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： 

7 _ \5 x2 `3 m4 S0 H

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

9 \ r* y( Z, U l9 |9 G

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

+ O8 g) j$ b0 l' C0 E5 e( M; L

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   

11             //方法二： 

12         //获取整个网页 

1 }: A* ?' c7 S5 }

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

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

+ B% G, P: C+ n' o- o2 {8 Z/ y

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

8 A8 A5 w6 y4 f

16             string html = sr.ReadToEnd(); 

8 } ^* s i' t9 j' A) l

17             sr.Close(); 

5 g- \' g/ k7 i# o y

18             //根据规则获取想要的内容 

- N5 F8 _5 H- B/ O$ P" i

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); 

8 J5 R) v. x2 i) D; _7 |

22         }

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