函数用于去除文本中的html标签,可以控制删除哪些标签.
要控制被删除的标签列表,可以通过向TAGLIST常数中添加/删除标记来实现. 例如,要保留所有的<B>标签,则从TAGLIST中删除B. 当前的列表包含了MSDN中的所有html标签以及 LAYER 标签. 每个标签要用";"括起来.
开始标签和结束标签都会被删除,例如"<A...>"和</A...>
若标签同时在 TAGLIST 和 BLOCKTAGLIST 常数中,则起始标签和结束标签之间的所有内容都会被删除
没有结束标记的标签不被视为html标签,其内容不会被删除
块标签若没有结尾标记,从此标签开始到文本结束的所有内容会被删除
若"<!--"后跟的字符不是空格,注释标签不会被删除
使用这个函数很简单: strPlainText = RemoveHTML(strTextWithHTML)
函数内容如下:
Function RemoveHTML( strText )
Dim TAGLIST
TAGLIST = ";!--;!DOCTYPE;A;ACRONYM;ADDRESS;APPLET;AREA;B;BASE;BASEFONT;" &_
"BGSOUND;BIG;BLOCKQUOTE;BODY;BR;BUTTON;CAPTION;CENTER;CITE;CODE;" &_
"COL;COLGROUP;COMMENT;DD;DEL;DFN;DIR;DIV;DL;DT;EM;EMBED;FIELDSET;" &_
"FONT;FORM;FRAME;FRAMESET;HEAD;H1;H2;H3;H4;H5;H6;HR;HTML;I;IFRAME;IMG;" &_
"INPUT;INS;ISINDEX;KBD;LABEL;LAYER;LAGEND;LI;LINK;LISTING;MAP;MARQUEE;" &_
"MENU;META;NOBR;NOFRAMES;NOSCRIPT;OBJECT;OL;OPTION;P;PARAM;PLAINTEXT;" &_
"PRE;Q;S;SAMP;SCRIPT;SELECT;SMALL;SPAN;STRIKE;STRONG;STYLE;SUB;SUP;" &_
"TABLE;TBODY;TD;TEXTAREA;TFOOT;TH;THEAD;TITLE;TR;TT;U;UL;VAR;WBR;XMP;"
Const BLOCKTAGLIST = ";APPLET;EMBED;FRAMESET;HEAD;NOFRAMES;NOSCRIPT;OBJECT;SCRIPT;STYLE;"
Dim nPos1
Dim nPos2
Dim nPos3
Dim strResult
Dim strTagName
Dim bRemove
Dim bSearchForBlock
nPos1 = InStr(strText, "<")
Do While nPos1 > 0
nPos2 = InStr(nPos1 + 1, strText, ">")
If nPos2 > 0 Then
strTagName = Mid(strText, nPos1 + 1, nPos2 - nPos1 - 1)
strTagName = Replace(Replace(strTagName, vbCr, " "), vbLf, " ")
nPos3 = InStr(strTagName, " ")
If nPos3 > 0 Then
strTagName = Left(strTagName, nPos3 - 1)
End If
If Left(strTagName, 1) = "/" Then
strTagName = Mid(strTagName, 2)
bSearchForBlock = False
Else
bSearchForBlock = True
End If
If InStr(1, TAGLIST, ";" & strTagName & ";", vbTextCompare) > 0 Then
bRemove = True
If bSearchForBlock Then
If InStr(1, BLOCKTAGLIST, ";" & strTagName & ";", vbTextCompare) > 0 Then
nPos2 = Len(strText)
nPos3 = InStr(nPos1 + 1, strText, "</" & strTagName, vbTextCompare)
If nPos3 > 0 Then
nPos3 = InStr(nPos3 + 1, strText, ">")
End If
If nPos3 > 0 Then
nPos2 = nPos3
End If
End If
End If
Else
bRemove = False
End If
If bRemove Then
strResult = strResult & Left(strText, nPos1 - 1)
strText = Mid(strText, nPos2 + 1)
Else
strResult = strResult & Left(strText, nPos1)
strText = Mid(strText, nPos1 + 1)
End If
Else
strResult = strResult & strText
strText = ""
End If
nPos1 = InStr(strText, "<")
Loop
strResult = strResult & strText
RemoveHTML = strResult
End Function