Download HTML from URL and Convert to XML

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

Download Chilkat HTML-to-XML ActiveX (also includes HTML-to-PlainText conversion)

Download Chilkat HTTP ActiveX

<?php

//  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 existing Chilkat components.  Also, new-version upgrades are always free.

$http = new COM("Chilkat.Http");

//  Any string argument automatically begins the 30-day trial.
$success = $http->UnlockComponent('30-day trial');
if ($success != true) {
    print $http->lastErrorText() . "\n";
    exit;
}

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

$htmlToXml = new COM("Chilkat.HtmlToXml");

//  Any string argument automatically begins the 30-day trial.
$success = $htmlToXml->UnlockComponent('30-day trial');
if ($success != true) {
    print $htmlToXml->lastErrorText() . "\n";
    exit;
}

//  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.
$htmlToXml->WriteStringToFile($xml,'out.xml','utf-8');

print 'Finished.' . "\n";
?>