Mike Nott

function singlethread_crawl($url)
    {
        $agent = “Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)”;

        $ch = curl_init();

        curl_setopt($ch, CURLOPT_NOSIGNAL, 1);
        curl_setopt($ch, CURLOPT_NOPROGRESS, 1);
        curl_setopt($ch, CURLOPT_FAILONERROR, 1);
        curl_setopt($ch, CURLOPT_URL, $url);
        curl_setopt($ch, CURLOPT_USERAGENT, $agent);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0);
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
        curl_setopt($ch, CURLOPT_MAXREDIRS, 1);
        curl_setopt($ch, CURLOPT_TIMEOUT, 5);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);

        $html = curl_exec($ch);

        curl_close ($ch);

        return $html;
    }

    function multithread_crawl($urls, $timeout)
    {
        $agent = “Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)”;

        $mh = curl_multi_init();

        foreach ($urls as $i => $url)
        {
            $conn[$i] = curl_init($url);
            curl_setopt($conn[$i], CURLOPT_RETURNTRANSFER, 1);
            curl_setopt($conn[$i], CURLOPT_NOSIGNAL, 1);
            curl_setopt($conn[$i], CURLOPT_NOPROGRESS, 1);
            curl_setopt($conn[$i], CURLOPT_FAILONERROR, 1);
            curl_setopt($conn[$i], CURLOPT_URL, $url);
            curl_setopt($conn[$i], CURLOPT_USERAGENT, $agent);
            curl_setopt($conn[$i], CURLOPT_SSL_VERIFYPEER, 0);
            curl_setopt($conn[$i], CURLOPT_FOLLOWLOCATION, 1);
            curl_setopt($conn[$i], CURLOPT_MAXREDIRS, 1);
            curl_setopt($conn[$i], CURLOPT_TIMEOUT, $timeout);

            curl_multi_add_handle ($mh, $conn[$i]);
        }

        do
        {
            $mrc = curl_multi_exec($mh, $active);
        }
        while ($mrc == CURLM_CALL_MULTI_PERFORM);

        while ($active and $mrc == CURLM_OK)
        {
            if (curl_multi_select($mh) != -1)
            {
                do
                {
                    $mrc = curl_multi_exec($mh, $active);
                }
                while ($mrc == CURLM_CALL_MULTI_PERFORM);
            }
        }

        if ($mrc != CURLM_OK)
        {
            print “Curl multi read error $mrc\n“;
        }

        $res = array();
        $e = 0;

        foreach ($urls as $i => $url)
        {
            if (($err = curl_error($conn[$i])) == ”)
            {
                $res[$i]=curl_multi_getcontent($conn[$i]);
            }
            else
            {
                echo “error: “.$url.” (”.$err.“)\n“;
            }

            curl_multi_remove_handle($mh,$conn[$i]);
            curl_close($conn[$i]);
        }

        curl_multi_close($mh);

        return $res;
    }

        function googleresults($ip, $search, $num){

                $url = “http://”.$ip.“/ie?q=”.urlencode($search).“&num=”.$num;

                $html = singlethread_crawl($url);

                preg_match_all(“/\” href=(.*)>/iU”, $html, $links);

                $urlarray = str_replace(“<b>”,“”,$links[1]);
                $urlarray = str_replace(“</b>”,“”,$urlarray);
                $urlarray = preg_replace(“/>.*$/i”,“”, $urlarray);

                return $urlarray;
        }

        function googleresults_multi($ips, $search, $num){

        for ($i=0; $i < count($ips); $i++)
        {
                    $urls[$i] = “http://”.$ips[$i].“/ie?q=”.urlencode($search).“&num=”.$num;
        }

                $html = multithread_crawl($urls, count($ips)/2);

        for ($i=0; $i < count($ips); $i++)
        {
                    preg_match_all(“/\” href=(.*)>/iU”, $html[$i], $links[$i]);

                    $urlarray[$i] = str_replace(“<b>”,“”,$links[$i][1]);
                    $urlarray[$i] = str_replace(“</b>”,“”,$urlarray[$i]);
                    $urlarray[$i] = preg_replace(“/>.*$/i”,“”, $urlarray[$i]);
        }

                return $urlarray;
        }

        function removehttp($url){

                if ((substr($url,0,7) == ‘http://’) || (substr($url,0,8) == ‘https://’))
                {
                        $url = substr($url,7);
                }

                $url = trim($url);

                return $url;
        }

        function rank($arr, $item){

                for ($i = 0; $i < count($arr); $i++)
                {
                        if (eregi($item,$arr[$i]))
                        {
                                $result = $i+1;

                                break;
                        }
                }

                return($result);
        }

    $ips = array(“64.233.161.99″, “64.233.161.104″, “64.233.161.105″, “64.233.161.106″, “64.233.161.107″, “64.233.161.147″, “64.233.163.99″, “64.233.163.104″, “64.233.167.99″, “64.233.167.104″, “64.233.167.106″, “64.233.167.107″, “64.233.167.147″, “64.233.171.99″, “64.233.171.104″, “64.233.171.105″, “64.233.171.106″, “64.233.171.107″, “64.233.171.147″, “64.233.179.99″, “64.233.179.104″, “64.233.179.106″, “64.233.179.107″, “64.233.183.99″, “64.233.183.104″, “64.233.183.107″, “64.233.185.99″, “64.233.185.104″, “64.233.185.106″, “64.233.185.107″, “64.233.187.99″, “64.233.187.104″, “64.233.187.106″, “64.233.187.107″, “64.233.189.104″, “66.102.7.99″, “66.102.7.104″, “66.102.7.105″, “66.102.7.106″, “66.102.7.107″, “66.102.7.147″, “66.102.9.99″, “66.102.9.104″, “66.102.9.106″, “66.102.9.107″, “66.102.9.147″, “66.102.11.99″, “66.102.11.104″, “66.102.11.106″, “66.102.11.107″, “66.249.81.99″, “66.249.81.104″, “66.249.81.106″, “66.249.81.107″, “66.249.83.99″, “66.249.83.104″, “66.249.83.106″, “66.249.83.107″, “66.249.85.99″, “66.249.85.104″, “66.249.85.106″, “66.249.85.107″, “66.249.87.99″, “66.249.87.104″, “66.249.89.99″, “66.249.89.104″, “66.249.89.106″, “66.249.89.107″, “66.249.93.99″, “66.249.93.104″, “66.249.93.106″, “66.249.93.107″, “72.14.203.99″, “72.14.203.104″, “72.14.203.106″, “72.14.203.107″, “72.14.205.99″, “72.14.205.104″, “72.14.205.106″, “72.14.205.107″, “72.14.207.99″, “72.14.207.104″, “72.14.207.106″, “72.14.207.107″, “216.239.37.99″, “216.239.37.104″, “216.239.37.105″, “216.239.37.106″, “216.239.37.107″, “216.239.37.147″, “216.239.39.99″, “216.239.39.104″, “216.239.39.106″, “216.239.39.107″, “216.239.53.99″, “216.239.53.104″, “216.239.53.106″, “216.239.53.107″, “216.239.57.98″, “216.239.57.99″, “216.239.57.103″, “216.239.57.104″, “216.239.57.105″, “216.239.57.106″, “216.239.57.107″, “216.239.57.147″, “216.239.59.98″, “216.239.59.99″, “216.239.59.103″, “216.239.59.104″, “216.239.59.105″, “216.239.59.106″, “216.239.59.107″, “216.239.59.147″, “216.239.63.99″, “216.239.63.104″);

    $query = array(“porn”, “pills”, “casino”);

    $num = “100″;

    for ($i=0; $i < count($query); $i++)
    {
        echo $query[$i].“\n“;

        $numrank = array();

//        $serps = googleresults_multi($ips, $query[$i], $num);   //for multithreaded

        for ($j=0; $j < count($ips); $j++)
        {
            $serps[$j] = googleresults($ips[$j], $query[$i], $num);       //for single threaded

            $pos = rank($serps[$j], “www.mattcutts.com”);

            if (empty($pos)){$pos = 0;}

            if (empty($numrank[$pos]))
            {
                $numrank[$pos] = 1;
            }else{
                $numrank[$pos] = $numrank[$pos]+1;
            }
        }

        ksort($numrank);

        foreach ($numrank as $key => $num)
        {
            echo $key.” - “.$num.“\n“;
        }
    }