网页采集程序（超级简单版）

网页采集程序（超级简单版）

1 i- k8 j; l+ Q* ]

' b. d) [# s8 u, S* `( k

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

# ` v# j: Q! K

02         { 

/ Q5 _: N6 Q5 \! ^

03             //方法一： 

/ f, d+ w! A+ H0 g( U5 s8 {3 b8 v

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

3 u" u/ p: f/ d$ A7 P- Z

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

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

G1 P* C" t$ i, X7 u

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); 

! m8 u5 Y4 b/ v1 L" e5 D

10   

11             //方法二： 

& k6 z# Q, ]) ]$ q

12         //获取整个网页 

5 q, O$ s# O' |) }

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

$ [# M0 b" M2 f i3 N% F

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

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

4 v* d% J6 [8 |; p# v' u( k! ]

16             string html = sr.ReadToEnd(); 

; S' L7 r! {6 `2 H

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); 

. \/ A' g) v% @- s8 w! I4 j& G

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

21             Response.Write(html); 

# Z3 K5 f" z0 N, `

22         }

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