网页采集程序（超级简单版）

3 K( Q9 s) b- j) a/ A. j# J

网页采集程序（超级简单版）

9 k. B1 h: x" E7 w% A" d4 w5 y

+ F8 E/ E3 w+ g6 ~

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

% a/ I' j/ I# n( }: b/ [3 t

02         { 

5 `, q2 Z; ]- f% ?1 m3 s% x6 F( M& @

03             //方法一： 

* o+ O) n$ W7 R2 }4 b S

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

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

5 s4 p3 z8 Z4 W# K! |: d

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 

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); 

# r0 g5 `5 m* X) R5 D

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

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); 

8 f( |3 A+ r1 @( G

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

21             Response.Write(html); 

22         }

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