Chilkat2-Python

Download HTML from URL and Convert to XML

See more HTML-to-XML/Text Examples

Downloads an HTML page from a URL and converts it to XML. Chilkat2-Python

import sys
import chilkat2

success = False

# Note: This example requires the Chilkat Bundle license.

# Any string argument automatically begins the 30-day trial.
glob = chilkat2.Global()
success = glob.UnlockBundle("30-day trial")
if (success != True):
    print(glob.LastErrorText)
    sys.exit()

http = chilkat2.Http()

html = http.QuickGetStr("http://www.intel.com/")
if (http.LastMethodSuccess != True):
    print(http.LastErrorText)
    sys.exit()

htmlToXml = chilkat2.HtmlToXml()

# Indicate the charset of the output XML we'll want.
htmlToXml.XmlCharset = "utf-8"

# Set the HTML:
htmlToXml.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.
success = htmlToXml.WriteStringToFile(xml,"qa_output/out.xml","utf-8")

print("Finished.")