Perl

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. Perl

use chilkat();

$success = 0;

# 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 != 1) {
    print $glob->lastErrorText() . "\r\n";
    exit;
}

$http = chilkat::CkHttp->new();

$html = $http->quickGetStr("http://www.intel.com/");
if ($http->get_LastMethodSuccess() != 1) {
    print $http->lastErrorText() . "\r\n";
    exit;
}

$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." . "\r\n";