diff options
author | Sergey M․ <[email protected]> | 2017-04-08 20:08:31 +0700 |
---|---|---|
committer | Sergey M․ <[email protected]> | 2017-04-08 20:08:31 +0700 |
commit | 90e3f18fc1cff2c12361cbbd85303774bf7d59f7 (patch) | |
tree | 54a76c4b44738528e9cabc0b10c0f90e80ccb6ee /youtube_dl | |
parent | 5f3e0b69efa8ae80f536fb54ace4bb4d9c667d2e (diff) | |
download | youtube-dl-90e3f18fc1cff2c12361cbbd85303774bf7d59f7.tar.gz youtube-dl-90e3f18fc1cff2c12361cbbd85303774bf7d59f7.zip |
[thesun] Extract playlists (closes #11298, closes #12674)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/thesun.py | 29 |
1 files changed, 17 insertions, 12 deletions
diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py index 7f96bf8c9..22d003776 100644 --- a/youtube_dl/extractor/thesun.py +++ b/youtube_dl/extractor/thesun.py @@ -1,27 +1,32 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from .ooyala import OoyalaIE 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 = { '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': { - 'id': 'h4OXN0NzE6rv6ObkEifKcNA-gYUw4xFf', - 'ext': 'mp4', - 'title': 'Katy Perry and Orlando Bloom shut down split rumours with cute Thanksgiving video', - 'description': 'Still going strong', - 'duration': 31.28, - } + 'id': '2261604', + 'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf', + }, + 'playlist_count': 2, } def _real_extract(self, url): - video_id = self._match_id(url) + article_id = self._match_id(url) + + webpage = self._download_webpage(url, article_id) - webpage = self._download_webpage(url, video_id) - ooyala_id = self._search_regex(r'id\s*=\s*"thesun-ooyala-player-([^"]+)"', webpage, '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 OoyalaIE._build_url_result(ooyala_id) + return self.playlist_result( + entries, article_id, self._og_search_title(webpage, fatal=False)) |