youtube_dl/extractor/thesun.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .ooyala import OoyalaIE
   7
   8
   9 class TheSunIE(InfoExtractor):
  10     _VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/[^/]+/(?P<id>\d+)'
  11     _TEST = {
  12         'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/',
  13         'info_dict': {
  14             'id': '2261604',
  15             'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf',
  16         },
  17         'playlist_count': 2,
  18     }
  19
  20     def _real_extract(self, url):
  21         article_id = self._match_id(url)
  22
  23         webpage = self._download_webpage(url, article_id)
  24
  25         entries = []
  26         for ooyala_id in re.findall(
  27                 r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)',
  28                 webpage):
  29             entries.append(OoyalaIE._build_url_result(ooyala_id))
  30
  31         return self.playlist_result(
  32             entries, article_id, self._og_search_title(webpage, fatal=False))