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) 

0 `# E7 ^; y/ V Q5 B

02         { 

* v [" I( Q+ m9 Q1 i

03             //方法一： 

. X) ~* u$ k' X9 G! V6 ?/ f

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

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

0 z% k, K: I; k

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

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

$ o4 J0 I- j, Q9 c

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

$ }7 s$ I9 E, X0 E1 s. F

09             //Response.Write(html); 

/ g( ~* Y' p. I& I \/ \

10   

% v7 s2 `4 y2 y1 U- ~

11             //方法二： 

12         //获取整个网页 

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

; y/ w, F% m6 \

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

( A7 ^7 }* @; ]! j

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 

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

' T: s- m: h" {

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

: K, _$ o, Q# }& r1 J

21             Response.Write(html); 

# x6 A! {7 k2 P: F. Y+ B

22         }

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