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
|
1
2
3
4
5
6
7
8
|
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：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
|
<?php
$ServerName = $_SERVER["SERVER_NAME"] ;
$ServerPort = $_SERVER["SERVER_PORT"] ;
$ScriptName = $_SERVER["SCRIPT_NAME"] ;
$QueryString = $_SERVER["QUERY_STRING"];
$serverip = $_SERVER["REMOTE_ADDR"] ;
$Url="http://".$ServerName;
if ($ServerPort != "")
{
$Url = $Url.":".$ServerPort ;
}
$Url=$Url.$ScriptName;
if ($QueryString !="")
{
$Url=$Url."?".$QueryString;
}
$GetLocationURL=$Url ;
$agent = $_SERVER["HTTP_USER_AGENT"];
$agent=strtolower($agent);
$Bot ="";
if (strpos($agent,"bot")>-)
{
$Bot = "Other Crawler";
}
if (strpos($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。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
view sourceprint?
<?php
include './robot.php';
include '../library/page.Class.php';
$page = $_GET['page'];
include '../library/conn_new.php';
$count = $mysql -> num_rows($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);
?>
<table width="">
<thead>
<tr>
<td bgcolor="#CCFFFF"></td>
<td bgcolor="#CCFFFF" align="center" style="color:#">爬虫访问时间</td>
<td bgcolor="#CCFFFF" align="center" style="color:#">爬虫分类</td>
<td bgcolor="#CCFFFF" align="center" style="color:#">爬虫IP</td>
<td bgcolor="#CCFFFF" align="center" style="color:#">爬虫访问的URL</td>
</tr>
</thead>
<?php
while($myrow = $mysql -> fetch_array($result)){
?>
<tr>
<td width=""><img src="../images/topicnew.gif" /></td>
<td width="" style="font-family:Georgia"><? echo $myrow["crawler_date"] ?></td>
<td width="" style="color:#FA"><? echo $myrow["crawler_category"] ?></td>
<td width=""><? echo $myrow["crawler_IP"] ?></td>
<td width=""><? echo $myrow["crawler_url"] ?></td>
</tr>
<?php
}
?>
</table>
<?php
echo $pages -> myde_write();
?>
|
以上代码就是PHP代码实现爬虫记录——超管用的全部内容，希望对大家有所帮助。