网页采集程序（超级简单版）

% p4 j+ ?. k+ c

网页采集程序（超级简单版）

/ w; \' g$ ?- h/ n4 C

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

& x; d8 T/ L! \, Q1 b

02         { 

; p9 m8 H4 g1 Z/ |6 V

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); 

8 W# Y2 a: C! P3 e

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

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

09             //Response.Write(html); 

10   

11             //方法二： 

12         //获取整个网页 

6 t8 Q/ ~. `% @5 A. C8 U

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

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

7 O; w" x4 O' A

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

6 U8 D" F5 }% S/ |* L

16             string html = sr.ReadToEnd(); 

5 X: n; G4 w+ B! a, ?" A" `

17             sr.Close(); 

% b2 ^" L' q' p/ E8 p

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); 

! Z* c: F" M; Z5 ]

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

) V c. _# w8 v2 u Y- j4 V

21             Response.Write(html); 

22         }

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