThePlatformFeed',
 389             }
 390
 391
 392 class NBCOlympicsIE(InfoExtractor):
 393     _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
 394
 395     _TEST = {
 396         # Geo-restricted to US
 397         'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 398         'md5': '54fecf846d05429fbaa18af557ee523a',
 399         'info_dict': {
 400             'id': 'WjTBzDXx5AUq',
 401             'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 402             'ext': 'mp4',
 403             'title': 'Rose\'s son Leo was in tears after his dad won gold',
 404             'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
 405             'timestamp': 1471274964,
 406             'upload_date': '20160815',
 407             'uploader': 'NBCU-SPORTS',
 408         },
 409     }
 410
 411     def _real_extract(self, url):
 412         display_id = self._match_id(url)
 413
 414         webpage = self._download_webpage(url, display_id)
 415
 416         drupal_settings = self._parse_json(self._search_regex(
 417             r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
 418             webpage, 'drupal settings'), display_id)
 419
 420         iframe_url = drupal_settings['vod']['iframe_url']
 421         theplatform_url = iframe_url.replace(
 422             'vplayer.nbcolympics.com', 'player.theplatform.com')
 423
 424         return {
 425             '_type': 'url_transparent',
 426             'url': theplatform_url,
 427             'ie_key': ThePlatformIE.ie_key(),
 428             'display_id': display_id,
 429         }