有些人當(dāng)抓取程序是個(gè)寶，到目前還TND有人在賣錢，強(qiáng)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(gè)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(yùn)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(dāng)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(nèi)容

    '=========取文章分類及相關(guān)ID參數(shù) 開始=======================
    Content_TempCode = RegExpText(Content_PageCode,"<a href=""/article/"">技術(shù)教程</a> >> ",">> 內(nèi)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(jié)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(jié)束===============
    '=========取文章分類及相關(guān)ID參數(shù) 結(jié)束=======================

    '=========取文章標(biāo)題及內(nèi)容 開始=============================