网页采集程序（超级简单版）

W0 a; T4 g/ \! ?) j9 h

网页采集程序（超级简单版）

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

2 H# g. w/ u4 v1 w6 _/ X5 j

02         { 

03             //方法一： 

* w2 @, T p3 x! {! ^" R" i

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

2 \+ ^ b/ G& @

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

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

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   

) g* N' c2 t1 P! S7 A/ l& W. e

11             //方法二： 

: L) c5 K" t! A$ _0 |; ]

12         //获取整个网页 

6 \3 o' ^: x; _

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

! G6 x$ C" Y! c# a2 F

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); 

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>")); 

5 J1 v" M4 f1 U( T |0 M

21             Response.Write(html); 

. P. P; Q4 q# `4 }5 i" [# G& [

22         }

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