网页采集程序（超级简单版）

7 }/ ~/ c( M! J7 B; o- g% t; d9 }

网页采集程序（超级简单版）

1 Z6 A4 R- \' c, l0 U; ^

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

1 G4 F7 @. _- z4 @" c2 g/ i* c9 q

02         { 

03             //方法一： 

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

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

7 U3 D0 n% S7 ?: I: E6 l

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

4 R+ [) I8 w3 L" V# J3 P

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

g% v: h1 m" Y* J9 {- P

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

09             //Response.Write(html); 

5 j3 L" D/ D( k. K3 k8 `

10   

11             //方法二： 

* V" z2 k& w( W/ P$ @) O; _% q

12         //获取整个网页 

4 {! l a7 p" u$ d, p, E8 w' b

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

1 M3 X; E# ^: |& n0 ]9 g

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

3 k; X2 R4 O: J8 _/ }7 F" b' X

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

16             string html = sr.ReadToEnd(); 

" ~, I/ |! {0 V# Q

17             sr.Close(); 

18             //根据规则获取想要的内容 

% t$ U6 u+ w+ J* l4 b' t

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

8 C. P" S# }+ q5 ~ y3 K

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

21             Response.Write(html); 

8 x/ o: g4 o" v

22         }

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