网页采集程序（超级简单版）

; q) m; w/ R: ^2 Z+ L: |/ f! I

网页采集程序（超级简单版）

2 b+ }* p8 _4 J) M" z8 T1 f

+ E5 q: w$ R# C" ]; ^; d

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

) m0 d0 s' ~: |0 C' W

02         { 

0 q- O$ b; E' R; y- U6 c. I

03             //方法一： 

( l) q: V' o E# s

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

4 m6 Y5 c* i s$ L/ {

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

3 c9 w# [- _% `6 O. K

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

. K! w# v# R: g. C ^" K7 b

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

4 |5 L7 p' z: L6 F% b

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

2 Z1 X$ X I0 R; j" A. k( c

09             //Response.Write(html); 

1 l) `$ ~3 ^6 A$ h0 B4 O' w9 o4 X

10   

6 [" q" t' r# i! i

11             //方法二： 

4 ~1 h/ Y z( f8 X

12         //获取整个网页 

L. J5 _; @6 N& C3 m; e' B

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

0 Q8 k$ N& ^0 u' ~8 K7 D! f

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

3 S9 ^; z' T3 [- Z- E

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

16             string html = sr.ReadToEnd(); 

& ^4 I: A% U' @) Q3 }1 O

17             sr.Close(); 

18             //根据规则获取想要的内容 

" @: x+ H7 }5 s4 `. C

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

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

1 S. C9 \# H* s. j1 K

21             Response.Write(html); 

22         }

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