实例讲解ASP实现抓取网上房产信息

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

1<html>
2<head>
3<title>Untitled Document</title>
4<meta content="text/html; charset=utf-8" http-equiv="Content-Type"/>
5<meta content="300;URL=steal_house.asp" http-equiv="refresh"/>
6</head>
7<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 0""","<="" border="" class="k2" 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 400""="" bottom""="" valign="" width="">","<hr #808080""="" 1""="" 760""="" color="" noshade="" size="" width=""/> ")
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:"&ContactMan&" ")
response.Write("联系方式:"&Contact&" ")
'title=RemoveHTML(aa(i))
'response.Write("title:"&title)
for n=0 to application.Contents.count
if(application.Contents(n)=KeyId) then
ifexit=true
end if
next
if not ifexit then
application(time&i)=KeyId
'添加到数据库
'====================================================
set rs=server.CreateObject("adodb.recordset")
rs.open "select top 1 * from news order by id desc",conn,3,3
rs.addnew
rs("NewsClass")=NewsClass
rs("City")=City
rs("Position")=Position
rs("HouseType")=HouseType
rs("Level")=Level
rs("Area")=Area
rs("Price")=Price
rs("Demostra")=Demostra
rs("ContactMan")=ContactMan
rs("Contact")=Contact
rs.update
rs.close
set rs=nothing
end if
'==================================================

next
function RemoveTag(body)

Set regEx = New RegExp
regEx.Pattern = "<[a].*?</[a]>"
regEx.IgnoreCase = True
regEx.Global = True
Set Matches = regEx.Execute(body)
dim i,arr(15),ifexit
i=0
j=0
For Each Match in Matches
TempStr = Match.Value
TempStr=replace(TempStr,"<td>","")
TempStr=replace(TempStr,"</td>","")
TempStr=replace(TempStr,"<tr>","")
TempStr=replace(TempStr,"</tr>","")
arr(i)=TempStr
i=i+1
if(i>=15) then
exit for
end if
Next
Set regEx=nothing
Set Matches =nothing
RemoveTag=arr

end function
function RegexHtml(body)
dim r_arr(47),r_temp
Set regEx2 = New RegExp
regEx2.Pattern ="<a.*?<\ a="">"
regEx2.IgnoreCase = True
regEx2.Global = True
Set Matches2 = regEx2.Execute(body)
iii=0
For Each Match in Matches2

r_arr(iii)=Match.Value

iii=iii+1
Next
RegexHtml=r_arr
set regEx2=nothing
set Matches2=nothing
end function
'======================================================

conn.close
set conn=nothing

1</a.*?<\></td></table></body>
2</html>

function.asp

 1   
 2'**************************************************   
 3'函数名：gotTopic   
 4'作 用：截字符串，汉字一个算两个字符，英文算一个字符   
 5'参 数：str ----原字符串   
 6' strlen ----截取长度   
 7'返回值：截取后的字符串   
 8'**************************************************   
 9function gotTopic(str,strlen)   
10if str="" then   
11gotTopic=""   
12exit function   
13end if   
14dim l,t,c, i   
15str=replace(replace(replace(replace(str," "," "),""",chr(34)),">",">"),"<","<")   
16str=replace(str,"?","")   
17l=len(str)   
18t=0   
19for i=1 to l   
20c=Abs(Asc(Mid(str,i,1)))   
21if c>255 then   
22t=t+2   
23else   
24t=t+1   
25end if   
26if t>=strlen then   
27gotTopic=left(str,i) & "…"   
28exit for   
29else   
30gotTopic=str   
31end if   
32next   
33gotTopic=replace(replace(replace(replace(gotTopic," "," "),chr(34),"""),">",">"),"<","<")   
34end function   
35'=========================================================   
36'函数：RemoveHTML(strHTML)   
37'功能：去除HTML标记   
38'参数：strHTML --要去除HTML标记的字符串   
39'=========================================================   
40Function RemoveHTML(strHTML)   
41Dim objRegExp, Match, Matches   
42Set objRegExp = New Regexp 
43
44objRegExp.IgnoreCase = True   
45objRegExp.Global = True   
46'取闭合的<>   
47objRegExp.Pattern = "<.+?>"   
48'进行匹配   
49Set Matches = objRegExp.Execute(strHTML) 
50
51' 遍历匹配集合，并替换掉匹配的项目   
52For Each Match in Matches   
53strHtml=Replace(strHTML,Match.Value,"")   
54Next   
55RemoveHTML=strHTML   
56Set objRegExp = Nothing   
57set Matches=nothing   
58End Function

conn.asp

 1   
 2'on error resume next   
 3set conn=server.CreateObject("adodb.connection")   
 4con= "driver={Microsoft Access Driver (*.mdb)};dbq=" & Server.MapPath("stest.mdb")   
 5conn.open con 
 6
 7sub connclose   
 8conn.close   
 9set conn=nothing   
10end sub

附：抓取信息的详细页面事例

总序列号：

479280

---|---

信息类别：

出租

所在城市：

济南

房屋具体位置：

华龙路华信路交界口

房屋类型：

其他

楼层：

六层

使用面积：

24～240 平方米之间

房价：

0 [租赁:元/月,买卖:万元/套]

其他说明：

华信商务楼3至6层小空间对外出租（0.5元/平起），本楼属纯商务办公投资使用，可用于办公写字间，周边设施齐全、交通便利（37、80、K95在本楼前经过），全产权、市证，楼内设施包括水、电、暖、电梯设施齐全，有意者可电讯！

联系人：

鲁、王

联系方式：

88017966、86812217

信息来源：

2005-8-4 8:28:55 来自：218.98.86.175

点击次数：