网页采集程序（超级简单版）

3 b, A" K- \0 S! c4 ]7 \

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) 

0 R) t* O9 \& }& g

02         { 

9 T3 ^+ v1 A' d

03             //方法一： 

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

) l o- J. a8 q' h6 Q

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

4 P2 _+ I+ ?$ m/ m; [, E

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); 

10   

9 Z9 N$ g" H; B- l5 p, ?; s* ?6 U/ B

11             //方法二： 

12         //获取整个网页 

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

* ?' C; R) z4 a1 u

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 

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

% z& T0 }: t8 e9 e$ U) o9 Z

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

21             Response.Write(html); 

. w8 @4 B/ Z8 b

22         }

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