网页采集程序（超级简单版）

6 ^, X) O5 I* C4 ~

* S& L9 l' W; c" K4 P

网页采集程序（超级简单版）

+ H" I( l0 R) ^7 H

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

02         { 

03             //方法一： 

" |' x. E& Y1 I. h- N7 i; x n" o( v

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

) E9 C B9 `# T& s$ v, c# R

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

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

/ L" M" a$ q2 n) s5 ^

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

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

7 l9 @0 m- W2 n. C5 ?6 o/ s

09             //Response.Write(html); 

+ L( q% N' r" I$ S

10   

11             //方法二： 

% M& a( j- s4 v! M/ T

12         //获取整个网页 

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

5 ^- c. ]1 q* z. f3 ^, Y# W2 T

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

/ t& E/ h8 w$ y1 e5 U; T3 o

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

) G7 u. F0 ?, {

18             //根据规则获取想要的内容 

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

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

+ J9 R% G' f( b, _+ d M% t& H

21             Response.Write(html); 

22         }

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