From 2cb434e53ee861c8bcbd538455be107085f444ae Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sun, 15 Mar 2015 01:05:01 +0800 Subject: [PATCH] [Sohu] Fix title extraction --- youtube_dl/extractor/sohu.py | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 7db5b2f13..ea5cc06b9 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -73,6 +73,17 @@ class SohuIE(InfoExtractor): 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', } }] + }, { + 'info': 'Video with title containing dash', + 'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml', + 'info_dict': { + 'id': '78932792', + 'ext': 'mp4', + 'title': 'youtube-dl testing video', + }, + 'params': { + 'skip_download': True + } }] def _real_extract(self, url): @@ -97,10 +108,8 @@ def _fetch_data(vid_id, mytv=False): mytv = mobj.group('mytv') is not None webpage = self._download_webpage(url, video_id) - raw_title = self._html_search_regex( - r'(?s)(.+?)', - webpage, 'video title') - title = raw_title.partition('-')[0].strip() + + title = self._og_search_title(webpage) vid = self._html_search_regex( r'var vid ?= ?["\'](\d+)["\']',