JAVA简单小爬虫 & 《JAVA2核心技术卷1：基本知识（原书第7版）》源代码-CSDN博客

文章目录

简单爬虫
源代码

简单爬虫

这段代码源自《JAVA2核心技术卷1：基本知识（原书第7版）》例12-10：

/**
   @version 1.01 2004-06-04
   @author Cay Horstmann
*/

import java.io.*;
import java.net.*;
import java.util.regex.*;

/**
   This program displays all URLs in a web page by
   matching a regular expression that describes the
   <a href=...> HTML tag. Start the program as
   java HrefMatch URL
*/
public class HrefMatch
{
   public static void main(String[] args)
   {
      try
      {
         // get URL string from command line or use default
         String urlString;
         if (args.length > 0) urlString = args[0];
         else urlString = "http://java.sun.com";

         // open reader for URL
         InputStreamReader in = new InputStreamReader(new URL(urlString).openStream());

         // read contents into string buffer
         StringBuilder input = new StringBuilder();
         int ch;
         while ((ch = in.read()) != -1) input.append((char) ch);

         // search for all occurrences of pattern
         String patternString = "<a\\s+href\\s*=\\s*(\"[^\"]*\"|[^\\s>])\\s*>";
         Pattern pattern = Pattern.compile(patternString, Pattern.CASE_INSENSITIVE);
         Matcher matcher = pattern.matcher(input);

         while (matcher.find())
         {
            int start = matcher.start();
            int end = matcher.end();
            String match = input.substring(start, end);
            System.out.println(match);
         }
      }
      catch (IOException e)
      {
         e.printStackTrace();
      }
      catch (PatternSyntaxException e)
      {
         e.printStackTrace();
      }
   }
}