(Ruby) Download HTML from URL and Convert to XML
Downloads an HTML page from a URL and converts it to XML.
require 'chilkat'
# Note: This example requires the Chilkat Bundle license.
# Any string argument automatically begins the 30-day trial.
glob = Chilkat::CkGlobal.new()
success = glob.UnlockBundle("30-day trial")
if (success != true)
print glob.lastErrorText() + "\n";
exit
end
http = Chilkat::CkHttp.new()
html = http.quickGetStr("http://www.intel.com/")
if (http.get_LastMethodSuccess() != true)
print http.lastErrorText() + "\n";
exit
end
htmlToXml = Chilkat::CkHtmlToXml.new()
# Indicate the charset of the output XML we'll want.
htmlToXml.put_XmlCharset("utf-8")
# 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.
success = htmlToXml.WriteStringToFile(xml,"qa_output/out.xml","utf-8")
print "Finished." + "\n";
|