KEKSOV

$s = file_get_contents( 'yandex.html' );

$tidy = new tidy();
$tidy->parseString( $s, array(
    'output-xml'       => true,
    'clean'            => true,
    'numeric-entities' => true
), 'utf8' );

$tidy->cleanRepair();
$xml = simplexml_load_string( tidy_get_output( $tidy ) );

$adwords = $xml->xpath( '//*[@class="b-adv"]' );
var_dump( $adwords );
exit;

$tads = $xml->xpath( '//*[@id="tads"]' );
var_dump( $tads );
exit;

$a = $xml->xpath( '//a[@href]' );
//var_dump( $a );

array_walk( $a, function( $item ) {
    $href = $item->attributes()->href;
    if ( strpos( $href, 'start=' ) !== false )
        echo $href."\n";
    //var_dump( $attrs );
    //exit;
} );