Update Standards-Version to 3.9.8 (no changes required).

[youtubedl] / youtube_dl / extractor / shared.py

diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index 26ced716e8a875f1c4c5c9527b856475dce83f9e..d592dfeb8ed99d45d7c9b8245f5570e06f260a20 100644 (file)
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -1,57 +1,68 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re

 import base64
 
 from .common import InfoExtractor
 import base64
 
 from .common import InfoExtractor

-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)

 from ..utils import (
     ExtractorError,
     int_or_none,
 from ..utils import (
     ExtractorError,
     int_or_none,

+    urlencode_postdata,

 )
 
 
 class SharedIE(InfoExtractor):
 )
 
 
 class SharedIE(InfoExtractor):

-    _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})'
+    IE_DESC = 'shared.sx and vivo.sx'
+    _VALID_URL = r'https?://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'

 
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://shared.sx/0060718775',
         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
         'info_dict': {
             'id': '0060718775',
             'ext': 'mp4',
             'title': 'Bmp4',
         'url': 'http://shared.sx/0060718775',
         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
         'info_dict': {
             'id': '0060718775',
             'ext': 'mp4',
             'title': 'Bmp4',

+            'filesize': 1720110,

         },
         },

-    }
+    }, {
+        'url': 'http://vivo.sx/d7ddda0e78',
+        'md5': '15b3af41be0b4fe01f4df075c2678b2c',
+        'info_dict': {
+            'id': 'd7ddda0e78',
+            'ext': 'mp4',
+            'title': 'Chicken',
+            'filesize': 528031,
+        },
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

-        webpage = self._download_webpage(url, video_id)
+
+        webpage, urlh = self._download_webpage_handle(url, video_id)

 
         if '>File does not exist<' in webpage:
             raise ExtractorError(
                 'Video %s does not exist' % video_id, expected=True)
 
 
         if '>File does not exist<' in webpage:
             raise ExtractorError(
                 'Video %s does not exist' % video_id, expected=True)
 

-        download_form = dict(re.findall(
-            r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
-        request = compat_urllib_request.Request(
-            url, compat_urllib_parse.urlencode(download_form))
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        download_form = self._hidden_inputs(webpage)

 
         video_page = self._download_webpage(
 
         video_page = self._download_webpage(

-            request, video_id, 'Downloading video page')
+            urlh.geturl(), video_id, 'Downloading video page',
+            data=urlencode_postdata(download_form),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Referer': urlh.geturl(),
+            })

 
         video_url = self._html_search_regex(
 
         video_url = self._html_search_regex(

-            r'data-url="([^"]+)"', video_page, 'video URL')
+            r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            video_page, 'video URL', group='url')

         title = base64.b64decode(self._html_search_meta(
         title = base64.b64decode(self._html_search_meta(

-            'full:title', webpage, 'title')).decode('utf-8')
+            'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')

         filesize = int_or_none(self._html_search_meta(
             'full:size', webpage, 'file size', fatal=False))
         thumbnail = self._html_search_regex(
         filesize = int_or_none(self._html_search_meta(
             'full:size', webpage, 'file size', fatal=False))
         thumbnail = self._html_search_regex(

-            r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
+            r'data-poster=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            video_page, 'thumbnail', default=None, group='url')

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,