How to add rel=“nofollow” to links with preg_replace()

Question

The function below is designed to apply rel=\"nofollow\" attributes to all external links and no internal links unless the path matches a predefined root URL de

Answer 1

Thanks @alex for your nice solution. But, I was having a problem with Japanese text. I have fixed it as following way. Also, this code can skip multiple domains with the $whiteList array.

public function addRelNoFollow($html, $whiteList = [])
{
    $dom = new \DOMDocument();
    $dom->preserveWhiteSpace = false;
    $dom->loadHTML(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'));
    $a = $dom->getElementsByTagName('a');

    /** @var \DOMElement $anchor */
    foreach ($a as $anchor) {
        $href = $anchor->attributes->getNamedItem('href')->nodeValue;
        $domain = parse_url($href, PHP_URL_HOST);

        // Skip whiteList domains
        if (in_array($domain, $whiteList, true)) {
            continue;
        }

        // Check & get existing rel attribute values
        $noFollow = 'nofollow';
        $rel = $anchor->attributes->getNamedItem('rel');
        if ($rel) {
            $values = explode(' ', $rel->nodeValue);
            if (in_array($noFollow, $values, true)) {
                continue;
            }
            $values[] = $noFollow;
            $newValue = implode($values, ' ');
        } else {
            $newValue = $noFollow;
        }

        // Create new rel attribute
        $rel = $dom->createAttribute('rel');
        $node = $dom->createTextNode($newValue);
        $rel->appendChild($node);
        $anchor->appendChild($rel);
    }

    // There is a problem with saveHTML() and saveXML(), both of them do not work correctly in Unix.
    // They do not save UTF-8 characters correctly when used in Unix, but they work in Windows.
    // So we need to do as follows. @see https://stackoverflow.com/a/20675396/1710782
    return $dom->saveHTML($dom->documentElement);
}