<?php
/*
The source code for the PageRank script is below.
Copy & Paste the code between the <?php and ?> tags below into some file with a .php extension, e.g. pagerank.php.
You can use it in PHP as follows. To get the Toolbar PageRank:
    $url = "www.google.com";
    echo "PageRank of " . $url . " is:<br />" . getrank($url);
To use the getrealrank() function, you will need an xmltoarray function. Some can be found at the PHP.net entry for xml_parse_into_struct:    www.php.net/xml_parse_into_struct
    *What the getrealreank() function does is parse the Google XML page for the URL, looking for any <U> tag that matches the URL, or some permutation of it (with or without the http:// prefix, www. prefix, or a trailing slash /). The matching is case-insensitive.
    *It then returns the <RK> value for this item as the "real" pagerank.
    *Because of this, the tool has problems with URLs that are redirected. For example, www.espn.com is redirected to www.espn.go.com; and amazon.com is redirected to something like amazon.com/exec/obidos/subst/home/home.html. Even though Google recognizes this, the getrealrank() function will not.
E.g.:
    $url = "www.google.com";
    echo "The real PageRank of " . $url . " might be: <br />" . getrealrank($url);
*/

/*
    This code is released unto the public domain
    This script is originally from: http://www.googlecommunity.com/scripts/google-pagerank.php
    It is also hosted, and was modified slightly, by: http://www.searchengineengine.com
    The architecture is:
        getrank($url) function - The function called externally to get the PageRank
            strord($url) function - Function called by getrank() to convert the url string into a numeric string
            GoogleCH($numericstring) function - Function called by getrank() to get the checksum of the url
                mix($a, $b, $c) function - Called by GoogleCH() during checksum calculation
                    zeroFill($a, $b) function - Called by mix() during mixing
*/

//header("Content-Type: text/plain; charset=utf-8");        //Uncommenting this makes the file downloadable rather than executable

define("GOOGLE_MAGIC", 0xE6359A60);        //Define the named constant "GOOGLE_MAGIC"

//unsigned shift right
function zeroFill($a, $b) {
    $z = hexdec(80000000);
    if ($z & $a) {
        $a = ($a>>1);
        $a &= (~$z);
        $a |= 0x40000000;
        $a = ($a>>($b-1));
    }
    else {
        $a = ($a>>$b);
    }
    return $a;
}

function mix($a, $b, $c) {        //This function is used in the Google Checksum calculation
    $a -= $b;
    $a -= $c;
    $a ^= (zeroFill($c,13));
    $b -= $c;
    $b -= $a;
    $b ^= ($a<<8);
    $c -= $a;
    $c -= $b;
    $c ^= (zeroFill($b,13));
    $a -= $b;
    $a -= $c;
    $a ^= (zeroFill($c,12));
    $b -= $c;
    $b -= $a;
    $b ^= ($a<<16);
    $c -= $a;
    $c -= $b;
    $c ^= (zeroFill($b,5));
    $a -= $b;
    $a -= $c;
    $a ^= (zeroFill($c,3));
    $b -= $c;
    $b -= $a;
    $b ^= ($a<<10);
    $c -= $a;
    $c -= $b;
    $c ^= (zeroFill($b,15));
    return array($a,$b,$c);
}

function GoogleCH($url, $length=null, $init=GOOGLE_MAGIC) {        //Calculate the Google Checksum for a given URL
    if(is_null($length)) {
        $length = sizeof($url);
    }
    $a = $b = 0x9E3779B9;
    $c = $init;
    $k = 0;
    $len = $length;
    while($len >= 12) {
        $a += ($url[$k+0] +($url[$k+1]<<8) +($url[$k+2]<<16) +($url[$k+3]<<24));
        $b += ($url[$k+4] +($url[$k+5]<<8) +($url[$k+6]<<16) +($url[$k+7]<<24));
        $c += ($url[$k+8] +($url[$k+9]<<8) +($url[$k+10]<<16)+($url[$k+11]<<24));
        $mix = mix($a,$b,$c);
        $a = $mix[0];
        $b = $mix[1];
        $c = $mix[2];
        $k += 12;
        $len -= 12;
    }
    $c += $length;
    switch($len)            /* all the case statements fall through */
    {
        case 11: $c+=($url[$k+10]<<24);
        case 10: $c+=($url[$k+9]<<16);
        case 9 : $c+=($url[$k+8]<<8);
            /* the first byte of c is reserved for the length */
        case 8 : $b+=($url[$k+7]<<24);
        case 7 : $b+=($url[$k+6]<<16);
        case 6 : $b+=($url[$k+5]<<8);
        case 5 : $b+=($url[$k+4]);
        case 4 : $a+=($url[$k+3]<<24);
        case 3 : $a+=($url[$k+2]<<16);
        case 2 : $a+=($url[$k+1]<<8);
        case 1 : $a+=($url[$k+0]);
            /* case 0: nothing left to add */
    }
    $mix = mix($a,$b,$c);
    return $mix[2];
}

function strord($string) {        //converts a string into an array of integers containing the numeric value of the char
    for($i=0;$i<strlen($string);$i++) {
        $result[$i] = ord($string{$i});
    }
    return $result;
}

function getrank($url, $prefix="info:", $datacenter="www.google.com") {                //This is the function used to get the PageRank value.
        //If $prefix is "info:", then the Toolbar pagerank will be returned.
        //$datacenter sets the datacenter to get the results from. e.g., "www.google.com", "216.239.53.99", "66.102.11.99".
    $url = $prefix.$url;
    $ch = GoogleCH(strord($url));        //Get the Google checksum for $url using the GoogleCH function.
    $file = "http://$datacenter/search?client=navclient-auto&ch=6$ch&features=Rank&q=$url";
        //To get the Crawl Date instead of the PageRank, change "&features=Rank" to "&features=Crawldate"
        //To get detailed XML results, remove "&features=Rank"
    $oldlevel = error_reporting(0);        //Suppress error reporting temporarily.
    $data = file($file);
    error_reporting($oldlevel);            //Restart error reporting.
    if(!$data || preg_match("/(.*)\.(.*)/i", $url)==0) return "N/A";            //If the Google data is unavailable, or the URL is invalid, return "N/A".
        //The preg_match check is a very basic url validator that only checks if the URL has a period in it.
    $rankarray = explode (":", $data[2]);        //There are two line breaks before the PageRank data on the Google page.
    $rank = trim($rankarray[2]);        //Trim whitespace and line breaks.
    if($rank=="") return "N/A";            //Return N/A if no rank.
    return $rank;
}

function getrealrank($url, $datacenter="www.google.com"){
    $ch = GoogleCH(strord($url));
    $array = xmltoarray("http://$datacenter/search?client=navclient-auto&ch=6$ch&q=$url");
    $infoarray = $array['GSP'][0]['RES'][0]['R'];
    $nonwwwurl = str_replace("www.", "", $url);
    $urlpermutationsarray = array($url, "http://".$url, "http://www.".$url, $url."/", "http://".$url."/", "http://www.".$url."/", $nonwwwurl, "http://".$nonwwwurl, "http://www.".$nonwwwurl, $nonwwwurl."/", "http://".$nonwwwurl."/", "http://www.".$nonwwwurl."/");
    for($i=0; $i<count($infoarray); $i++){
        $urlU = $infoarray[$i]['U'];        //U is the URL. UE is the 'clean' URL.
        $urlrank = $infoarray[$i]['RK'];
        foreach($urlpermutationsarray as $permutation){
            if(strtolower($permutation)==strtolower($urlU)) return $urlrank;        //Case insensitive match.
        }
    }
    return "Unknown";        //If no matches found.
}

$url = "habrahabr.ru";
echo "PageRank of ".$url." is:<br />".getrank($url);


?>

   if(!$data || preg_match("/(.*)\.(.*)/i", $url)==0) return "N/A";            //If the Google data is unavailable, or the URL is invalid, return "N/A".
        //The preg_match check is a very basic url validator that only checks if the URL has a period in it.
    $rankarray = explode (":", $data[2]);        //There are two line breaks before the PageRank data on the Google page.
    $rank = trim($rankarray[2]);        //Trim whitespace and line breaks.
    if($rank=="") return "N/A";            //Return N/A if no rank.

<?php
	define('GOOGLE_MAGIC', 0xE6359A60);

		function _zeroFill($a, $b){
			$z = hexdec(80000000);
			if ($z & $a){
				$a = ($a>>1);
				$a &= (~$z);
				$a |= 0x40000000;
				$a = ($a>>($b-1));
			}else
				$a = ($a>>$b);
			return $a;
		}

		function _mix($a,$b,$c){
			$a -= $b; $a -= $c; $a ^= (_zeroFill($c,13));
			$b -= $c; $b -= $a; $b ^= ($a<<8);
			$c -= $a; $c -= $b; $c ^= (_zeroFill($b,13));
			$a -= $b; $a -= $c; $a ^= (_zeroFill($c,12));
			$b -= $c; $b -= $a; $b ^= ($a<<16);
			$c -= $a; $c -= $b; $c ^= (_zeroFill($b,5));
			$a -= $b; $a -= $c; $a ^= (_zeroFill($c,3));
			$b -= $c; $b -= $a; $b ^= ($a<<10);
			$c -= $a; $c -= $b; $c ^= (_zeroFill($b,15));
			return array($a,$b,$c);
		}

		function _GoogleCH($url, $length=null, $init=GOOGLE_MAGIC){
			if(is_null($length))
				$length = sizeof($url); 
			$a = $b = 0x9E3779B9;
			$c = $init;
			$k = 0;
			$len = $length;
			while($len >= 12){
				$a += ($url[$k+0] +($url[$k+1]<<8) +($url[$k+2]<<16) +($url[$k+3]<<24));
				$b += ($url[$k+4] +($url[$k+5]<<8) +($url[$k+6]<<16) +($url[$k+7]<<24));
				$c += ($url[$k+8] +($url[$k+9]<<8) +($url[$k+10]<<16)+($url[$k+11]<<24));
				$_mix = _mix($a,$b,$c);
				$a = $_mix[0]; $b = $_mix[1]; $c = $_mix[2];
				$k += 12;
				$len -= 12;
			}
			$c += $length;
			switch($len){
				case 11: $c+=($url[$k+10]<<24);
				case 10: $c+=($url[$k+9]<<16);
				case 9 : $c+=($url[$k+8]<<8);
				case 8 : $b+=($url[$k+7]<<24);
				case 7 : $b+=($url[$k+6]<<16);
				case 6 : $b+=($url[$k+5]<<8);
				case 5 : $b+=($url[$k+4]);
				case 4 : $a+=($url[$k+3]<<24);
				case 3 : $a+=($url[$k+2]<<16);
				case 2 : $a+=($url[$k+1]<<8);
				case 1 : $a+=($url[$k+0]);
			}
			$_mix = _mix($a,$b,$c);
			return $_mix[2];
		}

		function _strord($string){
			for($i=0;$i<strlen($string);$i++)
				$result[$i] = ord($string{$i});
			return $result;
		}

		function getPageRank($url){
			$pagerank = -1;
			$ch = "6"._GoogleCH(_strord("info:" . $url));
			$fp = fsockopen("www.google.com", 80, $errno, $errstr, 30);
			if($fp){
				$out = "GET /search?client=navclient-auto&ch=" . $ch .  "&features=Rank&q=info:" . $url . " HTTP/1.1\r\n";
				$out .= "Host: www.google.com\r\n";
				$out .= "Connection: Close\r\n\r\n";
				fwrite($fp, $out);
				while (!feof($fp)){
					$data = fgets($fp, 128);
					$pos = strpos($data, "Rank_");
					if($pos === false){
					}else
						$pagerank = substr($data, $pos + 9);
				}
				fclose($fp);
			}
			return $pagerank;
		}
?>

<?php
/**
 * @link	http://info.sectorit.net
 * @version	2011-01-26
 */

/**
 * Конвертируем строку в 32-bit
 * @param	string	$str
 * @param	hex		$check
 * @param	hex		$magic
 * @return	integer
 */
function strToNum($str, $check, $magic)
{
	$int32Unit = 4294967296;  // 2^32

	$length = strlen($str);
	for ($i = 0; $i < $length; $i++) {
		$check *= $magic;
		/**
		 * Если выпадаем за граници инта (обычно +/- 2.15e+9 = 2^31), то
		 * получим undefined, читать ниже по ссылке:
		 * http://www.php.net/manual/en/language.types.integer.php
		 * потому танцуем с бубном
		 */
		if ($check >= $int32Unit) {
			$check = ($check - $int32Unit * (int) ($check / $int32Unit));
			//if the check less than -2^31
			$check = ($check < -2147483648) ? ($check + $int32Unit) : $check;
		}
		$check += ord($str{$i});
	}
	return $check;
}

/**
 * Получаем хеш URL-а
 * @param	string	$string
 * @return	integer
 */
function hashUrl($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);
}

/**
 * Получаем чексум URL-а
 * @param	integer	$Hashnum	хеш URL-а
 * @return	integer
 */
function checkHash($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;
}

/**
 * Получаем PR с одного из сайтов гугла "закосив" под мозиллу
 * @param	string	$url	URL страницы
 */
function getPR($url)
{
	if ( ! preg_match('/^(http:\/\/)(.*)/i', $url)) {
		$url = 'http://' . $url;
	}
	$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';

	$ch = checkHash(hashUrl($url));
	/**
	 * Используя сокеты, вероятность бана снижается до 0,
	 * темболее что едим только 30 первых символов ;)
	 */
	$fp = fsockopen($googlehost, 80, $errno, $errstr, 30);
	if ($fp) {
		$out = "GET /tbr?client=navclient-auto&ch=$ch&features=Rank&q=info:$url HTTP/1.1\r\n";
		$out .= "User-Agent: $googleua\r\n";
		$out .= "Host: $googlehost\r\n";
		$out .= "Connection: Close\r\n\r\n";

		fwrite($fp, $out);

		while ( ! feof($fp)) {
			$data = fgets($fp, 128);
			// ПР идёт в строке Rank_1:1:Х где Х наш ПР
			$pos = strpos($data, "Rank_");
			if($pos === false){} else{
				fclose($fp);
				$pr=substr($data, $pos + 9);
				$pr=trim($pr);
				$pr=str_replace("\n",'',$pr);
				return $pr ? $pr : '0';
			}
		}
		fclose($fp);
	}
}