网页采集程序（超级简单版）

$ S, s5 t; W3 k. L

网页采集程序（超级简单版）

3 h$ }7 H2 V* V' j

网页采集程序（超级简单版）
01 protected void btn_click(object sender, EventArgs e) 

02         { 

2 Y) K8 V6 P; T$ q& i5 q9 N: C

03             //方法一： 

8 B% H, X2 }6 v4 d5 u6 x

04             //System.Net.WebClient wc = new System.Net.WebClient(); 

05             //byte[] b = wc.DownloadData("http://www.baidu.com"); 

06             //string html = System.Text.Encoding.GetEncoding("gb2312").GetString(b); 

07             //html = html.Substring(html.IndexOf("<p id=\"lg\">") + "<p id=\"lg\">".Length); 

$ S2 }" `, l5 `

08             //html = html.Substring(0, html.IndexOf("</p>")); 

09             //Response.Write(html); 

10   

11             //方法二： 

12         //获取整个网页 

13             System.Net.WebClient wc = new System.Net.WebClient(); 

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

15             System.IO.StreamReader sr = new System.IO.StreamReader(sm, System.Text.Encoding.Default, true, 256000); 

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

0 r+ M6 S' M3 V0 ~6 [9 j

19             html = html.Substring(html.IndexOf("<p id=\"lg\">") + "<p id=\"lg\">".Length); 

20             html = html.Substring(0, html.IndexOf("</p>")); 

21             Response.Write(html); 

8 \: X0 s1 o, y' B `* w$ H. c4 D+ Y

22         }

http://hereson.javaeye.com/blog/207468