网页采集程序（超级简单版）

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) 

02         { 

03             //方法一： 

: B% ~- P2 ]& f# r: B) ^2 _7 Q. i

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

& ?% T( f& L5 Z: Q

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>")); 

1 A: G" K( M( p8 m/ {/ K+ O

09             //Response.Write(html); 

10   

1 T" K) I' ?0 ?( E

11             //方法二： 

& G; P9 [ M6 S9 {' w

12         //获取整个网页 

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

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); 

4 }2 ^7 G K& w: B }5 z& @

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

6 [( l4 M7 O2 @ L$ Y/ U( B

18             //根据规则获取想要的内容 

3 c ?% U5 n5 G! H9 h

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); 

/ I9 ?6 m- o% O/ e2 {

22         }

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