C# 实现抓取网站页面内容的实例方法

!-- publish_helper name='要闻-新闻' p_id='1' t_id='850' d_id='1' -->

内容。。。。

!-- publish_helper name='要闻-财经' p_id='30' t_id='98' d_id='1' -->

protected void Enter_Click(object sender, EventArgs e)
        {
            WebClient we = new WebClient();  //主要使用WebClient类
            byte[] myDataBuffer;
            myDataBuffer = we.DownloadData(txtURL.Text);  //该方法返回的是 字节数组，所以需要定义一个byte[]
            string download = Encoding.Default.GetString(myDataBuffer);  //对下载的数据进行编码

          
            //通过查询源代码，获取某两个值之间的新闻内容
            int startIndex = download.IndexOf("!-- publish_helper name='要闻-新闻' p_id='1' t_id='850' d_id='1' -->");
            int endIndex = download.IndexOf("!-- publish_helper name='要闻-财经' p_id='30' t_id='98' d_id='1' -->");

            string temp = download.Substring(startIndex, endIndex - startIndex + 1);  //截取新闻内容

            lblMessage.Text = temp;//显示所截取的新闻内容
        }

WebClient wc = new WebClient();
            wc.DownloadFile(TextBox1.Text, @"F:\test.txt");
            Label1.Text = "文件下载完成";

WebClient wc = new WebClient();
            Stream  s =  wc.OpenRead(TextBox1.Text);

            StreamReader sr = new StreamReader(s);
            Label1.Text =  sr.ReadToEnd();