alexandriz_parse_links.py

import urllib
import xml.dom.minidom as dom
import sys
import re

#Feeds
url = "http://www.teamalexandriz.org/category/policier/feed/"
#url = "http://www.teamalexandriz.org/category/aventure/feed/"
#url = "http://www.teamalexandriz.org/category/science-fiction/feed/"

sock  = urllib.urlopen(url)
resp = sock.read()
encoding = sock.headers['Content-type'].split('charset=')[1]

#Transcoding (Needed for xml.dom)
resp = resp.decode(encoding,'ignore').encode('ascii', 'xmlcharrefreplace')
dom = dom.parseString(resp)

items = dom.getElementsByTagName("item")

#Extra the first node with this name
def extractUtfNode(parent,name):
	return parent.getElementsByTagName(name)[0].firstChild.data.encode('UTF-8')

for i in items:
	title = extractUtfNode(i,"title")
	megaupload_urls = re.search('(http://www.megaupload.com/[^\"]+)',extractUtfNode(i,"content:encoded"))
	url = megaupload_urls.group(0)
	
	print "-----"
	print title
	print url