当前位置: 移动技术网 > IT编程>开发语言>PHP > Google PR查询接口checksum新算法第1/2页

Google PR查询接口checksum新算法第1/2页

2019年05月09日  | 移动技术网IT编程  | 我要评论

google本身提供了查询指定的url的pagerank值的接口,知道了这个接口,就可以很容易编写脚本在页面上实现这一功能,而无需再依赖google toolbar才能进行查询。本文提供了一个用php实现的pr查询接口。同时修正了大部分版本中存在的 linux 操作系统及64位操作系统下无法正常生成checksum的问题。

使用很简单,只要在需要的地方

<?php
include_once("./pr.inc.php");
echo getpr($urltoquery);
?>

即可显示出指定url的pagerank的数值。知道了这个数值再在其基础上模拟出google toolbar上面的图形化的pr显示也就不是难事了。实际上实现原理说白了也很简单,就是传递特定的查询参数到google的搜索引擎,然后抓取返回的页面内容。

演示页面请参见 :

本文代码素材来源:  ;newgch方法实现参考于firefox的工具栏的相关代码实现。

网上还有一个开源的pr状态查询的项目:  , 可以从cvs上直接抓取完整的源代码(cvs用户密码 guest):

cvs -d :pserver:guest@mozdev.org:/cvs login
cvs -d :pserver:guest@mozdev.org:/cvs co pagerankstatus

一个专门提供pr显示接口的网站:

------------------------------------------------------------------

pr.inc.php源文件如下(updated 2008-05-04 14:29 -- google修改了checksum的计算算法,需要在原有的gch方法之后再套一层newgch方法来得到正确的checksum,同时引发的php int overflow及64位机器兼容性问题请参照以下源代码的变化部分):


复制代码 代码如下:

<?php
// url get method macro.
define('g_pr_get_type_file', 1); // use fopen() function
define('g_pr_get_type_socket', 2); // use standard fsocketopen function
// main function to be called
function getpr($_url,$gettype=g_pr_get_type_socket){
$url = 'info:'.$_url;
$ch = gch(strord($url));
$ch = newgch($ch);
$url=str_replace("_","%5f",'info:'.urlencode($_url));
$googleprurl =
"http://toolbarqueries.google.com/search?client=navclient-auto&ch=6"
.$ch."&ie=utf-8&oe=utf-8&features=rank&q=".$url;
$pr_str = retrieveurlcontent($googleprurl,$gettype);
return substr($pr_str,strrpos($pr_str, ":")+1);
}
//unsigned shift right
function zerofill($a, $b){
$z = hexdec('8'.implode('',array_fill(0,php_int_size*2-1,'0')));
if ($z & $a){
$a = ($a>>1);
$a &= (~$z);
$a |= hexdec('4'.implode('',array_fill(0,php_int_size*2-1,'0')));
$a = ($a>>($b-1));
}
else{
$a = ($a>>$b);
}
return $a;
}
// discard bits beyonds 32 bit.
function trunkbitforce32bit($n){
if(php_int_size <= 4){
settype($n,'float');
if ( $n < 0 ) $n += 4294967296;
return $n;
}
else{
$clearbit = '';
for($i=0;$i<php_int_size-4;$i++){
$clearbit .= '00';
}
for($i=0;$i<4;$i++){
$clearbit .= 'ff';
}
return ($n & hexdec($clearbit));
}
}
function bigxor($m,$n){
//if(function_exists('gmp_init')){
// return floatval(gmp_strval(gmp_xor($m,$n)));
//}
//else{
return $m ^ $n;
//}
}
function mix($a,$b,$c){
$a = trunkbitforce32bit($a);
$b = trunkbitforce32bit($b);
$c = trunkbitforce32bit($c);
$a -= $b; $a = trunkbitforce32bit($a);
$a -= $c; $a = trunkbitforce32bit($a);
$a = bigxor($a,(zerofill($c,13))); $a = trunkbitforce32bit($a);
$b -= $c; $b = trunkbitforce32bit($b);
$b -= $a; $b = trunkbitforce32bit($b);
$b = bigxor($b,trunkbitforce32bit($a<<8)); $b = trunkbitforce32bit($b);
$c -= $a; $c = trunkbitforce32bit($c);
$c -= $b; $c = trunkbitforce32bit($c);
$c = bigxor($c,(zerofill($b,13))); $c = trunkbitforce32bit($c);
$a -= $b;$a = trunkbitforce32bit($a);
$a -= $c;$a = trunkbitforce32bit($a);
$a = bigxor($a,(zerofill($c,12)));$a = trunkbitforce32bit($a);
$b -= $c;$b = trunkbitforce32bit($b);
$b -= $a;$b = trunkbitforce32bit($b);
$b = bigxor($b,trunkbitforce32bit($a<<16));
$c -= $a; $c = trunkbitforce32bit($c);
$c -= $b; $c = trunkbitforce32bit($c);
$c = bigxor($c,(zerofill($b,5))); $c = trunkbitforce32bit($c);
$a -= $b;$a = trunkbitforce32bit($a);
$a -= $c;$a = trunkbitforce32bit($a);
$a = bigxor($a,(zerofill($c,3)));$a = trunkbitforce32bit($a);
$b -= $c;$b = trunkbitforce32bit($b);
$b -= $a;$b = trunkbitforce32bit($b);
$b = bigxor($b,trunkbitforce32bit($a<<10));
$c -= $a; $c = trunkbitforce32bit($c);
$c -= $b; $c = trunkbitforce32bit($c);
$c = bigxor($c,(zerofill($b,15))); $c = trunkbitforce32bit($c);
return array($a,$b,$c);
}
function newgch($ch){
$ch = ( trunkbitforce32bit( ( $ch / 7 ) << 2 ) |
( ( myfmod( $ch,13 ) ) & 7 ) );
$prbuf = array();
$prbuf[0] = $ch;
for( $i = 1; $i < 20; $i++ )
{
$prbuf[$i] = $prbuf[$i-1] - 9;
}
$ch = gch( c32to8bit( $prbuf ) );
return $ch;
}
function myfmod($x,$y){
$i = floor( $x / $y );
return ( $x - $i * $y );
}
function c32to8bit($arr32){
$arr8 = array();
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 $arr8;
}
function gch($url, $length=null){
if(is_null($length)) {
$length = sizeof($url);
}
$init = 0xe6359a60;
$a = 0x9e3779b9;
$b = 0x9e3779b9;
$c = 0xe6359a60;
$k = 0;
$len = $length;
$mixo = array();
while( $len >= 12 ){
$a += ($url[$k+0] +trunkbitforce32bit($url[$k+1]<<8)
+trunkbitforce32bit($url[$k+2]<<16)
+trunkbitforce32bit($url[$k+3]<<24));
$b += ($url[$k+4] +trunkbitforce32bit($url[$k+5]<<8)
+trunkbitforce32bit($url[$k+6]<<16)
+trunkbitforce32bit($url[$k+7]<<24));
$c += ($url[$k+8] +trunkbitforce32bit($url[$k+9]<<8)
+trunkbitforce32bit($url[$k+10]<<16)
+trunkbitforce32bit($url[$k+11]<<24));
$mixo = mix($a,$b,$c);
$a = $mixo[0]; $b = $mixo[1]; $c = $mixo[2];
$k += 12;
$len -= 12;
}
$c += $length;
switch( $len ) {
case 11:
$c += trunkbitforce32bit($url[$k+10]<<24);
case 10:
$c+=trunkbitforce32bit($url[$k+9]<<16);
case 9 :
$c+=trunkbitforce32bit($url[$k+8]<<8);
case 8 :
$b+=trunkbitforce32bit($url[$k+7]<<24);
case 7 :
$b+=trunkbitforce32bit($url[$k+6]<<16);
case 6 :
$b+=trunkbitforce32bit($url[$k+5]<<8);
case 5 :
$b+=trunkbitforce32bit($url[$k+4]);
case 4 :
$a+=trunkbitforce32bit($url[$k+3]<<24);
case 3 :
$a+=trunkbitforce32bit($url[$k+2]<<16);
case 2 :
$a+=trunkbitforce32bit($url[$k+1]<<8);
case 1 :
$a+=trunkbitforce32bit($url[$k+0]);
}
$mixo = mix( $a, $b, $c );
$mixo[2] = trunkbitforce32bit($mixo[2]);
if( $mixo[2] < 0 ){
return (
hexdec('1'.
implode('',
array_fill(0,php_int_size*2,'0')))
+ $mixo[2] );
}
else{
return $mixo[2];
}
}
// converts a string into an array of integers
// containing the numeric value of the char
function strord($string){
for($i=0;$i<strlen($string);$i++){
$result[$i] = ord($string{$i});
}
return $result;
}
// return url page content or false if failed.
function retrieveurlcontent($url,$gettype){
switch($gettype){
case g_pr_get_type_file:
return retrieveurlcontentbyfile($url);
break;
default:
return retrieveurlcontentbysocket($url);
break;
}
}
function retrieveurlcontentbyfile($url){
$fd = @fopen($url,"r");
if(!$fd){
return false;
}
$result = "";
while($buffer = fgets($fd, 4096)) {
$result .= $buffer;
}
fclose($fd);
return $result;
}
function retrieveurlcontentbysocket($url,
$host="",
$port=80,
$timeout=30){
if($host == ""){
if(!($pos = strpos($url,'://'))){
return false;
}
$host = substr( $url,
$pos+3,
strpos($url,'/',$pos+3) - $pos - 3);
$uri = substr($url,strpos($url,'/',$pos+3));
}
else{
$uri = $url;
}
$request = "get ".$uri." http/1.0\r\n"
."host: ".$host."\r\n"
."accept: */*\r\n"
."user-agent: zealget\r\n"
."\r\n";
$shnd = @fsockopen ($host, $port, $errno, $errstr, $timeout);
if(!$shnd){
return false;
}
@fputs ($shnd, $request);
// get source
$result = "";
while (!feof($shnd)){
$result .= fgets($shnd,4096);
}
fclose($shnd);
$headerend = strpos($result,"\r\n\r\n");
if (is_bool($headerend))
{
return $result;
}
else{
return substr($result,$headerend+4);
}
}

made in zeal 转载请保留原始链接:
2

如对本文有疑问, 点击进行留言回复!!

相关文章:

验证码:
移动技术网