Extract all HTML Objects from a Web Page

Demonstrates how to download a Web page (at a URL) and extract all HTML objects. Eg. images, links, CSS files, JavaScript files, etc.

Download Chilkat MHT ActiveX

<?php

$mht = new COM("Chilkat.Mht");

$success = $mht->UnlockComponent('Anything for 30-day trial');
if ($success != true) {
    print $mht->lastErrorText() . "\n";
    exit;
}

//  Download a URL into an in-memory MHT web archive contained
//  in a string variable:

$mhtDoc = $mht->getMHT('http://www.gopackaging.com/');
if (is_null($mhtDoc)) {
    print $mht->lastErrorText() . "\n";
    exit;
}

//  Now extract the HTML and embedded objects:
$unpackDir = '/Users/chilkat/temp/';
$htmlFilename = 'gopackaging.html';
$partsSubdir = 'objects';
//  Extract to /Users/chilkat/temp/gopackaging.html.
//  images and other embedded objects are placed in
//  /Users/chilkat/temp/objects.  Directories are automatically
//  created if they don't already exist.
$success = $mht->UnpackMHTString($mhtDoc,$unpackDir,$htmlFilename,$partsSubdir);
if ($success != true) {
    print $mht->lastErrorText() . "\n";
}
else {
    print 'Unpacked!' . "\n";
}


?>