您的位置：首页 > 编程语言 > PHP开发

关于如何判断是不是百度或者其它搜索引擎蜘蛛的php代码

2013-03-01 16:22 519 查看

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>无标题文档</title>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
<link rel="stylesheet" type="text/css" href="/c3.css" />
<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
<meta http-equiv="Content-Language" content="zh-cn" />
<meta name="robots" content="all" />
<meta name="author" content="lunanzuche.com" />
<meta name="Copyright" content="Copyright www.lunanzuche.com All Rights Reserved." />
<meta name="MSSmartTagsPreventParsing" content="true" />
<meta http-equiv="imagetoolbar" content="false" />

</head>

<body>
<?PHP
/**
* 判断是否为搜索引擎蜘蛛
*
* @author Eddy
* @return bool
*/
function isCrawler(){
$agent= strtolower($_SERVER['HTTP_USER_AGENT']);
if (!empty($agent)) {
$spiderSite= array(
"TencentTraveler",
"Baiduspider+",
"BaiduGame",
"Googlebot",
"msnbot",
"Sosospider+",
"Sogou web spider",
"ia_archiver",
"Yahoo! Slurp",
"YoudaoBot",
"Yahoo Slurp",
"MSNBot",
"Java (Often spam bot)",
"BaiDuSpider",
"Voila",
"Yandex bot",
"BSpider",
"twiceler",
"Sogou Spider",
"Speedy Spider",
"Google AdSense",
"Heritrix",
"Python-urllib",
"Alexa (IA Archiver)",
"Ask",
"Exabot",
"Custo",
"OutfoxBot/YodaoBot",
"yacy",
"SurveyBot",
"legs",
"lwp-trivial",
"Nutch",
"StackRambler",
"The web archive (IA Archiver)",
"Perl tool",
"MJ12bot",
"Netcraft",
"MSIECrawler",
"WGet tools",
"larbin",
"Fish search",
);
foreach($spiderSite as $val) {
$str = strtolower($val);
if (strpos($agent, $str) !== false) {
return true;
}
}
}else {
return false;
}
}
?>
</body>
</html>

以上主要就是根据函数进行判断

内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理

标签：

相关文章推荐

新的分享

章节导航