yt-dlp/yt_dlp/extractor/thesun.py

37 lines
1.3 KiB
Python
Raw Normal View History

import re
2017-04-07 19:52:48 +00:00
from .common import InfoExtractor
2019-10-28 12:32:35 +00:00
from ..utils import extract_attributes
2017-04-07 19:52:48 +00:00
class TheSunIE(InfoExtractor):
_VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/[^/]+/(?P<id>\d+)'
2017-04-07 19:52:48 +00:00
_TEST = {
'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/',
'info_dict': {
'id': '2261604',
'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf',
},
'playlist_count': 2,
2017-04-07 19:52:48 +00:00
}
2019-10-28 12:32:35 +00:00
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
2017-04-07 19:52:48 +00:00
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
2017-04-07 19:52:48 +00:00
entries = []
2019-10-28 12:32:35 +00:00
for video in re.findall(
r'<video[^>]+data-video-id-pending=[^>]+>',
webpage):
2019-10-28 12:32:35 +00:00
attrs = extract_attributes(video)
video_id = attrs['data-video-id-pending']
account_id = attrs.get('data-account', '5067014667001')
entries.append(self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id),
'BrightcoveNew', video_id))
2017-04-07 19:52:48 +00:00
return self.playlist_result(
entries, article_id, self._og_search_title(webpage, fatal=False))