当前位置: 首页 > 图文教程 > 网络编程 > ASP > 制作一个个人搜索引擎(源码)

ASP
自动采集程序
一个防止被采集的方法
帮你打造属于自己的搜索引擎---百度篇
实例讲解ASP实现抓取网上房产信息
XMLHTTP批量抓取远程资料
XMLHTTP抓取远程数据的后期处理
用XMLHTTP很好的一个例子
采集原理---采集技术篇---XMLHTTP
小偷,采集程序常用函数
服务器常用组件
如何在不支持数据库的asp主页上运用ado
做文章系统时, 如何让长篇的文章自动换行
Access中使用Create Procedure创建存储过程
ASP中的时间函数大全 时间操作函数
无组件实现文件上传/下载
asp网页邮箱访问
不用模板只用ASP+FSO生成静态HTML页的一个方法
用sql设置access的默认值
Asp事务处理
统计有多少行JS代码和ASP代码

ASP 中的 制作一个个人搜索引擎(源码)


出处:互联网   整理: 软晨网(RuanChen.com)   发布: 2009-11-03   浏览: 98 ::
收藏到网摘: n/a

  <%
Response.Buffer=True

'
' OneFile Search Engine (ofSearch v1.0)
' Copyright ?000 Sixto Luis Santos <[email protected]>
' All Rights Reserved
'
' Note:
' This program is freeware. This program is NOT in the Public Domain.
' You can freely use this program in your own site.
'
' You cannot re-distribute the code, by any means,
' without the express written authorization by the author.
'
' Use this program at your own risk.
'


' Globals --------------------------------------
' ----------------------------------------------

Const ValidFiles = "htmltxt"
Const RootFld = "./"

Dim Matched
Dim Regex
Dim GetTitle
Dim fs
Dim rfLen
dim RootFolder
Dim DocCount
Dim DocMatchCount
Dim MatchedCount

' ----------------------------------------------
' Procedure: SearchFiles()
' ----------------------------------------------
Public Sub SearchFiles(FolderPath)
Dim fsFolder
Dim fsFolder2
Dim fsFile
Dim fsText
Dim FileText
Dim FileTitle
Dim FileTitleMatch
Dim MatchCount
Dim OutputLine

' Get the starting folder
Set fsFolder = fs.GetFolder(FolderPath)
' Iterate thru every file in the folder
For Each fsFile In fsFolder.Files
    ' Compare the current file extension with the list of valid target files
    If InStr(1, ValidFiles, Right(fsFile.Name, 3), vbTextCompare) > 0 Then
     DocCount = DocCount + 1
     ' Open the file to read its content
        Set fsText = fsFile.OpenAsTextStream
            FileText = fsText.ReadAll
            ' Apply the regex search and get the count of matches found
            MatchCount = Regex.Execute(FileText).Count
            MatchedCount = MatchedCount + MatchCount
            If  MatchCount > 0 Then
                DocMatchCount = DocMatchCount + 1
                ' Apply another regex to get the html document's title
                Set FileTitleMatch = GetTitle.Execute(FileText)
                If FileTitleMatch.Count > 0 Then
                    ' Strip the title tags
                    FileTitle = Trim(replace(Mid(FileTitleMatch.Item(0),8),"</title>","",1,1,1))
                    ' In case the title is empty
                    If FileTitle = "" Then
                     FileTitle = "No Title (" & fsFile.Name & ")"
                    End If
                Else