网页采集程序（超级简单版）

" m, @/ i' m" m) M3 m6 i! j% I

8 }: x+ O& V. } ~% F; m+ e

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) 

/ `- K: O$ \; \! I, `& {, w9 a

02         { 

`, Z8 L& I' u6 I* y: }2 ~

03             //方法一： 

. j' T6 a3 y! \7 J! x& T: X

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

* L% K8 ^" ^# i

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

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

5 M* O6 ~! l$ b' J/ {. V7 @" q9 u

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

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

5 t2 @( p! U3 n

09             //Response.Write(html); 

10   

6 G8 A7 G* C% ?8 S0 d4 O

11             //方法二： 

12         //获取整个网页 

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

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

! w2 e8 q4 g1 b6 A5 S( u

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

16             string html = sr.ReadToEnd(); 

- L; x+ q$ H3 X! y

17             sr.Close(); 

18             //根据规则获取想要的内容 

( [7 N) D3 Y7 n/ Y5 P

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

6 u) }" H' ]- |0 d* q) p1 Z) f

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

21             Response.Write(html); 

22         }

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