Parse sitemaps.xml for urls

parse_sitemaps.py

#!/usr/bin/env python

from xml.etree import ElementTree

def main():
  namespace = 'http://www.google.com/schemas/sitemap/0.84'
  xml = ElementTree.parse('./sitemap.xml')
  root = xml.getroot()
  for item in root.findall('.//s:loc', namespaces=dict(s=namespace)):
    print item.text

if __name__ == '__main__':
  main()