网页采集程序（超级简单版）

7 K) Z3 [. U( G( Y' `0 C4 ]/ D! n

4 k V6 o$ b6 O! Q

网页采集程序（超级简单版）

E& N2 z$ B; Z2 {7 b

$ h I1 O4 K" g. p/ a

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

02         { 

$ m& P. g I; x6 Y. P

03             //方法一： 

' y* \9 X& m+ N# [! n+ c

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

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

: @6 U; {* z0 b% D

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

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

3 m' ~# f! A2 t, K

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

- V0 t+ {1 d1 m: ]6 H1 ?6 n& G

09             //Response.Write(html); 

10   

11             //方法二： 

12         //获取整个网页 

~ H& h: @9 E, P3 s$ e7 A0 Q0 T! f

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(); 

/ U; v8 p( j( B: C Y a

17             sr.Close(); 

6 w+ D o6 V' p1 y

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>")); 

21             Response.Write(html); 

22         }

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