Prepare for upload.

[youtubedl] / youtube_dl / extractor / sina.py

diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py
index 14b1c656c538637b6922ff68a0785c448825e553..0891a441f85f42b75d91f1d267fabdd1b5e952ce 100644 (file)
--- a/youtube_dl/extractor/sina.py
+++ b/youtube_dl/extractor/sina.py
@@ -1,46 +1,52 @@
 # coding: utf-8
 # coding: utf-8

+from __future__ import unicode_literals

 
 import re
 
 import re

-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_urllib_request,
     compat_urllib_parse,
 )
 
 
 class SinaIE(InfoExtractor):
     compat_urllib_request,
     compat_urllib_parse,
 )
 
 
 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=))(?P<id>\d+?)($|&))))
+                            (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-))))

                             |
                             # This is used by external sites like Weibo
                             (api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
                         )
                   '''
 
                             |
                             # This is used by external sites like Weibo
                             (api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
                         )
                   '''
 

-    _TEST = {
-        u'url': u'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
-        u'file': u'110028898.flv',
-        u'md5': u'd65dd22ddcf44e38ce2bf58a10c3e71f',
-        u'info_dict': {
-            u'title': u'《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
-        }
-    }
-
-    @classmethod
-    def suitable(cls, url):
-        return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
+    _TESTS = [
+        {
+            'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
+            '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',
+            }
+        },
+        {
+            'url': 'http://video.sina.com.cn/v/b/101314253-1290078633.html',
+            'info_dict': {
+                'id': '101314253',
+                'ext': 'flv',
+                'title': '军方提高对朝情报监视级别',
+            },
+        },
+    ]

 
     def _extract_video(self, video_id):
         data = compat_urllib_parse.urlencode({'vid': video_id})
 
     def _extract_video(self, video_id):
         data = compat_urllib_parse.urlencode({'vid': video_id})

-        url_page = self._download_webpage('http://v.iask.com/v_play.php?%s' % data,
-            video_id, u'Downloading video url')
+        url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
+                                     video_id, 'Downloading video url')

         image_page = self._download_webpage(
             'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
         image_page = self._download_webpage(
             'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,

-            video_id, u'Downloading thumbnail info')
-        url_doc = xml.etree.ElementTree.fromstring(url_page.encode('utf-8'))
+            video_id, 'Downloading thumbnail info')

 
         return {'id': video_id,
                 'url': url_doc.find('./durl/url').text,
 
         return {'id': video_id,
                 'url': url_doc.find('./durl/url').text,


@@ -50,11 +56,11 @@ 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
         video_id = mobj.group('id')
         if mobj.group('token') is not None:
             # The video id is in the redirected url

-            self.to_screen(u'Getting video id')
+            self.to_screen('Getting video id')

             request = compat_urllib_request.Request(url)
             request.get_method = lambda: 'HEAD'
             (_, urlh) = self._download_webpage_handle(request, 'NA', False)
             request = compat_urllib_request.Request(url)
             request.get_method = lambda: 'HEAD'
             (_, urlh) = self._download_webpage_handle(request, 'NA', False)


@@ -62,6 +68,6 @@ class SinaIE(InfoExtractor):
         elif video_id is None:
             pseudo_id = mobj.group('pseudo_id')
             webpage = self._download_webpage(url, pseudo_id)
         elif video_id is None:
             pseudo_id = mobj.group('pseudo_id')
             webpage = self._download_webpage(url, pseudo_id)

-            video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, u'video id')
+            video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, 'video id')

 
         return self._extract_video(video_id)
 
         return self._extract_video(video_id)