网页采集程序（超级简单版）

' L1 Z( i4 t* C3 J9 k6 ]

网页采集程序（超级简单版）

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

0 }! g2 ^1 z8 l

02         { 

3 k- g/ l- [4 j- v8 R$ f$ ?

03             //方法一： 

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

5 C5 L$ k1 ^7 E" t: o8 x

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

3 q& S! e7 P. Y6 c! B+ \- g

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

) D1 F0 Q0 \) p( b: b

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

' y+ l/ z/ E5 D6 [6 {3 y

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

09             //Response.Write(html); 

10   

1 b* n' d" @- V0 d5 e

11             //方法二： 

12         //获取整个网页 

0 p& Z& `. L6 S: d/ x& y5 o6 @

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

; o8 H2 J; A2 l3 @

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); 

16             string html = sr.ReadToEnd(); 

+ Z3 n) \: i! \6 f

17             sr.Close(); 

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); 

1 p$ w$ ~9 j: B; J. h4 f

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

21             Response.Write(html); 

22         }

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