网页采集程序（超级简单版）

( w5 X4 K& Y" p4 o& _8 N

) v4 ]6 r% X% {" ]0 H

网页采集程序（超级简单版）

2 `$ J, E, A$ ~; n7 j! C

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

8 f/ o7 j7 i/ [; _$ `

02         { 

, @8 B0 H6 A& q& H5 D

03             //方法一： 

6 U$ s+ _" Y2 @6 f& w

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

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

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

4 T' Z3 {4 X: o% D( y0 h' Z

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

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

3 H N7 S6 p9 C- U; g% c: g+ i

09             //Response.Write(html); 

10   

11             //方法二： 

3 l. F6 I+ H' e; H, ~- y* p

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(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

' r2 E; x; ~ h/ s% X, {: M

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

% e) Y# H* c8 a R1 k

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

( @- p. S$ R. g. S O7 |1 ~/ C

21             Response.Write(html); 

* z& d* L8 `- s4 R

22         }

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