取得HTML中的img

        /// <summary>   
        /// 取得HTML中所有圖片的 URL。   
        /// </summary>   
        /// <param name="sHtmlText">HTML程式碼</param>   
        /// <returns>圖片的URL列表</returns>   
        public static string[] GetHtmlImageUrlList(string sHtmlText)
        {
            
 
// 定義正則表示式用來匹配 img 標籤   
            Regex regImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);

            // 搜尋匹配的字串   
            MatchCollection matches = regImg.Matches(sHtmlText);
            
 
int i = 0;
            string[] sUrlList = new string[matches.Count];

            // 取得匹配項列表   
            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;
            //刪除指令碼   
            htmlString = Regex.Replace(htmlString, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
            //刪除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 = System.Web.HttpUtility.HtmlEncode(htmlString);

            return htmlString;
        }