From 9c51a2464276f5eb26d1b571d32052df55d6ead9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?D=C3=A9stin=20Reed?= Date: Fri, 30 Sep 2016 20:06:08 +0200 Subject: [PATCH] [criterion] Rely on _match_id, improve regex and add thumbnail to test --- youtube_dl/extractor/criterion.py | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py index ad32673a81..cf6a5d6cbe 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 {