网页采集程序（超级简单版）

网页采集程序（超级简单版）

6 g" t% h: I' e* m2 S9 D: ^* w

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

02         { 

+ B9 F, c" x5 I9 A+ I% k

03             //方法一： 

9 |6 K7 e6 m; _7 G5 C- O

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

) n. B) B, E8 W3 k/ K

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

9 k0 d' w/ m: p: [" K# E4 @

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

7 e7 I, B4 M, s& `+ p- k% ^

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

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

7 v( I4 F1 h s. q; c3 I+ @* x& R. n

09             //Response.Write(html); 

6 ?9 q ?* X6 @$ p1 X. I! `, ^& }" r

10   

11             //方法二： 

& U6 f# G% s! X% [2 n& ? m

12         //获取整个网页 

% p3 k* ?* h. g9 P; _4 D, A

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

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); 

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

6 F' u3 p( {# `& p2 ?

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

* x1 m" J* Q8 B! c1 i& n+ s& ?. g3 Y. J

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

) Q& M/ G4 W; e( Z" l# Y& ~( a! ]

21             Response.Write(html); 

22         }

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