- simplexml_load_string: documentation ( source)
- print_r: documentation ( source)
- parse_url: documentation ( source)
<?php
$pattern = "/(?<=href=(\"|'))[^\"']+(?=(\"|'))/";
$string = "<a class=\"hola\" href=\"link1\">Hola qué tal 1</a>";
$string .= "<a class=\'hola\' href=\'link2\'>Hola qué tal 2</a>";
$string .= "<a class=\"hola\" href=\"link3\">Hola qué tal 3</a>";
$string .= "<a class=\"hola\" href=\"link4\">Hola qué tal 4</a>";
$xml = simplexml_load_string($string);
$list = $xml->xpath("//@href");
$preparedUrls = array();
foreach($list as $item) {
$item = parse_url($item);
$preparedUrls[] = $item['scheme'] . '://' . $item['host'] . '/';
}
print_r($preparedUrls);