thesun.py (1402B)
1 from __future__ import unicode_literals 2 3 import re 4 5 from .common import InfoExtractor 6 from ..utils import extract_attributes 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 BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' 20 21 def _real_extract(self, url): 22 article_id = self._match_id(url) 23 24 webpage = self._download_webpage(url, article_id) 25 26 entries = [] 27 for video in re.findall( 28 r'<video[^>]+data-video-id-pending=[^>]+>', 29 webpage): 30 attrs = extract_attributes(video) 31 video_id = attrs['data-video-id-pending'] 32 account_id = attrs.get('data-account', '5067014667001') 33 entries.append(self.url_result( 34 self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), 35 'BrightcoveNew', video_id)) 36 37 return self.playlist_result( 38 entries, article_id, self._og_search_title(webpage, fatal=False))