Check if a URL exists testing its header.

checkUrl.php

<?php

function checkUrl($url) {

        if( !extension_loaded('curl')) {
                trigger_error('The curl extension was not loaded.', E_USER_ERROR);
        }
        
        $status = preg_match('/^https?:\/\/([-\w\.]+)+(:\d+)?(\/([\w\/_\.\-?]*(\?\S+)?)?)?$/i', $url);
        if( $status === false ) {
                trigger_error('The preg_match returns a error code: ' . preg_last_error() , E_USER_ERROR);
        } elseif( $status === 0 ) {
                trigger_error('The url given is not valid.' , E_USER_ERROR);
        }

        ob_start();
        $curl = curl_init();

        curl_setopt($curl, CURLOPT_URL, $url);
        curl_setopt($curl, CURLOPT_HEADER, true);
        curl_setopt($curl, CURLOPT_TIMEOUT, 10);
        curl_setopt($curl, CURLOPT_NOBODY, true);
        curl_setopt($curl, CURLOPT_VERBOSE, false);
        curl_setopt($curl, CURLOPT_RETURNTRANSFER, false);
        curl_setopt($curl, CURLOPT_FAILONERROR, true);
        curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
        curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2 GTB5');

        curl_exec($curl);

        curl_close($curl);
        $data = ob_get_clean();

        preg_match("/HTTP\/1\.[1|0]\s(\d{3})/",$data,$matches);

        return ( isset($matches[1]) && $matches[1] == 200 ) ? true : false;
}

// true
var_dump(checkUrl('http://www.google.com.br'));
// true
var_dump(checkUrl('http://www.globo.com'));
// true
var_dump(checkUrl('http://www.gradsch.ohio-state.edu/Depo/ETD_Tutorial/lesson2.pdf'));
// false
var_dump(checkUrl('http://www.globooooooooo.com'));
// false
var_dump(checkUrl('http://www.gradsch.ohio-state.edu/Depo/ETD_Tutorial/lesson2asdasd9a8s7d9as86d.pdf'));

I wonder how this compares to simply opening a socket and reading a couple bytes.