XMLHTTP抓取远程数据的后期处理
更新时间：2006年09月04日 00:00:00 作者：
<%
hehe = Hello("http://mmsg.qq.com/cgi-bin/gddylist?Type=13&Sort=1&Page=3", "<html>", "</html>", ".*(<td width=""35%"" bgcolor=""#[\dABCDE]{6}"">(.*)</td>)[.\n]*", "<font style=""font-size:9pt;"" color=blue>$2</font><br>")
response.Write hehe
Function Hello(strUrl, strStart, strEnd, patrn, replStr)
Str = GetBody(strUrl)
Str = MyMid(Str, strStart, strEnd)
Str = ReplaceTest(patrn, replStr, Str)
Hello = Str
End Function
Function MyMid(Str, strstart, strend)
If strstart = "" Then
i = 0
Else
i = InStr(Str, strstart)
End If
If strend = "" Then
j = Len(Str)
Else
j = InStr(i, Str, strend)
End If
MyMid = Mid(Str, i, j - i + 1)
End Function
Function ReplaceTest(patrn, replStr, str1)
Dim regEx, match, matches
Set regEx = New RegExp
regEx.Pattern = patrn
regEx.IgnoreCase = True
regEx.Global = True
Set matches = regEx.Execute(str1)
For Each match in matches
ReplaceTest = ReplaceTest®Ex.Replace(Match.Value, replStr)
Next
End Function
Function GetBody(Url)
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
Function BytesToBstr(strBody, CodeBase)
Set objStream = Server.createObject("Adodb.Stream")
With objStream
.Type = 1
.Mode = 3
.Open
.Write strBody
.Position = 0
.Type = 2
.Charset = CodeBase
BytesToBstr = .ReadText
.Close
End With
Set objStream = Nothing
End Function
%>
其他调用示例：
hehe = Hello("http://list.mp3.baidu.com/song/A.htm", "<table width=""90%"" border=""0"" align=""center"" cellpadding=""3"" cellspacing=""0"" bgcolor=""#f5f5f5"" >", "<DIV align=center>", ".*(<td width=""20%""><a href="".*\.htm"" target=_blank>)(.*)(</a></td>)[.\n]*", "<font style=""font-size:9pt;"" color=blue>$2</font><br>")
hehe = Hello("http://mmsg.qq.com/cgi-bin/gddylist?Type=13&Sort=1&Page=3", "<html>", "</html>", ".*(<td width=""35%"" bgcolor=""#[\dABCDE]{6}"">(.*)</td>)[.\n]*", "<font style=""font-size:9pt;"" color=blue>$2</font><br>")
response.Write hehe
Function Hello(strUrl, strStart, strEnd, patrn, replStr)
Str = GetBody(strUrl)
Str = MyMid(Str, strStart, strEnd)
Str = ReplaceTest(patrn, replStr, Str)
Hello = Str
End Function
Function MyMid(Str, strstart, strend)
If strstart = "" Then
i = 0
Else
i = InStr(Str, strstart)
End If
If strend = "" Then
j = Len(Str)
Else
j = InStr(i, Str, strend)
End If
MyMid = Mid(Str, i, j - i + 1)
End Function
Function ReplaceTest(patrn, replStr, str1)
Dim regEx, match, matches
Set regEx = New RegExp
regEx.Pattern = patrn
regEx.IgnoreCase = True
regEx.Global = True
Set matches = regEx.Execute(str1)
For Each match in matches
ReplaceTest = ReplaceTest®Ex.Replace(Match.Value, replStr)
Next
End Function
Function GetBody(Url)
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
Function BytesToBstr(strBody, CodeBase)
Set objStream = Server.createObject("Adodb.Stream")
With objStream
.Type = 1
.Mode = 3
.Open
.Write strBody
.Position = 0
.Type = 2
.Charset = CodeBase
BytesToBstr = .ReadText
.Close
End With
Set objStream = Nothing
End Function
%>
其他调用示例：
hehe = Hello("http://list.mp3.baidu.com/song/A.htm", "<table width=""90%"" border=""0"" align=""center"" cellpadding=""3"" cellspacing=""0"" bgcolor=""#f5f5f5"" >", "<DIV align=center>", ".*(<td width=""20%""><a href="".*\.htm"" target=_blank>)(.*)(</a></td>)[.\n]*", "<font style=""font-size:9pt;"" color=blue>$2</font><br>")
相关文章
Asp定时执行操作 Asp定时读取数据库(网页定时操作详解)
由于目前部分网页语言的限制，在定时操作上有一定的困难，但是经过我多次的求证，发现第四种方法无疑是效果最好的，最省心的。2009-10-10
在浏览器的地址栏里直接输入一个doc或xls或jpg的文件的url路径，那么该文件会直接显示在浏览器里。而在很多时候我们希望能直接弹出下载提示框让用户下载，我们该怎么办呢2007-12-12
一个防止被采集的方法...2006-09-09
asp中xmlhttp组件发包...2007-11-11
非常不错的flash采集程序测试通过...2006-12-12
XML相关技术资料...2006-07-07
写了段批量抓取某个列表页的东东...2006-07-07
一搜图片搜索小偷...2006-09-09
蓝色空间 天气小偷...2006-08-08
采集原理---采集技术篇---XMLHTTP...2006-09-09
最新评论