网页采集程序（超级简单版）

; F( I$ h& q! l, m4 g& U/ f# R

; Z. h% [$ V) S2 o+ p

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) 

' ]7 [7 t+ S# b+ y

02         { 

03             //方法一： 

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

$ D( L* v, t8 L. b1 A# n) N

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); 

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

, P0 p: u4 x* M

09             //Response.Write(html); 

10   

11             //方法二： 

1 O k; u) p) e |

12         //获取整个网页 

1 u Q3 e8 ~0 M+ X" t8 D5 W- f

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

' D5 R6 t- ?2 T/ @4 D- p% u

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); 

' L% K+ m& [$ P! q/ S; B- C+ R/ I

16             string html = sr.ReadToEnd(); 

) {7 c, a: `* N; e

17             sr.Close(); 

18             //根据规则获取想要的内容 

& G6 h7 _/ x( A$ v. S5 J+ a

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

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

# u3 w) q+ L2 c8 T; m4 j

21             Response.Write(html); 

22         }

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