Php add nofollow to links if domains are in the array?

Question

How can i check if in the same string one or many from a list of domains stored in an array are present and link to them?

the array:

array  = ('example.com','domain.com','example.net')

and the text:

Lorem ipsum <a href="http://example.net">dolor sit amet</a>, consectetur adipiscing <a href="http://domain.com">elit</a>. 
Quisque quam urna, <a href="http://example.com/some-page/">hendrerit ut</a> vestibulum sit amet, elementum interdum dolor.

What i want to do is to add nofollow to the links if they are present in the array.

Can somebody help me?

Answer 1

Don't parse HTML with a regex. Use a DOM Parser instead.

function getRootDomain($url) 
{
    // @ http://stackoverflow.com/a/19068356/1438393
    if (!preg_match("~^(?:f|ht)tps?://~i", $url)) {
        $url = "http://" . $url;
    }
    return implode('.', array_slice(explode('.', parse_url($url, PHP_URL_HOST)), -2));
}

// your domains array
$domains = array('example.com','domain.com','example.net');

$dom = new DOMDocument;
$dom->loadHTML($html);
$dom->preserveWhiteSpace = false; 
$dom->formatOutput = true; 

// loop through all links
foreach ($dom->getElementsByTagName('a') as $link) {
    $href = $link->getAttribute('href');
    if (in_array(getRootDomain($href), $domains)) {
        $link->setAttribute('rel', 'nofollow');
    }
}

echo $dom->saveHTML();

Demo!