Download HTML from URL and Convert to XML

Downloads an HTML page from a URL and converts it to XML.

Download Chilkat Python Library

import sys
import chilkat

#  Note: This example uses two Chilkat products: Chilkat HTTP
#  and Chilkat HTML-to-XML.  The "Chilkat Bundle" can be licensed
#  at a price that is less than purchasing each product individually.
#  The "Chilkat Bundle" provides licenses to all Chilkat components.  Also, new-version upgrades are always free.

http = chilkat.CkHttp()

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

html = http.quickGetStr("http://www.intel.com/")
if (html == None ):
    print http.lastErrorText()
    sys.exit()

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("iso-8859-1")

#  Set the HTML:
htmlToXml.put_Html(html)

#  Convert to XML:

xml = htmlToXml.toXml()

#  Save the XML to a file.
#  Make sure your charset here matches the charset
#  used for the XmlCharset property.
htmlToXml.WriteStringToFile(xml,"out.xml","iso-8859-1")

print "Finished."