w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[thesun] Extract playlists (closes #11298, closes #12674)

Browse source
This commit is contained in:
Sergey M․ 2017-04-08 20:08:31 +07:00
parent 5f3e0b69ef
commit 90e3f18fc1
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 17 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/extractor/thesun.py
View file

@ -1,27 +1,32 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from .ooyala import OoyalaIE from .ooyala import OoyalaIE
class TheSunIE(InfoExtractor): class TheSunIE(InfoExtractor):
_VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/\w+/(?P<id>\d+)/[\w-]' _VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/[^/]+/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/', 'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/',
'md5': '5667123b24f25f43f4c4f381ef34c5c2',
'info_dict': { 'info_dict': {
'id': 'h4OXN0NzE6rv6ObkEifKcNA-gYUw4xFf', 'id': '2261604',
'ext': 'mp4', 'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf',
'title': 'Katy Perry and Orlando Bloom shut down split rumours with cute Thanksgiving video', },
'description': 'Still going strong', 'playlist_count': 2,
'duration': 31.28,
}
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) article_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, article_id)
ooyala_id = self._search_regex(r'id\s*=\s*"thesun-ooyala-player-([^"]+)"', webpage, 'ooyala id')
return OoyalaIE._build_url_result(ooyala_id) 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))
return self.playlist_result(
entries, article_id, self._og_search_title(webpage, fatal=False))