X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/75535d182355c0cc00271ceae302e8e4aba9c04e..3ea185de6ec59da4fe6e7a4553101b8398580333:/youtube_dl/extractor/criterion.py diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py index 4fb1781..f7815b9 100644 --- a/youtube_dl/extractor/criterion.py +++ b/youtube_dl/extractor/criterion.py @@ -1,13 +1,11 @@ -# -*- coding: utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor class CriterionIE(InfoExtractor): - _VALID_URL = r'https?://www\.criterion\.com/films/(?P[0-9]+)-.+' + _VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P[0-9]+)-.+' _TEST = { 'url': 'http://www.criterion.com/films/184-le-samourai', 'md5': 'bc51beba55685509883a9a7830919ec3', @@ -16,22 +14,20 @@ class CriterionIE(InfoExtractor): 'ext': 'mp4', 'title': 'Le Samouraï', 'description': 'md5:a2b4b116326558149bef81f76dcbb93f', + 'thumbnail': r'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_regex( - r'', - webpage, 'video description') + description = self._html_search_meta('description', webpage) thumbnail = self._search_regex( - r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', + r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;', webpage, 'thumbnail url') return {