gistfile1.txt

import urllib  
import urllib2
import simplejson
import re
import time 
from urlparse import urlparse

RESOURCE_URL = 'https://graph.facebook.com/'

params = {'access_token':'SOMEHTING'}
values = urllib.urlencode(params)
req = urllib2.Request("%sme/friends?%s" % (RESOURCE_URL,values), None)

excluded_hostname = ['flickr.com', 'soundcloud.com' 'www.couchsurfing.org', 'twitter.com', 'www.linkedin.com', 'plus.google.com', 'www.behance.net', 'flavors.me', 'www.youtube.com', 'picasaweb.google.com', 'meebo.com', 'yelp.com', 'facebook.com', 'viadeo.com','www.myspace.com','www.last.fm','www.facebook.com']

response = urllib2.urlopen(req)

content = response.read()
json_content = simplejson.loads(content)


for friend in json_content['data']:
    time.sleep(2)
    req = urllib2.Request("%s%s?%s" % (RESOURCE_URL,friend['id'],values), None)
    try:
        response = urllib2.urlopen(req)
    except urllib2.HTTPError:
        print 'error for %s' % (friend['name'])
        continue
    content = response.read()
    boom = simplejson.loads(content)
    if 'website' in boom:
        try:
            biim = re.findall(r'(https?://\S+)', boom['website'])
        except AttributeError:
            continue
        for b in biim:
            parsed = urlparse(b)
            hostname = parsed.hostname
            if hostname not in excluded_hostname:
                print hostname