有关Java web爬虫问题

问题:

源代码如下：

---

import java.util.Scanner;
import java.util.ArrayList;

public class WebCrawler
{
    public static void main(String[] args)
    {
        ArrayList<String> listOfPendingURLs = new ArrayList<>();
        ArrayList<String> listOfTraversedURLs = new ArrayList<>();
        
        System.out.println("Enter a URL : ");
        String URLString = new Scanner(System.in).nextLine();
        
        try
        {
            listOfPendingURLs.add(URLString);
            
            while(!listOfPendingURLs.isEmpty() && (listOfTraversedURLs.size() <= 100))
            {
                String urlString = listOfPendingURLs.get(0);
                listOfPendingURLs.remove(listOfPendingURLs);
                
                if(!listOfTraversedURLs.contains(urlString))
                {
                    listOfTraversedURLs.add(urlString);
                    System.out.println("Crawling :" + urlString);
        
                    java.net.URL url = new java.net.URL(urlString);
                    Scanner input = new Scanner(url.openStream());
                    
                    int current = 0;
                    while(input.hasNext())
                    {
                        String line = input.nextLine();
                        current = line.indexOf("http:",current);/**String类中的其中一种方法indexOf(s,fromIndex)
                                                                  *返回字符串中fromIndex之后出现的第一个字符串s的下标。如果没有匹配的，返回-1。
                                                                  *这里的意思是：返回URL                                                     
                                                                  */
                        while(current > 0)
                        {
                            int endIndex = line.indexOf("\"",current);//假设URL以“（引号）结束
                            if(endIndex > 0)
                            {
                                String newURL = new String();
                                newURL = line.substring(current,endIndex);
                                if(!listOfTraversedURLs.contains(newURL))
                                {
                                    listOfPendingURLs.add(newURL);
                                }
                                else
                                    current = -1;
                            }
                        }
                    }
                }
            
            }
        }
        
        catch(java.net.MalformedURLException ex)
        {
            System.out.println("Invalid URL");
        }
        
        catch(java.io.IOException ex)
        {
            System.out.println("I/O Errors: no such file");
        }
        
    }
}

---

控制台结果显示：

---

请问改报错怎么解决？为什么会出现该类错误？谢谢！

回答1:

Exception in thread "main" java.lang.OutOfMemoryError: Java heap space(Java堆空间内存溢出)解决方法

回答2:

oom错误，内存溢出了。你再仔细看下代码吧

回答3:

无限循环导致的内存溢出。你看看自己的第二个while语句吧