实例讲解实现抓取网上房产信息的ASP程序

<%@LANGUAGE="VBSCRIPT" CODEPAGE="936"%>

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>Untitled Document</title>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312">
<meta http-equiv="refresh" content="300;URL=steal_house.asp">
</head>

<body>
<%
on error resume next
'
Server.ScriptTimeout = 999999
'========================================================
'字符编码函数
'====================================================
Function BytesToBstr(body,code)
 dim objstream
 set objstream = Server.CreateObject("adodb.stream")
 objstream.Type = 1
 objstream.Mode =3
 objstream.Open
 objstream.Write body
 objstream.Position = 0
 objstream.Type = 2
 objstream.Charset =code
 BytesToBstr = objstream.ReadText
 objstream.Close
 set objstream = nothing
End Function

'取行字符串在另一字符串中的出现位置
Function Newstring(wstr,strng)
Newstring=Instr(lcase(wstr),lcase(strng))
if Newstring<=0 then Newstring=Len(wstr)
End Function
'替换字符串函数
function ReplaceStr(ori,str1,str2)
ReplaceStr=replace(ori,str1,str2)
end function
'====================================================
function ReadXml(url,code,start,ends)
set oSend=createobject("Microsoft.XMLHTTP")
SourceCode = oSend.open ("GET",url,false)
oSend.send()
ReadXml=BytesToBstr(oSend.responseBody,code )
start=Instr(ReadXml,start)
ReadXml=mid(ReadXml,start)
ends=Instr(ReadXml,ends)
ReadXml=left(ReadXml,ends-1)
end function

function SubStr(body,start,ends)
start=Instr(body,start)
SubStr=mid(body,start+len(start)+1)
ends=Instr(SubStr,ends)
SubStr=left(SubStr,ends-1)
end function

dim getcont,NewsContent
dim url,title
url="http://www.***.com"'新闻网址knowsky.com
getcont=ReadXml(url,"gb2312","<table class=k2 border=""0""","</table>")
getcont=RegexHtml(getcont)
dim KeyId,NewsClass,City,Position,HouseType,Level,Area,Price,Demostra

dim ContactMan,Contact
for i=2 to ubound(getcont)
response.Write(getcont(i)&"__ ")

tempLink=mid(getcont(i),instr(getcont(i),"href=""")+6,instr(getcont(i),""" onClick")-10)
tempLink=replace(tempLink,"../","")

response.Write(i&":"&tempLink&" ")
NewsContent=ReadXml(tempLink,"gb2312","<td valign=""bottom"" width=""400"">","<hr width=""760"" noshade size=""1"" color=""#808080""> ")
NewsContent=RemoveHtml(NewsContent)
NewsContent=replace(NewsContent,VbCrLf,"")
NewsContent=replace(NewsContent,vbNewLine,"")
NewsContent=replace(NewsContent," ","")
NewsContent=replace(NewsContent," ","")
NewsContent=replace(NewsContent," ","")
NewsContent=replace(NewsContent,"\n","")
NewsContent=replace(NewsContent,chr(10),"")
NewsContent=replace(NewsContent,chr(13),"")
'===============get Content=======================
response.Write(NewsContent)
KeyId=SubStr(NewsContent,"列号：","信息类别：")
NewsClass=SubStr(NewsContent,"类别：","所在城市：")
City=SubStr(NewsContent,"城市：","房屋具体位置：")
Position=SubStr(NewsContent,"位置：","房屋类型：")
HouseType=SubStr(NewsContent,"类型：","楼层：")
Level=SubStr(NewsContent,"楼层：","使用面积：")
Area=SubStr(NewsContent,"面积：","房价：")
Price=SubStr(NewsContent,"房价：","其他说明：")
Demostra=SubStr(NewsContent,"说明：","联系人：")
ContactMan=SubStr(NewsContent,"联系人：","联系方式：")
Contact=SubStr(NewsContent,"联系方式：","信息来源：")
response.Write("总序列号:"&KeyId&" ")
response.Write("信息类别:"&NewsClass&" ")
response.Write("所在城市:"&City&" ")
response.Write("房屋具体位置:"&Position&" ")
response.Write("房屋类型:"&HouseType&" ")
response.Write("楼层:"&Level&" ")
response.Write("使用面积:"&Area&" ")
response.Write("房价:"&Price&" ")
response.Write("其他说明:"&Demostra&" ")
response.Write("联系人:"&ContactMH[YHBHZYHHHLB][YHY`9g*9g ]BZYHHH B[OHPTSQLcceB[YHYH[YHBHZYHHHLB][YHY/mcy]BZYHHH B[OHPTSQLccoz-c/9cB[YHYH[YHBHZYHHHLB][YHY/n&]BZYHHH B[OHPTSQLam.B[YHYH[YHBHZYHHHLB][YHYo9l`]BZYHHH B[OHPTSQLakyl`B[YHYH[YHBHZYHHHLB][YHY/oh]BZYHHH B[OHPTSQL;9nllB[YHYH[YHBHZYHHHLB][YHY/&]BZYHHH B[OHPTSQL8`Na`"9.l9ce.!ieB[YHYH[YHBHZYHHHLB][YHYam.#]BZYHHH B[OHPTSQLcc/abyol`l#%a"ya`nl"{+9o9lgeabybak9z-a9/o#9c*9.bak9ayke#9dj:/z+zod9aj8.:`&/"8yg*9+9o9bcy/"{aj9. yn +#9o9az+yc!y-8zod9aj;"y#-z+B[YHYH[YHBHZYHHHLB][YHY e9.]BZYHHH B[OHPTSQLlxB[YHYH[YHBHZYHHHLB][YHY e9yo#]BZYHHH B[OHPTSQLM LMB[YHYH[YHBHZYHHHLB][YHY/k;]BZYHHH B[OHPTSQL KNMMI&NN MB[YHYH[YHBHZYHHHLB][YHYa(yl;]BZYHHH B[OHPTSQLNOOXO