Asp 使用 Microsoft.XMLHTTP 抓取網(wǎng)頁內(nèi)容并過濾需要的

2024-05-04 10:59:35

字體：大中小

供稿：網(wǎng)友

Asp 使用 Microsoft.XMLHTTP 抓取網(wǎng)頁內(nèi)容(沒用亂碼)，并過濾需要的內(nèi)容

示例源碼：
復(fù)制代碼代碼如下:
<%
Dim xmlUrl,http,strHTML,strBody
xmlUrl = Request.QueryString("u")

REM 異步讀取XML源
Set http = server.CreateObject("Microsoft.XMLHTTP")
http.Open "POST",xmlUrl,false
http.setrequestheader "User-Agent", "Mozilla/4.0"
http.setrequestheader "Connection", "Keep-Alive"
http.setRequestHeader "Content-Type", "application/x-www-form-urlencoded"
http.Send()

strHTML = BytesToBstr(http.ResponseBody)
set http = nothing

REM 抓取主要內(nèi)容
strBody = GetBody(strHTML,"<div id=""Div_newsContentc"" class=""cnt"">","</div>",0,0)
strBody =Replace(strBody,"（本文首發(fā)于","")
strBody =Replace(strBody,"財(cái)富動(dòng)力網(wǎng)</a>，轉(zhuǎn)載請(qǐng)注明出處。）","")
strBody =Replace(strBody,"本文首發(fā)于，轉(zhuǎn)載請(qǐng)注明出處。）","")
strBody =Replace(strBody,"財(cái)富動(dòng)力網(wǎng)</a>:http://www.927953.com","")
strBody =Replace(strBody,"本文首發(fā)于","")

Response.Write RegRemoveHref(strBody)

REM 獲取對(duì)應(yīng)網(wǎng)址響應(yīng)的HTML
Function BytesToBstr(body)
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 = "UTF-8"

'轉(zhuǎn)換原來默認(rèn)的UTF-8編碼轉(zhuǎn)換成GB2312編碼，否則直接用
'XMLHTTP調(diào)用有中文字符的網(wǎng)頁得到的將是亂碼
BytesToBstr = objstream.ReadText
objstream.Close
set objstream = nothing
End Function

REM 使用正則表達(dá)式，抓取之內(nèi)標(biāo)記的內(nèi)容
Function GetBody(ConStr,StartStr,OverStr,IncluL,IncluR)
If ConStr="$False$" or ConStr="" or IsNull(ConStr)=True Or StartStr="" or IsNull(StartStr)=True Or OverStr="" or IsNull(OverStr)=True Then
GetBody="$False$"
Exit Function
End If
Dim ConStrTemp
Dim Start,Over
ConStrTemp=Lcase(ConStr)
StartStr=Lcase(StartStr)
OverStr=Lcase(OverStr)
Start = InStrB(1, ConStrTemp, StartStr, vbBinaryCompare)
If Start<=0 then
GetBody="$False$"
Exit Function
Else
If IncluL=False Then
Start=Start+LenB(StartStr)
End If
End If
Over=InStrB(Start,ConStrTemp,OverStr,vbBinaryCompare)
If Over<=0 Or Over<=Start then
GetBody="$False$"
Exit Function
Else
If IncluR=True Then
Over=Over+LenB(OverStr)
End If
End If
GetBody=MidB(ConStr,Start,Over-Start)
End Function

REM 過濾a超鏈接
Function RegRemoveHref(HTMLstr)
Set ra = New RegExp
ra.IgnoreCase = True
ra.Global = True
ra.Pattern = "<a[^>]+>(.+?)<//a>"

RegRemoveHref = Replace(ra.replace(HTMLstr,"$1"),"href=""http://www.927953.com""","")
END Function
%>

效果圖如下：