网页采集程序（超级简单版）

, {0 S' i" ]: M" W8 D1 ~" g. ?5 S

+ g- C: l9 ~" v4 r# V

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) 

$ Q1 q- W: A# z

02         { 

+ g+ N5 x- m! r+ d9 {* [

03             //方法一： 

! e3 i- J* I1 K6 V1 T1 L9 M

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

- M. f3 g1 I* e* e/ X

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

/ Z3 y7 T* j- 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>")); 

09             //Response.Write(html); 

9 `( ~4 Y) Z8 G9 h

10   

11             //方法二： 

12         //获取整个网页 

1 j* z6 K" c- U+ F& C+ K. s

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

3 [ H3 A' d% N, A* Z

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

8 ~/ q1 u0 C: j! |6 N

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

, O# V5 g( E& |/ B9 a, Q" N

16             string html = sr.ReadToEnd(); 

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); 

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

' a! |9 X2 \0 p) w0 K) L8 v6 w

21             Response.Write(html); 

22         }

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