网页采集程序（超级简单版）

7 j$ U* E7 E. @

网页采集程序（超级简单版）

" f, V; j6 L0 O

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

02         { 

03             //方法一： 

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); 

1 s0 ]0 B" G7 q) F/ X

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

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

) {2 T) w3 }/ J

09             //Response.Write(html); 

f5 t& V* F `. l' q( W7 ?

10   

11             //方法二： 

& k0 T6 r& ~/ A8 \* y

12         //获取整个网页 

' P2 D, l) c% c) N

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

: T/ m1 U- g: X8 g# F

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(); 

' R: a- a, c o3 l

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); 

- d$ g5 G, q& D9 b& |

22         }

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