php抓取关键词排名,如何 用php抓取google关键词排名？

说下思路，利用PHP的curl函数储存cookie，google搜索页面是无法用file_get_connents打开的，必须要完全模拟浏览器才行,百度就不同了，直接用file_get_conntens抓取页面，然后用正则处理下就行了，这里就不列举百度了。[code]<?php

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

functionggsearch($url_s,$keyword,$page=1){

$enKeyword=urlencode($keyword);

$rsState=false;

$page_num=($page-1)*10;

if($page<=10){

$interface="eth0:".rand(1,4);//避免GG封IP

$cookie_file=dirname(__FILE__)."/temp/google.txt";//存储cookie值

$url="http://www.google.com/search?q=$enKeyword&hl=en&prmd=imvns&ei=JPnJTvLFI8HlggeXwbRl&start=$page_num&sa=N";

$ch=curl_init();

curl_setopt($ch,CURLOPT_URL,$url);

//curl_setopt($ch,CURLOPT_USERAGENT,$_SERVER['HTTP_USER_AGENT']);//获取浏览器类型

curl_setopt($ch,CURLOPT_USERAGENT,"Mozilla/5.0(Windows;U;WindowsNT6.1;en-US;rv:1.9.1.2)Gecko/20090729Firefox/3.5.2GTB5");

curl_setopt($ch,CURLOPT_INTERFACE,"$interface");//指定访问IP地址

curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);

curl_setopt($ch,CURLOPT_FOLLOWLOCATION,1);

curl_setopt($ch,CURLOPT_COOKIEJAR,$cookie_file);

$contents=curl_exec($ch);

curl_close($ch);

$match="!

(.*)

\s+!";

preg_match_all("$match","$contents",$line);

while(list($k,$v)=each($line[0])){

preg_match_all("!

]+>(.*?)!",$v,$title);

$num=count($title[1]);

for($i=0;$i

if(strstr($title[0][$i],$url_s)){

$rsState=true;

$j=$i+1;

$sum=$j+(($page)*10-10);

//echo$contents;

echo"关键字".$keyword."
"."排名：".''.$sum.''."####"."第".''.$page.''."页"."第".''.$j.''."名".$title[0][$i]."
";

echo""."点击搜索结果".""."
";

echo"

---

";

break;

}

}

}

unset($contents);

if($rsState===false){

ggsearch($url_s,$keyword,++$page);//找不到搜索页面的继续往下搜索

}

}else{

echo'关键字'.$keyword.'10页之内没有该网站排名'.'
';

echo"

---

";

}

}

if(!empty($_POST['submit'])){

$time=explode('',microtime());

$start=$time[0]+$time[1];

$more_key=trim($_POST['textarea']);

$url_s=trim($_POST['url']);

if(!empty($more_key)&&!empty($url_s)){

/*判断输入字符的规律*/

if(strstr($more_key,"\n")){

$exkey=explode("\n",$more_key);

}

if(strstr($more_key,"|")){

$exkey=explode("|",$more_key);

}

if(!strstr($more_key,"\n")&&!strstr($more_key,"|")){

$exkey=array($more_key);

}

/*判断是否有www或者http://之类的东西*/

if(count(explode('.',$url_s))<=2){

$url=ltrim($url_s,'http://www');

$url='www.'.$url_s;

}

foreach($exkeyas$keyword){

//$keyword;

ggsearch($url_s,$keyword);

}

$endtime=explode('',microtime());

$end=$endtime[0]+$endtime[1];

echo'

---

';

echo'程序运行时间:';

echo$end-$start;

//die();

}

}

?>

-//W3C//DTDXHTML1.0Transitional//EN""http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">

抓取排名

关键字：

格式例如：keyword1|keyword2|keyword3

或者:keyword1

keyword2

keyword3

url地址：