网页采集程序（超级简单版）

1 }9 K$ O% _% m1 c

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         { 

7 m3 P7 I9 l, T0 v

03             //方法一： 

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

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

, [+ v- |% R# G: b- o) t

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

1 j2 T) r* D6 |4 z2 \% \" n

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); 

- b( Z; X4 s5 z7 G

10   

11             //方法二： 

) b$ {5 \* U; U2 t

12         //获取整个网页 

M4 e% W2 M& m

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

p* ~2 H/ z' S

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); 

0 @7 v9 p/ E9 c8 ]0 U1 _

16             string html = sr.ReadToEnd(); 

9 L! A9 B: X- J" w

17             sr.Close(); 

18             //根据规则获取想要的内容 

) n* t* i$ Q3 R4 ^8 I7 W9 [ | u8 M4 e

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

5 J6 R: Q; P& X; V7 q& F6 C

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

: b" |9 `! U8 x; z2 I+ \* c

21             Response.Write(html); 

$ Q0 \1 H- n/ W# K

22         }

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