文件名 正则表达式提取方法
更新时间:2008年03月06日 10:22:02 作者:
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("[img]2312.jpg[/img][img]2312.jpg[/img]hh[img]http://www.dc9.cn/cm/upload/2ed312.jpg[/img]<a href=""http://www.dc9.cn/ddd.jpg""></a> href=""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)
Next
For i=0 to Ubound(aryMatch)
If Not IsNull(aryMatch(i)) And Trim(aryMatch(i))<>"" Then Response.write aryMatch(i)&"<br>"
Next
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
Next
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("[img]2312.jpg[/img][img]2312.jpg[/img]hh[img]http://www.dc9.cn/cm/upload/2ed312.jpg[/img]<a href=""http://www.dc9.cn/ddd.jpg""></a> href=""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"" src=http://www.dc9.cn/upload/sasds.jpg'>")
Dim TmpMatch
For i=0 to Matches.Count-1
Call InsertDataToArray(Matches(i).SubMatches(0),aryMatch)
Call InsertDataToArray(Matches(i).SubMatches(1),aryMatch)
Next
For i=0 to Ubound(aryMatch)
If Not IsNull(aryMatch(i)) And Trim(aryMatch(i))<>"" Then Response.write aryMatch(i)&"<br>"
Next
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
Next
If Not ZC_UPLOAD_MATCH Then aryMatch(Ubound(aryMatch))=Data
End If
End Function
PS:最近正则又精进不少...
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("[img]2312.jpg[/img][img]2312.jpg[/img]hh[img]http://www.dc9.cn/cm/upload/2ed312.jpg[/img]<a href=""http://www.dc9.cn/ddd.jpg""></a> href=""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)
Next
For i=0 to Ubound(aryMatch)
If Not IsNull(aryMatch(i)) And Trim(aryMatch(i))<>"" Then Response.write aryMatch(i)&"<br>"
Next
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
Next
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("[img]2312.jpg[/img][img]2312.jpg[/img]hh[img]http://www.dc9.cn/cm/upload/2ed312.jpg[/img]<a href=""http://www.dc9.cn/ddd.jpg""></a> href=""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"" src=http://www.dc9.cn/upload/sasds.jpg'>")
Dim TmpMatch
For i=0 to Matches.Count-1
Call InsertDataToArray(Matches(i).SubMatches(0),aryMatch)
Call InsertDataToArray(Matches(i).SubMatches(1),aryMatch)
Next
For i=0 to Ubound(aryMatch)
If Not IsNull(aryMatch(i)) And Trim(aryMatch(i))<>"" Then Response.write aryMatch(i)&"<br>"
Next
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
Next
If Not ZC_UPLOAD_MATCH Then aryMatch(Ubound(aryMatch))=Data
End If
End Function
PS:最近正则又精进不少...
相关文章
在Vista IIS 7 中用 vs2005 调试 Web 项目的注意事项
在Vista IIS 7 中用 vs2005 调试 Web 项目核心是要解决以下几个问题2008-09-09asp之GetArray提取链接地址,以$Array$分隔的代码
asp之GetArray提取链接地址,以$Array$分隔的代码...2007-09-09ASP代码实现自动清除替换ACCESS(MDB)数据库的日文字符的
我们都知道ACCESS是ASP的亲密伙伴。因为两种最简单的东西碰在一起总能迸发出火花。 然而,当我们过滤不严格的时候经常出现日文字符,这个时候搜索之后就会出现日文溢出。2008-06-06
最新评论