网页采集程序（超级简单版）

+ G7 N. r9 q3 v( f1 d

/ X* J1 a" g' r) W3 {' {

网页采集程序（超级简单版）

( F3 T: v. P7 i, K2 w# |

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

02         { 

: H7 h3 |& R& Y1 w" s$ I4 h

03             //方法一： 

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

5 d. y! {5 ]- H* S7 {5 ^- W X& P

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); 

' }" M% @; e* b& l+ `- R1 T

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

6 F6 e/ V* ~' c, h0 T

09             //Response.Write(html); 

10   

8 S. ^9 |0 D; ?1 e

11             //方法二： 

% z) }1 n3 }1 u( Q8 h

12         //获取整个网页 

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

8 R2 H% z& L9 i6 p- O6 V+ ]

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(); 

; w: J1 z/ y$ F- U, g# \

17             sr.Close(); 

18             //根据规则获取想要的内容 

6 l [( y+ {3 w# W4 t1 t w4 ~

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

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

21             Response.Write(html); 

& Q) d; r' o% F5 h

22         }

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