Revert "[sohu] Update extractor"

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

diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index 5adc734d9da1dc0b0aa8e50184f416403f5bd3d8..7644cc02d71e8dc09cbe8536983d33fba19c3dec 100644 (file)
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -8,7 +8,10 @@ from ..compat import (
     compat_str,
     compat_urllib_request
 )
-from ..utils import url_sanitize_consecutive_slashes
+from ..utils import (
+    sanitize_url_path_consecutive_slashes,
+    ExtractorError,
+)
 
 
 class SohuIE(InfoExtractor):
@@ -23,9 +26,7 @@ class SohuIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'MV：Far East Movement《The Illest》',
         },
-        'params': {
-            'cn_verification_proxy': 'proxy.uku.im:8888'
-        }
+        'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
         'md5': '699060e75cf58858dd47fb9c03c42cfb',
@@ -42,6 +43,49 @@ 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',
+            'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+        },
+        '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',
+            }
+        }]
+    }, {
+        '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):
@@ -58,23 +102,31 @@ 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 = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage))
 
         vid = self._html_search_regex(
             r'var vid ?= ?["\'](\d+)["\']',
             webpage, 'video path')
         vid_data = _fetch_data(vid, mytv)
+        if vid_data['play'] != 1:
+            if vid_data.get('status') == 12:
+                raise ExtractorError(
+                    'Sohu said: There\'s something wrong in the video.',
+                    expected=True)
+            else:
+                raise ExtractorError(
+                    'Sohu said: The video is only licensed to users in Mainland China.',
+                    expected=True)
 
         formats_json = {}
         for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
@@ -106,7 +158,7 @@ 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({
@@ -131,9 +183,10 @@ class SohuIE(InfoExtractor):
             info['id'] = video_id
         else:
             info = {
-                '_type': 'playlist',
+                '_type': 'multi_video',
                 'entries': playlist,
                 'id': video_id,
+                'title': title,
             }
 
         return info