网页采集程序（超级简单版）

8 O& x% g$ C5 ]7 V! G, `

网页采集程序（超级简单版）

4 B# l% ?3 H) t5 j

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

& W! Q \; |0 o& g* V

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); 

0 S) l6 c, ^9 P g4 \

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

5 Z4 C& V* Q% R' o& T

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

- p6 I! G# R# x7 g) S: q1 e i

09             //Response.Write(html); 

- U$ b2 q% S, `- Y5 C

10   

9 y. ^4 l0 ^+ I7 j5 A( n

11             //方法二： 

12         //获取整个网页 

1 D% Y( t0 [8 @# }. |

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); 

& \ E F, G4 v, Z9 X- L

16             string html = sr.ReadToEnd(); 

! D) H Y7 C0 L" D

17             sr.Close(); 

18             //根据规则获取想要的内容 

" ~4 h- r. j) p' w P

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

/ f4 t# h. t9 T9 u5 A$ {8 z

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

; S! ?5 D7 h6 k4 |' Z. V% ~- b

21             Response.Write(html); 

& v1 W0 m" M$ l0 M# Q- y

22         }

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