Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/inc.py

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