字符串截取

 ///   <summary>   
        ///   将指定字符串按指定长度进行剪切，   
        ///   </summary>   .   ///   <param   name= "oldStr "> 需要截断的字符串 </param>   
        ///   <param   name= "maxLength "> 字符串的最大长度 </param>   
        ///   <param   name= "endWith "> 超过长度的后缀 </param>   
        ///   <returns> 如果超过长度，返回截断后的新字符串加上后缀，否则，返回原字符串 </returns>   
        public static string StringTruncat(string oldStr, int maxLength, string endWith)
        {
            if (string.IsNullOrEmpty(oldStr))
                //   throw   new   NullReferenceException( "原字符串不能为空 ");   
                return oldStr + endWith;
            if (maxLength < 1) throw new Exception("返回的字符串长度必须大于[0] ");
            if (oldStr.Length > maxLength)
            {
                string strTmp = oldStr.Substring(0, maxLength);
                if (string.IsNullOrEmpty(endWith))
                    return strTmp;
                else
                    return strTmp + endWith;
            }
            return oldStr;
        }

 

 /// <summary>
       /// 从字符串中截取图片信息
       /// </summary>
       /// <param name="str"></param>
       /// <returns></returns>
        protected string GetSrc(string str)
        {
            string regStr = "\\<IMG\\ [\\s\\S]*?src=['\"]?(?<p>[^'\"\\>\\ ]+)['\"\\>\\ ]";
            string cont1 = string.Empty; //图片的src
            Regex reg = new Regex(regStr, RegexOptions.Compiled | RegexOptions.IgnoreCase);
            Match match = reg.Match(str);
            string picSrc = "";
            if (match.Success)
            {
                picSrc = match.Groups["p"].Value;
                return picSrc;
            }
            else 
            {
                return "";
            }
        }

 

        /*
      * *
      * 按字节长度截取字符串(支持截取带HTML代码样式的字符串)  *
      * @param param 将要截取的字符串参数  * @param length 截取的字节长度  * 
      * @param end 字符串末尾补上的字符串  * @return 返回截取后的字符串  */
        public static string subStringHTML(string param, int length, string end)
        {
            string Pattern = null; MatchCollection m = null; StringBuilder result = new StringBuilder(); int n = 0; char temp; 
            bool isCode = false; //是不是HTML代码
            bool isHTML = false; //是不是HTML特殊字符,如    
            char[] pchar = param.ToCharArray();
            for (int i = 0; i < pchar.Length; i++)
            {
                temp = pchar[i];
                if (temp == '<')
                {
                    isCode = true;
                }
                else if (temp == '&')
                {
                    isHTML = true;
                }
                else if (temp == '>' && isCode)
                {
                    n = n - 1; isCode = false;
                }
                else if (temp == ';' && isHTML)
                {
                    isHTML = false;
                }
                if (!isCode && !isHTML)
                {
                    n = n + 1;     //UNICODE码字符占两个字节    
                    //if (System.Text.Encoding.Default.GetBytes(temp + "").Length > 1)
                    //{
                    //    n = n + 1;
                    //}
                }
                result.Append(temp);
                if (n >= length)
                { break; }
            }
            if (result.Length > length)
            {
                result.Append("..."); 
            }
             
            //取出截取字符串中的HTML标记   
            string temp_result = result.ToString().Replace("(>)[^<>]*(<?)", "$1$2");
            //去掉不需要结素标记的HTML标记  
            temp_result = temp_result.Replace(@"</?(AREA|BASE|BASEFONT|BODY|BR|COL|COLGROUP|DD|DT|FRAME|HEAD|HR|HTML|IMG|INPUT|ISINDEX|LI|LINK|META|OPTION|P|PARAM|TBODY|TD|TFOOT|TH|THEAD|TR|area|base|basefont|body|br|col|colgroup|dd|dt|frame|head|hr|html|img|input|isindex|li|link|meta|option|p|param|tbody|td|tfoot|th|thead|tr)[^<>]*/?>", "");   //去掉成对的HTML标记 
            temp_result = temp_result.Replace(@"<([a-zA-Z]+)[^<>]*>(.*?)<//1>", "$2");   
            //用正则表达式取出标记   
            Pattern = ("<([a-zA-Z]+)[^<>]*>"); 
            m = Regex.Matches(temp_result, Pattern); 
            ArrayList endHTML = new ArrayList(); 
            foreach (Match mt in m) 
            {
                endHTML.Add(mt.Result("$1"));
            }
            //补全不成对的HTML标记 
            for (int i = endHTML.Count - 1; i >= 0; i--)
            { 
                result.Append("</"); result.Append(endHTML[i]); result.Append(">");
            }
            return result.ToString();
        }