Use this RegEx to get URL's of html:
$url = "http://www.example.net/somepage.html";
$input = @file_get_contents($url) or die("Could not access file: $url");
$regexp = "<a\s[^>]*href=(\"??)([^\" >]*?)\\1[^>]*>(.*)<\/a>";
if(preg_match_all("/$regexp/siU", $input, $matches)) {
// $matches[2] = array of link addresses
// $matches[3] = array of link text - including HTML code
}
?>