网页采集程序（超级简单版）

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) 

02         { 

03             //方法一： 

' m1 ]/ P' v- k7 [9 Z

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

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

. L1 ?5 j7 x( U4 ^: n6 J; T0 N( B

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

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

6 M- j+ O: ^; a' [; E! o2 ^+ t

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

09             //Response.Write(html); 

0 b0 }9 b+ f0 j/ |

10   

11             //方法二： 

12         //获取整个网页 

& Z- ]+ Z8 L3 B; W- X# x0 Z

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

' X# b; K+ i F

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(); 

3 [5 f0 t& i% {8 Y( I) N

18             //根据规则获取想要的内容 

! P$ s, `6 s' e- ]6 N5 l

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

6 K0 P4 V/ f1 r

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

21             Response.Write(html); 

% }) e# C! U7 M0 j# ~

22         }

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