网页采集程序（超级简单版）

/ @: _6 d# Y& T

网页采集程序（超级简单版）

+ a4 \- a* k, X8 D, ^

, j- E3 ~) u$ n7 U. i# M

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

( I8 v9 m, d. j

02         { 

03             //方法一： 

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

% a: D7 A3 ?: N6 H" n# g

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

( h8 O# ^* M9 K/ O4 j& I% g

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

. ?' J+ Z* P. k

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

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

% a3 M5 B8 s2 j, [- s

09             //Response.Write(html); 

$ H" ?* F8 r. C# E, w& F" N8 w7 b

10   

11             //方法二： 

12         //获取整个网页 

9 U# Q* n+ Q/ w. u( Y& c

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); 

. |' d, m8 V7 ?, h4 [

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

5 S6 U& c G$ Z7 T. k2 J7 f

18             //根据规则获取想要的内容 

* r6 {5 b8 E& i* {' C9 u' d# y

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

- s- H. z% `; A- w- g2 T

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

21             Response.Write(html); 

22         }

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