From: Yen Chi Hsuan Date: Sat, 12 Sep 2015 18:51:20 +0000 (+0800) Subject: [tudou] Improve regexs X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=349b3a2ea0d6c264facacd92508516e8530108b2;p=youtube-dl [tudou] Improve regexs --- diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 3b993192c..53ba8511f 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -44,21 +44,21 @@ class TudouIE(InfoExtractor): webpage = self._download_webpage(url, video_id) youku_vcode = self._search_regex( - r'vcode:\s*[\'"](.+?)[\'"]', webpage, 'youku vcode', default=None) + r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None) if youku_vcode: return self.url_result('youku:' + youku_vcode, ie='Youku') title = self._search_regex( - r",kw:\s*['\"](.+?)[\"']", webpage, 'title') + r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title') thumbnail_url = self._search_regex( - r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) + r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False) player_url = self._search_regex( - r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']", + r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]', webpage, 'player URL', default=self._PLAYER_URL) segments = self._parse_json(self._search_regex( - r'segs: \'(.*)\'', webpage, 'segments'), video_id) + r'segs: \'([^\']+)\'', webpage, 'segments'), video_id) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher # Also, filter non-number qualities (see issue #3643).