网页采集程序（超级简单版）

$ R: _4 p) f# ]2 z) p4 H( d# F% W

; b; [: h* O* @, w: e N* K

网页采集程序（超级简单版）

; L6 }' k; S, j1 {8 T% ?

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

02         { 

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); 

' X# @; b1 z% _* |6 Z6 H0 {

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

9 G3 E; B5 R/ G' ], k ]

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

: v' u9 R4 R' B E

09             //Response.Write(html); 

5 j2 B4 ~% W6 g! q, m

10   

9 V1 {# Y c- z) b; P9 o

11             //方法二： 

12         //获取整个网页 

. `/ a$ X6 D; a# T

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(); 

18             //根据规则获取想要的内容 

; j" t) ]( o3 C1 L9 i

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

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

* a" h* f4 I, y7 R: W( ?8 e

21             Response.Write(html); 

" p, R* B4 A" J# W9 m& w

22         }

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