网页采集程序（超级简单版）

0 e- O$ z; P6 q0 H

% v5 i5 T& p4 N- o5 Z. U

网页采集程序（超级简单版）

* _+ | ?. D" x% W$ L$ \

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(); 

/ B: {/ O: g8 r7 `6 H) K0 @

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

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

& }7 V6 H+ {* W0 L) F9 L# J

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

+ Z' b( Y& A4 Z0 i. K$ Y% ~

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

09             //Response.Write(html); 

% J3 d# {- W: j+ u% ^

10   

11             //方法二： 

: C2 E/ K& |. B2 o

12         //获取整个网页 

2 K; a( b; P8 ]7 c

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

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

4 U l. B2 v; h8 ^" l K# p# a* M

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

( D [ |4 X) ]1 j8 B8 {: o

16             string html = sr.ReadToEnd(); 

4 R7 j, X' |4 ]3 g! J- b" Z% O

17             sr.Close(); 

18             //根据规则获取想要的内容 

( G) t' ]9 B7 |( ` c

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

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

21             Response.Write(html); 

3 T) y) T) @( M( Y/ x$ m" B

22         }

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