如何獲取網頁上的內容

如何獲取http://cheman.chemnet.com/dict/zd.html網頁中cas號中的信息為例

第一步：到http://htmlagilitypack.codeplex.com/網上下載簡單好用的快速 HTML Parser，HtmlAgilityPack.dll文件

第二步：到VS中建一個控制台應用程式，將HtmlAgilityPack.dll文件引用。

第三步：在CS文件中寫入如下代碼

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using HtmlAgilityPack;
using System.Net;
using System.IO;


namespace Cas20080503
{
    class Program
    {
       static  StringBuilder sb = new StringBuilder();
        static void Main(string[] args)
        {
            int a = 0;
            for (int i = 1; i < 394; i++)
            {
                string url = "http://cheman.chemnet.com/dict/cas/" + i + ".html";
                GetNode(url);
                a++;
            }
            System.IO.File.WriteAllText(@"d:\test.txt", sb.ToString());//將信息寫到txt文件中
            Console.WriteLine("ok  a="+a);
            Console.ReadLine();
           
        }
        public static  void GetNode(string url)
        {
            // 下載
            WebClient client = new WebClient();

           //以下是設置代理
            WebProxy wp = new WebProxy("192.168.0.83", 80);
            NetworkCredential nc = new NetworkCredential("auyeungck", "it_auyeung41");
            client.Proxy = wp;
            client.Proxy.Credentials = nc;
           //將網頁上的內容放到内存流中
            MemoryStream ms = new MemoryStream(client.DownloadData(url));
            // client.DownloadFileAsync(uri, Path.Combine(saveDir, saveName));


            
          
            // 使用預設編碼讀入 HTML
            HtmlDocument doc = new HtmlDocument();
            doc.Load(ms, Encoding.GetEncoding(936));//此處的936能解決中文亂碼問題

            // 裝載第一層查詢結果
            HtmlDocument docStockContext = new HtmlDocument();

            docStockContext.LoadHtml(doc.DocumentNode.SelectSingleNode(
        "/html[1]/body[1]/div[3]/div[2]/div[2]/div[1]/dl[1]").InnerHtml);

            // 取標頭
            // HtmlNodeCollection nodeHeaders =docStockContext.DocumentNode.SelectNodes("./dt[1]/p");
            // 取得數值
            HtmlNodeCollection nodes = docStockContext.DocumentNode.SelectNodes(
        "./dd[1]/ul[1]");

           

            // 輸出資料
            foreach (HtmlNode nodeses in nodes)
            {
                Console.WriteLine("nodes: {0}", nodeses.InnerText);
               // Console.WriteLine("nodes: {0}", nodeses.SelectNodes("./li[1]/a[1]"));
                sb.AppendLine(string.Format("{0}", nodeses.OuterHtml));//將信息寫到字符串對象中
               // sb.AppendLine(string.Format("{0}", nodeses.OwnerDocument));

            }

           // System.IO.File.WriteAllText(@"d:\test.txt", sb.ToString());
            doc = null;
            docStockContext = null;
            client = null;
            ms.Close();
            Console.WriteLine("Completed.");
           // Console.ReadLine();
        }
    }
}

參考網站http://msdn.microsoft.com/zh-tw/ee787055.aspx