网页采集程序（超级简单版）

6 g) f& U9 b5 S$ z9 @7 f7 o2 K

1 t' D9 D% T# a- e9 z

网页采集程序（超级简单版）

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(); 

2 G1 b4 I& k P% w

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

' s! ?( M" ?1 h+ }( 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>")); 

4 H5 W, O, M7 S* t1 L

09             //Response.Write(html); 

10   

11             //方法二： 

9 p( m2 Y! b0 |0 Y' O7 y, Y

12         //获取整个网页 

/ O6 a; x' ?& |7 T; @

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

. a2 }7 _- D/ t; T% d

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); 

* O& J/ U# ^ u

16             string html = sr.ReadToEnd(); 

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); 

% c/ Q/ \# `$ m( H' J* M

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

21             Response.Write(html); 

. P) \+ s2 @8 E1 X) e# Y" f- ~9 J

22         }

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