实例讲解实现抓取网上房产信息的ASP程序_小偷/采集_

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

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

<%
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","

")
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","

","")
  TempStr=replace(TempStr,"","")
  TempStr=replace(TempStr,"","") 
  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 =""
 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
%>

 

　　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 gotTopic(str,strlen)
 if str="" then
  gotTopic=""
  exit function
 end if
 dim l,t,c, i
 str=replace(replace(replace(replace(str," "," "),""",chr(34)),">",">"),"<","<")
 str=replace(str,"?","")
 l=len(str)
 t=0
 for i=1 to l
  c=Abs(Asc(Mid(str,i,1)))
  if c>255 then
   t=t+2
  else
   t=t+1
  end if
  if t>=strlen then
   gotTopic=left(str,i) & "…"
   exit for
  else
   gotTopic=str
  end if
 next
 gotTopic=replace(replace(replace(replace(gotTopic," "," "),chr(34),"""),">",">"),"<","<")
end function
'=========================================================
'函数：RemoveHTML(strHTML)
'功能：去除HTML标记
'参数：strHTML  --要去除HTML标记的字符串
'=========================================================
Function RemoveHTML(strHTML)
Dim objRegExp, Match, Matches
Set objRegExp = New Regexp

objRegExp.IgnoreCase = True
objRegExp.Global = True
'取闭合的<>
objRegExp.Pattern = "<.+?>"
'进行匹配
Set Matches = objRegExp.Execute(strHTML)

' 遍历匹配集合，并替换掉匹配的项目
For Each Match in Matches
strHtml=Replace(strHTML,Match.Value,"")
Next
RemoveHTML=strHTML
Set objRegExp = Nothing
set Matches=nothing
End Function

%>
 

　　conn.asp

 <%
'on error resume next
set conn=server.CreateObject("adodb.connection")
con= "driver={Microsoft Access Driver (*.mdb)};dbq=" & Server.MapPath("stest.mdb")
conn.open con

sub connclose
   conn.close
   set conn=nothing  
end sub
%>
 

　　附：抓取信息的详细页面事例

"," ")  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,"

","")   TempStr=replace(TempStr,"

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]
提示： 本文由神整理自网络，如有侵权请联系本站删除！ 本站声明： 1、本站所有资源均来源于互联网，不保证100%完整、不提供任何技术支持； 2、本站所发布的文章以及附件仅限用于学习和研究目的;不得将用于商业或者非法用途；否则由此产生的法律后果，本站概不负责！ 上一篇：asp的程序能实现伪静态化的方法_应用技巧_ 下一篇：用QuickWAP组件结合ASP建设Wap站点第1/2页_应用技巧_ 相关内容 asp的程序能实现伪静态化的方法_应用技巧_ 一段ASP 伪静态代码_应用技巧_ asp之字符串操作函数_ASP基础_ asp中实现随机分组程序的代码_应用技巧_ 超级ASP版DataGrid——SkyGrid本地下载_应用技巧_ ASP中怎么实现SQL数据库备份、恢复！_应用技巧_ ASP之简化创建关闭记录集对象并创建使用简单的MSSQL存储过程_存储过程_ 用正则和xmlHttp实现的asp小偷程序_小偷/采集_ 厉害的用Asp获取Dll加密新闻内容_应用技巧_ 用ASP VBS xmlhttp adodbstream下载和保存图片的代码_应用技巧_ 点击排行 唯唯绸否猜打一最佳正确生肖[最佳成语最佳释义解释答] TYSB手游公测版下载-TYSB官方唯一正版手游下载 _安卓网 洗牌猫下载-洗牌猫(卡牌对战)Shuffle Cats v0.14.8_安卓网 士绅名流代表什么生肖，成语释义解释落实 士绅名流代表是指什么生肖数字，成语释义解释落实 丛林动物宝宝发型沙龙游戏-丛林动物宝宝发型沙龙(休闲装扮)Baby Jungle Animal Hair Salon v1.0.10_安卓网 士绅名流是指代表什么生肖、释义成语解释落实 project h试玩版-project h手游试玩版预约 v1.0_安卓网 本栏推荐 pandas获取对应的行或者列方式_python_ pandas如何获取某个数据的行号_python_ python进程池Pool中apply方法与apply_async方法的区别_python_ python array中关于[a，b，c]的使用方式_python_ Python进程multiprocessing.Process()的使用解读_python_ selenium常用API的使用过程记录（包括自动登录）_python_ Python使用multiprocessing如何实现多进程_python_ 猜你喜欢 pandas获取对应的行或者列方式_python_ pandas如何获取某个数据的行号_python_ python进程池Pool中apply方法与apply_async方法的区别_python_ python array中关于[a，b，c]的使用方式_python_ Python进程multiprocessing.Process()的使用解读_python_ selenium常用API的使用过程记录（包括自动登录）_python_ Python使用multiprocessing如何实现多进程_python_