网页采集程序（超级简单版）

, W1 B/ L3 C/ ?8 k8 K- K3 n, A. q

网页采集程序（超级简单版）

8 U" m' e0 D7 @1 ]

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

02         { 

4 I) |. x5 v" N/ J W

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); 

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

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

) v/ C$ l( W7 g* `& M

09             //Response.Write(html); 

10   

11             //方法二： 

/ J5 `. d- G$ v" _8 u) Q1 H

12         //获取整个网页 

" \& S7 f# n% U1 f, P

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(); 

! I' p" D/ D, F' A/ K6 d' ?: o O9 s

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>")); 

+ N! |6 M, d. D8 y

21             Response.Write(html); 

22         }

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