yt_dlp/extractor/cnbc.py

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