网页采集程序（超级简单版）

5 W- A& W _. z8 ^- | D

网页采集程序（超级简单版）

9 x- o9 j- u& R& p. I

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

! S/ [8 b2 {8 ~5 Z

02         { 

z- A7 R+ n, E2 I" b

03             //方法一： 

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

, y/ N( C! o" q

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

' v" C8 A N. c% H; m0 H% x

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   

; ~$ }" N$ y' W* B% o0 \

11             //方法二： 

2 e6 C" t! _1 O' `; B+ W

12         //获取整个网页 

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

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

% N& b0 ~/ ~% n. e' y( {

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

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

3 R. I& @9 U3 m1 W2 ~& c: m5 ?) d

18             //根据规则获取想要的内容 

' e3 J: @6 |% f* v# f: u

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