Fix code for metacafe.com (this fixes issue #8)
authorRicardo Garcia <sarbalap+freshmeat@gmail.com>
Sat, 25 Apr 2009 09:52:33 +0000 (11:52 +0200)
committerRicardo Garcia <sarbalap+freshmeat@gmail.com>
Sun, 31 Oct 2010 10:24:08 +0000 (11:24 +0100)
youtube-dl

index f276d9caa9e3616599cab3156cfd19212549ba70..8764acda0592df1c628b0a7d4dceeaa59d2b7394 100755 (executable)
@@ -624,6 +624,7 @@ class MetacafeIE(InfoExtractor):
 
        _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+       _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None
 
        def __init__(self, youtube_ie, downloader=None):
@@ -665,7 +666,7 @@ class MetacafeIE(InfoExtractor):
                        'filters': '0',
                        'submit': "Continue - I'm over 18",
                        }
-               request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+               request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
                try:
                        self.report_age_confirmation()
                        disclaimer = urllib2.urlopen(request).read()
@@ -702,13 +703,13 @@ class MetacafeIE(InfoExtractor):
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
-               mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
+               mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return
-               mediaURL = mobj.group(1).replace('\\', '')
+               mediaURL = urllib.unquote(mobj.group(1))
 
-               mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
+               mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract gdaKey')
                        return
@@ -722,11 +723,11 @@ class MetacafeIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
 
-               mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
+               mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
-               video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
+               video_uploader = mobj.group(1)
 
                # Process video information
                self._downloader.process_info({