网页采集程序（超级简单版）

9 b+ g5 S: z+ x' D( Z

) N. k2 H7 u$ ?, x7 _# i. n

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         { 

9 w% K1 k" s& t$ A: W# p

03             //方法一： 

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

" p' h# L/ A z+ O4 `

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

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

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

3 G9 m. b, W* H9 x

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

, S# Y! J1 f4 [, E0 q r) x+ T- A

09             //Response.Write(html); 

6 ^, K( c9 C K& }9 {

10   

5 Y9 ^4 W8 v. C7 j3 q

11             //方法二： 

12         //获取整个网页 

/ y) m4 ?$ [2 j5 {2 L

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

( V; ~ b( |7 ?' T' J8 _

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(); 

/ I' \! ^) i: T# Y( I

17             sr.Close(); 

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>")); 

, r& i: t7 ^* l# K" m5 o2 _# w

21             Response.Write(html); 

. C1 [3 a' F. c6 ]- f6 n; f; Q. r

22         }

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