Fix code for metacafe.com (this fixes issue #8)

This commit is contained in:
Ricardo Garcia 2009-04-25 11:52:33 +02:00
parent 98164eb3b9
commit dbccb6cd84

View file

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