yt_dlp/extractor/localnews8.py

   1 from .common import InfoExtractor
   2
   3
   4 class LocalNews8IE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?localnews8\.com/(?:[^/]+/)*(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
   6     _TEST = {
   7         'url': 'http://www.localnews8.com/news/rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings/35183304',
   8         'md5': 'be4d48aea61aa2bde7be2ee47691ad20',
   9         'info_dict': {
  10             'id': '35183304',
  11             'display_id': 'rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings',
  12             'ext': 'mp4',
  13             'title': 'Rexburg business turns carbon fiber scraps into wedding ring',
  14             'description': 'The process was first invented by Lamborghini and less than a dozen companies around the world use it.',
  15             'duration': 153,
  16             'timestamp': 1441844822,
  17             'upload_date': '20150910',
  18             'uploader_id': 'api',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = self._match_valid_url(url)
  24         video_id = mobj.group('id')
  25         display_id = mobj.group('display_id')
  26
  27         webpage = self._download_webpage(url, display_id)
  28
  29         partner_id = self._search_regex(
  30             r'partnerId\s*[:=]\s*(["\'])(?P<id>\d+)\1',
  31             webpage, 'partner id', group='id')
  32         kaltura_id = self._search_regex(
  33             r'videoIdString\s*[:=]\s*(["\'])kaltura:(?P<id>[0-9a-z_]+)\1',
  34             webpage, 'videl id', group='id')
  35
  36         return {
  37             '_type': 'url_transparent',
  38             'url': 'kaltura:%s:%s' % (partner_id, kaltura_id),
  39             'ie_key': 'Kaltura',
  40             'id': video_id,
  41             'display_id': display_id,
  42         }