yt_dlp/extractor/cnbc.py

   1 from .common import InfoExtractor
   2 from ..utils import smuggle_url
   3
   4
   5 class CNBCIE(InfoExtractor):
   6     _VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
   7     _TEST = {
   8         'url': 'http://video.cnbc.com/gallery/?video=3000503714',
   9         'info_dict': {
  10             'id': '3000503714',
  11             'ext': 'mp4',
  12             'title': 'Fighting zombies is big business',
  13             'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e',
  14             'timestamp': 1459332000,
  15             'upload_date': '20160330',
  16             'uploader': 'NBCU-CNBC',
  17         },
  18         'params': {
  19             # m3u8 download
  20             'skip_download': True,
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         return {
  27             '_type': 'url_transparent',
  28             'ie_key': 'ThePlatform',
  29             'url': smuggle_url(
  30                 'http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id,
  31                 {'force_smil_url': True}),
  32             'id': video_id,
  33         }
  34
  35
  36 class CNBCVideoIE(InfoExtractor):
  37     _VALID_URL = r'https?://(?:www\.)?cnbc\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\.html)'
  38     _TEST = {
  39         'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
  40         'info_dict': {
  41             'id': '7000031301',
  42             'ext': 'mp4',
  43             'title': "Trump: I don't necessarily agree with raising rates",
  44             'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3',
  45             'timestamp': 1531958400,
  46             'upload_date': '20180719',
  47             'uploader': 'NBCU-CNBC',
  48         },
  49         'params': {
  50             'skip_download': True,
  51         },
  52     }
  53
  54     def _real_extract(self, url):
  55         path, display_id = self._match_valid_url(url).groups()
  56         video_id = self._download_json(
  57             'https://webql-redesign.cnbcfm.com/graphql', display_id, query={
  58                 'query': '''{
  59   page(path: "%s") {
  60     vcpsId
  61   }
  62 }''' % path,
  63             })['data']['page']['vcpsId']
  64         return self.url_result(
  65             'http://video.cnbc.com/gallery/?video=%d' % video_id,
  66             CNBCIE.ie_key())