网页采集程序（超级简单版）

( s! V) |' }" _' K, r7 \

# b: b% m2 P l' B9 e; m* T' J

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) 

02         { 

03             //方法一： 

* M( {' b2 }; |8 V- z

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); 

5 e% m; w) {( `' R( w

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

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

, |( C, P2 J0 m$ d' f2 U

09             //Response.Write(html); 

10   

& y* ~; N, H# G

11             //方法二： 

12         //获取整个网页 

) a( }- B8 {- c& F5 v. e" L

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

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

) ]) ]" K$ O: n" k. A

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

. O# S& t0 f1 ]2 Z# ]* `

16             string html = sr.ReadToEnd(); 

' A* f2 N* ^0 t* o$ R* U, f

17             sr.Close(); 

18             //根据规则获取想要的内容 

2 Q# P2 X' C6 S- \

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

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

7 R! O. Y% U L8 ~5 [! n8 ~* B/ L9 ^

21             Response.Write(html); 

22         }

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