X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsohu.py;h=11edf616ac8a781f0765cec94a7e49b2cb07c32c;hb=372f08c99057b6a994c72cf2591e184231b3e850;hp=7db5b2f13367749aebef75e0785bc842bdba19fd;hpb=cd65491c306f644d7bb3c7ad98795a3f8660be49;p=youtube-dl

diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index 7db5b2f13..11edf616a 100644
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -8,7 +8,7 @@ from ..compat import (
     compat_str,
     compat_urllib_request
 )
-from ..utils import url_sanitize_consecutive_slashes
+from ..utils import sanitize_url_path_consecutive_slashes
 
 
 class SohuIE(InfoExtractor):
@@ -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',
             }
         }]
+    }, {
+        'note': '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):
@@ -89,18 +100,17 @@ class SohuIE(InfoExtractor):
             if cn_verification_proxy:
                 req.add_header('Ytdl-request-proxy', cn_verification_proxy)
 
-            return self._download_json(req, video_id,
-                                       'Downloading JSON data for %s' % vid_id)
+            return self._download_json(
+                req, video_id,
+                'Downloading JSON data for %s' % vid_id)
 
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         mytv = mobj.group('mytv') is not None
 
         webpage = self._download_webpage(url, video_id)
-        raw_title = self._html_search_regex(
-            r'(?s)<title>(.+?)</title>',
-            webpage, 'video title')
-        title = raw_title.partition('-')[0].strip()
+
+        title = self._og_search_title(webpage)
 
         vid = self._html_search_regex(
             r'var vid ?= ?["\'](\d+)["\']',
@@ -137,7 +147,7 @@ class SohuIE(InfoExtractor):
 
                 part_info = part_str.split('|')
 
-                video_url = url_sanitize_consecutive_slashes(
+                video_url = sanitize_url_path_consecutive_slashes(
                     '%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
 
                 formats.append({