Merge pull request #10818 from TRox1972/criterion_match_id

[criterion] Rely on _match_id, improve regex and add thumbnail to test
This commit is contained in:
Yen Chi Hsuan 2016-10-01 19:49:18 +08:00 committed by GitHub
commit 63e0fd5bcc

View File

@ -1,8 +1,6 @@
# -*- coding: utf-8 -*- # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
@ -16,20 +14,20 @@ class CriterionIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Le Samouraï', 'title': 'Le Samouraï',
'description': 'md5:a2b4b116326558149bef81f76dcbb93f', 'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
'thumbnail': 're:^https?://.*\.jpg$',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
final_url = self._search_regex( final_url = self._search_regex(
r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url') r'so\.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
description = self._html_search_meta('description', webpage) description = self._html_search_meta('description', webpage)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url') webpage, 'thumbnail url')
return { return {