网页采集程序（超级简单版）

7 Q6 N& ]" C9 x/ ?8 ?

! F" l6 D+ O7 m& P3 x

网页采集程序（超级简单版）

5 J$ G. B# x% b1 p; |" F

" Q5 Y# v- G7 o+ _; \8 x

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

02         { 

03             //方法一： 

8 |1 V J/ s9 ^! n1 ]8 ]% C

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

- W# Y6 I' w. @2 [5 S

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

9 _# v- _: G) P: N! v( \

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

& i: y# P0 ?% d3 X m

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

% Q/ q3 h) ^! r1 K

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

09             //Response.Write(html); 

10   

11             //方法二： 

' `/ k9 ]# ]: ~% q

12         //获取整个网页 

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

) u. V% j' x7 ~; ?/ ?) K$ t6 p

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

# B1 g0 j6 j$ K7 e

15             System.IO.StreamReader sr = new System.IO.StreamReader(sm, System.Text.Encoding.Default, true, 256000); 

$ k: ?8 o1 }$ i* v0 R+ c7 _

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

3 y' A; ^ X7 g# o" J q8 L* L

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

! x# k& J/ W6 c

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

21             Response.Write(html); 

, }' P) }" E; {# C* W' I- m

22         }

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