Usa questa libreria: http://simplehtmldom.sourceforge.net/
Codice PHP:
require 'simple_html_dom.php';
$output = array();
$html = file_get_html('tobeparsed.html');
foreach ( $html->find('a') as $anchor ) {
$output[] = array(
'link' => $anchor->href,
'title' => $anchor->innertext,
);
}
print_r($output);