实现爬虫记录本文从创建crawler 数据库，robot.PHP记录来访的爬虫从而将信息插入数据库crawler,然后从数据库中就可以获得所有的爬虫信息。实现代码具体如下：
数据库设计
PHP;">
create table crawler
(
crawler_ID bigint() unsigned not null auto_increment primary key,crawler_category varchar() not null,crawler_date datetime not null default '-- ::',crawler_url varchar() not null,crawler_IP varchar() not null
)default charset=utf;
以下文件 robot.PHP 记录来访的爬虫，并将信息写入数据库：
PHP;">
-)
{
$Bot = "Other Crawler";
}
if (strpos($agent,"googlebot")>-)
{
$Bot = "Google";
}
if (strpos($agent,"mediapartners-google")>-)
{
$Bot = "Google Adsense";
}
if (strpos($agent,"baiduspider")>-)
{
$Bot = "Baidu";
}
if (strpos($agent,"sogou spider")>-)
{
$Bot = "Sogou";
}
if (strpos($agent,"yahoo")>-)
{
$Bot = "Yahoo!";
}
if (strpos($agent,"msn")>-)
{
$Bot = "MSN";
}
if (strpos($agent,"ia_archiver")>-)
{
$Bot = "Alexa";
}
if (strpos($agent,"iaarchiver")>-)
{
$Bot = "Alexa";
}
if (strpos($agent,"sohu")>-)
{
$Bot = "Sohu";
}
if (strpos($agent,"sqworm")>-)
{
$Bot = "AOL";
}
if (strpos($agent,"yodaoBot")>-)
{
$Bot = "Yodao";
}
if (strpos($agent,"iaskspider")>-)
{
$Bot = "Iask";
}
require("./dbinfo.PHP");
date_default_timezone_set('PRC');
$shijian=date("Y-m-d h:i:s",time());
// 连接到 MysqL 服务器
$connection = MysqL_connect ($host,$username,$password);
if (!$connection)
{
die('Not connected : ' . MysqL_error());
}
// 设置活动的 MysqL 数据库
$db_selected = MysqL_select_db($database,$connection);
if (!$db_selected)
{
die ('Can\'t use db : ' . MysqL_error());
}
// 向数据库插入数据
$query = "insert into crawler (crawler_category,crawler_date,crawler_url,crawler_IP) values ('$Bot','$shijian','$GetLocationURL','$serverip')";
$result = MysqL_query($query);
if (!$result)
{
die('Invalid query: ' . MysqL_error());
}
?>
成功了，现在访问数据库即可得知什么时候哪里的蜘蛛爬过你的什么页面。
num_rows($MysqL -> query("select * from crawler"));
$pages = new PageClass($count,$_GET['page'],$_SERVER['PHP_SELF'].'?page={page}');
$sql = "select * from crawler order by ";
$sql .= "crawler_date desc limit ".$pages -> page_limit.",".$pages -> myde_size;
$result = $MysqL -> query($sql);
?>
