网页采集程序（超级简单版）

6 A: h, y5 {1 d& g8 O) \

网页采集程序（超级简单版）

1 g) n0 E, ]8 z+ L

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

3 E1 p Y5 m3 g+ B1 T' ^

02         { 

4 y7 Y, j, M9 E, _

03             //方法一： 

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

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); 

! Q$ C% e, O+ _- X# a% W3 v6 X; x

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

09             //Response.Write(html); 

$ Q2 n: n9 { ~$ h, x# k

10   

0 B. y- l* _" F$ O

11             //方法二： 

12         //获取整个网页 

! _& l8 Q# V. f5 n! C6 J3 T

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

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

# S+ X+ n, i3 w1 i/ Z. M7 R" N

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

8 N0 i7 T- v z& b0 p# j* C, t

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

- U Y0 V5 d" J) M

18             //根据规则获取想要的内容 

7 ?$ n# m8 r) Q

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