网页采集程序（超级简单版）

- j, ]$ f, D$ d" e- i3 o! ^& w5 M

# [& D$ `/ Y7 p4 J" r0 D

网页采集程序（超级简单版）

9 E8 W+ |$ t' W7 O7 R9 Y

8 R- U* P) F) D- ^* C/ r3 _8 ~7 S

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

. ^, \# u% |% n9 C

02         { 

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); 

3 w9 R$ K6 c5 ^

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

, A; q5 j9 A3 G+ Z

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

' Z, |( d' a4 d2 w0 o1 {

09             //Response.Write(html); 

3 N7 P* V3 {5 ~( n5 \

10   

11             //方法二： 

4 v( }- V. V- |) o+ `" Y

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); 

+ u: a& n3 \1 b2 j; j' G. V

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); 

# s+ b: r) ?" |) s

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

21             Response.Write(html); 

22         }

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