网页采集程序（超级简单版）

网页采集程序（超级简单版）

, d& H, y& X h/ K" T; x

5 z- X/ U3 [" S& P: @# j

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

02         { 

0 T2 e0 C) I7 ?4 R0 t

03             //方法一： 

" w+ G4 G, e: ~! B. q4 f( j+ A

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

; ^- F2 Y" L# w, o

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

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

- Y1 M6 c% U" j6 A) }5 l

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

7 f9 t9 H3 x6 V

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

* P; [4 Y# \! }

09             //Response.Write(html); 

* N* S7 \; W: o' u

10   

5 L5 |5 Y7 S+ X p1 @6 v

11             //方法二： 

12         //获取整个网页 

' y% M0 s" ]3 J _- T

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

0 U; f! Q# J$ u) W+ ^% E; ?' O

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); 

) P5 W, m1 P6 z5 ~

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

18             //根据规则获取想要的内容 

# \7 v. u" o9 T

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

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

n2 {# u/ l4 j' P! ]2 o

21             Response.Write(html); 

22         }

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