网页采集程序（超级简单版）

; c) y8 K0 ]5 n

网页采集程序（超级简单版）

9 K; N, |, I7 x! M8 [4 z

: F: z! r, Z: O# `/ ~* m

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

02         { 

; _5 v& a( H- j+ L

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); 

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

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

- ?9 q6 M1 O9 @) O" `! `9 `

09             //Response.Write(html); 

7 ]2 ~& T8 k N; A c) \' U. w# ]

10   

3 X% U+ v+ t y3 F" R. m

11             //方法二： 

, d% e4 ?# v( I

12         //获取整个网页 

" J! H& E. v6 {8 w. D5 v0 e/ t

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

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

2 J. Y/ G ^- c, M9 O

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

* W9 Y6 V# Z( X

16             string html = sr.ReadToEnd(); 

$ q) w: S9 n( x

17             sr.Close(); 

0 Z" ]6 q0 T* I( J' M" W

18             //根据规则获取想要的内容 

$ A$ D4 s) ?( N

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

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

* |5 ]! |+ F1 p+ P2 F

21             Response.Write(html); 

( F& z% o- z# e9 E5 o! q; E; q2 {2 x& P

22         }

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