图文混排控件FreeTextBox过滤图片

 

/// <summary>
        /// 获取图文混排中的image路径,返回（Hashtable）ImageHashtable
        /// </summary>
        /// <param name="HtmlStr"></param>
        /// <returns></returns>
        public bool ParseImageFromHtmlConent(string HtmlStr)
        {
            bool exc = false;
            try
            {
                //搜索图像的正则表达式
                string pattern = @"(<img[^>]*((>)|(/>)|(>\s*</img>)))";
                System.Text.RegularExpressions.Regex reg = new System.Text.RegularExpressions.Regex(pattern, System.Text.RegularExpressions.RegexOptions.Multiline | System.Text.RegularExpressions.RegexOptions.Compiled | System.Text.RegularExpressions.RegexOptions.IgnoreCase);
                HtmlStr = reg.Replace(HtmlStr, new System.Text.RegularExpressions.MatchEvaluator(ParseImageTag));
                if (HtmlStr == "1")
                {
                    exc = true;
                }
                else
                {
                    exc = false;
                }
            }
            catch 
            {
                exc = false;
            }
            return exc;

        }
        private string ParseImageTag(System.Text.RegularExpressions.Match m)
        {
            string exc = "0";
            try
            {
                System.Text.RegularExpressions.GroupCollection gc = m.Groups;
                string img = gc[1].ToString();
                if (ParseImagePropertiesTages(img) == true)
                {
                    //exc = "1";
                    exc = "";
                }
                else
                {
                    //exc = "0";
                    exc = "";
                }

            }
            catch 
            {
                exc = "0";
            }
            return exc;
        }
        private bool ParseImagePropertiesTages(string img)
        {
            bool exc = false;
            try
            {
                //Dictionary<string, string> dic = new Dictionary<string, string>();
                //搜索属性的正则表达式
                string pattern = @"([a-zA-Z]+)\s*=\s*[""']\s*([^""']+)\s*[""']";
                System.Text.RegularExpressions.Regex reg = new System.Text.RegularExpressions.Regex(pattern);
                System.Text.RegularExpressions.MatchCollection mc = reg.Matches(img);
                foreach (System.Text.RegularExpressions.Match m in mc)
                {
                    System.Text.RegularExpressions.GroupCollection groupCol = m.Groups;
                    string key = "Imag@" + groupCol[1].ToString().Trim();
                    string value = groupCol[2].ToString().Trim();
                    ImageHashtable.Add(key, value);
                }
                exc = true;
            }
            catch 
            {
                exc = false;
            }
            return exc;

        }
        /// <summary>
        ///  去除图文混排中的image
        /// </summary>
        /// <param name="HtmlStr"></param>
        /// <returns></returns>
        public string ParseImageFrom(string HtmlStr)
        {
            string content = "";
            try
            {
                string pattern = @"(<img[^>]*((>)|(/>)|(>\s*</img>))|<img>)";
                System.Text.RegularExpressions.Regex reg = new System.Text.RegularExpressions.Regex(pattern, System.Text.RegularExpressions.RegexOptions.Multiline | System.Text.RegularExpressions.RegexOptions.Compiled | System.Text.RegularExpressions.RegexOptions.IgnoreCase);
                content = reg.Replace(HtmlStr, new System.Text.RegularExpressions.MatchEvaluator(ParseImageTag));
                pattern = @"(<a[^>]*((>)|(/>)|(>\s*</a>))|</a>)";
                reg = new System.Text.RegularExpressions.Regex(pattern, System.Text.RegularExpressions.RegexOptions.Multiline | System.Text.RegularExpressions.RegexOptions.Compiled | System.Text.RegularExpressions.RegexOptions.IgnoreCase);
                System.Text.RegularExpressions.MatchCollection mc = reg.Matches(content);
                content = reg.Replace(content, "", mc.Count);
            }
            catch 
            {

            }
            return content;
        }


        ///   去除HTML标记   
        ///   </summary>   
        ///   <param   name="NoHTML">包括HTML的源码</param>   
        ///   <returns>已经去除后的文字</returns> 
        public 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 = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

            return Htmlstring;
        }

需要引用的命名空间有以下两个：

using System.Reflection;
using System.Text.RegularExpressions;