Merge tag 'upstream/2016.02.22'

[youtubedl] / youtube_dl / extractor / metacafe.py

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 1a896b536dd813a561cea8f870258bf73519e00b..67d6271e1ad107aceddaa2c8b4bd96558426bfce 100644 (file)
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -3,13 +3,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

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

     compat_parse_qs,
     compat_urllib_parse,
     compat_parse_qs,
     compat_urllib_parse,

-    compat_urllib_request,
+    compat_urllib_parse_unquote,
+)
+from ..utils import (

     determine_ext,
     ExtractorError,
     int_or_none,
     determine_ext,
     ExtractorError,
     int_or_none,

+    sanitized_Request,

 )
 
 
 )
 
 


@@ -22,7 +25,7 @@ class MetacafeIE(InfoExtractor):
         # Youtube video
         {
             'add_ie': ['Youtube'],
         # Youtube video
         {
             'add_ie': ['Youtube'],

-            'url':  'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
+            'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',

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


@@ -114,7 +117,7 @@ class MetacafeIE(InfoExtractor):
             'filters': '0',
             'submit': "Continue - I'm over 18",
         }
             'filters': '0',
             'submit': "Continue - I'm over 18",
         }

-        request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
+        request = sanitized_Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))

         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self.report_age_confirmation()
         self._download_webpage(request, None, False, 'Unable to confirm age')
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self.report_age_confirmation()
         self._download_webpage(request, None, False, 'Unable to confirm age')


@@ -139,7 +142,7 @@ class MetacafeIE(InfoExtractor):
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
         # Retrieve video webpage to extract further information
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
         # Retrieve video webpage to extract further information

-        req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
+        req = sanitized_Request('http://www.metacafe.com/watch/%s/' % video_id)

 
         # AnyClip videos require the flashversion cookie so that we get the link
         # to the mp4 file
 
         # AnyClip videos require the flashversion cookie so that we get the link
         # to the mp4 file


@@ -151,10 +154,10 @@ class MetacafeIE(InfoExtractor):
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         video_url = None
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         video_url = None

-        mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+        mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage)

         if mobj is not None:
         if mobj is not None:

-            mediaURL = compat_urllib_parse.unquote(mobj.group(1))
-            video_ext = mediaURL[-3:]
+            mediaURL = compat_urllib_parse_unquote(mobj.group(1))
+            video_ext = determine_ext(mediaURL)

 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)


@@ -219,14 +222,14 @@ class MetacafeIE(InfoExtractor):
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(

-                r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
-                webpage, 'uploader nickname', fatal=False)
+            r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
+            webpage, 'uploader nickname', fatal=False)

         duration = int_or_none(
             self._html_search_meta('video:duration', webpage))
 
         age_limit = (
             18
         duration = int_or_none(
             self._html_search_meta('video:duration', webpage))
 
         age_limit = (
             18

-            if re.search(r'"contentRating":"restricted"', webpage)
+            if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)

             else 0)
 
         if isinstance(video_url, list):
             else 0)
 
         if isinstance(video_url, list):