网页采集程序（超级简单版）

网页采集程序（超级简单版）

/ m9 r4 `7 N. `* s

8 J1 V* c1 Y$ p" W% }' j' \

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

! I: C; x4 U& `9 J1 m1 P3 _

02         { 

03             //方法一： 

2 S, \1 d4 n: O5 q+ m

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

4 p! H; ?" {/ ~3 s/ z; G6 m

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

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

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

1 f8 [# B3 x0 c4 t9 Y% p- h

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

09             //Response.Write(html); 

10   

; y }# v) e+ P, B k5 W# A5 n

11             //方法二： 

12         //获取整个网页 

3 B0 D; Y$ b$ ~! c

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); 

; T. k6 N/ V% O

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); 

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

$ n3 |+ X, X0 m) a9 P# e

21             Response.Write(html); 

2 _+ R1 v9 `0 e

22         }

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