XMLHTTP批量抓取遠(yuǎn)程資料
2020-07-27 13:28:39
供稿：網(wǎng)友
可以在此基礎(chǔ)上結(jié)合正則表達(dá)式做成更好的效果，希望大家能分享一下Xmlhttp的session共享技術(shù)
<html>
<head>
<title>AUTOGET</title>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312">
</head>
<body bgcolor="#FFFFFF" style="font-family:Arial;font-size:12px">
<%
'=================================================
'FileName: Getit.Asp
'Intro : Auto Get Data From Remote WebSite
'Author: Babyt(阿泰)
'URL: http://blog.csdn.net/babyt
'createAt: 2002-02 Lastupdate:2004-09
'DB Table : data
'Table Field:
' UID -> Long -> Keep ID Of the pages
' UContent -> Text -> Keep Content Of the Pages(HTML)
'=================================================
Server.ScriptTimeout=5000
'on error resume next
Set conn = Server.createObject("ADODB.Connection")
conn.open "Provider=Microsoft.Jet.OLEDB.4.0;Data Source=" & Server.MapPath("getit.mdb")
Set rs = Server.createObject("ADODB.Recordset")
sql="select * from data"
rs.open sql,conn,1,3
Dim comeFrom,myErr,myCount
'========================================================
comeFrom="http://www.xxx.com/U.asp?ID="
myErr1="該資料不存在"
myErr2="該資料已隱藏"
'========================================================
'***************************************************************
' 只需要更改這里 i 的始點(diǎn)intMin和終點(diǎn)intMax,設(shè)定步長(zhǎng)intStep
' 每次區(qū)間設(shè)置成5萬(wàn)左右。估計(jì)要兩個(gè)多小時(shí)。期間不需要人工干預(yù)
'****************************************************************
intMin=0
intMax=10000
'設(shè)定步長(zhǎng)
intStep=100
'==========================================================
'以下代碼不要更改
'==========================================================
Call GetPart (intMin)
Response.write "已經(jīng)轉(zhuǎn)換完成" & intMin & "~~" & intMax & "之間的數(shù)據(jù)"
rs.close
Set rs=Nothing
conn.Close
set conn=nothing
%>
</body>
</html>
<%
'使用XMLHTTP抓取地址并進(jìn)次內(nèi)容處理
Function GetBody(Url)
Dim objXML
On Error Resume Next
Set objXML = createObject("Microsoft.XMLHTTP")
With objXML
.Open "Get", Url, False, "", ""
.Send
GetBody = .ResponseBody
End With
GetBody=BytesToBstr(GetBody,"GB2312")
Set objXML = Nothing
End Function
'使用Adodb.Stream處理二進(jìn)制數(shù)據(jù)
Function BytesToBstr(strBody,CodeBase)
dim objStream
set objStream = Server.createObject("Adodb.Stream")
objStream.Type = 1
objStream.Mode =3
objStream.Open
objStream.Write strBody
objStream.Position = 0
objStream.Type = 2
objStream.Charset = CodeBase
BytesToBstr = objStream.ReadText
objStream.Close
set objStream = nothing
End Function
'主函數(shù)
Function GetPart(iStart)
Dim iGo
time1=timer()
myCount=0
For iGo=iStart To iStart+intStep
If iGo<=intMax Then
Response.Execute comeFrom & iGo
'進(jìn)行簡(jiǎn)單的數(shù)據(jù)處理
content = GetBody(comeFrom & iGo )
content = Replace(content,chr(34),""")
If instr(content,myErr1) OR instr(content,myErr2) Then
'跳過(guò)錯(cuò)誤信息
Else
'寫(xiě)入數(shù)據(jù)庫(kù)
rs.AddNew
rs("UID")=iGo
'********************************
rs("UContent")=Replace(content,""",chr(34))
'*********************************
rs.update
myCount=myCount+1
Response.Write iGo & "<BR>"
Response.Flush
End If
Else
Response.write "<font color=red>成功抓取"&myCount&"條記錄,"
time2=timer()
Response.write "耗時(shí):" & Int(FormatNumber((time2-time1)*1000000,3)) & " 秒</font><BR>"
Response.Flush
Exit Function
End If
Next
Response.write "<font color=red>成功抓取"&myCount&"條記錄,"
time2=timer()
Response.write "耗時(shí):" & CInt(FormatNumber((time2-time1),3)) & " 秒</font><BR>"
Response.Flush
'遞歸
GetPart(iGo+1)
End Function%>
