网页采集程序（超级简单版）

; l* u% H3 R' y

9 N) z+ r k, d7 T! \

网页采集程序（超级简单版）

) |6 J0 i# g/ 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： 

1 h4 ^4 N' T8 P) x& R

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

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

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

, z+ }% f8 G# d4 p" f3 J3 r

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

/ `* f8 l5 d% S- b7 [) k

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

09             //Response.Write(html); 

2 [. v" @ C% k$ @7 r6 N; [8 b! G! Q

10   

11             //方法二： 

12         //获取整个网页 

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

3 }. o8 h+ o! W H

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(); 

7 J) o1 K' Y D

18             //根据规则获取想要的内容 

1 _, V0 J5 }( i# q' @

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

0 C) ?4 Q3 |0 ?

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

* f, ~! H% \' s0 I" C& `% s |4 f

21             Response.Write(html); 

22         }

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