!-- #include file="conn.ASP" --> !-- #include file="inc/function.asp" --> !DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd" />

电脑技术吧

会员投稿 会员登录 会员注册 网站公告:
搜索: 您现在的位置主页 > 网站开发 > ASP亚博ios下载地址 > ASP基础 > 正文

实例讲解asp抓取网上房产信息(1)

作者:admin    文章来源:互联网 电脑技术吧     点击数:    更新时间:2011-09-27
收藏】 【挑错】 【推荐】 【打印


"http://www.w3.org/TR/html4/loose.dtd">


Untitled Document




<%
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),, [5]$False$

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
getcont=ReadXml(url,"gb2312","")
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","
width=""400"">","
noshade size=""1"" color=""#808080"">
")
NewsContent=RemoveHtml(NewsContent)
NewsContent=replace(NewsContent,VbCrLf,"")
NewsContent=replace(NewsContent,vbNewLine,"")
NewsContent=replace(NewsContent," ","")
NewsContent=replace(NewsContent," ",,点击这里 -->

附:抓取信息的详细页面事例

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


"http://www.w3.org/TR/html4/loose.dtd">


Untitled Document




<%
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 本文来自织梦
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),, [5]$False$

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

内容来自dedecms

dim url,title
url="http://www.***.com"'新闻网址
getcont=ReadXml(url,"gb2312","")
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","
width=""400"">","
noshade size=""1"" color=""#808080"">
")
NewsContent=RemoveHtml(NewsContent)
NewsContent=replace(NewsContent,VbCrLf,"")
NewsContent=replace(NewsContent,vbNewLine,"")
NewsContent=replace(NewsContent," ","")
NewsContent=replace(NewsContent," ",,点击这里
Tags:  
责任编辑:admin
相关文章列表
发表评论 请自觉遵守互联网相关的政策法规,严禁发布色情、暴力、反动的言论。
用户名:密码:新注册
评论总数: [ 查看全部 ] 网友评论