Parse a Google Sitemap

How to parse a Google sitemap.

Download Chilkat Python Library

import chilkat


xml = chilkat.CkXml()

#  The Chilkat XML component is freeware.

#  Load an XML sitemap:
xml.LoadXmlFile("sitemap.xml")

#  Iterate over the URL nodes:

xUrl = xml.FirstChild()

#  Loop over the records in the sitemap and display each URL.
while not (xUrl == None ) :

    print xUrl.getChildContent("loc")

    xUrl = xUrl.NextSibling()