网页采集程序（超级简单版）

; O& p: T8 \! r) s

网页采集程序（超级简单版）

6 x% s9 C! u4 P3 g" F

: R5 s, C6 s% I! G

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

2 u5 ], g# p7 i3 K, u

02         { 

: Y$ _: v5 [6 G( g b7 |

03             //方法一： 

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

- \6 I+ N* R8 ]1 @

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

9 l; l+ ^+ h, H* m

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

* j# Z$ \! w& u+ X0 |

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

$ D* e! p" G/ [

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

6 \, C. S' O' ~5 q# S1 c( J( ^ L

09             //Response.Write(html); 

10   

+ R& E9 {7 @0 Y3 E% M9 l% Q

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"); 

m5 B; C1 Q3 M& C6 B

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

x2 n. ^6 Q t: P1 x; v- Y( ?. v

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); 

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

+ K9 e9 i# J9 I+ i4 J( D: r3 g: D

21             Response.Write(html); 

22         }

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