网页采集程序（超级简单版）

. P* ]: n/ s1 i/ e

3 n* Y1 w) C. e& k) k) L0 x! f

网页采集程序（超级简单版）

' f' b4 I {5 k( d0 h

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： 

5 @6 N, Z' @7 \0 g1 d

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

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

Q8 B2 Z+ k# q U5 m9 |. u3 N3 ^

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

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

1 m* W4 B. H M

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

$ Q6 A& y1 N/ t# B6 g7 Y

09             //Response.Write(html); 

10   

' u/ \4 z. X' U1 E" L

11             //方法二： 

12         //获取整个网页 

. e% _9 S/ O* d( o) t- u

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

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

# T3 I" l0 ]: g; a( y0 a0 `- o2 d

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

16             string html = sr.ReadToEnd(); 

7 X: v7 y* M4 ]4 U

17             sr.Close(); 

18             //根据规则获取想要的内容 

& p2 `6 n; A- h6 L: A

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