网页采集程序（超级简单版）

( M, k! x: i+ `$ Q' y

网页采集程序（超级简单版）

% o @7 O X- Q$ ~9 Y/ ^% W0 S

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

! K9 v8 Z7 j0 u$ P* S& _ G4 D! Y

02         { 

: `/ ^ d) i5 k

03             //方法一： 

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

2 e2 j" I3 X0 b5 ^8 w) m. x2 l

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

* V) U- c3 a h, X

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

2 l' A. M/ f* N

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

9 p# ^! \, T5 V

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

09             //Response.Write(html); 

@, R5 ]* o7 W, L0 i h

10   

11             //方法二： 

8 Y2 y6 d# o. b s; p K1 D( r& ?

12         //获取整个网页 

+ s0 J7 ?5 T0 F; u

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

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

* p: \; W5 x3 c/ w5 u4 J$ a ~

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

8 K% G6 Y& U# |/ u2 k7 c+ M

16             string html = sr.ReadToEnd(); 

, f" ?* K% P/ I6 O! t

17             sr.Close(); 

18             //根据规则获取想要的内容 

% q. v$ b- ^/ `0 ?8 n2 z2 {9 B

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

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

' ~ r2 o& y; C, E5 x8 A) ^

21             Response.Write(html); 

22         }

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