import urllib import xml.dom.minidom as minidom import re feeds = urllib.urlopen('http://news.bbc.co.uk/rss/feeds.opml').read() doc = minidom.parseString(feeds) xml = doc.getElementsByTagName("body")[0].toxml() xml = re.sub(r' ([A-Za-z]*?)="', r' bbc:\1="', xml) xml = xml.replace("", '') print xml.encode("utf-16")