删除HTML标签的正则表达式

删除HTML标签

privatestringStripHTML(stringstrHtml)

{

string[]aryReg={

@"<script[^>]*?>.*?</script>",

@"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>",

@"([\r\n])[\s]+",

@"&(quot|#34);",

@"&(amp|#38);",

@"&(lt|#60);",

@"&(gt|#62);",

@"&(nbsp|#160);",

@"&(iexcl|#161);",

@"&(cent|#162);",

@"&(pound|#163);",

@"&(copy|#169);",

@"&#(\d+);",

@"-->",

@"<!--.*\n"

};

string[]aryRep={

"",

"",

"",

"\"",

"&",

"<",

">",

"",

"\xa1",//chr(161),

"\xa2",//chr(162),

"\xa3",//chr(163),

"\xa9",//chr(169),

"",

"\r\n",

""

};

stringnewReg=aryReg[0];

stringstrOutput=strHtml;

try

{

for(inti=0;i<aryReg.Length;i++)

{

Regexregex=newRegex(aryReg[i],RegexOptions.IgnoreCase);

strOutput=regex.Replace(strOutput,aryRep[i]);

}

}

catch(Exceptionex)

{

}

strOutput.Replace("<","");

strOutput.Replace(">","");

strOutput.Replace("\r\n","");

returnstrOutput;

}