网页采集程序（超级简单版）

: z- f5 x e: B* N& d% o, w5 Q2 M

% k3 p" {! M. k& w* T

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) 

- _3 Y0 {8 y) r' Z

02         { 

( }% X6 F& V& m9 t

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); 

/ D# l8 _ ]7 g! y; a( R6 U

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

3 ^) ^% V/ g9 y& X

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

, t, Y" w, v0 z! U" C

09             //Response.Write(html); 

$ _) l# z; ]% N

10   

. D: H* W; |+ U( Y

11             //方法二： 

$ ^: Y3 m7 }0 Q& M6 t# @

12         //获取整个网页 

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

+ w% V A# s A- d4 c1 y

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(); 

1 g* _4 t5 n5 H# I! W

18             //根据规则获取想要的内容 

' R2 U7 V6 c7 L6 z/ c

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

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

% c, ^$ G% K$ W2 Y4 C2 [

21             Response.Write(html); 

' \1 [" `9 s, X6 p: y6 [" q; _- M

22         }

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