蝙蝠岛资源网 Design By www.hbtsch.com
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.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="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 comeFrom & iGo
'进行简单的数据处理
content = GetBody(comeFrom & 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.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="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 comeFrom & iGo
'进行简单的数据处理
content = GetBody(comeFrom & 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%>
标签：
XMLHTTP批量抓取远程资料
蝙蝠岛资源网 Design By www.hbtsch.com
广告合作：本站广告合作请联系QQ：858582 申请时备注：广告合作（否则不回）
免责声明：本站文章均来自网站采集或用户投稿，网站不提供任何软件下载或自行开发的软件！ 如有用户或公司发现本站内容信息存在侵权行为，请邮件告知！ 858582#qq.com
免责声明：本站文章均来自网站采集或用户投稿，网站不提供任何软件下载或自行开发的软件！ 如有用户或公司发现本站内容信息存在侵权行为，请邮件告知！ 858582#qq.com
蝙蝠岛资源网 Design By www.hbtsch.com
暂无XMLHTTP批量抓取远程资料的评论...
更新日志
2024年12月23日
2024年12月23日
- 小骆驼-《草原狼2(蓝光CD)》[原抓WAV+CUE]
- 群星《欢迎来到我身边 电影原声专辑》[320K/MP3][105.02MB]
- 群星《欢迎来到我身边 电影原声专辑》[FLAC/分轨][480.9MB]
- 雷婷《梦里蓝天HQⅡ》 2023头版限量编号低速原抓[WAV+CUE][463M]
- 群星《2024好听新歌42》AI调整音效【WAV分轨】
- 王思雨-《思念陪着鸿雁飞》WAV
- 王思雨《喜马拉雅HQ》头版限量编号[WAV+CUE]
- 李健《无时无刻》[WAV+CUE][590M]
- 陈奕迅《酝酿》[WAV分轨][502M]
- 卓依婷《化蝶》2CD[WAV+CUE][1.1G]
- 群星《吉他王(黑胶CD)》[WAV+CUE]
- 齐秦《穿乐(穿越)》[WAV+CUE]
- 发烧珍品《数位CD音响测试-动向效果（九）》【WAV+CUE】
- 邝美云《邝美云精装歌集》[DSF][1.6G]
- 吕方《爱一回伤一回》[WAV+CUE][454M]