网页采集程序（超级简单版）

9 s* r! T; j# ]: G

+ B' R6 |: S: U, S ]0 l

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) 

9 z+ S3 x/ ]/ ~

02         { 

03             //方法一： 

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

7 }1 k2 j' K. N4 s# L! ~

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

* s4 t! T- {1 [# Z8 ]" w

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>")); 

; ]& l# F/ X4 l

09             //Response.Write(html); 

+ k" N7 _* h5 m. l9 v

10   

0 T/ F# N" A- c7 o. ?9 m

11             //方法二： 

12         //获取整个网页 

& S, R% K: X$ }' f; o' p* n* F

13             System.Net.WebClient wc = new System.Net.WebClient(); 

" A- \0 \; Z( g; K

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

/ s3 ^. l5 T" P" o7 w8 [- R) {, C9 f

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

1 l! C( J4 n u6 R

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

+ \; d; T. W# x7 l' o

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); 

) U( _ s# s2 e+ h2 o3 Y ^7 E

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

21             Response.Write(html); 

22         }

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