网页采集程序（超级简单版）

" X2 L2 R% U+ `1 \& l; Z; p

6 R1 F5 S {% N7 z# z. x

网页采集程序（超级简单版）

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

* l- v, Y0 z: H; `8 O

02         { 

+ A' E h& y! I

03             //方法一： 

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

# u, Y. i1 n' ~7 t) \

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

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

# \2 z2 D7 P/ @! \: s% e

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); 

) w& H t' ^2 e$ w" G" U$ O* W

10   

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"); 

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

5 L; J/ X/ n" R, Y ^# B

16             string html = sr.ReadToEnd(); 

) x- H% p! `- m/ l/ p, E

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); 

7 v% f0 I/ X0 k7 Q x" }* x' T8 Z: H0 t

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

21             Response.Write(html); 

22         }

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