网页采集程序（超级简单版）

网页采集程序（超级简单版）

/ t) \; P3 P; o6 t

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

5 P: z. H# q4 F4 o2 w O' S

02         { 

# y- |! `1 j) u. G0 z

03             //方法一： 

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

$ k& c1 h0 w( U$ B

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); 

0 w3 Y4 \' i2 p9 }

10   

' a6 w" Z1 C+ _/ Z2 R9 w

11             //方法二： 

9 w; z! y( P: ~4 t/ T

12         //获取整个网页 

, x) A& q* ?( T# E1 \# I

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); 

9 q+ y$ j+ D7 l5 d( p$ S

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

! c5 Q! H5 w; C* b% B, _

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