网页采集程序（超级简单版）

9 }7 o4 w) @9 O

网页采集程序（超级简单版）

+ Y# a" }: Q$ U1 _8 z6 r

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

( {! N" T) S( U; u( N. L! i; W

02         { 

7 F8 K5 K e; ?2 B E

03             //方法一： 

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

& s% C' W# p$ @0 N8 \( P4 t

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： 

* [3 v3 L# f/ \2 k; ^% J& X& U' m" g

12         //获取整个网页 

* |/ O" l+ z7 ^0 B( z# V

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

& g0 s9 F c6 ~1 Z& N

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

6 R6 s, @. K! @& g- v

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

8 |% Y2 L9 C, X- P2 o. E) D

18             //根据规则获取想要的内容 

. c" C" Z' N/ Y6 W

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

, z' _, ?, W1 w! _( `9 Q5 c7 m

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

21             Response.Write(html); 

22         }

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