网页采集程序（超级简单版）

3 z `( ^3 [3 o- s

网页采集程序（超级简单版）

1 L( _/ g5 X8 [0 Y

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"); 

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

2 f! a x8 P( F0 A5 t: L

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); 

! {7 y1 z& A( `& L* _

10   

/ a, m6 a! {$ q6 p% |

11             //方法二： 

! G; }3 j0 b% C+ ]+ R

12         //获取整个网页 

% a/ ^' E# m2 g

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); 

: _* H! s; C& k- u/ T. q( A

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

% r8 q& Y( `. r# a. M6 p# s ]

18             //根据规则获取想要的内容 

m: V+ t5 `2 e: r% f% I X- W% I

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

0 B3 F' r6 K, o! i! \; G

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

21             Response.Write(html); 

22         }

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