网页采集程序（超级简单版）

网页采集程序（超级简单版）

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

" {+ ]5 f1 h `' v

02         { 

03             //方法一： 

6 ~5 v2 S+ l# z8 s. J1 `5 R

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

$ a J; Y( {6 r; b2 |

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

0 @/ G) V" ~6 ?

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

6 u8 X2 M3 L9 \

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); 

3 C4 c2 D5 N& D0 z' q' Z# L

10   

" d1 @7 B" m% V- ^% t" @% O, R

11             //方法二： 

12         //获取整个网页 

5 z: \# X! b. @1 v) W

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

}$ b( b3 t* m( E6 C+ 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); 

16             string html = sr.ReadToEnd(); 

9 G, W Y& g) `7 A

17             sr.Close(); 

1 E# M$ T' H( Z7 T

18             //根据规则获取想要的内容 

" R1 s8 d& N; P9 F+ b' v% ~% u

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

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

6 c: p3 q, k0 A

21             Response.Write(html); 

( y k+ n) _* N5 N2 s6 [7 u

22         }

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