网页采集程序（超级简单版）

6 N. [ ]2 O- u

! H, \0 P& X+ p- _% C: G

网页采集程序（超级简单版）

$ V. A- x! P: i, k0 x: x

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

02         { 

% \; {" i1 z+ c+ Q7 u! t

03             //方法一： 

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

, o: |- i$ C7 J

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

/ w M4 _ e" d8 b m

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   

11             //方法二： 

12         //获取整个网页 

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

, m B- ^1 F& F4 u" x

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); 

/ R, s6 P2 `. u. n/ B2 W

16             string html = sr.ReadToEnd(); 

' y/ s% B4 o$ s1 V0 c

17             sr.Close(); 

$ U O; E3 q0 B* I1 M3 o5 i

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>")); 

9 s: U/ F1 ^9 P% B$ ~0 ?( b

21             Response.Write(html); 

22         }

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