网页采集程序（超级简单版）

T- f/ x0 }4 |) d8 |* d0 k

8 U/ w5 C/ L7 @" {7 w- M4 f

网页采集程序（超级简单版）

' y H) ^ \" B l' S4 n' S

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

02         { 

+ b: T2 f- M9 { D i! v

03             //方法一： 

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

7 E O2 l: T5 x+ N) C8 j

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

6 C7 Y$ t/ ^6 E6 n! i3 o3 W1 n

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>")); 

* ^% ~/ S+ k" v7 T

09             //Response.Write(html); 

10   

, a# R6 S S0 }: J) [

11             //方法二： 

" q$ k4 ?4 |1 ]9 W, M

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"); 

6 v0 F. ~+ u0 Q; I

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

16             string html = sr.ReadToEnd(); 

* H3 s: e0 }6 V# k% r+ ]5 G" K

17             sr.Close(); 

: t* m* l- W2 E ~! P. _7 r( E. E

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); 

9 q% s: f A0 H# r

22         }

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