PHP统计nginx访问日志中的搜索引擎抓取404链接页面路径

<?php
//访问test.php?s=google
$domain=’https://www.gaodaima.com&#8217;;
$spiders=array(‘baidu’=>’Baiduspider’,’360’=>’360Spider’,
‘google’=>’Googlebot’,’soso’=>’Sosospider’,’sogou’=>
‘Sogou web spider’,’easou’=>’EasouSpider’,’bing’=>’bingbot’);
 
$path=’/home/nginx/logs/’.date(‘Y/m/’).(date(‘d’)-1).’/access_www.txt’;
 
$s=$_GET[‘s’];
 
if(!array_key_exists($s,$spiders)) die();
$spider=$spiders[$s];
 
$file=$s.’_’.date(‘ym’).(date(‘d’)-1).’.txt’;
if(!file_exists($file)){
    $in=file_get_contents($path);
    $pattern=’/GET (.*) HTTP\/1.1″ 404.*’.$spider.’/’;
    preg_match_all ( $pattern , $in , $matches );
    $out=”;
    foreach($matches[1] as $k=>$v){
        $out.=$domain.$v.”\r\n”;
    }
    file_put_contents($file,$out);
}
 
$url=$domain.’/silian/’.$file;
echo $url;