寫了段批量抓取某個列表頁的東東

有些人當抓取程序是個寶，到目前還TND有人在賣錢，強烈BS一下這些家伙 真是的！可能偶下邊這段東西比較爛哈
下邊這個沒有寫入庫功能，已經(jīng)到這一步了，入庫功能是很簡單的事了，需要的請自己去完成吧，其它功能各位自行完善吧！把代碼拷貝過去直接運行即可看到效果

Dim Url,List_PageCode,Array_ArticleID,i,ArticleID
Dim Content_PageCode,Content_TempCode
Dim Content_CategoryID,Content_CategoryName,BorderID,ClassID,BorderName,ClassName
Dim ArticleTitle,ArticleAuthor,ArticleFrom,ArticleContent

Url = "http://www.webasp.net/article/class/1.htm"
List_PageCode = getHTTPPage(Url)
List_PageCode = RegExpText(List_PageCode,"打印/th>/tr>","/table>table border=0 cellpadding=5",0)
List_PageCode = RegExpText(List_PageCode,"td align=left>a href='../","'>img border=0 src='../images/authortype0.gif'",1)    '取得當前列表頁的文章鏈接，以,分隔
Array_ArticleID = Split(List_PageCode,",")    '創(chuàng)建數(shù)組，存儲文章ID

For i=0 To Ubound(Array_ArticleID)-1
    ArticleID = Array_ArticleID(i)    '文章ID
    Content_PageCode = getHTTPPage("http://www.webasp.net/article/"ArticleID)    '取得文章頁的內容

    '=========取文章分類及相關ID參數(shù) 開始=======================
    Content_TempCode = RegExpText(Content_PageCode,"a href=""/article/"">技術教程/a> gt;gt; ","gt;gt; 內容/td>",0)
    Content_CategoryID = RegExpText(Content_PageCode,"a href='../class","/'>",1)
    BorderID = Split(Content_CategoryID,",")(0)    '大類ID
    ClassID = Split(Content_CategoryID,",")(1)    '子類ID
        '==========檢查大類是否存在 開始===============
        '如果不存在則入庫

        '==========檢查大類是否存在 結束===============
    'Response.Write(BorderID "," ClassID "br />")
    Content_CategoryName = RegExpText(Content_PageCode,"/'>","/a>",1)
    BorderName = Split(Content_CategoryName,",")(0)    '大類名稱
    ClassName = Split(Content_CategoryName,",")(1)    '子類名稱
        '==========檢查子類是否存在 開始===============
        '如果不存在則入庫

        '==========檢查子類是否存在 結束===============
    '=========取文章分類及相關ID參數(shù) 結束=======================

    '=========取文章標題及內容 開始=============================
    ArticleTitle = RegExpText(Content_PageCode,"tr>td align=center bgcolor=#DEE2F5>strong>","/strong>/td>/tr>",0)
    ArticleAuthor = RegExpText(Content_PageCode,"tr>td>span class=blue>作者：/span>","/td>/tr>",0)
    ArticleFrom = RegExpText(Content_PageCode,"tr>td>span class=blue>來源：/span>","/td>/tr>",0)
    ArticleContent = RegExpText(Content_PageCode,"tr>td class=content style=""WORD-WRAP: break-word"" id=zoom>","/td>/tr>"VBCrlf"        /table>"VBCrlf"    /td>/tr>/table>",0)
    '=========取文章標題及內容 結束=============================
    Response.Write(ArticleTitle "br />br />")
    Response.Flush()
Next

Function RegExpText(strng,strStart,strEnd,n)
    Dim regEx,Match,Matches,RetStr
    SET regEx = New RegExp
    regEx.Pattern = strStart"([\s\S]*?)"strEnd
    regEx.IgnoreCase = True
    regEx.Global = True
    SET Matches = regEx.Execute(strng)
    For Each Match in Matches
        IF(n=1)THEN
            RetStr = RetStr regEx.Replace(Match.Value,"$1") ","
        ELSE
            RetStr = RetStr regEx.Replace(Match.Value,"$1")
        END IF
    Next
    RegExpText = RetStr
    SET regEx=NOTHING
End Function