我有以下工作代码(在此处和此处更改了,因此在复制和粘贴时会用到大脑)。我想对其进行改进,以便它检测到所有无效页面,包括待出售的域名。它的效率约为89%。如果您看到任何东西,我可以通过使用其他现有的库或进行一些微妙的调整来改善。

 List all = linkService.getAllLinks();
    notValidLinks = new LinkedList();
    final ArrayBlockingQueue<Runnable> queue = new ArrayBlockingQueue<Runnable>(39867);
    int poolSize = 90;
    int maxPoolSize = 100;
    long keepAliveTime = 40;
    ThreadPoolExecutor tpe = new ThreadPoolExecutor(poolSize, maxPoolSize,
            keepAliveTime, TimeUnit.SECONDS, queue);

    for (link : all) {
       Thread task = new CheckSite(link);
       tpe.execute(task);
       System.out.println("Task count:" + queue.size());
    }

class CheckSite extends Thread {
    Link link;

    CheckSite(Link link) {
        this.link = link;
    }

    public void run() {
        boolean notValid = false;
        try {
            log.info(link.getLink() + " " + link.getId());
            URL u = new URL(link.getLink());
            HttpURLConnection huc = (HttpURLConnection) u.openConnection();
            HttpURLConnection.setFollowRedirects(false);
            huc.setConnectTimeout(40000);
            huc.setRequestMethod("GET");
            huc.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2 (.NET CLR 3.5.30729)");

            huc.connect();
            int code = huc.getResponseCode();

            if (code != HttpURLConnection.HTTP_OK
                    && code != HttpURLConnection.HTTP_MOVED_PERM
                    && code != HttpURLConnection.HTTP_MOVED_TEMP ){
                notValid = true;
                log.info("Invalid code: " + code + " - " + link.getLink());
            }
            if (code == HttpURLConnection.HTTP_MOVED_PERM) {
                log.info(link.getLink() + " Perm move");
            }
            if (code == HttpURLConnection.HTTP_MOVED_TEMP) {
                log.info(link.getLink() + " Temp move");
            }

            try {
                if (!notValid) {
                    BufferedReader reader = new BufferedReader(new InputStreamReader(huc.getInputStream()));
                    StringBuilder stringBuilder = new StringBuilder();

                    String line;
                    while ((line = reader.readLine()) != null) {
                        stringBuilder.append(line);
                    }

                    notValid = StringUtils.containsIgnoreCase(Jsoup.parse(stringBuilder.toString()).text(), "Related Searches");

                }
            } catch (Exception e) {
                   log.error(e.getMessage());
            }

            huc.disconnect();
        } catch (MalformedURLException me) {
            log.info("Malformed URL:" + link.getLink());
            notValid = true;
        } catch (IOException e) {
            log.info("Refused connection | Does not exist:" + link.getLink());
            notValid = true;
        }
        if (notValid) {
            link.setApproved(false);
            link.setDateApproved(null);
            notValidLinks.add(linkService.save(link));

        }
        log.debug("URL Finieshed!");
    }
}

最佳答案

请查看Bloom Filter [wiki]。这将帮助您快速且高效地进行内存查找。Bloom过滤器的问题在于它会误报。对于不存在的内容,它会说是对的。但是,如果Bloom过滤器说为false,那肯定是错误的。

10-06 07:29