网页采集程序（超级简单版）

网页采集程序（超级简单版）

, x( i5 x2 Z* N. g6 c" w; Q

z' O5 @" \1 h, p3 f. n# h

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

02         { 

; k V m9 h( P) ~

03             //方法一： 

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

3 U* [% K+ `. s3 ]) ]) _$ `

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

1 S7 I! ~9 G% W. _* [

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

; t' ]0 E9 T5 I, q* F$ e* U) K* q3 X: F7 X

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

% ? e8 M X, N2 n! V

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

6 p+ y& v0 ~5 B

09             //Response.Write(html); 

$ h2 B0 h: T, h4 I4 {& A$ ]

10   

6 g/ C" H3 C9 f+ `

11             //方法二： 

! a4 {7 E7 ]8 t* U4 x+ `

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); 

16             string html = sr.ReadToEnd(); 

: B3 ?3 ]% \- s- c" Q* X5 L+ f

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); 

4 M4 @! c1 W. {) D

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

; G' ^- P& B9 | l! z# `# g- }9 L

21             Response.Write(html); 

+ _/ P# ~* ?- V$ p4 g

22         }

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