网页采集程序（超级简单版）

* l. s# K; B5 T- H7 V% H3 q: G

网页采集程序（超级简单版）

* k; d9 J5 I! F/ _2 V

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

" @) j, @6 X; h c- d+ }

02         { 

" l! j/ ]3 g1 O) @

03             //方法一： 

1 M* D2 ^! q$ Q! N, M( P

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

( \+ h/ Y6 \, Z) J: p- a4 {" ^

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

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

3 u; A% E( ~" B

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

. c% g8 f# C) W& P7 j2 j

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

1 g/ u( f. ^7 S# O# w% R

09             //Response.Write(html); 

. f g7 |' i0 i% g( p& C; q# W" J

10   

11             //方法二： 

2 s, `9 [9 r) A

12         //获取整个网页 

: K* w9 x+ d2 _# v3 k0 r4 s- ]4 v

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); 

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

- f2 M% J. s+ c2 a

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); 

/ x1 z6 ?% Z2 `& e

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

1 V0 M: \5 r# Z5 h

21             Response.Write(html); 

22         }

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