网页采集程序（超级简单版）

& Y" V8 a. l$ o, c& Q

2 I" V/ l0 }& c' H8 \7 M

网页采集程序（超级简单版）

9 ?) I! U. L! z% P

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

6 s( e/ w! d; ~4 H

02         { 

03             //方法一： 

8 j% \% a! r8 t/ f

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

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

- z2 a8 q1 R* ^ o( y

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

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); 

$ J' M$ p3 N6 i+ t$ b

10   

11             //方法二： 

12         //获取整个网页 

% A1 Z8 L. h) a% {

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

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

; e# g6 D& J, t0 h

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

16             string html = sr.ReadToEnd(); 

* o. B8 }+ ?! P7 z

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); 

* `0 A! S* J* d: P* @( w

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

21             Response.Write(html); 

22         }

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