网页采集程序（超级简单版）

: z3 H/ ]% D" `4 r j

9 R3 X4 g t, d) O( K; i

网页采集程序（超级简单版）

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

: g; q; g& O" H' A# S( _

02         { 

03             //方法一： 

( B4 e# i* K* f5 g1 M& W' `% A, C5 e

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

9 q; z' [2 n% A/ L0 ?- V: W

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

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); 

10   

11             //方法二： 

12         //获取整个网页 

3 T5 H* ?+ w( `/ T$ `

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

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

% n. M4 L7 p" ~6 Y+ F* r

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

16             string html = sr.ReadToEnd(); 

+ O' g9 D$ ^, h8 |! H) X3 d& v

17             sr.Close(); 

: D- C w% w* } y# }

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>")); 

3 W7 d, g/ x& K

21             Response.Write(html); 

& }6 O- R/ J# t I

22         }

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