网页采集程序（超级简单版）

2 { e, N7 ~- C$ P( M% x: F

网页采集程序（超级简单版）

$ P. H" C0 ?8 ?9 {+ l7 F7 w2 d4 f

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

02         { 

- ^& R c5 {! U: j

03             //方法一： 

* I6 [+ _" ~4 c! l! w

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

( x! A' v" _7 Y$ g& {" ^) Q

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

7 b2 L2 r- S5 i3 U) f) X( C

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

2 {' n7 C& \- Y

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

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

% ^( P- l& B0 Y, S2 f+ s

09             //Response.Write(html); 

7 L$ K* U; ]; R8 P$ |+ O! \/ Q9 _

10   

11             //方法二： 

12         //获取整个网页 

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

/ Z6 f. q4 i. e- ]9 V7 I

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(); 

* D8 i9 c4 d! T3 c; J

18             //根据规则获取想要的内容 

) N' t! N8 Z3 Z4 U' s) d3 j* h& q- F$ h

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); 

22         }

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