XMLHTTP批量抓取远程资料
网络编程 2021-07-05 10:57www.168986.cn编程入门
可以在此基础上结合正则表达式做成更好的效果，希望大家能分享一下Xmlhttp的session共享技术
<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./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 eFrom,myErr,myCount
'========================================================
eFrom="http://.xxx./U.asp?ID="
myErr1="该资料不存在"
myErr2="该资料已隐藏"
'========================================================
'
' 只需要更改这里 i 的始点intMin和终点intMax,设定步长intStep
' 每次区间设置成5万左右。估计要两个多小时。期间不需要人工干预
'
intMin=0
intMax=10000
'设定步长
intStep=100
'==========================================================
'以下代码不要更改
'==========================================================
Call GetPart (intMin)
Response.write "已经转换完成" & intMin & "~~" & intMax & "之间的数据"
rs.close
Set rs=Nothing
conn.Close
set conn=nothing
%>
</body>
</html>
<%
'使用XMLHTTP抓取地址并进次内容处理
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处理二进制数据
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
'主函数
Function GetPart(iStart)
Dim iGo
time1=timer()
myCount=0
For iGo=iStart To iStart+intStep
If iGo<=intMax Then
Response.Execute eFrom & iGo
'进行简单的数据处理
content = GetBody(eFrom & iGo )
content = Replace(content,chr(34),""")
If instr(content,myErr1) OR instr(content,myErr2) Then
'跳过错误信息
Else
'写入数据库
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&"条记录,"
time2=timer()
Response.write "耗时:" & 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&"条记录,"
time2=timer()
Response.write "耗时:" & CInt(FormatNumber((time2-time1),3)) & " 秒</font><BR>"
Response.Flush
'递归
GetPart(iGo+1)
End Function%>
<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./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 eFrom,myErr,myCount
'========================================================
eFrom="http://.xxx./U.asp?ID="
myErr1="该资料不存在"
myErr2="该资料已隐藏"
'========================================================
'
' 只需要更改这里 i 的始点intMin和终点intMax,设定步长intStep
' 每次区间设置成5万左右。估计要两个多小时。期间不需要人工干预
'
intMin=0
intMax=10000
'设定步长
intStep=100
'==========================================================
'以下代码不要更改
'==========================================================
Call GetPart (intMin)
Response.write "已经转换完成" & intMin & "~~" & intMax & "之间的数据"
rs.close
Set rs=Nothing
conn.Close
set conn=nothing
%>
</body>
</html>
<%
'使用XMLHTTP抓取地址并进次内容处理
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处理二进制数据
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
'主函数
Function GetPart(iStart)
Dim iGo
time1=timer()
myCount=0
For iGo=iStart To iStart+intStep
If iGo<=intMax Then
Response.Execute eFrom & iGo
'进行简单的数据处理
content = GetBody(eFrom & iGo )
content = Replace(content,chr(34),""")
If instr(content,myErr1) OR instr(content,myErr2) Then
'跳过错误信息
Else
'写入数据库
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&"条记录,"
time2=timer()
Response.write "耗时:" & 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&"条记录,"
time2=timer()
Response.write "耗时:" & CInt(FormatNumber((time2-time1),3)) & " 秒</font><BR>"
Response.Flush
'递归
GetPart(iGo+1)
End Function%>
上一篇：XMLHTTP抓取远程数据的后期处理
下一篇：实例讲解ASP实现抓取网上房产信息
编程语言
- 如何快速学会编程 如何快速学会ug编程
- 免费学编程的app 推荐12个免费学编程的好网站
- 电脑怎么编程：电脑怎么编程网咯游戏菜单图标
- 如何写代码新手教学 如何写代码新手教学手机
- 基础编程入门教程视频 基础编程入门教程视频华
- 编程演示：编程演示浦丰投针过程
- 乐高编程加盟 乐高积木编程加盟
- 跟我学plc编程 plc编程自学入门视频教程
- ug编程成航林总 ug编程实战视频
- 孩子学编程的好处和坏处
- 初学者学编程该从哪里开始 新手学编程从哪里入
- 慢走丝编程 慢走丝编程难学吗
- 国内十强少儿编程机构 中国少儿编程机构十强有
- 成人计算机速成培训班 成人计算机速成培训班办
- 孩子学编程网上课程哪家好 儿童学编程比较好的
- 代码编程教学入门软件 代码编程教程