正则表达式结合数组提取文章中的文件名

今天编ZBlog上传模块的时候，需要用到一个提取文章中文件名的子程，开始我把问题想复杂了，匹配了所有可能的文件名，不仅正则表达式写了一大串，而且下面还Split了半天，后来我突然发现Z-Blog的上传文件都存在upload下，白写了那么多复杂的匹配。。。哎，不能浪费掉啊，还是贴上来万一哪个兄弟以后需要也好拿去用~~

下面这段子程基本上可以算是比较不错的通用匹配了。(PS:我突然发现CODE_LITE把我的UBB转义了！！！晕,我只好自己转义了。。。)

--------------------------------------------------------------------------------

Dim objRegExp,Matches,i,DC9_DOT_CN_MATCH

Dim aryMatch()

Redim Preserve aryMatch(0)

Set objRegExp=New RegExp

objRegExp.IgnoreCase =True

objRegExp.Global=True

objRegExp.Pattern="(?:\[[^\]]+\]([^\[]+)\[\/[^\]]+\])|(?:(?:href|src)=([^\s|^>]+)[""|>|\s\'])"

Set Matches = objRegExp.Execute("

<a href=""[/url]http://www.dc9.cn/ddd.jpg""></a> href=""[url=http://www.dc9.cn/dccdd.jpg][IMG_RIGHT=400,300,title]upload/2assas.jpg[/IMG_RIGHT]http://www.dc9.cn/dccdd.jpg"">[IMG_RIGHT=400,300,title]upload/2assas.jpg[/IMG_RIGHT]<sctipt src=""http://www.dc9.cn/upload/sss.jpg""")

Dim TmpMatch

For i=0 to Matches.Count-1

Call InsertDataToArray(Matches(i).SubMatches(0),aryMatch)

Call InsertDataToArray(Matches(i).SubMatches(1),aryMatch)

For i=0 to Ubound(aryMatch)

If Not IsNull(aryMatch(i)) And Trim(aryMatch(i))<>"" Then Response.write aryMatch(i)&"<br>"

Function InsertDataToArray(Data,ByRef aryMatch)

If Trim(Data)<>"" Then

Data=Replace(Data,"'","")

Data=Replace(Data,"""","")

Data=Replace(Data,"\","/")

Data=Split(Data,"/")(Ubound(Split(Data,"/")))

Redim Preserve aryMatch(Ubound(aryMatch)+1)

DC9_DOT_CN_MATCH=False

For j=0 to Ubound(aryMatch)

If aryMatch(j)=Data Then DC9_DOT_CN_MATCH=True

If Not DC9_DOT_CN_MATCH Then aryMatch(Ubound(aryMatch))=Data

End If

End Function

--------------------------------------------------------------------------------

实际上，Z-Blog的话就匹配Upload就可以了（但是我为了省事，也为了更精确些，就干脆在上面的那个匹配上面加上了upload，所以看上去好像下面这个更复杂些，其实理论上应该下面这个简单些，毕竟有upload管着呢。。），也不用SPLit那个/.这么写就可以了：

--------------------------------------------------------------------------------

Dim objRegExp,Matches,i,ZC_UPLOAD_MATCH

Dim aryMatch()

Redim Preserve aryMatch(0)

Set objRegExp=New RegExp

objRegExp.IgnoreCase =True

objRegExp.Global=True

objRegExp.Pattern="(?:\[[^\]]+\][^\[]*upload\/([^\[|^\\|^\/]+)\[\/[^\]]+\])|(?:(?:href|src)=""{0,1}[^\s|^""|^>|^']*upload\/([^\s|^>]+)[""|>|\s\'])"

Set Matches = objRegExp.Execute("

Dim TmpMatch

For i=0 to Matches.Count-1

Call InsertDataToArray(Matches(i).SubMatches(0),aryMatch)

Call InsertDataToArray(Matches(i).SubMatches(1),aryMatch)

For i=0 to Ubound(aryMatch)

If Not IsNull(aryMatch(i)) And Trim(aryMatch(i))<>"" Then Response.write aryMatch(i)&"<br>"

Function InsertDataToArray(Data,ByRef aryMatch)

If Trim(Data)<>"" Then

Data=Replace(Data,"'","")

Data=Replace(Data,"""","")

Redim Preserve aryMatch(Ubound(aryMatch)+1)

ZC_UPLOAD_MATCH=False

For j=0 to Ubound(aryMatch)

If aryMatch(j)=Data Then ZC_UPLOAD_MATCH=True

If Not ZC_UPLOAD_MATCH Then aryMatch(Ubound(aryMatch))=Data

End If

End Function

出处：http://www.dc9.cn/post/279.html