debian/watch: Add back pgpsigurlmangle.

[youtubedl] / youtube_dl / extractor / metacafe.py

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 3c786a36dfb6c8908668cdf3191e660487862c82..b6f00cc25ff9c2769176e551b33bd5901c121f64 100644 (file)
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,

-    compat_urllib_parse,

     compat_urllib_parse_unquote,
 )
 from ..utils import (
     compat_urllib_parse_unquote,
 )
 from ..utils import (


@@ -13,11 +12,12 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     sanitized_Request,
     ExtractorError,
     int_or_none,
     sanitized_Request,

+    urlencode_postdata,

 )
 
 
 class MetacafeIE(InfoExtractor):
 )
 
 
 class MetacafeIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'

     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = 'metacafe'
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = 'metacafe'


@@ -81,6 +81,9 @@ class MetacafeIE(InfoExtractor):
                 'title': 'Open: This is Face the Nation, February 9',
                 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
                 'duration': 96,
                 'title': 'Open: This is Face the Nation, February 9',
                 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
                 'duration': 96,

+                'uploader': 'CBSI-NEW',
+                'upload_date': '20140209',
+                'timestamp': 1391959800,

             },
             'params': {
                 # rtmp download
             },
             'params': {
                 # rtmp download


@@ -117,7 +120,7 @@ class MetacafeIE(InfoExtractor):
             'filters': '0',
             'submit': "Continue - I'm over 18",
         }
             'filters': '0',
             'submit': "Continue - I'm over 18",
         }

-        request = sanitized_Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
+        request = sanitized_Request(self._FILTER_POST, urlencode_postdata(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')


@@ -154,10 +157,10 @@ 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:
             mediaURL = compat_urllib_parse_unquote(mobj.group(1))
         if mobj is not None:
             mediaURL = compat_urllib_parse_unquote(mobj.group(1))

-            video_ext = mediaURL[-3:]
+            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)


@@ -229,7 +232,7 @@ class MetacafeIE(InfoExtractor):
 
         age_limit = (
             18
 
         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):