网页采集程序（超级简单版）

$ _# j# E2 V1 l# S& C0 L

8 f' j. L6 a- O* n1 P5 z

网页采集程序（超级简单版）

2 c/ _- C, c& C C* [# V& g

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： 

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

P% B8 f: q+ d, I* w; J. P% d9 B7 c

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

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

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

$ J" l, S( G* ]$ t

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

/ V( B" j" y: K" M& v8 ?6 r- a

09             //Response.Write(html); 

) _1 ^( ]7 I4 F2 M

10   

11             //方法二： 

12         //获取整个网页 

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

2 ~: Z! g5 @$ i3 [0 b2 k- \' o p; F

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

* ?! t9 f' o$ S; M2 W7 F9 U

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

4 ^. z: v8 E1 ?

16             string html = sr.ReadToEnd(); 

+ R7 w7 `9 Y5 g& d. g- N* Z

17             sr.Close(); 

* }0 q( K9 c( @- ~( q& Z

18             //根据规则获取想要的内容 

7 H7 s# u" a. Z/ M& a

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

: S8 O1 D q4 h7 W) C& e2 m6 X

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

/ N. `6 M. C- W6 c3 ?6 G/ J; w/ I* M

21             Response.Write(html); 

22         }

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