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 ..utils import (
   8     find_xpath_attr,
   9     lowercase_escape,
  10     smuggle_url,
  11     unescapeHTML,
  12 )
  13
  14
  15 class NBCIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
  17
  18     _TESTS = [
  19         {
  20             'url': 'http://www.nbc.com/the-tonight-show/segments/112966',
  21             'info_dict': {
  22                 'id': '112966',
  23                 'ext': 'mp4',
  24                 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
  25                 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
  26                 'timestamp': 1424246400,
  27                 'upload_date': '20150218',
  28                 'uploader': 'NBCU-COM',
  29             },
  30             'params': {
  31                 # m3u8 download
  32                 'skip_download': True,
  33             },
  34         },
  35         {
  36             'url': 'http://www.nbc.com/the-tonight-show/episodes/176',
  37             'info_dict': {
  38                 'id': '176',
  39                 'ext': 'flv',
  40                 'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen',
  41                 'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.',
  42             },
  43             'skip': '404 Not Found',
  44         },
  45         {
  46             'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
  47             'info_dict': {
  48                 'id': '2832821',
  49                 'ext': 'mp4',
  50                 'title': 'Star Wars Teaser',
  51                 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
  52                 'timestamp': 1417852800,
  53                 'upload_date': '20141206',
  54                 'uploader': 'NBCU-COM',
  55             },
  56             'params': {
  57                 # m3u8 download
  58                 'skip_download': True,
  59             },
  60             'skip': 'Only works from US',
  61         },
  62         {
  63             # This video has expired but with an escaped embedURL
  64             'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
  65             'only_matching': True,
  66         },
  67         {
  68             # HLS streams requires the 'hdnea3' cookie
  69             'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
  70             'info_dict': {
  71                 'id': 'n1806',
  72                 'ext': 'mp4',
  73                 'title': 'Goliath',
  74                 '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.',
  75                 'timestamp': 1237100400,
  76                 'upload_date': '20090315',
  77                 'uploader': 'NBCU-COM',
  78             },
  79             'params': {
  80                 'skip_download': True,
  81             },
  82             'skip': 'Only works from US',
  83         }
  84     ]
  85
  86     def _real_extract(self, url):
  87         video_id = self._match_id(url)
  88         webpage = self._download_webpage(url, video_id)
  89         theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
  90             [
  91                 r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
  92                 r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
  93                 r'"embedURL"\s*:\s*"([^"]+)"'
  94             ],
  95             webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
  96         if theplatform_url.startswith('//'):
  97             theplatform_url = 'http:' + theplatform_url
  98         return {
  99             '_type': 'url_transparent',
 100             'ie_key': 'ThePlatform',
 101             'url': smuggle_url(theplatform_url, {'source_url': url}),
 102             'id': video_id,
 103         }
 104
 105
 106 class NBCSportsVPlayerIE(InfoExtractor):
 107     _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
 108
 109     _TESTS = [{
 110         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
 111         'info_dict': {
 112             'id': '9CsDKds0kvHI',
 113             'ext': 'flv',
 114             'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
 115             'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
 116             'timestamp': 1426270238,
 117             'upload_date': '20150313',
 118             'uploader': 'NBCU-SPORTS',
 119         }
 120     }, {
 121         'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
 122         'only_matching': True,
 123     }]
 124
 125     @staticmethod
 126     def _extract_url(webpage):
 127         iframe_m = re.search(
 128             r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
 129         if iframe_m:
 130             return iframe_m.group('url')
 131
 132     def _real_extract(self, url):
 133         video_id = self._match_id(url)
 134         webpage = self._download_webpage(url, video_id)
 135         theplatform_url = self._og_search_video_url(webpage)
 136         return self.url_result(theplatform_url, 'ThePlatform')
 137
 138
 139 class NBCSportsIE(InfoExtractor):
 140     # Does not include https because its certificate is invalid
 141     _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 142
 143     _TEST = {
 144         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
 145         'info_dict': {
 146             'id': 'PHJSaFWbrTY9',
 147             'ext': 'flv',
 148             'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
 149             'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
 150             'uploader': 'NBCU-SPORTS',
 151             'upload_date': '20150330',
 152             'timestamp': 1427726529,
 153         }
 154     }
 155
 156     def _real_extract(self, url):
 157         video_id = self._match_id(url)
 158         webpage = self._download_webpage(url, video_id)
 159         return self.url_result(
 160             NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
 161
 162
 163 class CSNNEIE(InfoExtractor):
 164     _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
 165
 166     _TEST = {
 167         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
 168         'info_dict': {
 169             'id': 'yvBLLUgQ8WU0',
 170             'ext': 'mp4',
 171             'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
 172             'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
 173             'timestamp': 1459369979,
 174             'upload_date': '20160330',
 175             'uploader': 'NBCU-SPORTS',
 176         }
 177     }
 178
 179     def _real_extract(self, url):
 180         display_id = self._match_id(url)
 181         webpage = self._download_webpage(url, display_id)
 182         return {
 183             '_type': 'url_transparent',
 184             'ie_key': 'ThePlatform',
 185             'url': self._html_search_meta('twitter:player:stream', webpage),
 186             'display_id': display_id,
 187         }
 188
 189
 190 class NBCNewsIE(ThePlatformIE):
 191     _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
 192         (?:video/.+?/(?P<id>\d+)|
 193         ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
 194         '''
 195
 196     _TESTS = [
 197         {
 198             'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
 199             'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
 200             'info_dict': {
 201                 'id': '52753292',
 202                 'ext': 'flv',
 203                 'title': 'Crew emerges after four-month Mars food study',
 204                 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
 205             },
 206         },
 207         {
 208             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
 209             'md5': 'af1adfa51312291a017720403826bb64',
 210             'info_dict': {
 211                 'id': '269389891880',
 212                 'ext': 'mp4',
 213                 'title': 'How Twitter Reacted To The Snowden Interview',
 214                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
 215                 'uploader': 'NBCU-NEWS',
 216                 'timestamp': 1401363060,
 217                 'upload_date': '20140529',
 218             },
 219         },
 220         {
 221             'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
 222             'md5': 'fdbf39ab73a72df5896b6234ff98518a',
 223             'info_dict': {
 224                 'id': '529953347624',
 225                 'ext': 'mp4',
 226                 'title': 'FULL EPISODE: Family Business',
 227                 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
 228             },
 229             'skip': 'This page is unavailable.',
 230         },
 231         {
 232             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
 233             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
 234             'info_dict': {
 235                 'id': '394064451844',
 236                 'ext': 'mp4',
 237                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
 238                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
 239                 'timestamp': 1423104900,
 240                 'uploader': 'NBCU-NEWS',
 241                 'upload_date': '20150205',
 242             },
 243         },
 244         {
 245             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
 246             'md5': 'a49e173825e5fcd15c13fc297fced39d',
 247             'info_dict': {
 248                 'id': '529953347624',
 249                 'ext': 'mp4',
 250                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
 251                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
 252                 'upload_date': '20150922',
 253                 'timestamp': 1442917800,
 254                 'uploader': 'NBCU-NEWS',
 255             },
 256         },
 257         {
 258             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
 259             'md5': '118d7ca3f0bea6534f119c68ef539f71',
 260             'info_dict': {
 261                 'id': '669831235788',
 262                 'ext': 'mp4',
 263                 'title': 'See the aurora borealis from space in stunning new NASA video',
 264                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
 265                 'upload_date': '20160420',
 266                 'timestamp': 1461152093,
 267                 'uploader': 'NBCU-NEWS',
 268             },
 269         },
 270         {
 271             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
 272             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
 273             'info_dict': {
 274                 'id': '314487875924',
 275                 'ext': 'mp4',
 276                 'title': 'The chaotic GOP immigration vote',
 277                 '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.',
 278                 'thumbnail': 're:^https?://.*\.jpg$',
 279                 'timestamp': 1406937606,
 280                 'upload_date': '20140802',
 281                 'uploader': 'NBCU-NEWS',
 282                 'categories': ['MSNBC/Topics/Franchise/Best of last night', 'MSNBC/Topics/General/Congress'],
 283             },
 284         },
 285         {
 286             'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
 287             'only_matching': True,
 288         },
 289         {
 290             # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
 291             'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
 292             'only_matching': True,
 293         },
 294     ]
 295
 296     def _real_extract(self, url):
 297         mobj = re.match(self._VALID_URL, url)
 298         video_id = mobj.group('id')
 299         if video_id is not None:
 300             all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
 301             info = all_info.find('video')
 302
 303             return {
 304                 'id': video_id,
 305                 'title': info.find('headline').text,
 306                 'ext': 'flv',
 307                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
 308                 'description': info.find('caption').text,
 309                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
 310             }
 311         else:
 312             # "feature" and "nightly-news" pages use theplatform.com
 313             video_id = mobj.group('mpx_id')
 314             if not video_id.isdigit():
 315                 webpage = self._download_webpage(url, video_id)
 316                 info = None
 317                 bootstrap_json = self._search_regex(
 318                     [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
 319                      r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"'],
 320                     webpage, 'bootstrap json', default=None)
 321                 bootstrap = self._parse_json(
 322                     bootstrap_json, video_id, transform_source=unescapeHTML)
 323                 if 'results' in bootstrap:
 324                     info = bootstrap['results'][0]['video']
 325                 elif 'video' in bootstrap:
 326                     info = bootstrap['video']
 327                 else:
 328                     info = bootstrap
 329                 video_id = info['mpxId']
 330
 331             return {
 332                 '_type': 'url_transparent',
 333                 'id': video_id,
 334                 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
 335                 'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byId=%s' % video_id,
 336                 'ie_key': 'ThePlatformFeed',
 337             }
 338
 339
 340 class NBCOlympicsIE(InfoExtractor):
 341     _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
 342
 343     _TEST = {
 344         # Geo-restricted to US
 345         'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 346         'md5': '54fecf846d05429fbaa18af557ee523a',
 347         'info_dict': {
 348             'id': 'WjTBzDXx5AUq',
 349             'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
 350             'ext': 'mp4',
 351             'title': 'Rose\'s son Leo was in tears after his dad won gold',
 352             'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
 353             'timestamp': 1471274964,
 354             'upload_date': '20160815',
 355             'uploader': 'NBCU-SPORTS',
 356         },
 357     }
 358
 359     def _real_extract(self, url):
 360         display_id = self._match_id(url)
 361
 362         webpage = self._download_webpage(url, display_id)
 363
 364         drupal_settings = self._parse_json(self._search_regex(
 365             r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
 366             webpage, 'drupal settings'), display_id)
 367
 368         iframe_url = drupal_settings['vod']['iframe_url']
 369         theplatform_url = iframe_url.replace(
 370             'vplayer.nbcolympics.com', 'player.theplatform.com')
 371
 372         return {
 373             '_type': 'url_transparent',
 374             'url': theplatform_url,
 375             'ie_key': ThePlatformIE.ie_key(),
 376             'display_id': display_id,
 377         }