Merge branch 'sohu_fix' of https://github.com/yan12125/youtube-dl into yan12125-sohu_fix

[youtube-dl] / youtube_dl / extractor / sohu.py

diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index ef7ec51df4c857ca5cb4628c850b9f6f227d4587..ea5cc06b980771fb4c9ab29459846084269c75a2 100644 (file)
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -4,8 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_str
-from ..compat import compat_urllib_request
+from ..compat import (
+    compat_str,
+    compat_urllib_request
+)
+from ..utils import url_sanitize_consecutive_slashes
 
 
 class SohuIE(InfoExtractor):
@@ -39,6 +42,48 @@ class SohuIE(InfoExtractor):
             'ext': 'mp4',
             'title': '【爱范品】第31期：MWC见不到的奇葩手机',
         }
+    }, {
+        'note': 'Multipart video',
+        'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
+        'info_dict': {
+            'id': '78910339',
+        },
+        'playlist': [{
+            'md5': 'bdbfb8f39924725e6589c146bc1883ad',
+            'info_dict': {
+                'id': '78910339_part1',
+                'ext': 'mp4',
+                'duration': 294,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }, {
+            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
+            'info_dict': {
+                'id': '78910339_part2',
+                'ext': 'mp4',
+                'duration': 300,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }, {
+            'md5': '8407e634175fdac706766481b9443450',
+            'info_dict': {
+                'id': '78910339_part3',
+                'ext': 'mp4',
+                'duration': 150,
+                '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):
@@ -63,10 +108,8 @@ class SohuIE(InfoExtractor):
         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+)["\']',
@@ -103,11 +146,8 @@ class SohuIE(InfoExtractor):
 
                 part_info = part_str.split('|')
 
-                # Sanitize URL to prevent download failure
-                if part_info[0][-1] == '/' and su[i][0] == '/':
-                    su[i] = su[i][1:]
-
-                video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+                video_url = url_sanitize_consecutive_slashes(
+                    '%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
 
                 formats.append({
                     'url': video_url,