Asp 使用 Microsoft.XMLHTTP 抓取網頁內容(沒用亂碼),并過濾需要的內容
示例源碼:
復制代碼 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 抓取主要內容
strBody = GetBody(strHTML,"div id=""Div_newsContentc"" class=""cnt"">","/div>",0,0)
strBody =Replace(strBody,"(本文首發于","")
strBody =Replace(strBody,"財富動力網/a>,轉載請注明出處。)","")
strBody =Replace(strBody,"本文首發于,轉載請注明出處。)","")
strBody =Replace(strBody,"財富動力網/a>:http://www.927953.com","")
strBody =Replace(strBody,"本文首發于","")
Response.Write RegRemoveHref(strBody)
REM 獲取對應網址響應的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"
'轉換原來默認的UTF-8編碼轉換成GB2312編碼,否則直接用
'XMLHTTP調用有中文字符的網頁得到的將是亂碼
BytesToBstr = objstream.ReadText
objstream.Close
set objstream = nothing
End Function
REM 使用正則表達式,抓取之內標記的內容
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:
您可能感興趣的文章:- 用asp+xmlhttp編寫web采集程序
- asp.net HttpWebRequest自動識別網頁編碼
- Asp.net XMLHTTP封裝類(GET,Post發送和接收數據)
- 運行asp.net時出現 http錯誤404-文件或目錄未找到
- Javascript+XMLHttpRequest+asp.net無刷新讀取數據庫數據
- asp.net利用HttpModule實現防sql注入
- asp.net 模擬提交有文件上傳的表單(通過http模擬上傳文件)
- asp頁面提示Response 對象 錯誤 ASP 0156 : 80004005 HTTP 頭錯誤
- Asp WinHttp.WinHttpRequest.5.1 對象使用詳解 偽造 HTTP 頭信息
- asp中利用xmlhttp抓取網頁內容的代碼
- asp中使用MSXML2.ServerXMLHTTP實現異步請求例子
- 解決ASP中http狀態跳轉返回錯誤頁的問題