debian/watch: Skip pgpsigurlmangle for the moment.

[youtubedl] / youtube_dl / extractor / sina.py

diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py
index 5eadbb7eaea263b8a37307fbdcc01c3e54c5eaa2..b2258a0f64c9f985edb5354ae5c11a381ebcc8af 100644 (file)
--- a/youtube_dl/extractor/sina.py
+++ b/youtube_dl/extractor/sina.py
@@ -4,14 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

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

 
 
 class SinaIE(InfoExtractor):
 
 
 class SinaIE(InfoExtractor):

-    _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/
+    _VALID_URL = r'''(?x)https?://(.*?\.)?video\.sina\.com\.cn/

                         (
                             (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-))))
                             |
                         (
                             (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-))))
                             |


@@ -23,9 +21,10 @@ class SinaIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
     _TESTS = [
         {
             'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',

-            'file': '110028898.flv',

             'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f',
             'info_dict': {
             'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f',
             'info_dict': {

+                'id': '110028898',
+                'ext': 'flv',

                 'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
             }
         },
                 'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
             }
         },


@@ -39,10 +38,6 @@ class SinaIE(InfoExtractor):
         },
     ]
 
         },
     ]
 

-    @classmethod
-    def suitable(cls, url):
-        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
-

     def _extract_video(self, video_id):
         data = compat_urllib_parse.urlencode({'vid': video_id})
         url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
     def _extract_video(self, video_id):
         data = compat_urllib_parse.urlencode({'vid': video_id})
         url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,


@@ -59,12 +54,12 @@ class SinaIE(InfoExtractor):
                 }
 
     def _real_extract(self, url):
                 }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        mobj = re.match(self._VALID_URL, url)

         video_id = mobj.group('id')
         if mobj.group('token') is not None:
             # The video id is in the redirected url
             self.to_screen('Getting video id')
         video_id = mobj.group('id')
         if mobj.group('token') is not None:
             # The video id is in the redirected url
             self.to_screen('Getting video id')

-            request = compat_urllib_request.Request(url)
+            request = sanitized_Request(url)

             request.get_method = lambda: 'HEAD'
             (_, urlh) = self._download_webpage_handle(request, 'NA', False)
             return self._real_extract(urlh.geturl())
             request.get_method = lambda: 'HEAD'
             (_, urlh) = self._download_webpage_handle(request, 'NA', False)
             return self._real_extract(urlh.geturl())