网页采集程序（超级简单版）

5 o! Y- i! n M; b

网页采集程序（超级简单版）

( j! H$ W: I1 T* L

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

) [( a8 p/ g5 K% j# a6 o

02         { 

03             //方法一： 

" Y7 w# i7 J; [- f7 q

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

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>")); 

5 w& N) ~) E) B' H9 h1 F/ \& B

09             //Response.Write(html); 

10   

, A& g( s0 d8 e' S! B) C( b4 l6 F$ Z) W3 w

11             //方法二： 

/ U ` [8 N! |$ R& X- @; h+ [

12         //获取整个网页 

$ T5 ?2 L3 J7 w# Q, T

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

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(); 

17             sr.Close(); 

$ d9 j9 h3 \' ~! S6 b. |

18             //根据规则获取想要的内容 

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); 

22         }

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