网页采集程序（超级简单版）

& D- L3 P# N, `' V" q5 k# n

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) 

02         { 

03             //方法一： 

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

0 R8 I9 f, s7 M

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

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

5 G! e' f6 C7 J; z; s" ~+ V

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

8 W2 \0 E& }, I. ^: q, H

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

! j, l- n" R% Y' m/ p8 J- \

09             //Response.Write(html); 

6 Y% `. k+ N. ?/ q; L( b

10   

11             //方法二： 

2 g7 N& @& ~3 s8 n2 B e

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"); 

8 W# _2 D! n; p) X' O1 e# W5 O

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

: O8 t: ^% l' R+ Y6 u

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

7 e8 R0 R, S" g b& w8 n) C

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