php 爬虫检查,PHP检查搜索引擎蜘蛛爬虫真实性

if(getspider()){

exit('假的搜索引擎！');

}

function getspider(){

$访问UA = strtolower($_SERVER['HTTP_USER_AGENT']);

$访问IP = isset($_SERVER['REMOTE_ADDR']) ? $_SERVER['REMOTE_ADDR'] : '';

if(isset($_SERVER['HTTP_X_FORWARDED_FOR'])){

$list = explode(',', $_SERVER['HTTP_X_FORWARDED_FOR']);

$访问IP = $list[0];

}

if (!ip2long($访问IP)) $访问IP = '未知IP';

$访问主机 = str_replace('.', '-', $访问IP);

if (strpos($访问UA, 'googlebot') !== false){

$解析主机 = gethostbyaddr($_SERVER['REMOTE_ADDR']);

if ($解析主机 != 'crawl-'.$访问主机.'.googlebot.com') return 'googlebot?';

}

if (strpos($访问UA, 'sogou') !== false){

$解析主机 = gethostbyaddr($_SERVER['REMOTE_ADDR']);

if ($解析主机 != 'sogouspider-'.$访问主机.'.crawl.sogou.com') return 'sogou';

}

if (strpos($useragent, 'bing') !== false){

$解析主机 = gethostbyaddr($_SERVER['REMOTE_ADDR']);

if ($解析主机 != 'msnbot-'.$访问主机.'.search.msn.com') return 'bing';

}

if (strpos($访问UA, 'baiduspider') !== false){

$解析主机 = gethostbyaddr($_SERVER['REMOTE_ADDR']);

if ($解析主机 != 'baiduspider-'.$访问主机.'.crawl.baidu.com') return 'baiduspider?';

}

return false;

}

赏

如果文章或资源对您有帮助，欢迎打赏作者。一路走来，感谢有您！