网页采集程序（超级简单版）

网页采集程序（超级简单版）

+ u0 U# R" V6 S

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(); 

8 A7 z u6 m# v* p; m& X( G- B4 s

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

. J, e, z8 @$ w7 @0 p

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

+ s% K& u! @* k+ v# ?- k) P; j' M

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

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

+ f. {( ^& s- N$ g" R+ @

09             //Response.Write(html); 

z6 \' `7 ~# P$ c: G

10   

6 L! z ]0 p9 C I4 V* |

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"); 

0 `4 S7 D5 H* O: a

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

( U3 p! _3 b) N- d

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

! h8 |8 Z7 h; v" I

18             //根据规则获取想要的内容 

+ y9 T7 P. n3 A" A; O

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