1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-27 19:36:50 +01:00

[tudou] Improve regexs

This commit is contained in:
Yen Chi Hsuan 2015-09-13 02:51:20 +08:00
parent 87813a8570
commit 349b3a2ea0

View File

@ -44,21 +44,21 @@ class TudouIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
youku_vcode = self._search_regex( 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: if youku_vcode:
return self.url_result('youku:' + youku_vcode, ie='Youku') return self.url_result('youku:' + youku_vcode, ie='Youku')
title = self._search_regex( title = self._search_regex(
r",kw:\s*['\"](.+?)[\"']", webpage, 'title') r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title')
thumbnail_url = self._search_regex( 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( player_url = self._search_regex(
r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']", r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]',
webpage, 'player URL', default=self._PLAYER_URL) webpage, 'player URL', default=self._PLAYER_URL)
segments = self._parse_json(self._search_regex( 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 # 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 # the hd field in the request url, we pick the higher
# Also, filter non-number qualities (see issue #3643). # Also, filter non-number qualities (see issue #3643).