其他分享
首页 > 其他分享> > .net工具类——HTML处理

.net工具类——HTML处理

作者:互联网

 

 

        #region 截取字符长度

        /// <summary>
        /// 截取字符长度
        /// </summary>
        /// <param name="inputString">字符</param>
        /// <param name="len">长度</param>
        /// <returns></returns>
        public static string SubString(string inputString, int len)
        {
            if (string.IsNullOrEmpty(inputString))
                return "";
            inputString = DropHTML(inputString);
            ASCIIEncoding ascii = new ASCIIEncoding();
            int tempLen = 0;
            string tempString = "";
            byte[] s = ascii.GetBytes(inputString);
            for (int i = 0; i < s.Length; i++)
            {
                if ((int)s[i] == 63)
                {
                    tempLen += 2;
                }
                else
                {
                    tempLen += 1;
                }

                try
                {
                    tempString += inputString.Substring(i, 1);
                }
                catch
                {
                    break;
                }

                if (tempLen > len)
                    break;
            }
            //如果截过则加上半个省略号
            byte[] mybyte = System.Text.Encoding.Default.GetBytes(inputString);
            if (mybyte.Length > len)
                tempString += "…";
            return tempString;
        }

        #endregion

        #region 清除HTML标记

        public static string DropHTML(string Htmlstring)
        {
            if (string.IsNullOrEmpty(Htmlstring)) return "";
            //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 = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
            return Htmlstring;
        }

        #endregion

        #region 清除HTML标记且返回相应的长度

        public static string DropHTML(string Htmlstring, int strLen)
        {
            return SubString(DropHTML(Htmlstring), strLen);
        }

        #endregion

        #region TXT代码转换成HTML格式

        /// <summary>
        /// 字符串字符处理
        /// </summary>
        /// <param name="chr">等待处理的字符串</param>
        /// <returns>处理后的字符串</returns>
        /// //把TXT代码转换成HTML格式
        public static String ToHtml(string Input)
        {
            StringBuilder sb = new StringBuilder(Input);
            sb.Replace(" ", "&nbsp;");
            //sb.Replace("&", "&amp;");
            sb.Replace("<", "&lt;");
            sb.Replace(">", "&gt;");
            sb.Replace("\r\n", "<br />");
            sb.Replace("\n", "<br />");
            sb.Replace("\t", " ");
            return sb.ToString();
        }

        #endregion

        #region HTML代码转换成TXT格式

        /// <summary>
        /// 字符串字符处理
        /// </summary>
        /// <param name="chr">等待处理的字符串</param>
        /// <returns>处理后的字符串</returns>
        /// //把HTML代码转换成TXT格式
        public static String ToTxt(String Input)
        {
            StringBuilder sb = new StringBuilder(Input);
            sb.Replace("&nbsp;", " ");
            sb.Replace("<br>", "\r\n");
            sb.Replace("<br>", "\n");
            sb.Replace("<br />", "\n");
            sb.Replace("<br />", "\r\n");
            sb.Replace("&lt;", "<");
            sb.Replace("&gt;", ">");
            sb.Replace("&amp;", "&");
            return sb.ToString();
        }

        #endregion

 

标签:Regex,Htmlstring,Replace,IgnoreCase,HTML,RegexOptions,sb,net,工具
来源: https://www.cnblogs.com/amusement1992/p/13496235.html