Get Referenced Domains

Demonstrates how to accumulate a list of unique domain names referenced from outbound URLs.

Download Chilkat Spider ActiveX

<?php

//  The Chilkat Spider component/library is free.
$spider = new COM("Chilkat.Spider");

$domainList = new COM("Chilkat.CkStringArray");

//  Set the Unique property so that duplicates are not added.
$domainList->Unique = true;

//  Crawl the home page of joelonsoftware.com and get the outbound URLs
$spider->Initialize('www.joelonsoftware.com');
$spider->AddUnspidered('http://www.joelonsoftware.com/');

$success = $spider->CrawlNext();

//  Build a list of unique domains.

for ($i = 0; $i <= $spider->NumOutboundLinks - 1; $i++) {
    $url = $spider->getOutboundLink($i);
    $domainList->Append($spider->getDomain($url));
}

//  Display the domains.
for ($i = 0; $i <= $domainList->Count - 1; $i++) {
    print $domainList->getString($i) . "\n";
}

?>