Google PageRank 的checksum新算法

王朝other·作者佚名  2006-01-09
窄屏简体版  字體: |||超大  

在一个国外网站看到的, 先贴出来,有时间的话再仔细分析一下,

并转成jsp语言的,或者asp的

New PageRank Checksum Algorithm

.]

<?php

/*

Written and contributed by

Alex Stapleton,

Andy Doctorow,

Tarakan,

Bill Zeller,

Vijay "Cyberax" Bhatter

traB

This code is released into the public domain

*/

//header("Content-Type: text/plain; charset=utf-8");

define('GOOGLE_MAGIC', 0xE6359A60);

function obtainPR($data)

{

$ret = array();

$parser = xml_parser_create();

xml_parser_set_option($parser,XML_OPTION_CASE_FOLDING,0);

xml_parser_set_option($parser,XML_OPTION_SKIP_WHITE,1);

xml_parse_into_struct($parser,$data,$values,$tags);

xml_parser_free($parser);

$hash_stack = array();

foreach ($values as $key => $val)

{

switch ($val['type'])

{

case 'complete':

array_push($hash_stack, $val['tag']);

$type = implode($hash_stack, "][");

if ($type == "RK")

{

$PageRank = $val[value];

}

array_pop($hash_stack);

break;

}//swhitch

}//foreach

return $PageRank;

}//obtainPR

//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) {

$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) /* 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);

/*-------------------------------------------- report the result */

return $mix[2];

}

//converts a string into an array of integers containing the numeric value of the char

function strord($string) {

for($i=0;$i<strlen($string);$i++) {

$result[$i] = ord($string{$i});

}

return $result;

}

// converts an array of 32 bit integers into an array with 8 bit values. Equivalent to (BYTE *)arr32

function c32to8bit($arr32) {

for($i=0;$i<count($arr32);$i++) {

for ($bitOrder=$i*4;$bitOrder<=$i*4+3;$bitOrder++) {

$arr8[$bitOrder]=$arr32[$i]&255;

$arr32[$i]=zeroFill($arr32[$i], 8);

}

}

return $arr8;

}

// http://www.example.com/ - Checksum: 6540747202

print("<b>URL .... $url</b>\n");

$url = 'info:' . $url;

$ch = GoogleCH(strord($url));

$url_to_parse = sprintf ("http://toolbarqueries.google.com/search?client=navclient-auto&ch=6%u&ie=UTF-8&oe=UTF-8&q=%s", $ch, $url);

$value = obtainPR(file_get_contents($url_to_parse));

printf("<li> <u>Checksum <2.0.114:</u> ..... 6%u ...... <A href=$url_to_parse>link</A> .... PR = $value\n",$ch);

$ch=sprintf("%u", $ch);

// new since Toolbar 2.0.114

$ch = ((($ch/7) << 2) | (((int)fmod($ch,13))&7));

$prbuf = array();

$prbuf[0] = $ch;

for($i = 1; $i < 20; $i++) {

$prbuf[$i] = $prbuf[$i-1]-9;

}

$ch = GoogleCH(c32to8bit($prbuf), 80);

$url_to_parse = sprintf ("http://toolbarqueries.google.com/search?client=navclient-auto&ch=6%u&ie=UTF-8&oe=UTF-8&q=%s", $ch, $url);

$value = obtainPR(file_get_contents($url_to_parse));

//

printf("<li> <u>Checksum >=2.0.114:</u> ..... 6%u ...... <A href=$url_to_parse>link</A> .... PR = $value\n",$ch);

?>

 
 
 
免责声明:本文为网络用户发布,其观点仅代表作者个人观点,与本站无关,本站仅提供信息存储服务。文中陈述内容未经本站证实,其真实性、完整性、及时性本站不作任何保证或承诺,请读者仅作参考,并请自行核实相关内容。
 
 
© 2005- 王朝網路 版權所有 導航