diff options
| author | Yen Chi Hsuan <yan12125@gmail.com> | 2016-10-01 19:49:18 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2016-10-01 19:49:18 +0800 |
| commit | 63e0fd5bccf5cfb85e00e5935f4b6961ff26c58c (patch) | |
| tree | 45d73756611043568717acb5c534067488b7ac53 | |
| parent | 9bd7bd0b8054231adbeb2a0eddd42a0b969fd6c4 (diff) | |
| parent | 9c51a2464276f5eb26d1b571d32052df55d6ead9 (diff) | |
Merge pull request #10818 from TRox1972/criterion_match_id
[criterion] Rely on _match_id, improve regex and add thumbnail to test
| -rw-r--r-- | youtube_dl/extractor/criterion.py | 12 |
1 files changed, 5 insertions, 7 deletions
diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py index ad32673a8..cf6a5d6cb 100644 --- a/youtube_dl/extractor/criterion.py +++ b/youtube_dl/extractor/criterion.py @@ -1,8 +1,6 @@ -# -*- coding: utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -16,20 +14,20 @@ class CriterionIE(InfoExtractor): 'ext': 'mp4', 'title': 'Le Samouraï', 'description': 'md5:a2b4b116326558149bef81f76dcbb93f', + 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) 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) description = self._html_search_meta('description', webpage) thumbnail = self._search_regex( - r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', + r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;', webpage, 'thumbnail url') return { |