/**
 * 多線程爬蟲
 */
public class ThreadCrawler implements Runnable {
  // 采集的文章數(shù)
  private final AtomicLong pageCount = new AtomicLong(0);
  // 列表頁(yè)鏈接正則表達(dá)式
  public static final String URL_LIST = "https://voice.hupu.com/nba";
  protected Logger logger = LoggerFactory.getLogger(getClass());
  // 待采集的隊(duì)列
  LinkedBlockingQueue<String> taskQueue;
  // 采集過的鏈接列表
  HashSet<String> visited;
  // 線程池
  CountableThreadPool threadPool;
  /**
   *
   * @param url 起始頁(yè)
   * @param threadNum 線程數(shù)
   * @throws InterruptedException
   */
  public ThreadCrawler(String url, int threadNum) throws InterruptedException {
    this.taskQueue = new LinkedBlockingQueue<>();
    this.threadPool = new CountableThreadPool(threadNum);
    this.visited = new HashSet<>();
    // 將起始頁(yè)添加到待采集隊(duì)列中
    this.taskQueue.put(url);
  }

  @Override
  public void run() {
    logger.info("Spider started!");
    while (!Thread.currentThread().isInterrupted()) {
      // 從隊(duì)列中獲取待采集 URL
      final String request = taskQueue.poll();
      // 如果獲取 request 為空，并且當(dāng)前的線程采已經(jīng)沒有線程在運(yùn)行
      if (request == null) {
        if (threadPool.getThreadAlive() == 0) {
          break;
        }
      } else {
        // 執(zhí)行采集任務(wù)
        threadPool.execute(new Runnable() {
          @Override
          public void run() {
            try {
              processRequest(request);
            } catch (Exception e) {
              logger.error("process request " + request + " error", e);
            } finally {
              // 采集頁(yè)面 +1
              pageCount.incrementAndGet();
            }
          }
        });
      }
    }
    threadPool.shutdown();
    logger.info("Spider closed! {} pages downloaded.", pageCount.get());
  }

  /**
   * 處理采集請(qǐng)求
   * @param url
   */
  protected void processRequest(String url) {
    // 判斷是否為列表頁(yè)
    if (url.matches(URL_LIST)) {
      // 列表頁(yè)解析出詳情頁(yè)鏈接添加到待采集URL隊(duì)列中
      processTaskQueue(url);
    } else {
      // 解析網(wǎng)頁(yè)
      processPage(url);
    }
  }
  /**
   * 處理鏈接采集
   * 處理列表頁(yè)，將 url 添加到隊(duì)列中
   *
   * @param url
   */
  protected void processTaskQueue(String url) {
    try {
      Document doc = Jsoup.connect(url).get();
      // 詳情頁(yè)鏈接
      Elements elements = doc.select(" div.news-list > ul > li > div.list-hd > h4 > a");
      elements.stream().forEach((element -> {
        String request = element.attr("href");
        // 判斷該鏈接是否存在隊(duì)列或者已采集的 set 中，不存在則添加到隊(duì)列中
        if (!visited.contains(request) && !taskQueue.contains(request)) {
          try {
            taskQueue.put(request);
          } catch (InterruptedException e) {
            e.printStackTrace();
          }
        }
      }));
      // 列表頁(yè)鏈接
      Elements list_urls = doc.select("div.voice-paging > a");
      list_urls.stream().forEach((element -> {
        String request = element.absUrl("href");
        // 判斷是否符合要提取的列表鏈接要求
        if (request.matches(URL_LIST)) {
          // 判斷該鏈接是否存在隊(duì)列或者已采集的 set 中，不存在則添加到隊(duì)列中
          if (!visited.contains(request) && !taskQueue.contains(request)) {
            try {
              taskQueue.put(request);
            } catch (InterruptedException e) {
              e.printStackTrace();
            }
          }
        }
      }));

    } catch (Exception e) {
      e.printStackTrace();
    }
  }
  /**
   * 解析頁(yè)面
   *
   * @param url
   */
  protected void processPage(String url) {
    try {
      Document doc = Jsoup.connect(url).get();
      String title = doc.select("body > div.hp-wrap > div.voice-main > div.artical-title > h1").first().ownText();

      System.out.println(Thread.currentThread().getName() + " 在 " + new Date() + " 采集了虎撲新聞 " + title);
      // 將采集完的 url 存入到已經(jīng)采集的 set 中
      visited.add(url);

    } catch (IOException e) {
      e.printStackTrace();
    }
  }

  public static void main(String[] args) {

    try {
      new ThreadCrawler("https://voice.hupu.com/nba", 5).run();
    } catch (InterruptedException e) {
      e.printStackTrace();
    }
  }
}