网页采集程序（超级简单版）

/ w# L; B; z# Q

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(); 

. O6 S1 K3 M" g; I$ P7 D# X

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

* X! @0 K( l, K3 P

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>")); 

' Z& Z4 ?* E# @, M. |

09             //Response.Write(html); 

5 L" H& K; _4 b' a, t, |4 L/ T

10   

11             //方法二： 

12         //获取整个网页 

4 c7 `9 |4 k6 N, u- O4 i

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

+ F7 h& k4 @' Z8 C

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(); 

* f+ C; P. D# u) ^, d" d

18             //根据规则获取想要的内容 

' J, `, V" P9 ~

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

/ S! n8 {. B" z0 ?7 C' S

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

21             Response.Write(html); 

22         }

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