网页采集程序（超级简单版）

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         { 

03             //方法一： 

7 O3 X! K1 x5 h2 \! h0 d. G& D

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

/ @: ~1 H3 \) Y6 ]

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

! e5 x2 O: Q6 }. s

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

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

$ U8 H) g+ S8 h; m! P5 P7 p9 c/ g

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

. S5 P/ k+ I B. K: s# t5 P6 K

09             //Response.Write(html); 

10   

% s) }. K, `" t0 J C$ T m

11             //方法二： 

12         //获取整个网页 

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

C) C P3 s2 Q

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); 

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

c: W6 w: O9 E6 I% r3 j

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

6 |+ Q9 u$ p; }2 w( r/ {

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

4 N) g/ \5 {& ~

21             Response.Write(html); 

22         }

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