diff options
| author | Remita Amine <remitamine@gmail.com> | 2019-10-28 13:32:35 +0100 | 
|---|---|---|
| committer | Remita Amine <remitamine@gmail.com> | 2019-10-28 13:32:35 +0100 | 
| commit | 80c2126e80bc41f7b66d325c4c67c61887c58fb0 (patch) | |
| tree | bdc41f984ce7b2a3d96c8ef99a37fbfe87571eb4 | |
| parent | 71fa0b04f9099090f43f6747632a9bdc3a4b1015 (diff) | |
[thesun] fix extraction(closes #16966)
| -rw-r--r-- | youtube_dl/extractor/thesun.py | 14 | 
1 files changed, 10 insertions, 4 deletions
| diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py index 22d003776..15d4a6932 100644 --- a/youtube_dl/extractor/thesun.py +++ b/youtube_dl/extractor/thesun.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals  import re  from .common import InfoExtractor -from .ooyala import OoyalaIE +from ..utils import extract_attributes  class TheSunIE(InfoExtractor): @@ -16,6 +16,7 @@ class TheSunIE(InfoExtractor):          },          'playlist_count': 2,      } +    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'      def _real_extract(self, url):          article_id = self._match_id(url) @@ -23,10 +24,15 @@ class TheSunIE(InfoExtractor):          webpage = self._download_webpage(url, article_id)          entries = [] -        for ooyala_id in re.findall( -                r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)', +        for video in re.findall( +                r'<video[^>]+data-video-id-pending=[^>]+>',                  webpage): -            entries.append(OoyalaIE._build_url_result(ooyala_id)) +            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))          return self.playlist_result(              entries, article_id, self._og_search_title(webpage, fatal=False)) | 
