网页采集程序（超级简单版）

网页采集程序（超级简单版）

! l7 I1 ~ J, v5 s& e1 y/ T

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

3 _2 t6 T: u; w& O

02         { 

0 x+ H8 {: t4 Z8 h1 T$ W- ]

03             //方法一： 

, q1 M9 v% [. H2 [" o% s

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

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

7 C/ ], L1 D8 ~

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

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

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

& p6 Y( V$ Z' h; B* U% w

09             //Response.Write(html); 

5 L* m l# j2 j J$ d5 v# T9 @

10   

( I! X# V0 R8 m, W, b

11             //方法二： 

12         //获取整个网页 

+ w% t; m5 ]# _, ]" n; s9 k4 }8 T

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

5 E; K# N! i2 E1 c. Q% X

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(); 

6 @3 M/ w( I6 o- T+ d, o

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); 

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

21             Response.Write(html); 

9 v/ e# r: g0 J% @# r

22         }

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