How to send crawler4j data to CrawlerManager?





.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}







1















I'm working with a project where user can search some websites and look for pictures which have unique identifier.



public class ImageCrawler extends WebCrawler {

private static final Pattern filters = Pattern.compile(
".*(\.(css|js|mid|mp2|mp3|mp4|wav|avi|mov|mpeg|ram|m4v|pdf" +
"|rm|smil|wmv|swf|wma|zip|rar|gz))$");

private static final Pattern imgPatterns = Pattern.compile(".*(\.(bmp|gif|jpe?g|png|tiff?))$");

public ImageCrawler() {
}

@Override
public boolean shouldVisit(Page referringPage, WebURL url) {
String href = url.getURL().toLowerCase();
if (filters.matcher(href).matches()) {
return false;
}

if (imgPatterns.matcher(href).matches()) {
return true;
}

return false;
}

@Override
public void visit(Page page) {
String url = page.getWebURL().getURL();

byte imageBytes = page.getContentData();
String imageBase64 = Base64.getEncoder().encodeToString(imageBytes);
try {
SecurityContextHolder.getContext().setAuthentication(new UsernamePasswordAuthenticationToken(urlScan.getOwner(), null));
DecodePictureResponse decodePictureResponse = decodePictureService.decodePicture(imageBase64);
URLScanResult urlScanResult = new URLScanResult();
urlScanResult.setPicture(pictureRepository.findByUuid(decodePictureResponse.getPictureDTO().getUuid()).get());
urlScanResult.setIntegrity(decodePictureResponse.isIntegrity());
urlScanResult.setPictureUrl(url);
urlScanResult.setUrlScan(urlScan);
urlScan.getResults().add(urlScanResult);
urlScanRepository.save(urlScan);
}

} catch (ResourceNotFoundException ex) {
//Picture is not in our database
}
}


Crawlers will be run independently. ImageCrawlerManager class, which is singletone, run crawlers.



public class ImageCrawlerManager {

private static ImageCrawlerManager instance = null;


private ImageCrawlerManager(){
}

public synchronized static ImageCrawlerManager getInstance()
{
if (instance == null)
{
instance = new ImageCrawlerManager();
}
return instance;
}

@Transactional(propagation=Propagation.REQUIRED)
@PersistenceContext(type = PersistenceContextType.EXTENDED)
public void startCrawler(URLScan urlScan, DecodePictureService decodePictureService, URLScanRepository urlScanRepository, PictureRepository pictureRepository){

try {
CrawlConfig config = new CrawlConfig();
config.setCrawlStorageFolder("/tmp");
config.setIncludeBinaryContentInCrawling(true);

PageFetcher pageFetcher = new PageFetcher(config);
RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);

CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
controller.addSeed(urlScan.getUrl());

controller.start(ImageCrawler.class, 1);
urlScan.setStatus(URLScanStatus.FINISHED);
urlScanRepository.save(urlScan);
} catch (Exception e) {
e.printStackTrace();
urlScan.setStatus(URLScanStatus.FAILED);
urlScan.setFailedReason(e.getMessage());
urlScanRepository.save(urlScan);
}
}


How to send every image data to manager which decode this image, get the initiator of search and save results to database? In code above I can run multiple crawlers and save it to database. But unfortunately when i run two crawlers simultaneously, I can store two search results but all of them are connected to the crawler which was run first.










share|improve this question





























    1















    I'm working with a project where user can search some websites and look for pictures which have unique identifier.



    public class ImageCrawler extends WebCrawler {

    private static final Pattern filters = Pattern.compile(
    ".*(\.(css|js|mid|mp2|mp3|mp4|wav|avi|mov|mpeg|ram|m4v|pdf" +
    "|rm|smil|wmv|swf|wma|zip|rar|gz))$");

    private static final Pattern imgPatterns = Pattern.compile(".*(\.(bmp|gif|jpe?g|png|tiff?))$");

    public ImageCrawler() {
    }

    @Override
    public boolean shouldVisit(Page referringPage, WebURL url) {
    String href = url.getURL().toLowerCase();
    if (filters.matcher(href).matches()) {
    return false;
    }

    if (imgPatterns.matcher(href).matches()) {
    return true;
    }

    return false;
    }

    @Override
    public void visit(Page page) {
    String url = page.getWebURL().getURL();

    byte imageBytes = page.getContentData();
    String imageBase64 = Base64.getEncoder().encodeToString(imageBytes);
    try {
    SecurityContextHolder.getContext().setAuthentication(new UsernamePasswordAuthenticationToken(urlScan.getOwner(), null));
    DecodePictureResponse decodePictureResponse = decodePictureService.decodePicture(imageBase64);
    URLScanResult urlScanResult = new URLScanResult();
    urlScanResult.setPicture(pictureRepository.findByUuid(decodePictureResponse.getPictureDTO().getUuid()).get());
    urlScanResult.setIntegrity(decodePictureResponse.isIntegrity());
    urlScanResult.setPictureUrl(url);
    urlScanResult.setUrlScan(urlScan);
    urlScan.getResults().add(urlScanResult);
    urlScanRepository.save(urlScan);
    }

    } catch (ResourceNotFoundException ex) {
    //Picture is not in our database
    }
    }


    Crawlers will be run independently. ImageCrawlerManager class, which is singletone, run crawlers.



    public class ImageCrawlerManager {

    private static ImageCrawlerManager instance = null;


    private ImageCrawlerManager(){
    }

    public synchronized static ImageCrawlerManager getInstance()
    {
    if (instance == null)
    {
    instance = new ImageCrawlerManager();
    }
    return instance;
    }

    @Transactional(propagation=Propagation.REQUIRED)
    @PersistenceContext(type = PersistenceContextType.EXTENDED)
    public void startCrawler(URLScan urlScan, DecodePictureService decodePictureService, URLScanRepository urlScanRepository, PictureRepository pictureRepository){

    try {
    CrawlConfig config = new CrawlConfig();
    config.setCrawlStorageFolder("/tmp");
    config.setIncludeBinaryContentInCrawling(true);

    PageFetcher pageFetcher = new PageFetcher(config);
    RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
    RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);

    CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
    controller.addSeed(urlScan.getUrl());

    controller.start(ImageCrawler.class, 1);
    urlScan.setStatus(URLScanStatus.FINISHED);
    urlScanRepository.save(urlScan);
    } catch (Exception e) {
    e.printStackTrace();
    urlScan.setStatus(URLScanStatus.FAILED);
    urlScan.setFailedReason(e.getMessage());
    urlScanRepository.save(urlScan);
    }
    }


    How to send every image data to manager which decode this image, get the initiator of search and save results to database? In code above I can run multiple crawlers and save it to database. But unfortunately when i run two crawlers simultaneously, I can store two search results but all of them are connected to the crawler which was run first.










    share|improve this question

























      1












      1








      1








      I'm working with a project where user can search some websites and look for pictures which have unique identifier.



      public class ImageCrawler extends WebCrawler {

      private static final Pattern filters = Pattern.compile(
      ".*(\.(css|js|mid|mp2|mp3|mp4|wav|avi|mov|mpeg|ram|m4v|pdf" +
      "|rm|smil|wmv|swf|wma|zip|rar|gz))$");

      private static final Pattern imgPatterns = Pattern.compile(".*(\.(bmp|gif|jpe?g|png|tiff?))$");

      public ImageCrawler() {
      }

      @Override
      public boolean shouldVisit(Page referringPage, WebURL url) {
      String href = url.getURL().toLowerCase();
      if (filters.matcher(href).matches()) {
      return false;
      }

      if (imgPatterns.matcher(href).matches()) {
      return true;
      }

      return false;
      }

      @Override
      public void visit(Page page) {
      String url = page.getWebURL().getURL();

      byte imageBytes = page.getContentData();
      String imageBase64 = Base64.getEncoder().encodeToString(imageBytes);
      try {
      SecurityContextHolder.getContext().setAuthentication(new UsernamePasswordAuthenticationToken(urlScan.getOwner(), null));
      DecodePictureResponse decodePictureResponse = decodePictureService.decodePicture(imageBase64);
      URLScanResult urlScanResult = new URLScanResult();
      urlScanResult.setPicture(pictureRepository.findByUuid(decodePictureResponse.getPictureDTO().getUuid()).get());
      urlScanResult.setIntegrity(decodePictureResponse.isIntegrity());
      urlScanResult.setPictureUrl(url);
      urlScanResult.setUrlScan(urlScan);
      urlScan.getResults().add(urlScanResult);
      urlScanRepository.save(urlScan);
      }

      } catch (ResourceNotFoundException ex) {
      //Picture is not in our database
      }
      }


      Crawlers will be run independently. ImageCrawlerManager class, which is singletone, run crawlers.



      public class ImageCrawlerManager {

      private static ImageCrawlerManager instance = null;


      private ImageCrawlerManager(){
      }

      public synchronized static ImageCrawlerManager getInstance()
      {
      if (instance == null)
      {
      instance = new ImageCrawlerManager();
      }
      return instance;
      }

      @Transactional(propagation=Propagation.REQUIRED)
      @PersistenceContext(type = PersistenceContextType.EXTENDED)
      public void startCrawler(URLScan urlScan, DecodePictureService decodePictureService, URLScanRepository urlScanRepository, PictureRepository pictureRepository){

      try {
      CrawlConfig config = new CrawlConfig();
      config.setCrawlStorageFolder("/tmp");
      config.setIncludeBinaryContentInCrawling(true);

      PageFetcher pageFetcher = new PageFetcher(config);
      RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
      RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);

      CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
      controller.addSeed(urlScan.getUrl());

      controller.start(ImageCrawler.class, 1);
      urlScan.setStatus(URLScanStatus.FINISHED);
      urlScanRepository.save(urlScan);
      } catch (Exception e) {
      e.printStackTrace();
      urlScan.setStatus(URLScanStatus.FAILED);
      urlScan.setFailedReason(e.getMessage());
      urlScanRepository.save(urlScan);
      }
      }


      How to send every image data to manager which decode this image, get the initiator of search and save results to database? In code above I can run multiple crawlers and save it to database. But unfortunately when i run two crawlers simultaneously, I can store two search results but all of them are connected to the crawler which was run first.










      share|improve this question














      I'm working with a project where user can search some websites and look for pictures which have unique identifier.



      public class ImageCrawler extends WebCrawler {

      private static final Pattern filters = Pattern.compile(
      ".*(\.(css|js|mid|mp2|mp3|mp4|wav|avi|mov|mpeg|ram|m4v|pdf" +
      "|rm|smil|wmv|swf|wma|zip|rar|gz))$");

      private static final Pattern imgPatterns = Pattern.compile(".*(\.(bmp|gif|jpe?g|png|tiff?))$");

      public ImageCrawler() {
      }

      @Override
      public boolean shouldVisit(Page referringPage, WebURL url) {
      String href = url.getURL().toLowerCase();
      if (filters.matcher(href).matches()) {
      return false;
      }

      if (imgPatterns.matcher(href).matches()) {
      return true;
      }

      return false;
      }

      @Override
      public void visit(Page page) {
      String url = page.getWebURL().getURL();

      byte imageBytes = page.getContentData();
      String imageBase64 = Base64.getEncoder().encodeToString(imageBytes);
      try {
      SecurityContextHolder.getContext().setAuthentication(new UsernamePasswordAuthenticationToken(urlScan.getOwner(), null));
      DecodePictureResponse decodePictureResponse = decodePictureService.decodePicture(imageBase64);
      URLScanResult urlScanResult = new URLScanResult();
      urlScanResult.setPicture(pictureRepository.findByUuid(decodePictureResponse.getPictureDTO().getUuid()).get());
      urlScanResult.setIntegrity(decodePictureResponse.isIntegrity());
      urlScanResult.setPictureUrl(url);
      urlScanResult.setUrlScan(urlScan);
      urlScan.getResults().add(urlScanResult);
      urlScanRepository.save(urlScan);
      }

      } catch (ResourceNotFoundException ex) {
      //Picture is not in our database
      }
      }


      Crawlers will be run independently. ImageCrawlerManager class, which is singletone, run crawlers.



      public class ImageCrawlerManager {

      private static ImageCrawlerManager instance = null;


      private ImageCrawlerManager(){
      }

      public synchronized static ImageCrawlerManager getInstance()
      {
      if (instance == null)
      {
      instance = new ImageCrawlerManager();
      }
      return instance;
      }

      @Transactional(propagation=Propagation.REQUIRED)
      @PersistenceContext(type = PersistenceContextType.EXTENDED)
      public void startCrawler(URLScan urlScan, DecodePictureService decodePictureService, URLScanRepository urlScanRepository, PictureRepository pictureRepository){

      try {
      CrawlConfig config = new CrawlConfig();
      config.setCrawlStorageFolder("/tmp");
      config.setIncludeBinaryContentInCrawling(true);

      PageFetcher pageFetcher = new PageFetcher(config);
      RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
      RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);

      CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
      controller.addSeed(urlScan.getUrl());

      controller.start(ImageCrawler.class, 1);
      urlScan.setStatus(URLScanStatus.FINISHED);
      urlScanRepository.save(urlScan);
      } catch (Exception e) {
      e.printStackTrace();
      urlScan.setStatus(URLScanStatus.FAILED);
      urlScan.setFailedReason(e.getMessage());
      urlScanRepository.save(urlScan);
      }
      }


      How to send every image data to manager which decode this image, get the initiator of search and save results to database? In code above I can run multiple crawlers and save it to database. But unfortunately when i run two crawlers simultaneously, I can store two search results but all of them are connected to the crawler which was run first.







      spring asynchronous crawler4j






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 22 '18 at 12:44









      Przemek Przemek

      104




      104
























          1 Answer
          1






          active

          oldest

          votes


















          2














          You should inject your database service into your ẀebCrawler instances and not use a singleton to manage the result of your web-crawl.



          crawler4j supports a custom CrawlController.WebCrawlerFactory (see here for reference), which can be used with Spring to inject your database service into a ImageCrawler instance.



          Every single crawler thread should be responsible for the whole process you described with (e.g. by using some specific services for it):




          decode this image, get the initiator of search and save results to
          database




          Setting it up like this, your database will be the only source of truth and you will not have to deal with synchronizing crawler-states between different instances or user-sessions.






          share|improve this answer
























            Your Answer






            StackExchange.ifUsing("editor", function () {
            StackExchange.using("externalEditor", function () {
            StackExchange.using("snippets", function () {
            StackExchange.snippets.init();
            });
            });
            }, "code-snippets");

            StackExchange.ready(function() {
            var channelOptions = {
            tags: "".split(" "),
            id: "1"
            };
            initTagRenderer("".split(" "), "".split(" "), channelOptions);

            StackExchange.using("externalEditor", function() {
            // Have to fire editor after snippets, if snippets enabled
            if (StackExchange.settings.snippets.snippetsEnabled) {
            StackExchange.using("snippets", function() {
            createEditor();
            });
            }
            else {
            createEditor();
            }
            });

            function createEditor() {
            StackExchange.prepareEditor({
            heartbeatType: 'answer',
            autoActivateHeartbeat: false,
            convertImagesToLinks: true,
            noModals: true,
            showLowRepImageUploadWarning: true,
            reputationToPostImages: 10,
            bindNavPrevention: true,
            postfix: "",
            imageUploader: {
            brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
            contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
            allowUrls: true
            },
            onDemand: true,
            discardSelector: ".discard-answer"
            ,immediatelyShowMarkdownHelp:true
            });


            }
            });














            draft saved

            draft discarded


















            StackExchange.ready(
            function () {
            StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53431335%2fhow-to-send-crawler4j-data-to-crawlermanager%23new-answer', 'question_page');
            }
            );

            Post as a guest















            Required, but never shown

























            1 Answer
            1






            active

            oldest

            votes








            1 Answer
            1






            active

            oldest

            votes









            active

            oldest

            votes






            active

            oldest

            votes









            2














            You should inject your database service into your ẀebCrawler instances and not use a singleton to manage the result of your web-crawl.



            crawler4j supports a custom CrawlController.WebCrawlerFactory (see here for reference), which can be used with Spring to inject your database service into a ImageCrawler instance.



            Every single crawler thread should be responsible for the whole process you described with (e.g. by using some specific services for it):




            decode this image, get the initiator of search and save results to
            database




            Setting it up like this, your database will be the only source of truth and you will not have to deal with synchronizing crawler-states between different instances or user-sessions.






            share|improve this answer




























              2














              You should inject your database service into your ẀebCrawler instances and not use a singleton to manage the result of your web-crawl.



              crawler4j supports a custom CrawlController.WebCrawlerFactory (see here for reference), which can be used with Spring to inject your database service into a ImageCrawler instance.



              Every single crawler thread should be responsible for the whole process you described with (e.g. by using some specific services for it):




              decode this image, get the initiator of search and save results to
              database




              Setting it up like this, your database will be the only source of truth and you will not have to deal with synchronizing crawler-states between different instances or user-sessions.






              share|improve this answer


























                2












                2








                2







                You should inject your database service into your ẀebCrawler instances and not use a singleton to manage the result of your web-crawl.



                crawler4j supports a custom CrawlController.WebCrawlerFactory (see here for reference), which can be used with Spring to inject your database service into a ImageCrawler instance.



                Every single crawler thread should be responsible for the whole process you described with (e.g. by using some specific services for it):




                decode this image, get the initiator of search and save results to
                database




                Setting it up like this, your database will be the only source of truth and you will not have to deal with synchronizing crawler-states between different instances or user-sessions.






                share|improve this answer













                You should inject your database service into your ẀebCrawler instances and not use a singleton to manage the result of your web-crawl.



                crawler4j supports a custom CrawlController.WebCrawlerFactory (see here for reference), which can be used with Spring to inject your database service into a ImageCrawler instance.



                Every single crawler thread should be responsible for the whole process you described with (e.g. by using some specific services for it):




                decode this image, get the initiator of search and save results to
                database




                Setting it up like this, your database will be the only source of truth and you will not have to deal with synchronizing crawler-states between different instances or user-sessions.







                share|improve this answer












                share|improve this answer



                share|improve this answer










                answered Dec 7 '18 at 13:42









                rzorzo

                3,25421755




                3,25421755
































                    draft saved

                    draft discarded




















































                    Thanks for contributing an answer to Stack Overflow!


                    • Please be sure to answer the question. Provide details and share your research!

                    But avoid



                    • Asking for help, clarification, or responding to other answers.

                    • Making statements based on opinion; back them up with references or personal experience.


                    To learn more, see our tips on writing great answers.




                    draft saved


                    draft discarded














                    StackExchange.ready(
                    function () {
                    StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53431335%2fhow-to-send-crawler4j-data-to-crawlermanager%23new-answer', 'question_page');
                    }
                    );

                    Post as a guest















                    Required, but never shown





















































                    Required, but never shown














                    Required, but never shown












                    Required, but never shown







                    Required, but never shown

































                    Required, but never shown














                    Required, but never shown












                    Required, but never shown







                    Required, but never shown







                    Popular posts from this blog

                    Guess what letter conforming each word

                    Port of Spain

                    Run scheduled task as local user group (not BUILTIN)