小编Din*_*rty的帖子

我在使用此代码时遇到了一些问题：

import edu.uci.ics.crawler4j.crawler.CrawlConfig;
import edu.uci.ics.crawler4j.crawler.CrawlController;
import edu.uci.ics.crawler4j.fetcher.PageFetcher;
import edu.uci.ics.crawler4j.robotstxt.RobotstxtConfig;
import edu.uci.ics.crawler4j.robotstxt.RobotstxtServer;

public class Controller {

     String crawlStorageFolder = "/data/crawl/root";
     int numberOfCrawlers = 7;

     CrawlConfig config = new CrawlConfig();
     config.setCrawlStorageFolder(crawlStorageFolder);
     /*
      * Instantiate the controller for this crawl.
      */
     PageFetcher pageFetcher = new PageFetcher(config);
     RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
     RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);
     CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);

     /*
      * For each crawl, you need to add some seed urls. These are the first
      * URLs that …