1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-21 04:33:17 -05:00
yt-dlp/youtube_dl/extractor/thesun.py

33 lines
1 KiB
Python
Raw Normal View History

2017-04-07 15:52:48 -04:00
from __future__ import unicode_literals
import re
2017-04-07 15:52:48 -04:00
from .common import InfoExtractor
from .ooyala import OoyalaIE
class TheSunIE(InfoExtractor):
_VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/[^/]+/(?P<id>\d+)'
2017-04-07 15:52:48 -04:00
_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 15:52:48 -04:00
}
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
2017-04-07 15:52:48 -04:00
entries = []
for ooyala_id in re.findall(
r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)',
webpage):
entries.append(OoyalaIE._build_url_result(ooyala_id))
2017-04-07 15:52:48 -04:00
return self.playlist_result(
entries, article_id, self._og_search_title(webpage, fatal=False))