网页采集程序（超级简单版）

- q+ o# R; B0 f

9 [2 @$ s9 X% f3 J! F3 s

网页采集程序（超级简单版）

/ y, L8 g' r. O6 E# l

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"); 

; ], H# j- E$ N+ W$ ~

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

" u# ~6 K& Y8 G( e% ?! B

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

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

09             //Response.Write(html); 

10   

0 y( s! X2 i) c8 r3 {

11             //方法二： 

. X% h0 i2 c9 b8 s- J1 ~8 i

12         //获取整个网页 

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

* C1 ]. H. M T0 r0 T

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

a& K" t* x' B- @

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

. S/ o0 H' k2 R: b2 D4 f9 u' q- T7 Q

16             string html = sr.ReadToEnd(); 

& T& J$ c' ?+ o5 {: E. G7 a' V

17             sr.Close(); 

1 A: _/ p5 I) ^3 W j) |

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); 

$ l7 R( u7 }# Z. g

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

21             Response.Write(html); 

! ?5 f# N* t u, C* a& W" [8 z

22         }

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