网页采集程序（超级简单版）

网页采集程序（超级简单版）

% ^: x. a0 K. w$ a: i

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

02         { 

0 e4 @# o: r& j! h8 E0 S

03             //方法一： 

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

, G) ^5 l" I& J H& f

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

7 r% M0 s ?- E. I* f( ?

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); 

3 N, o7 o/ W2 `

10   

! A) i' h r5 ?% B" @/ m( p( z- I

11             //方法二： 

12         //获取整个网页 

7 u! Z( X- _3 U: p: I

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

) V7 B: u: r% h! Y

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

( m( u* C) }& W# r8 ^+ l" c

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

% i- Q& i/ L# ]- A* h

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

. a$ m8 p& q# @

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