Tcl

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. Tcl

load ./chilkat.dll

set success 0

# Note: This example requires the Chilkat Bundle license.

# Any string argument automatically begins the 30-day trial.
set glob [new_CkGlobal]

set success [CkGlobal_UnlockBundle $glob "30-day trial"]
if {$success != 1} then {
    puts [CkGlobal_lastErrorText $glob]
    delete_CkGlobal $glob
    exit
}

set http [new_CkHttp]

set html [CkHttp_quickGetStr $http "http://www.intel.com/"]
if {[CkHttp_get_LastMethodSuccess $http] != 1} then {
    puts [CkHttp_lastErrorText $http]
    delete_CkGlobal $glob
    delete_CkHttp $http
    exit
}

set htmlToXml [new_CkHtmlToXml]

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

# Set the HTML:
CkHtmlToXml_put_Html $htmlToXml $html

# Convert to XML:

set xml [CkHtmlToXml_toXml $htmlToXml]

# Save the XML to a file.
# Make sure your charset here matches the charset
# used for the XmlCharset property.
set success [CkHtmlToXml_WriteStringToFile $htmlToXml $xml "qa_output/out.xml" "utf-8"]

puts "Finished."

delete_CkGlobal $glob
delete_CkHttp $http
delete_CkHtmlToXml $htmlToXml