标签：asp.net   httpwebrequest   源码   采集   

Asp.net 使用正则和网络编程抓取网页数据(实用)

Asp.net 使用正则和网络编程抓取网页数据(实用)

/// 

        /// 抓取网页相应内容
        /// 
        /// 采集地址
        /// 开始字符
        /// 结束字符
        /// 
        private static String GetContent(String strUrl, String Begin, String End)
        {
            String result = String.Empty;
            HttpWebRequest request = (HttpWebRequest)WebRequest.Create(strUrl);
            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
            using (StreamReader reader = new StreamReader(response.GetResponseStream(), System.Text.Encoding.Default))
            {
                result = reader.ReadToEnd();
            }

            //抓取内容
            Match table = Regex.Match(result, "(?
        ///去除HTML标记
        ///
        ///包括HTML的源码   
        ///已经去除后的文字
        private static string NoHTML(string Htmlstring)
        {
            //删除脚本
            Htmlstring = Regex.Replace(Htmlstring, @"", "",
                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, @"