网页采集程序（超级简单版）

6 @. {$ _6 B8 d M* n- k

网页采集程序（超级简单版）

n# l$ A+ n5 W \0 f4 r

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

' z4 V: W x3 s8 Q! `

02         { 

1 h% r3 {, |! _- o% W

03             //方法一： 

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

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

! R Y1 x3 l, U/ M* r, T

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>")); 

6 O4 ?! L' }! s. F

09             //Response.Write(html); 

10   

$ U" a5 Q- L; s2 f$ a0 c

11             //方法二： 

12         //获取整个网页 

; _/ F+ A6 S/ a& R- U8 d( e

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(); 

& u" g* \% a" ]; ~

17             sr.Close(); 

0 V I% ^& i0 z ^; H4 Z/ R

18             //根据规则获取想要的内容 

+ `2 n" w' p+ F4 [: E

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

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

" E0 [; W4 `% r+ [+ n

21             Response.Write(html); 

6 h2 d% E+ x# O+ e$ e! X7 P9 i6 [

22         }

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