网页采集程序（超级简单版）

; r/ p, b" E& K2 O8 b6 T

网页采集程序（超级简单版）

9 Z4 x3 b4 l+ E

2 P! Z1 A2 [) `# D. i

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

( k8 O9 H6 F6 J2 n7 u7 x

02         { 

. x# y, u+ c7 ~2 S* |8 M

03             //方法一： 

( T- {+ y% U1 \" ^) x& L- Z

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

* J# K- p* u! p& \

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

' \" B1 v' e- ^9 C/ s9 ^

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>")); 

; \2 K6 G; [2 a9 @2 l, ~

09             //Response.Write(html); 

8 O- H& B8 R* x: d

10   

11             //方法二： 

" E3 x2 {8 R" A9 i

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"); 

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

. S! n* `* G/ L8 d4 R

16             string html = sr.ReadToEnd(); 

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); 

$ e8 {& P+ j! v* J1 g4 n) g

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

21             Response.Write(html); 

8 G$ h! m$ |8 B& p

22         }

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