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) 

" ^7 g( y8 p2 C: y4 I* u6 ]! a+ A

02         { 

03             //方法一： 

& {& R5 W6 t, x: b, ~9 ~5 }

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 n5 S( ~* n1 N( U

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); 

5 w0 C( K! M& j6 J9 h0 q

10   

3 C; s7 X5 l3 [5 e7 X" {" q

11             //方法二： 

( B- f8 D3 P5 T

12         //获取整个网页 

* i% H8 B) _" ]" y' J

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

5 s: O. Z; O9 `- L. k' q8 N

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(); 

" ] ~$ E7 y7 a1 |; }

17             sr.Close(); 

/ l9 `/ W, a, ?" t& X1 ]/ s

18             //根据规则获取想要的内容 

4 _8 R o0 p8 | _

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

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

1 I0 w% g& j& {4 i$ x4 P

21             Response.Write(html); 

22         }

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