网页采集程序（超级简单版）

1 }$ c. ]1 y$ P* ?6 u; s

网页采集程序（超级简单版）

" t2 g, J/ T( c+ R

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

/ Y" \# ~! Z/ x% p. o1 E$ k% h

02         { 

# w0 h$ ~$ a, w4 F* |4 `

03             //方法一： 

* ]$ Q) l# c! X$ C% L

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

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

3 }/ [; K- t5 a6 f. D

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

* A5 X) c: J0 E1 d

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

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

# S; t" b2 \) z! P0 P8 n

09             //Response.Write(html); 

' }) n/ z% Z. f6 C! q2 ^, `

10   

11             //方法二： 

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"); 

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

# }" S1 p+ \. {/ Y. q) X$ w

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

3 n x, B! c! z0 m( X2 k

18             //根据规则获取想要的内容 

/ Q1 M4 a2 G0 S7 @# @

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

2 [& i% N9 C- e8 {0 a7 u% z5 P% I U

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

21             Response.Write(html); 

% W4 c$ n: F: _1 K% Y5 j% [1 ^

22         }

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