网页采集程序（超级简单版）

网页采集程序（超级简单版）

( P2 \* {" e0 v' }4 X

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(); 

X; y' ?: z7 x. h8 J

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

0 M0 n8 R m+ L- @% _

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

9 U! t N8 }+ j" i+ R0 @

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

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

% ~3 A, a' `6 v( w, o% k0 C' }

09             //Response.Write(html); 

) M. O' g+ m; V3 y- U$ m I

10   

9 i! o. t1 w: H3 |- L0 {2 F) c

11             //方法二： 

12         //获取整个网页 

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( ]' q; P* @" R) U

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); 

" ^+ h2 B2 I3 {

22         }

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