关于 Java 的 HTTP 抓取 [GET 方式请求]

下面是一个简单例子代码，可供参考.

1. /**
   
2. * (#)HttpGet.java　　　　创建时间：Apr 29, 2011 9:36:43 PM<br />
   
3. */
   
4. package org.iscripts.common.net;
   
5. 
   
6. import java.io.BufferedReader;
   
7. import java.io.IOException;
   
8. import java.io.InputStream;
   
9. import java.io.InputStreamReader;
   
10. import java.net.URL;
    
11. import java.net.URLConnection;
    
12. import java.util.regex.Matcher;
    
13. import java.util.regex.Pattern;
    
14. 
    
15. /**
    
16. * @author 林俊海(ialvin.cn) 广东·普宁·里湖
    
17. */
    
18. public class HttpGet {
    
19. 
    
20.   public static void main(String[] args) throws IOException {
    
21.     System.out.println(HttpGet.get("http://www.iscripts.org/", "utf-8"));
    
22.   }
    
23.   
    
24.   public static String get(String strURL) throws IOException {
    
25.     URLConnection conn = HttpGet.openURL(strURL);
    
26.     return HttpGet.read(conn.getInputStream(), HttpGet.getContentEncoding(conn));
    
27.   }
    
28.   
    
29.   public static String get(String strURL, String encoding) throws IOException {
    
30.     return HttpGet.read(HttpGet.openURL(strURL).getInputStream(), encoding);
    
31.   }
    
32.   
    
33.   private static URLConnection openURL(String strURL) throws IOException {
    
34.     URLConnection conn = new URL(strURL).openConnection();
    
35.     conn.connect();
    
36.     return conn;
    
37.   }
    
38.   
    
39.   private static String read(InputStream in, String encoding) throws IOException {
    
40.     if (encoding == null) encoding = "utf-8";
    
41.     BufferedReader reader = new BufferedReader(new InputStreamReader(in, encoding));
    
42.     char[] str = new char[4096];
    
43.     StringBuilder builder = new StringBuilder();
    
44.     for (int len; (len = reader.read(str)) > -1;)
    
45.       builder.append(str, 0, len);
    
46.     return builder.toString();
    
47.   }
    
48.   
    
49.   private static String getContentEncoding(URLConnection conn) {
    
50.     String contentType = conn.getContentType();
    
51.     if (contentType == null) return null;
    
52.     final Pattern ptnCharset = Pattern.compile("(?i)\\bcharset=([^\\s;]+)");
    
53.     Matcher m = ptnCharset.matcher(contentType);
    
54.     if (m.find())
    
55.       return m.group(1);
    
56.     return null;
    
57.   }
    
58. }

复制代码