去掉HTML代码 保留文字和图片

取得HTML中的img

        /// <summary>   
        /// 取得HTML中所有图片的 URL。   
        /// </summary>   
        /// <param name="sHtmlText">HTML代码</param>   
        /// <returns>图片的URL列表</returns>   
        public static string[] GetHtmlImageUrlList(string sHtmlText)
        {
            // 定义正则表达式用来匹配 img 标签   
            Regex regImg = new Regex(@"<img[^<>]*?src[s	
]*=[s	
]*[""']?[s	
]*(?<imgUrl>[^s	
""'<>]*)[^<>]*?/?[s	
]*>", RegexOptions.IgnoreCase);

            // 搜索匹配的字符串   
            MatchCollection matches = regImg.Matches(sHtmlText);
            int i = 0;
            string[] sUrlList = new string[matches.Count];

            // 取得匹配项列表   
            foreach (Match match in matches)
                sUrlList[i++] = match.Groups["imgUrl"].Value;
            return sUrlList;
        }

取得HTML中的文字

 /// <summary>
        /// 取得html中的文字
        /// </summary>
        /// <param name="htmlString"></param>
        /// <returns></returns>
        public static string NoHTML(string htmlString)
        {
            if (string.IsNullOrEmpty(htmlString)) return string.Empty;
            //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, @"([
])[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 = System.Web.HttpUtility.HtmlEncode(htmlString);

            return htmlString;
        }