网页采集程序（超级简单版）

+ J( P( }( F! Z) G1 b: q

网页采集程序（超级简单版）

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

/ _# m6 @" K5 r' ?5 n, g. }

02         { 

03             //方法一： 

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

# h, k) b* ` R0 a& C; l H) b- t

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

" ^( e( Z$ c( `4 n! Q

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

" G% b7 N% j0 ]8 K

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

. Y/ u/ @! n; T* b; ] l! l

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

09             //Response.Write(html); 

_7 s& C. }4 c* z) b: Y

10   

- W# O/ c2 t1 P9 }; w# Y: j# G' o

11             //方法二： 

( I/ _: a- u9 A A2 T' e% l

12         //获取整个网页 

2 u" G1 B0 H# V& Z1 l

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

( b! {6 o) O( E- p/ v

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

! z) y1 h& O3 ^" c7 o) [& }

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

9 k9 ]2 O# `9 H' A0 D( V

16             string html = sr.ReadToEnd(); 

6 d9 O8 ?! ?1 e. o( Q( t

17             sr.Close(); 

2 S4 y; ^ r* _3 o% I+ u1 K' [: i

18             //根据规则获取想要的内容 

3 z5 n! `# @( O; C, h Z Z C

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

# o: e8 L% A" y5 q4 o

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

( X, N3 D0 A: I( t

21             Response.Write(html); 

22         }

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