网页采集程序（超级简单版）

r. n, `) o/ o. B* S' }! M, i# l' l

网页采集程序（超级简单版）

2 s0 d) _0 h& T

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

02         { 

b: x3 C+ b) i& C" k: b

03             //方法一： 

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

2 H/ `+ C! u0 Q

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

9 Q6 X5 W/ ?, e4 v# p; E7 B1 P- q7 M$ b* {

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

) V. M. A9 k, V

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); 

7 z% m5 w% G4 @5 ]3 U) c3 ]' b

10   

: W- I+ y! F) F% v+ m' X

11             //方法二： 

! x- f) b& x5 v L! o/ _1 B* R8 j# T

12         //获取整个网页 

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

1 ^/ Q; Q7 v3 f3 J# E5 B

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); 

4 L! A( ]; B. A

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

7 M) d( y5 g4 J

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

; ^& x( O: U6 I8 e# M' D$ W- x

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

. H4 U" M: f" D% |" u- F

21             Response.Write(html); 

0 p& T- V y+ `" j

22         }

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