网页采集程序（超级简单版）

网页采集程序（超级简单版）

; j9 R J$ a+ a! |7 p" W. ?, x

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

! |2 [. _2 w8 Z4 a. `/ S) D: }, C# d

02         { 

: i4 F6 {9 r3 X; w& q% s

03             //方法一： 

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

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

6 N- O0 X, k* f! G6 A) d

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

! }5 l) }9 [7 ]3 L

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

[8 z1 m `! _. M0 r) V

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

09             //Response.Write(html); 

10   

4 F" ?* ~& r9 Z& P

11             //方法二： 

8 ~: q! d- i, [8 T

12         //获取整个网页 

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

( j' V' u+ Z# Z x

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); 

$ J0 q$ ~' T% F+ g# }+ K

16             string html = sr.ReadToEnd(); 

& Q2 j# ~( x' v& S) _

17             sr.Close(); 

18             //根据规则获取想要的内容 

3 d. A' J# Y- ^0 y6 Z4 o

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

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

x1 m5 V3 O& j# s

21             Response.Write(html); 

22         }

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