网页采集程序（超级简单版）

" `* g8 e9 l& }7 ^ i

网页采集程序（超级简单版）

+ ?$ L4 _1 ^- Y7 m' ]& c+ K

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

( C6 s4 P. p3 n. |8 m# C

02         { 

03             //方法一： 

; K$ b8 I. D1 t6 H0 Z

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

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

3 Y! O' Q+ \4 Y

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

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

* B! t# j1 e& Y4 M1 N, M: W

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

09             //Response.Write(html); 

10   

11             //方法二： 

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"); 

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

`5 d* o* ^) R$ W' C

18             //根据规则获取想要的内容 

7 P% m& C7 C; d, t# o

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

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

+ N+ K7 R# p2 W( z, l

21             Response.Write(html); 

22         }

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