C# 替换去除HTML标记方法(正则表达式)

[from] http://blog.csdn.net/sgear/article/details/6263848
/// <summary>

/// 将所有HTML标签替换成""

/// </summary>

/// <param name="strHtml"></param>

/// <returns></returns>

public static string StripHTML(string strHtml)

{

string[] aryReg ={

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

@"<(///s*)?!?((/w+:)?/w+)(/w+(/s*=?/s*(([""'])(file://[""'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",

""

};

string newReg = aryReg[];

string strOutput = strHtml;

for (int i = ; i < aryReg.Length; i++)

{

Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);

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

}

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

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

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

return strOutput;

}