网页采集程序（超级简单版）

5 O+ e0 s5 h% l: V1 w

网页采集程序（超级简单版）

- E( G, w/ f1 I4 O9 D5 ~

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

02         { 

1 L: t0 ` A* C

03             //方法一： 

3 \7 O# N- m. u6 x

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

. P2 w& c/ A# Z9 \8 u

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

+ Y$ l$ x p8 O8 r' H# ?

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

' A9 l. ~0 A2 ?# U. b" L6 W6 k P

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   

3 X0 o, M7 ~# a

11             //方法二： 

7 v5 _7 b, }" \0 M0 F# F

12         //获取整个网页 

2 e' ^# D8 W3 i+ E- y% L9 _

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

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

* S" c7 C1 Q. x+ a5 q5 f% z4 R5 k6 S

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

- E$ P3 @& K5 o8 o1 o1 L

18             //根据规则获取想要的内容 

& g' c9 x5 g s' F

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

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

; x" u, G" n/ I6 @ S# e; O

21             Response.Write(html); 

' V- {* m6 c/ c* L/ J

22         }

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