网页采集程序（超级简单版）

4 B8 F9 ~ ]1 c6 M" M9 {. y( [

网页采集程序（超级简单版）

7 y9 e5 Y* x9 n# M

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

7 N7 J" N, [1 c/ \8 ?) U( I& j

02         { 

. x5 W' w" y3 u& Q& D& e& [; T* S

03             //方法一： 

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

* z# |$ {7 b$ h! a5 K" M X1 M

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

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

8 y( |" |+ p! T- M2 o

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); 

10   

11             //方法二： 

& I7 z5 M# A' _/ R; S

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"); 

7 E1 x- S$ G4 O

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

- \0 y9 g5 u$ Z; J

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

: i2 }; _: B# ]. ?; |) G

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); 

0 E0 r: L* F U$ K5 _

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

% E' b6 \2 X& W: A- l, E6 K9 q

21             Response.Write(html); 

22         }

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