网页采集程序（超级简单版）

0 x! P; s/ F, n$ ^! [2 a

1 e3 g8 p+ L4 W! K( h! W

网页采集程序（超级简单版）

# \- \9 @2 \3 ^% _, l

( `" [% P" m" L! l0 D

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(); 

6 R/ E1 c% R* B" N

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

2 U' {, `0 x. [

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>")); 

09             //Response.Write(html); 

7 q( O( S, j; V2 {4 G# Q. Z0 n% v

10   

11             //方法二： 

' F5 {. D+ T* p8 P7 m$ e' e

12         //获取整个网页 

% P& U4 c8 w5 }) T, E& Z% l

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

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

8 p( ]& z9 X2 l5 G9 s% @5 ?- l

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

$ P; x' _, O0 H

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); 

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

21             Response.Write(html); 

22         }

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