网页采集程序（超级简单版）

网页采集程序（超级简单版）

# e$ e: ]" c& x- }4 i

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

02         { 

, N" `5 `. i) F% x

03             //方法一： 

. C$ V, g) a, ]4 T! K/ H

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

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

6 n$ v4 a6 s8 x6 g8 p$ {

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

# l; n' {0 ~' o$ U1 w0 e

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

# g# H6 k3 Z! c! r9 |/ H

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

09             //Response.Write(html); 

) D1 E. p3 J8 Z* U5 X' L+ g

10   

11             //方法二： 

12         //获取整个网页 

$ q( ^9 w# q2 s+ O

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(); 

; H, d7 E$ }1 _

17             sr.Close(); 

7 x+ h% U6 P8 O& O2 A( W

18             //根据规则获取想要的内容 

+ B, o( H2 W9 K: E4 U; m2 H. j- z4 v0 h

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

% ~- s1 D; e- h- P7 Z8 O2 p2 b

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

# t6 J' D5 A2 [, D1 T" r( R( T1 @

21             Response.Write(html); 

22         }

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