Prepare to upload.

[youtubedl] / youtube_dl / extractor / sohu.py

diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index 29bd9ce6f76247b5ac997050075c7e720d8a3b2b..ea8fc258d1e7f361bc2a75360dc4c65774674622 100644 (file)
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -6,9 +6,12 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
 from .common import InfoExtractor
 from ..compat import (
     compat_str,

-    compat_urllib_request
+    compat_urllib_parse,
+)
+from ..utils import (
+    ExtractorError,
+    sanitized_Request,

 )
 )

-from ..utils import ExtractorError

 
 
 class SohuIE(InfoExtractor):
 
 
 class SohuIE(InfoExtractor):


@@ -26,7 +29,7 @@ class SohuIE(InfoExtractor):
         'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
         'skip': 'On available in China',
     }, {
         'url': 'http://tv.sohu.com/20150305/n409385080.shtml',

-        'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a',
+        'md5': '699060e75cf58858dd47fb9c03c42cfb',

         'info_dict': {
             'id': '409385080',
             'ext': 'mp4',
         'info_dict': {
             'id': '409385080',
             'ext': 'mp4',


@@ -34,7 +37,7 @@ class SohuIE(InfoExtractor):
         }
     }, {
         'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
         }
     }, {
         'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',

-        'md5': '49308ff6dafde5ece51137d04aec311e',
+        'md5': '9bf34be48f2f4dadcb226c74127e203c',

         'info_dict': {
             'id': '78693464',
             'ext': 'mp4',
         'info_dict': {
             'id': '78693464',
             'ext': 'mp4',


@@ -48,7 +51,7 @@ class SohuIE(InfoExtractor):
             'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{
             'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
         },
         'playlist': [{

-            'md5': '492923eac023ba2f13ff69617c32754a',
+            'md5': 'bdbfb8f39924725e6589c146bc1883ad',

             'info_dict': {
                 'id': '78910339_part1',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '78910339_part1',
                 'ext': 'mp4',


@@ -56,7 +59,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {

-            'md5': 'de604848c0e8e9c4a4dde7e1347c0637',
+            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',

             'info_dict': {
                 'id': '78910339_part2',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '78910339_part2',
                 'ext': 'mp4',


@@ -64,7 +67,7 @@ class SohuIE(InfoExtractor):
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {
                 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
             }
         }, {

-            'md5': '93584716ee0657c0b205b8aa3d27aa13',
+            'md5': '8407e634175fdac706766481b9443450',

             'info_dict': {
                 'id': '78910339_part3',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '78910339_part3',
                 'ext': 'mp4',


@@ -93,7 +96,7 @@ class SohuIE(InfoExtractor):
             else:
                 base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
 
             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:
 
             cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
             if cn_verification_proxy:


@@ -139,21 +142,43 @@ class SohuIE(InfoExtractor):
         for i in range(part_count):
             formats = []
             for format_id, format_data in formats_json.items():
         for i in range(part_count):
             formats = []
             for format_id, format_data in formats_json.items():

+                allot = format_data['allot']
+

                 data = format_data['data']
                 data = format_data['data']

+                clips_url = data['clipsURL']
+                su = data['su']

 
 

-                # URLs starts with http://newflv.sohu.ccgslb.net/ is not usable
-                # so retry until got a working URL

                 video_url = 'newflv.sohu.ccgslb.net'
                 video_url = 'newflv.sohu.ccgslb.net'

+                cdnId = None

                 retries = 0
                 retries = 0

-                while 'newflv.sohu.ccgslb.net' in video_url and retries < 5:
-                    download_note = 'Download information from CDN gateway for format ' + format_id
+
+                while 'newflv.sohu.ccgslb.net' in video_url:
+                    params = {
+                        'prot': 9,
+                        'file': clips_url[i],
+                        'new': su[i],
+                        'prod': 'flash',
+                        'rb': 1,
+                    }
+
+                    if cdnId is not None:
+                        params['idc'] = cdnId
+
+                    download_note = 'Downloading %s video URL part %d of %d' % (
+                        format_id, i + 1, part_count)
+

                     if retries > 0:
                         download_note += ' (retry #%d)' % retries
                     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 = part_info['url']
+                    cdnId = part_info.get('nid')
+

                     retries += 1
                     retries += 1

-                    cdn_info = self._download_json(
-                        'http://data.vod.itc.cn/cdnList?new=' + data['su'][i],
-                        video_id, download_note)
-                    video_url = cdn_info['url']
+                    if retries > 5:
+                        raise ExtractorError('Failed to get video URL')

 
                 formats.append({
                     'url': video_url,
 
                 formats.append({
                     'url': video_url,