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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class IncIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?inc\.com(?:/[\w-]+)+/(?P<id>[\w-]+)(?:\.html)?'
   8     _TESTS = [{
   9         'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html',
  10         'md5': '7416739c9c16438c09fa35619d6ba5cb',
  11         'info_dict': {
  12             'id': '1_wqig47aq',
  13             'ext': 'mov',
  14             'title': 'Bill Gates Says These 5 Books Will Make You Smarter',
  15             'description': 'md5:bea7ff6cce100886fc1995acb743237e',
  16             'timestamp': 1474414430,
  17             'upload_date': '20160920',
  18             'uploader_id': 'video@inc.com',
  19         },
  20     }, {
  21         'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
  22         'only_matching': True,
  23     }]
  24
  25     def _real_extract(self, url):
  26         display_id = self._match_id(url)
  27         webpage = self._download_webpage(url, display_id)
  28
  29         partner_id = self._search_regex(
  30             r'var\s+_bizo_data_partner_id\s*=\s*"(\d+)";',
  31             webpage,
  32             'partner id')
  33
  34         kaltura_id = self._parse_json(self._search_regex(
  35             r'pageInfo\.videos\s*=\s*\[(.+)\];',
  36             webpage,
  37             'kaltura id'),
  38             display_id)['vid_kaltura_id']
  39
  40         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')