_ Git - youtube-dl/blob - youtube_dl/extractor/cnbc.py

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