网页采集程序（超级简单版）

4 C+ t9 D: u4 g3 Z6 i5 @ l+ w

' V3 r0 ?: U# d6 U, B2 x/ W' W7 ]

网页采集程序（超级简单版）

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

02         { 

0 a: d4 J/ D- U# |: t+ F l

03             //方法一： 

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

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); 

% F$ j: x8 s9 ~6 ?1 Q6 a: X& P0 c

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

3 U3 e3 X: D8 x, s# r: R+ z* u; O

09             //Response.Write(html); 

10   

# P1 s5 M" M. d, U/ @

11             //方法二： 

2 g$ V) R) ~& U# N E8 ~- g

12         //获取整个网页 

8 [. o( z- _4 f

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

7 o, X( n/ r" n. ~0 c6 w

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); 

: [0 \$ l2 f3 l7 A, r' k }" Q

16             string html = sr.ReadToEnd(); 

: F6 R+ c6 W1 z% M: [7 i y

17             sr.Close(); 

18             //根据规则获取想要的内容 

) W% ]/ M/ p5 w' S

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); 

# P0 o0 v; O) |; Q0 @0 z F

22         }

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