实例讲解ASP实现抓取网上房产信息

nt,"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&"<br>")
response.Write("信息类别:"&NewsClass&"<br>")
response.Write("所在城市:"&City&"<br>")
response.Write("房屋具体位置:"&Position&"<br>")
response.Write("房屋类型:"&HouseType&"<br>")
response.Write("楼层:"&Level&"<br>")
response.Write("使用面积:"&Area&"<br>")
response.Write("房价:"&Price&"<br>")
response.Write("其他说明:"&Demostra&"<br>")
response.Write("联系人:"&ContactMan&"<br>")
response.Write("联系方式:"&Contact&"<br>")
''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
%>
</body>
</html>




　　function.asp

<%
''**************************************************
''函数名：gotTopic
''作 用：截字符串，汉字一个算两个字符，英文算一个字符
''参 数：str ----原字符串
'' strlen ----截取长度
''返回值：截取后的字符串
''**************************************************
function gotTo