网页采集程序（超级简单版）

% a/ q5 D) U) ~! \

网页采集程序（超级简单版）

; \4 M/ ]. C) t4 u" K H

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(); 

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

$ j9 S" \5 {( h8 M

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

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

- \4 S; h8 z4 e* `' ~

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

6 `* ^' o6 A! \2 W- Y. B+ j+ _& P

09             //Response.Write(html); 

10   

11             //方法二： 

# N3 s! n2 ?* A/ a

12         //获取整个网页 

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

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

' q8 k; G/ I! H1 N

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

. M1 |, r2 [+ x N* ^" P, f' v% Z

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

) K$ b! r) n4 |+ o1 W' [5 T

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>")); 

21             Response.Write(html); 

22         }

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