网页采集程序（超级简单版）

3 g# _3 i% q/ Q

网页采集程序（超级简单版）

& X% |, p4 x! B% [! s

7 H$ r8 ?$ R2 Y: e* l1 N+ y

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： 

6 V' E* s( x: V0 |9 P

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

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

) i8 {6 r, k7 x- l' W; X

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

0 ~ I& J- O& `2 J6 Z

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

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

3 z! G) _3 R+ f/ _

09             //Response.Write(html); 

6 i6 |# u( o) o; `& q" `: X

10   

11             //方法二： 

12         //获取整个网页 

* v% y9 M9 ^. O) C9 E; i/ Z, e

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

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

3 V3 H' w8 |8 P ?. E

15             System.IO.StreamReader sr = new System.IO.StreamReader(sm, System.Text.Encoding.Default, true, 256000); 

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

* w0 \$ [/ ^- m

18             //根据规则获取想要的内容 

9 i6 |3 ?3 T! m

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

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

$ m0 i; L8 C/ |, R* w# n/ u" r

21             Response.Write(html); 

0 J! c8 G6 e% X# a) W5 J

22         }

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