网页采集程序（超级简单版）

/ k }: j& y0 \3 {/ E1 f" F& m

. ^- _# g; L0 t, Y5 R

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) 

0 _" e. ~; P3 e1 g& i

02         { 

03             //方法一： 

5 E; D! D% e% r8 |* h' T3 g! i$ t

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

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

{6 a2 Z! e& x

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); 

8 r; Q! q4 v2 D% `8 O0 }

10   

. y( S( A9 A* B/ W; w( n2 h4 `- P

11             //方法二： 

k! \* L# Q$ V

12         //获取整个网页 

1 i1 B e3 ~: c* W$ v0 S. n; G

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

* n( m# S* R: h3 b% s; l0 T7 D

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

& m7 e. `/ u& \- p; X4 V! p7 Z) b/ l

15             System.IO.StreamReader sr = new System.IO.StreamReader(sm, System.Text.Encoding.Default, true, 256000); 

- i7 S5 A6 w! ]& C1 G6 r8 J

16             string html = sr.ReadToEnd(); 

& G/ D h5 Y# ^) h% D8 u6 O. Y

17             sr.Close(); 

18             //根据规则获取想要的内容 

* T$ [' H& l/ G

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

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

7 |& i8 x; F& }2 G, u% J

21             Response.Write(html); 

3 [( O5 ^2 l { x1 j

22         }

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