网页采集程序（超级简单版）

( o, `5 b! |' `1 R

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) 

* C S' y# b% \" }6 M% r

02         { 

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); 

* p2 N- z4 w% a' {3 Y* z0 Z7 r

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

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

' D# Z- G+ Q! S% V, L* D* V1 N

09             //Response.Write(html); 

( @0 V# T9 X5 T6 r/ M8 m

10   

11             //方法二： 

12         //获取整个网页 

5 X, M( W" O' K, K$ u. u

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

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

, u8 J1 X, b! k% D6 E# i* f) r5 z

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

16             string html = sr.ReadToEnd(); 

5 p8 E6 i) V* _/ F

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); 

$ H$ @1 A- F! g0 p0 b2 ]0 C5 c

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

8 J S' M$ H5 {$ o1 z' C0 p( X: d% x

21             Response.Write(html); 

22         }

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