过滤html文本

最新推荐文章于 2021-06-03 09:05:38 发布

u010124544

最新推荐文章于 2021-06-03 09:05:38 发布

阅读量119

点赞数

分类专栏： c# 文章标签：过滤html

c# 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

/// <summary>
        /// 过滤html文本
        /// </summary>
        /// <param name="strHtml"></param>
        /// <returns></returns>
        public static string StripHTML(string strHtml)
        {
            if (string.IsNullOrEmpty(strHtml))
                return string.Empty;
            string[] aryReg ={
                @"<script[^>]*?>.*?</script>", @"<font[^>]*?>", @"</font>",
                @"<(\/\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++)
            {
                Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
                strOutput = regex.Replace(strOutput, aryRep[i]);
            }

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

            return strOutput;
        }