网页采集程序（超级简单版）

+ H; {( [# |( ?2 e6 `

网页采集程序（超级简单版）

5 B& \! k; G) \: e' y5 i% C

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

. c/ {" w8 m, ]$ S/ R! J9 S

02         { 

0 s/ v- R6 Y* z4 t

03             //方法一： 

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

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

0 O8 e3 T0 A) s/ P9 s6 n# w

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

. |) F o2 \" `9 P( a0 y- A* S2 Q3 A

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

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

1 t" c9 V& c: h! G8 R

09             //Response.Write(html); 

10   

6 _( ]1 Y7 L# d$ r4 k( b& i

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"); 

{- B8 `% ^2 T. M- O

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

7 `' d) v1 h9 L$ [6 n( X% r: R

16             string html = sr.ReadToEnd(); 

- H& z4 Z# g5 ?% O$ g6 ~) h

17             sr.Close(); 

18             //根据规则获取想要的内容 

# d. |: E: D3 ^1 Z; G/ 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