如何过滤HTML的标记 急！

[jce195447]

RT

[q107770540]

/// <summary>
    /// 去掉html标记
    /// </summary>
    /// <param name="str"></param>
    /// <returns></returns>
    protected static string ConvertGettext(string str)
    {
        Regex regex = new Regex(@"\<(.*?)\>", RegexOptions.IgnoreCase);

        return regex.Replace(str, "").Replace(" ", "").Replace("\n", "").Replace("\r", "");
    }

[shaoliang520xi]

#region 过滤掉 html代码
/// <summary>
/// 过滤html标签
/// </summary>
/// <param name="strHtml">html的内容</param>
/// <returns></returns>
public static string StripHTML(string strHtml)
{
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",
""
};

string newReg = aryReg[0];
string strOutput = strHtml;
for (int i = 0; i < aryReg.Length; i++)
{
System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(aryReg[i], System.Text.RegularExpressions.RegexOptions.IgnoreCase);
strOutput = regex.Replace(strOutput, aryRep[i]);
}
//strOutput.Replace("<", "");
//strOutput.Replace(">", "");
strOutput = strOutput.Replace("\r\n", "");
return strOutput;
}
#endregion

[jce195447]

regex 是什么？如何引用

[q107770540]

using System.Text.RegularExpressions;

[fellowcheng]

        #region replace html tag

        /// <summary>
        /// 移除Html标记
        /// </summary>
        /// <param name="content"></param>
        /// <returns></returns>
        public static string RemoveHtml(string content) {
            string regexstr = @"<[^>]*>";
            return Regex.Replace(content, regexstr, string.Empty, RegexOptions.IgnoreCase);
        }

        /// <summary>
        /// 过滤HTML中的不安全标签
        /// </summary>
        /// <param name="content"></param>
        /// <returns></returns>
        public static string RemoveUnsafeHtml(string content) {
            content = Regex.Replace(content, @"(\<|\s+)o([a-z]+\s?=)", "$1$2", RegexOptions.IgnoreCase);
            content = Regex.Replace(content, @"(script|frame|form|meta|behavior|style)([\s|:|>])+", "$1.$2", RegexOptions.IgnoreCase);
            return content;
        }


        public static string RemoveHTML(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[0];
            string strOutput = strHtml;
            for (int i = 0; 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;
        }

        public static string ClearSpecialHTMLTag(string strInput, string strPattern, string strReplace) {
            Regex regex = new Regex(strPattern, RegexOptions.IgnoreCase);
            return regex.Replace(strInput, strReplace);
        }

        #endregion

using System.Text.RegularExpressions;

[jce195447]

从客户端(TextBox7="<sss>")中检测到有潜在危险的 Request.Form 值

[wuyq11]

using System.Text.RegularExpressions;
Regex.Replace(str,@"<[^> ]+>",""); 过滤所有html.
<pages validateRequest="false" >

[SvenCows]

Server.HtmlEncode();

[龍月]

[Quote=引用 7 楼 wuyq11 的回复:]
using System.Text.RegularExpressions;
Regex.Replace(str,@"<[^> ]+>",""); 过滤所有html.
<pages validateRequest="false" >
[/Quote]

+1

[snihcel]

public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "",
RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9",
RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "",
RegexOptions.IgnoreCase);
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring =System.Web.HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

return Htmlstring;
}