网页采集程序（超级简单版）

. _# n" q1 M; I7 N

( T( |# u4 `3 h( P" y

网页采集程序（超级简单版）

, q5 V' {( D* C Z4 _/ J

9 k- e! b j$ {4 ^. f9 [

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

02         { 

4 E! f. `# R' h3 o9 `( a+ M

03             //方法一： 

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

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

F2 t7 `9 K- E$ n" |# t' v

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

* E( e- R* ^; H- v7 p

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

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

09             //Response.Write(html); 

10   

11             //方法二： 

12         //获取整个网页 

, l: f2 o: u% V& s( t* J2 [7 ~9 P0 R

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

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

2 z/ i, W, |3 E# y1 |+ Y; b7 F

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

( ~, h9 ^+ T8 B0 f) L6 I

16             string html = sr.ReadToEnd(); 

6 C& ~3 F r( ~

17             sr.Close(); 

18             //根据规则获取想要的内容 

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

! [+ Q. v4 q0 n

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

1 \2 l5 J4 X% c' q5 ~/ E2 m

21             Response.Write(html); 

1 T+ ~6 f3 j( @5 r

22         }

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