yt_dlp/extractor/thesun.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import extract_attributes
   5
   6
   7 class TheSunIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?the-?sun(\.co\.uk|\.com)/[^/]+/(?P<id>\d+)'
   9     _TESTS = [{
  10         'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/',
  11         'info_dict': {
  12             'id': '2261604',
  13             'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf',
  14         },
  15         'playlist_count': 2,
  16     }, {
  17         'url': 'https://www.the-sun.com/entertainment/7611415/1000lb-sisters-fans-rip-amy-dangerous-health-decision/',
  18         'info_dict': {
  19             'id': '7611415',
  20             'title': 'md5:e0b9b976f79dc770e5c80f22f40bb844',
  21         },
  22         'playlist_count': 1,
  23     }]
  24     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
  25
  26     def _real_extract(self, url):
  27         article_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, article_id)
  30
  31         entries = []
  32         for video in re.findall(
  33                 r'<video[^>]+data-video-id-pending=[^>]+>',
  34                 webpage):
  35             attrs = extract_attributes(video)
  36             video_id = attrs['data-video-id-pending']
  37             account_id = attrs.get('data-account', '5067014667001')
  38             entries.append(self.url_result(
  39                 self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id),
  40                 'BrightcoveNew', video_id))
  41
  42         return self.playlist_result(
  43             entries, article_id, self._og_search_title(webpage, fatal=False))