网页采集程序（超级简单版）

2 z8 }, f6 v% g% ?. R$ X0 q, f

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) 

3 l) I' s$ w4 c8 c" N7 r

02         { 

' k! r% @) {1 V3 S- v% l

03             //方法一： 

3 n# y; c2 a' U

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

( e# I$ ~$ C( G0 L

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

/ W8 W( N6 h7 C7 k# u/ L$ b

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

$ w; x- b8 P; f p/ S

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

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

# W/ T5 a) ?% L) E8 h

09             //Response.Write(html); 

+ q( b4 x! N5 b# G* a5 U' D/ u, [

10   

3 m) x5 }1 v3 r' `( O) }

11             //方法二： 

12         //获取整个网页 

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

14             System.IO.Stream sm = wc.OpenRead("http://www.baidu.com"); 

- E7 W) _. N: r& X; y9 r7 x5 f

15             System.IO.StreamReader sr = new System.IO.StreamReader(sm, System.Text.Encoding.Default, true, 256000); 

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

7 @: t& m: }6 L( q& |

18             //根据规则获取想要的内容 

' J* t2 V$ s. A6 R) I% K5 \

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

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

& w3 o. E, b$ p6 i) N

21             Response.Write(html); 

% F! ^; G9 u& E. |, H

22         }

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