网页采集程序（超级简单版）

" @0 p" \' e* e$ c! r

- P7 O3 h( u' S6 x) H

网页采集程序（超级简单版）

i, a' q1 b; a3 l& I

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： 

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

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

% y6 H" T1 c7 n% l3 a

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

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

: q h' R/ b. \; G

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

09             //Response.Write(html); 

10   

11             //方法二： 

/ y* Q* n4 d& V* x# ~4 E; _

12         //获取整个网页 

% b, w) _2 l2 _# @% Q

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

& x1 H- d% r; l5 H/ A: I2 x

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); 

/ }9 G C. g, R. m {

16             string html = sr.ReadToEnd(); 

9 h7 E8 y: M9 v, C1 c! F; @. V. P; @

17             sr.Close(); 

18             //根据规则获取想要的内容 

7 J6 o2 t/ a9 Y0 B

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

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

21             Response.Write(html); 

22         }

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