X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsohu.py;h=daf6ad555be2a84dc89ec8dfcabcdfde78cf0194;hb=5c2266df4b9aeb7881ed8c026a038e2a25e43734;hp=335e84fab7b990019aaf1063fd2fd6ea721bb465;hpb=5c7495a19429e3b27c003a4bd5bb96ed1e3a4932;p=youtube-dl

diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index 335e84fab..daf6ad555 100644
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -6,7 +6,11 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
-    compat_urllib_request
+    compat_urllib_parse,
+)
+from ..utils import (
+    ExtractorError,
+    sanitized_Request,
 )
 
 
@@ -22,9 +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',
@@ -41,6 +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):
@@ -51,29 +96,37 @@ class SohuIE(InfoExtractor):
             else:
                 base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
 
-            req = compat_urllib_request.Request(base_data_url + vid_id)
+            req = sanitized_Request(base_data_url + vid_id)
 
             cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
             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'):
@@ -90,26 +143,41 @@ class SohuIE(InfoExtractor):
             formats = []
             for format_id, format_data in formats_json.items():
                 allot = format_data['allot']
-                prot = format_data['prot']
 
                 data = format_data['data']
                 clips_url = data['clipsURL']
                 su = data['su']
 
-                part_str = self._download_webpage(
-                    'http://%s/?prot=%s&file=%s&new=%s' %
-                    (allot, prot, clips_url[i], su[i]),
-                    video_id,
-                    'Downloading %s video URL part %d of %d'
-                    % (format_id, i + 1, part_count))
+                video_url = 'newflv.sohu.ccgslb.net'
+                cdnId = None
+                retries = 0
+
+                while 'newflv.sohu.ccgslb.net' in video_url:
+                    params = {
+                        'prot': 9,
+                        'file': clips_url[i],
+                        'new': su[i],
+                        'prod': 'flash',
+                    }
+
+                    if cdnId is not None:
+                        params['idc'] = cdnId
 
-                part_info = part_str.split('|')
+                    download_note = 'Downloading %s video URL part %d of %d' % (
+                        format_id, i + 1, part_count)
 
-                # Sanitize URL to prevent download failure
-                if part_info[0][-1] == '/' and su[i][0] == '/':
-                    su[i] = su[i][1:]
+                    if retries > 0:
+                        download_note += ' (retry #%d)' % retries
+                    part_info = self._parse_json(self._download_webpage(
+                        'http://%s/?%s' % (allot, compat_urllib_parse.urlencode(params)),
+                        video_id, download_note), video_id)
 
-                video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+                    video_url = part_info['url']
+                    cdnId = part_info.get('nid')
+
+                    retries += 1
+                    if retries > 5:
+                        raise ExtractorError('Failed to get video URL')
 
                 formats.append({
                     'url': video_url,
@@ -133,9 +201,10 @@ class SohuIE(InfoExtractor):
             info['id'] = video_id
         else:
             info = {
-                '_type': 'playlist',
+                '_type': 'multi_video',
                 'entries': playlist,
                 'id': video_id,
+                'title': title,
             }
 
         return info