正则取页面图片URL和TABLE BackGround

        /// <summary>
        /// 根据html文本返回url地址集合
        /// </summary>
        /// <param name="sHtmlText"></param>
        /// <returns></returns>
        private List<string> GetImgUrlByHtmlText(string sHtmlText)
        {
            // 定义正则表达式用来匹配 img 标签 
            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);
            // 搜索匹配的字符串 
            MatchCollection matches = regImg.Matches(sHtmlText);


            List<string> sUrlList = new List<string>();
            // 取得匹配项列表 
            foreach (Match match in matches)
            {
                if (match.Groups["imgUrl"].Value != "")
                {
                    sUrlList.Add(match.Groups["imgUrl"].Value);
                }
            }


            // 定义正则表达式用来匹配 table 标签 
            Regex regTable = new Regex(@"<(table|tr|td)\b[^<>]*?\bbackground[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<backgroundUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);
            MatchCollection matchesTable = regTable.Matches(sHtmlText);
            // 取得匹配项列表 
            foreach (Match match in matchesTable)
            {
                if (match.Groups["backgroundUrl"].Value != "")
                {
                    sUrlList.Add(match.Groups["backgroundUrl"].Value);
                }
            }
            return sUrlList;
        }