Tidy up cleanup rule and keep lintian happy.

[youtubedl] / youtube_dl / extractor / shared.py

diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index e7e5f653eb2117936f568195e508f9e7778b1085..d592dfeb8ed99d45d7c9b8245f5570e06f260a20 100644 (file)
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -6,7 +6,6 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
 from ..utils import (
     ExtractorError,
     int_or_none,

-    sanitized_Request,

     urlencode_postdata,
 )
 
     urlencode_postdata,
 )
 


@@ -37,28 +36,33 @@ class SharedIE(InfoExtractor):
 
     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)
 
         download_form = self._hidden_inputs(webpage)
 
         if '>File does not exist<' in webpage:
             raise ExtractorError(
                 'Video %s does not exist' % video_id, expected=True)
 
         download_form = self._hidden_inputs(webpage)

-        request = sanitized_Request(
-            url, urlencode_postdata(download_form))
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')

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

-            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,