页面信息抓取

 

现在公司做这个，所以必须得学习**

using System;

using System.Collections.Generic;

using System.Text;

using System.Text.RegularExpressions;

using System.Net;

using System.IO;

namespace diytrade

{

    class Program

    {

        static void Main(string[] args)

        {

            ComMethord.FirstLeve _FirstLeve=new diytrade.ComMethord.FirstLeve() ;

            string strHtml = string.Empty;

            strHtml = GetSourceHtml(_FirstLeve.FirstLink);

            Console.Write(strHtml);

        }

        private static string GetSourceHtml(string urlstr)

        {

          //根据 url 读取 源文件

            urlstr = "http://www.diytrade.com/directory/china/buy/leads-catalogs.html";

            //WebRequest wreq = WebRequest.Create(urlstr);

            //WebResponse wres = wreq.GetResponse();

            //Stream rece = wres.GetResponseStream();

            //Byte[] read = new Byte[512];

            //int bytes = rece.Read(read, 0, 512);

            //string reshtml = "";

            //while (bytes > 0)

            //{

            //    Encoding encode = Encoding.GetEncoding("gb2312");

            //    reshtml += encode.GetString(read, 0, bytes);

            //    bytes = rece.Read(read, 0, 512);

            //}

            //return reshtml;

            System.Net.HttpWebRequest _Request = (System.Net.HttpWebRequest)System.Net.HttpWebRequest.Create(urlstr);

            System.Net.HttpWebResponse _Response = (System.Net.HttpWebResponse)_Request.GetResponse();

            System.IO.StreamReader _StreamReader = new System.IO.StreamReader(_Response.GetResponseStream(), Encoding.Default);

            StringBuilder _StreamString = new StringBuilder();

            _StreamString.Append(_StreamReader.ReadToEnd());

            _StreamReader.Close();

            return _StreamString.ToString();

        }   

    }

}//提取源文件中的文章内容，去掉页面的头尾。