网页采集程序（超级简单版）

" R, [- R" U( E3 Q7 x# K" j9 }

网页采集程序（超级简单版）

- N/ O2 T" G# _: ]) j& O

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(); 

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

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

: Y: o, K* {4 D; f% ^

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

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

09             //Response.Write(html); 

, q* b6 c7 k# h. a

10   

2 x7 X4 G' Z+ X! D- i H0 i) L

11             //方法二： 

4 p! w7 L, ?' E9 f- q9 E+ y

12         //获取整个网页 

j& k! u, P% n, G8 _9 w

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

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); 

! l \! ~5 J, R1 q; Q- P

16             string html = sr.ReadToEnd(); 

; @; }4 ^* d& x

17             sr.Close(); 

18             //根据规则获取想要的内容 

" T# U- p2 N' `4 O9 }4 F

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