网页采集程序（超级简单版）

网页采集程序（超级简单版）

$ d/ m, u8 P7 [6 [# `- W d. x

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

02         { 

2 e' A0 ]" l4 Z0 j

03             //方法一： 

& o# ^$ y" i$ \* }6 i+ `

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

8 U! c+ m! ]" l5 V$ x0 K3 \ V9 h

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

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

3 S6 }9 c- l. G& Z. d3 j V

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

. w) O8 R' o9 g" ^

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

09             //Response.Write(html); 

& ?$ I# O# Q/ z; l

10   

* ^7 {6 f+ r. |2 Q5 r6 ?) }3 ~8 \

11             //方法二： 

12         //获取整个网页 

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

: l$ U, D l5 q

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); 

- l. x6 Q! `3 Y5 Y" m% y

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

% {2 Z- B0 Z( U5 h( [, W

18             //根据规则获取想要的内容 

' }8 a1 I: o! E4 B0 L

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); 

22         }

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