Asp.net 远程抓取,分解,保存,匹配

　　    #region 日期随机函数
        /**********************************
         * 函数名称:DateRndName
         * 功能说明:日期随机函数
         * 参    数:ra:随机数
         * 调用示例:
         *          GetRemoteObj o = new GetRemoteObj();
         *          Random ra = new Random();
         *          string s = o.DateRndName(ra);
         *          Response.Write(s);
         *          o.Dispose();
         * ********************************/
        /// <summary>
        /// 日期随机函数
        /// </summary>
        /// <param name="ra">随机数</param>
        /// <returns></returns>
        public  string DateRndName(Random ra)
        {
            DateTime d = DateTime.Now;
            string s = null, y, m, dd, h, mm, ss;
            y = d.Year.ToString();
            m = d.Month.ToString();
            if (m.Length < 2) m = "0" + m;
            dd = d.Day.ToString();
            if (dd.Length < 2) dd = "0" + dd;
            h = d.Hour.ToString();
            if (h.Length < 2) h = "0" + h;
            mm = d.Minute.ToString();
            if (mm.Length < 2) mm = "0" + mm;
            ss = d.Second.ToString();
            if (ss.Length < 2) ss = "0" + ss;
            s += y + m + dd + h + mm + ss;
            s += ra.Next(100, 999).ToString();
            return s;
        }
        #endregion

        #region 取得文件后缀
        /**********************************
         * 函数名称:GetFileExtends
         * 功能说明:取得文件后缀
         * 参    数:filename:文件名称
         * 调用示例:
         *          GetRemoteObj o = new GetRemoteObj();
         *          string url = @"http://dotnet.chinaitlab.com/UploadFiles_6597/200705/20070508104252957.gif";
         *          string s = o.GetFileExtends(url);
         *          Response.Write(s);
         *          o.Dispose();
         * ********************************/
        /// <summary>
        /// 取得文件后缀
        /// </summary>
        /// <param name="filename">文件名称</param>
        /// <returns></returns>
        public string GetFileExtends(string filename)
        {
            string ext = null;
            if (filename.IndexOf('.') > 0)
            {
                string[] fs = filename.Split('.');
                ext = fs[fs.Length - 1];
            }
            return ext;
        }
        #endregion

        #region 获取远程文件源代码
        /**********************************
         * 函数名称:GetRemoteHtmlCode
         * 功能说明:获取远程文件源代码
         * 参    数:Url:远程url
         * 调用示例:
         *          GetRemoteObj o = new GetRemoteObj();
         *          string url = @"http://www.baidu.com";
         *          string s = o.GetRemoteHtmlCode(url);
         *          Response.Write(s);
         *          o.Dispose();
         * ********************************/
        /// <summary>
        /// 获取远程文件源代码
        /// </summary>
        /// <param name="url">远程url</param>
        /// <returns></returns>
        public string GetRemoteHtmlCode(string Url)
        {
            string s = "";
            MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass();
            _xmlhttp.open("GET", Url, false, null, null);
            _xmlhttp.send("");
            if (_xmlhttp.readyState == 4)
            {
                s = System.Text.Encoding.Default.GetString((byte[])_xmlhttp.responseBody);
            }
            return s;
        }

        #endregion
取得页面HTML代码的例子上面已经给出不少了
下面的代码是使用正则表达式取得ＨＴＭＬ中内容的代码
Regex regex1 = new Regex(this.NameKey, RegexOptions.Singleline | RegexOptions.IgnoreCase );
MatchCollection collection1 = regex1.Matches(this.ArtHtml);
if (collection1.Count>0)
{
result=collection1[0].Result("${title}");
}

查看本文来源