пузомерка выдачи яндекса

наваял тут для себя, для упрощения - может кому пригодится? =)

потребуется snoopy.class.php, качать с sourceforge

под Windows работает сразу из под NuSphere или стандартной php для.

заводите в формочку запросов в n-м количестве, он сразу выдает сайты с замеренными pr, cy, tr, ссылки по yahoo, Я.каталог из топ10 серпа яндекса.

pr и ссылки работают всегда, параметры Яндекса - только по ночам, так как Я.xml не пользует для анонимности, а bar-navig у Яндекса работает еле-еле, ибо ресурсы у них не резиновые

все функции - рабочие, отлаженные. может кому пригодятся в дальнейшем. выдидать - легко.

<?php

include("snoopy.class.php");

function cp1251_utf8( $sInput ) {

    $sOutput = "";

    for ( $i = 0; $i < strlen( $sInput ); $i++ )

    {

        $iAscii = ord( $sInput[$i] );

        if ( $iAscii >= 192 && $iAscii <= 255 )

            $sOutput .=  "&#".( 1040 + ( $iAscii - 192 ) ).";";

        else if ( $iAscii == 168 )

            $sOutput .= "&#".( 1025 ).";";

        else if ( $iAscii == 184 )

            $sOutput .= "&#".( 1105 ).";";

        else

            $sOutput .= $sInput[$i];

    }

    return $sOutput;

}

function parse_cook($hdr) {

    $ihdr = Array('path' => '','domain' => '','name' => '','val' => '','exp' => '');

    $texp = explode("expires=", $hdr);

    $ihdr['exp'] = $texp[1];

    $hdr = $hdr.";";

    $ctmp = explode(" ", $hdr);

    $carr = array();

    foreach ($ctmp as $tmp) $carr[] = substr($tmp, 0, strlen($tmp)-1);

    $tmp  = explode("=", $carr[1]);

    $ihdr['name'] = $tmp[0];

    $ihdr['val']  = $tmp[1];

    $tmp = explode("=", $carr[2]);

    $ihdr['path'] = $tmp[1];

    $tmp = explode("=", $carr[3]);

    $ihdr['domain'] = $tmp[1];

    return $ihdr;

}



$googlehost='toolbarqueries.google.com';

$googleua='Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.0.6) Gecko/20060728 Firefox/1.5';



function StrToNum($Str, $Check, $Magic) {

    $Int32Unit = 4294967296;

    $length = strlen($Str);

    for ($i = 0; $i < $length; $i++) {

        $Check *= $Magic; 	

        if ($Check >= $Int32Unit) {

            $Check = ($Check - $Int32Unit * (int) ($Check / $Int32Unit));

            $Check = ($Check < -2147483648) ? ($Check + $Int32Unit) : $Check;

        }

        $Check += ord($Str{$i}); 

    }

    return $Check;

}



function HashURL($String) {

    $Check1 = StrToNum($String, 0x1505, 0x21);

    $Check2 = StrToNum($String, 0, 0x1003F);

    $Check1 >>= 2; 	

    $Check1 = (($Check1 >> 4) & 0x3FFFFC0 ) | ($Check1 & 0x3F);

    $Check1 = (($Check1 >> 4) & 0x3FFC00 ) | ($Check1 & 0x3FF);

    $Check1 = (($Check1 >> 4) & 0x3C000 ) | ($Check1 & 0x3FFF);	

    $T1 = (((($Check1 & 0x3C0) << 4) | ($Check1 & 0x3C)) <<2 ) | ($Check2 & 0xF0F );

    $T2 = (((($Check1 & 0xFFFFC000) << 4) | ($Check1 & 0x3C00)) << 0xA) | ($Check2 & 0xF0F0000 );

    return ($T1 | $T2);

}



function CheckHash($Hashnum) {

    $CheckByte = 0;

    $Flag = 0;

    $HashStr = sprintf('%u', $Hashnum) ;

    $length = strlen($HashStr);

    for ($i = $length - 1;  $i >= 0;  $i --) {

        $Re = $HashStr{$i};

        if (1 === ($Flag % 2)) {              

            $Re += $Re;     

            $Re = (int)($Re / 10) + ($Re % 10);

        }

        $CheckByte += $Re;

        $Flag ++;	

    }

    $CheckByte %= 10;

    if (0 !== $CheckByte) {

        $CheckByte = 10 - $CheckByte;

        if (1 === ($Flag % 2) ) {

            if (1 === ($CheckByte % 2)) {

                $CheckByte += 9;

            }

            $CheckByte >>= 1;

        }

    }

    return '7'.$CheckByte.$HashStr;

}

function getch($url) { return CheckHash(HashURL($url)); }

function getpr($url) {

	global $googlehost,$googleua;

	$ch = getch($url);

	$fp = fsockopen($googlehost, 80, $errno, $errstr, 30);

	if ($fp) {

	   $out = "GET /search?client=navclient-auto&ch=$ch&features=Rank&q=info:$url HTTP/1.1\r\n";

	   //echo "<pre>$out</pre>\n"; //debug only

	   $out .= "User-Agent: $googleua\r\n";

	   $out .= "Host: $googlehost\r\n";

	   $out .= "Connection: Close\r\n\r\n";

	

	   fwrite($fp, $out);

	   

	   //$pagerank = substr(fgets($fp, 128), 4); //debug only

	   //echo $pagerank; //debug only

	   while (!feof($fp)) {

			$data = fgets($fp, 128);

			//echo $data;

			$pos = strpos($data, "Rank_");

			if($pos === false){} else{

				$pr=substr($data, $pos + 9);

				$pr=trim($pr);

				$pr=str_replace("\n",'',$pr);

				return $pr;

			}

	   }

	   //else { echo "$errstr ($errno)<br />\n"; } //debug only

	   fclose($fp);

	}

}



function get_cy($cyrl) {

	$res = Array();

	$sn = new Snoopy;

	$sn->agent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)";

	$sn->fetch("http://bar-navig.yandex.ru/u?ver=2&show=32&url=".$cyrl);

	$pattern = "/\s*rang\s*=\s*([\"\'])? (?(1) (.*?)\\1 | ([^\s\>]+))/isx";

	preg_match_all($pattern, $sn->results, $matches);

	$res['yr'] = $matches[2][0];

	if ($res['yr'] == '') $rec['yr'] = '-';

	$pattern = "/\s*value\s*=\s*([\"\'])?(?(1) (.*?)\\1 | ([^\s\>]+))/isx";

	preg_match_all($pattern, $sn->results, $matches);

	$res['cy'] = $matches[2][0];

	if ($res['cy'] == '') $rec['cy'] = '-';

	$pattern = "/\s*url\s*=\s*([\"\'])?(?(1) (.*?)\\1 | ([^\s\>]+))/isx";

	preg_match_all($pattern, $sn->results, $matches);

	$res['cat'] = $matches[2][0];

	if ($res['cat'] == '') $res['cat'] = '-';

	return $res;

}



function yahoo_pages($url) {

	$yahurl = urlencode($url);

	$sn = new Snoopy;

	$sn->agent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SP1 )";

	$sn->fetch("http://siteexplorer.search.yahoo.com/search?p=$yahurl&bwm=i&bwmf=s&bwmo=&fr2=seo-rd-se");

	$pattern = "/<strong>Inlinks\s\(([\w,]*)\)<\/strong>/";

	preg_match_all($pattern, $sn->results, $matches);

	$res = $matches[1][0];

	if ($res == '') $res = '*';

	return $res;

}



if ($_REQUEST['url'] == '') {

	header('Content-Type: text/html; charset=windows-1251');

    print "

    <form action=yandex.php method=POST>

    <textarea name=url rows=20 cols=100></textarea><br/>

    <input type=submit>

    </form>

    ";

}

elseif ($_REQUEST['url'] != '') {

	$url = $_REQUEST['url'];

	$snoopy = new Snoopy;

	$snoopy->agent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)";

	header('Content-Type: text/html; charset=utf-8');

	print "<style>body{font-family:Arial; font-size:11px;} h6 {margin:0px; font-family:Arial; font-size:16px;} td {margin:4px; padding:4px; height: 24px; font-family:Arial; font-size:11px;} a {font-family:Arial; font-size:11px;}</style>";

	print "<a href=/>/root/</a><br/><br/>";

	$url = $url."\n";

	$query = explode("\n", $url);

	$links = Array();

	print "/ ";

	foreach ($query as $tmp) {

			$links[] = $tmp;

			if ($tmp != '') print cp1251_utf8($tmp)." / ";

	}

	print "<br><table width=100% cellspacing=1 cellpadding=0 bgcolor=#999 border=0>\n"; 

	$yakey = '';

	foreach ($links as $url) {

		if ($url != "") {

			print cp1251_utf8("<tr bgcolor=#e0e0e0><td colspan=8><h6>$url</h6></td></tr>");

			print cp1251_utf8("<tr bgcolor=#eeeeee><td width=1>#</td><td>Заголовок</td><td>Страница</td><td width=1>PR</td><td width=1>тИЦ</td><td width=1>Я.Ранг</td><td align=center>Я.Каталог</td><td>Yahoo Links</td></tr>");

			$count = 0;

			$yakey = '';

			$url = urlencode($url);

			$snoopy->fetch("http://www.yandex.ru");

			while(list($key,$val) = each($snoopy->headers)) if ($key == "3: Set-Cookie") $yakey = $val;

			$ya = parse_cook($yakey);

			$snoopy->cookies[$ya['name']] = $ya['val'];

			$snoopy->fetch("http://www.yandex.ru/yandsearch?text=".$url);

			$pattern = "/<a\s[^>]*href=\"([^\"]*)\"[^>]*>(.*)<\/a>/siU";

			preg_match_all($pattern, $snoopy->results, $matches);

			for ($i=0; $i<count($matches[0]); $i++)

			{

				$link2 = $matches[2][$i];

				$link1 = $matches[1][$i];

				$link0 = $matches[0][$i];

				$link = parse_url($link1);   

            	if ($link['host'] != '' && stripos($link0, 'tabindex=') != '') { 

            		$count++;

            		$pr = getpr($link1);

            		sleep(rand(8));

            		$ya = get_cy($link1);

            		$pages = yahoo_pages($link1);

            		print "<tr bgcolor=white><td>$count</td><td>$link2</td><td><a href=$link1><font color=green>$link1</font></a></td><td>$pr</td>";

					print "<td>".$ya['cy']."</td><td>".$ya['yr']."</td>";

					print "<td align=center><font color=green>".$ya['cat']."</font></a></td>";

					$link1 = urlencode($link1);

					print "<td><a href='http://siteexplorer.search.yahoo.com/search?p=$link1&bwm=i&bwmf=s&bwmo=&fr2=seo-rd-se'>$pages</a></td>";

					print "</tr>";

				}

			}

		}

	}

	print "</table><br/>";

	print cp1251_utf8("<font color=green>Программа успешно завершила свою работу.</font>");              

}

?>