现在网上的采集程序很多，但是有时候你发现一个好的网站，想自己做个采集工具采集一些信息，就需要自己去写程序了，其实这样的采集程序并不难写，主要是去分析源网站的网页结构。
首先去下载个XMLHTTP的类文件：
<%
Class xhttp
private cset,sUrl,sError
Private Sub Class_Initialize()
'cset="UTF-8"
cset="GB2312"
sError=""
end sub
Private Sub Class_Terminate()
End Sub
Public Property LET URL(theurl)
sUrl=theurl
end property
public property GET BasePath()
BasePath=mid(sUrl,1,InStrRev(sUrl,"/")-1)
end property
public property GET FileName()
FileName=mid(sUrl,InStrRev(sUrl,"/")+1)
end property
public property GET Html()
Html=BytesToBstr(getBody(sUrl))
end property
public property GET xhttpError()
xhttpError=sError
end property
private Function BytesToBstr(body)
on error resume next
'Cset:GB2312 UTF-8
dim objstream
set objstream = Server.CreateObject("adodb.stream")
with objstream
.Type = 1 '
.Mode = 3 '
.Open
.Write body '
.Position = 0 '
.Type = 2 '
.Charset = Cset '
BytesToBstr = .ReadText '
.Close
end with
set objstream = nothing
End Function
private function getBody(surl)
on error resume next
dim xmlHttp
'Set xmlHttp=server.createobject("Msxml2.XMLHTTP.4.0")
'set xmlHttp=server.createobject("Microsoft.XMLHTTP")
set xmlHttp=server.createobject("MSXML2.ServerXMLHTTP")
xmlHttp.setTimeouts 10000,10000,10000,30000
xmlHttp.open "GET",surl,false
xmlHttp.send
if xmlHttp.readystate=4 then
'if xmlHttp.status=200 then
getBody=xmlhttp.responsebody
'end if
else
getBody=""
end if
if Err.Number<>0 then
sError=Err.Number
Err.clear
else
sError=""
end if
set xmlHttp=nothing
end function
Public function saveimage(tofile,isoverwrite)
on error resume next
dim objStream,objFSO,imgs
if Not isoverwrite Then
Set objFSO = Server.CreateObject("Scripting.FileSystemObject")
If objFSO.FileExists(Server.MapPath(tofile)) Then
Exit Function
End If
Set objFSO = Nothing
End IF
imgs=getBody(sUrl)
Set objStream = Server.CreateObject("ADODB.Stream")
with objStream
.Type =1
.Open
.write imgs
.SaveToFile server.mappath(tofile),2
.Close()
end with
set objstream=nothing
end function
end class
%>
用了这个类文件，做起事情来就方便多了。
然后就可以分析采集网站的网页结构，写采集程序了。
下面给个例子：
<!--#include file="conn.asp"-->
<!--#include file="inc/xhttp_class.asp"-->
<!--#include file="inc/function.asp"-->
<%
server.ScriptTimeout = 1000
%>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
<title>BT采集器</title>
</head>
<body>
<form name="form1" method="post" action="get81bt.asp">
分类ID：
<input type="text" name="cid" value="<%=request("cid")%>"><br>
开始ID：
<input type="text" name="startid" value="<%=request("startid")%>">
<br>
结束ID：
<input type="text" name="overid" value="<%=request("overid")%>">
<br>
分类名称：<input type="text" name="classname" value="<%=request("classname")%>">为空自动获取
<br>
<input name="action" type="hidden" id="action" value="getdata">
<input type="submit" name="Submit" value="采集">
</form>
当前ID：<%=request("id")%> <br>
<%
dim action
action = Request("action")
if action = "getdata" then
cid = Request("cid")
startid = Request("startid")
overid = Request("overid")
id = Request("id")
if id = "" then id = startid
set objxhttp = new xhttp
objxhttp.URL = "http://www.81dd.com/Class/"&cid&"_"&id&".htm"
content = objxhttp.Html
if InStr(content,"网站维护中") then
call NextID
response.End()
end if
list = GetContent(content,"<!--内容开始-->","<!--内容结束-->",0)
Dim regEx, Match, Matches,patrn
Set regEx = New RegExp
patrn = "<a href=""../BtHtml/(.+?)"">"
regEx.Pattern = patrn
regEx.IgnoreCase = True
regEx.Global = True
Set Matches = regEx.Execute(list)
on error resume next
For Each Match in Matches
'response.write Match.Value & "<br>"
weburl = "http://www.81dd.com/BtHtml/" & regEx.Replace(Match.Value,"$1")
response.write weburl & "<br>"
response.Flush()
objxhttp.URL = weburl
cpage = objxhttp.Html
cpage = GetContent(cpage,"<!--内容开始-->","<!--内容结束-->",0)
title = GetContent(cpage,"BT资源名称：<strong>","</strong>",0)
title = stripHTML(title)
IF Request("classname") <> "" then
classname = Request("classname")
Else
if InStr(title,"喜剧") then
classname = "喜剧"
Elseif InStr(title,"动作") then
classname = "动作"
Elseif InStr(title,"惊悚") then
classname = "惊悚"
Elseif InStr(title,"犯罪") then
&n