网页采集程序（超级简单版）

- f- i- G1 r$ n% g

! t; A: x& k0 q; h1 H

网页采集程序（超级简单版）

y3 c' `5 B- o0 A

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

02         { 

0 ?* T5 a! @2 M @2 r' j2 D+ k

03             //方法一： 

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

: |0 j. g. S% |" ~3 h$ H8 `

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

; X* D s7 a* _8 e% F7 f

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

8 W" `: K! y" Q* C6 W* d b

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

; T6 P- p* p3 _4 v

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

: O# O4 S. b* d- e9 ^/ A2 j: Q6 i

09             //Response.Write(html); 

10   

`+ V4 Y% d; Z

11             //方法二： 

12         //获取整个网页 

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

# y/ J# o+ N5 ~' j

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

) u# T: o& {1 a5 l( \

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

$ V0 g2 U: _/ o

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); 

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

21             Response.Write(html); 

' }. x. w+ ~( j& ~

22         }

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