网页采集程序（超级简单版）

8 D+ b, h% D: x0 K. h! h

网页采集程序（超级简单版）

; P. p8 K" t) w. @' C/ A

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

02         { 

6 m$ n9 S4 W9 N+ S$ L

03             //方法一： 

/ R( o& F1 W9 C- E& D

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

( k- h5 I4 B( F6 Z; U

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

3 b7 z& N, P5 p

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

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); 

" Z3 X+ d, z- ^1 C! c( b8 G

10   

& F$ t9 N/ Z& D: g- J+ `8 y4 p

11             //方法二： 

12         //获取整个网页 

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

6 W5 B& q! r! x1 G5 s

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

+ j) l7 r* ~4 E' B5 Y0 N

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

* T! C: X1 K7 q0 u8 Y( x

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

% Y. o. {3 ~8 L- K. o9 D

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

21             Response.Write(html); 

' P) R$ T! C9 }. K

22         }

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