网页采集程序（超级简单版）

网页采集程序（超级简单版）

/ V _- M8 x7 Y C. T# K

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

" {- `% y- D2 |, F4 W- E# o+ R6 q T

02         { 

4 }! C4 O* M5 F/ e: i

03             //方法一： 

3 D/ ^' {8 @) N6 M, j5 r. V/ g) j

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>")); 

09             //Response.Write(html); 

10   

11             //方法二： 

' \7 y- [& f' q) z* Q6 b

12         //获取整个网页 

2 L* n1 `) `' U( Z/ e0 M- }5 ?

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

2 b( k5 j! z' N8 @, q7 _

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); 

& H5 I' Z' X+ O4 ]) V0 }

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

0 @- t. }7 Z' m$ u/ k" W' V( @

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