Download HTML from URL and Convert to XML

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

Download Chilkat Perl Module

use 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 = new chilkat::CkHttp();

#  Any string argument automatically begins the 30-day trial.
$success = $http->UnlockComponent("30-day trial");
if ($success != 1) {
    print "HTTP component unlock failed" . "\n";
    exit;
}

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

$htmlToXml = new chilkat::CkHtmlToXml();

#  Any string argument automatically begins the 30-day trial.
$success = $htmlToXml->UnlockComponent("30-day trial");
if ($success != 1) {
    print "HtmlToXml component unlock failed" . "\n";
    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." . "\n";