C#去除HTML标记

最新推荐文章于 2022-01-02 20:53:20 发布

杨关古道

最新推荐文章于 2022-01-02 20:53:20 发布

阅读量358

点赞数

文章标签： c# html webview

本文链接：https://blog.csdn.net/qq_38952126/article/details/122260202

版权

HTML清理字符转义正则表达式字符串处理安全过滤

关键词由CSDN通过智能技术生成

        public string RemoveHTML(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++)
            {
                Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
                strOutput = regex.Replace(strOutput, aryRep[i]);
            }

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


            return strOutput;
        }