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         { 

* [3 f) t# y/ m% \. L

03             //方法一： 

: L( O! ^3 H G0 t* H( Z0 x

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

* ]( i# y7 k$ U& O

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

% V) E/ s$ p( M. j

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>")); 

% |( h% {) K2 u0 h

09             //Response.Write(html); 

- ^5 D# q9 L* Q6 w

10   

11             //方法二： 

12         //获取整个网页 

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

6 V/ M( A U& f# U7 Q

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); 

6 E: A( `0 k& g" ]# d

16             string html = sr.ReadToEnd(); 

17             sr.Close(); 

& a- v1 h0 }. y! I# l7 u- f4 }

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); 

22         }

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