public class Spider implements Runnable
{
private ArrayList urls; //URL列表
private HashMap indexedURLs; //已经检索过的URL列表
private int threads ; //初始化线程数
public static void main(String argv[]) throws Exception
{
if(argv[0] == null)
{
System.out.println("Missing required argument: [Sit URL]\");
return ;
}
Spider Spider = new Spider(argv[0]);
Spider。go();
}
public Spider(String strURL)
{
urls = new ArrayList();
threads = 10;
urls。add(strURL);
threadList = new ArrayList();
indexedURLs = new HashMap();
if (urls.size() == 0)
throw new IllegalArgumentException(”Missing required argument: —u [start url]”);
if (threads 〈 1)
(\"Invalid number of threads: ” +
threads);
}
public void go(String strURL) throws Exception {
// index each entry point URL
long start = System.currentTimeMillis();
for (int i = 0; i < threads; i++) {
Thread t = new Thread(this, ”Spide ” t.start();
threadList.add(t);
}
while (threadList。size() >; 0) {
+1));
+ (i Thread child = (Thread)threadList.remove(0);
child.join();
}
long elapsed = System.currentTimeMillis() - start;
}
public void run() {
String url;
try {
while ((url = dequeueURL()) != null) {
indexURL(url);
}
}catch(Exception e) {
logger.info(e.getMessage());
}
}
//检测URL列表容器中有没有URL没有被解析,如果有则返回URL由线程继续执行
public synchronized String dequeueURL() throws Exception while (true) {
if (urls.size() >; 0)
{
return (String)urls。remove(0);
}
else {
threads-—;
if (threads >; 0)
{
{ wait();
threads++;
}
else
{
notifyAll();
return null;
}
}
}
}
/*
* 添加URL和当前URL的级数,并唤醒睡眠线程
*/
public synchronized void enqueueURL(String url,int level)
{
if (indexedURLs。get(url) == null)
{
urls。add(url);
indexedURLs。put(url, new Integer(level));
notifyAll();
}
}
/**
* 通过URL解析出网页内容并解析出页面上的URL
* @param url 页面链接
* @throws java。lang。Exception
*/
private void indexURL(String url) throws Exception
{
boolean flag = true ;
//判断网页链接的级别,系统默认为三级
int level = 1 ;
if (indexedURLs。get(url) == null)
{
indexedURLs。put(url, new Integer(level));
}
else{
level = ((Integer)indexedURLs。get(url))。intValue();
//只检测到页面的第二级
if(level >; 2 )
return ;
level++ ;
}
String strBody = null ;
try{
//解析页面内容
strBody = loadURL(url);
}catch(Exception e){
return ;
}
if (strBody != null) {
String urlGroups[] = null ;
try{
//解析出页面所以URL
urlGroups = parseURLs(summary);
}catch(Exception e){
logger.info(e。getMessage());
}
if(urlGroups == null)
urlGroups = new String[0] ;
strBody = null ;
for (int i = 0; i < urlGroups.length; i++) enqueueURL(urlGroups[i],level);
}
{
}
}
}
因篇幅问题不能全部显示,请点此查看更多更全内容
Copyright © 2019- huatuo2.com 版权所有 湘ICP备2023021991号-2
违法及侵权请联系:TEL:199 1889 7713 E-MAIL:2724546146@qq.com
本站由北京市万商天勤律师事务所王兴未律师提供法律服务