网页采集程序（超级简单版）

: [( J- k9 |9 I8 e. U

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) 

02         { 

03             //方法一： 

) ^, f/ ?& ^" ?) x

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

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

0 e6 i ?! B9 D

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>")); 

) t9 t' c, E. R3 v: ^3 {

09             //Response.Write(html); 

10   

11             //方法二： 

12         //获取整个网页 

# q# D+ V1 G4 r$ w+ W

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

4 q: n; N1 d$ Q! d$ l/ U

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

% b- F8 e# q) ]2 d3 H

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

: y/ X& i7 x! K; }* c1 i6 M1 S, V& G

16             string html = sr.ReadToEnd(); 

2 F' ?, N6 J- @6 J4 J

17             sr.Close(); 

/ v3 W4 h8 O6 L. a

18             //根据规则获取想要的内容 

' `/ s1 s# B f/ o; ]

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

4 P5 l0 `0 I& D! e9 S

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

( L+ [7 F; [: Z# i' h0 j, j

21             Response.Write(html); 

0 U5 L1 }! U( e+ c. L! I" E% i* Z

22         }

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