Convert HTML File to XML File

Convert HTML file to XML file.

Download Chilkat Python Library

import sys
import chilkat



htmlToXml = chilkat.CkHtmlToXml()

#  Any string argument automatically begins the 30-day trial.
success = htmlToXml.UnlockComponent("30-day trial")
if (success != True):
    print "HtmlToXml component unlock failed"
    sys.exit()

#  Indicate the charset of the output XML we'll want.
htmlToXml.put_XmlCharset("utf-8")

success = htmlToXml.ConvertFile("test.html","out.xml")
if (success != True):
    print htmlToXml.lastErrorText()
else:
    print "Success"