网页采集程序（超级简单版）

6 S) W: L: G7 l

网页采集程序（超级简单版）

|- Z& g# Y- R4 u! R2 \$ y

; p/ |* d- {8 `' [- H

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

4 Z0 C+ E% W3 D6 m8 S: T) L

02         { 

03             //方法一： 

6 d3 h9 s/ w' s3 g) x

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

: m- P9 o: T) c* O K9 M2 ]1 H/ N

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

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

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

4 P1 C4 d) y3 G7 T& s( j# I! L3 a

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

09             //Response.Write(html); 

10   

, i" M0 f A& y9 M u7 z

11             //方法二： 

/ d% r# e1 n5 U

12         //获取整个网页 

0 I Q) x( Y; ~* n# y2 k

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

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

& `: q) `, [5 Z

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

8 c+ |* T* g$ V" C1 P

16             string html = sr.ReadToEnd(); 

- O! f/ [4 L/ ]

17             sr.Close(); 

18             //根据规则获取想要的内容 

5 U& T! k' q- `+ r+ R0 T2 |, f4 c

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

3 V P/ } V- R2 H, D# U

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

21             Response.Write(html); 

8 G. t- z8 H" I4 ^

22         }

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