Import Upstream version 2020.01.24

[youtubedl] / youtube_dl / extractor / metacafe.py

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index e6e7659a1de0ebe86f48a4128192de5d14d6d586..9e92416d1d804cfd7d0569d20c26f591655adf09 100644 (file)
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -1,17 +1,18 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import json

 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,

+    compat_urllib_parse,

     compat_urllib_parse_unquote,
 )
 from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,
     compat_urllib_parse_unquote,
 )
 from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,

-    urlencode_postdata,

     get_element_by_attribute,
     mimetype2ext,
 )
     get_element_by_attribute,
     mimetype2ext,
 )


@@ -50,6 +51,21 @@ class MetacafeIE(InfoExtractor):
             },
             'skip': 'Page is temporarily unavailable.',
         },
             },
             'skip': 'Page is temporarily unavailable.',
         },

+        # metacafe video with family filter
+        {
+            'url': 'http://www.metacafe.com/watch/2155630/adult_art_by_david_hart_156/',
+            'md5': 'b06082c5079bbdcde677a6291fbdf376',
+            'info_dict': {
+                'id': '2155630',
+                'ext': 'mp4',
+                'title': 'Adult Art By David Hart 156',
+                'uploader': '63346',
+                'description': 'md5:9afac8fc885252201ad14563694040fc',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },

         # AnyClip video
         {
             'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
         # AnyClip video
         {
             'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',


@@ -112,28 +128,12 @@ class MetacafeIE(InfoExtractor):
     def report_disclaimer(self):
         self.to_screen('Retrieving disclaimer')
 
     def report_disclaimer(self):
         self.to_screen('Retrieving disclaimer')
 

-    def _confirm_age(self):
-        # Retrieve disclaimer
-        self.report_disclaimer()
-        self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
-
-        # Confirm age
-        self.report_age_confirmation()
-        self._download_webpage(
-            self._FILTER_POST, None, False, 'Unable to confirm age',
-            data=urlencode_postdata({
-                'filters': '0',
-                'submit': "Continue - I'm over 18",
-            }), headers={
-                'Content-Type': 'application/x-www-form-urlencoded',
-            })
-

     def _real_extract(self, url):
         # Extract id and simplified title from URL
         video_id, display_id = re.match(self._VALID_URL, url).groups()
 
         # the video may come from an external site
     def _real_extract(self, url):
         # Extract id and simplified title from URL
         video_id, display_id = re.match(self._VALID_URL, url).groups()
 
         # the video may come from an external site

-        m_external = re.match('^(\w{2})-(.*)$', video_id)
+        m_external = re.match(r'^(\w{2})-(.*)$', video_id)

         if m_external is not None:
             prefix, ext_id = m_external.groups()
             # Check if video comes from YouTube
         if m_external is not None:
             prefix, ext_id = m_external.groups()
             # Check if video comes from YouTube


@@ -143,13 +143,15 @@ class MetacafeIE(InfoExtractor):
             if prefix == 'cb':
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
             if prefix == 'cb':
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 

-        # self._confirm_age()
+        headers = {
+            # Disable family filter
+            'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False}))
+        }

 
         # 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

-        headers = {}

         if video_id.startswith('an-'):
         if video_id.startswith('an-'):

-            headers['Cookie'] = 'flashVersion=0;'
+            headers['Cookie'] += 'flashVersion=0; '

 
         # Retrieve video webpage to extract further information
         webpage = self._download_webpage(url, video_id, headers=headers)
 
         # Retrieve video webpage to extract further information
         webpage = self._download_webpage(url, video_id, headers=headers)