feat: suite du passage en DDD de Scraping

src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php

@@ -3,7 +3,9 @@
 namespace App\Domain\Scraping\Infrastructure\Persistence;
 
 use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Model\ScrapingStatus;
 use App\Domain\Scraping\Domain\Repository\ScrapingJobRepositoryInterface;
+use App\Domain\Scraping\Infrastructure\Persistence\Entity\ScrapingJobEntity;
 use Doctrine\ORM\EntityManagerInterface;
 
 class DoctrineScrapingJobRepository implements ScrapingJobRepositoryInterface
@@ -14,38 +16,48 @@ class DoctrineScrapingJobRepository implements ScrapingJobRepositoryInterface
 
     public function save(ScrapingJob $job): void
     {
-        $this->entityManager->persist($job);
+        $entity = ScrapingJobEntity::fromDomain($job);
+        $this->entityManager->persist($entity);
         $this->entityManager->flush();
     }
 
     public function findById(string $id): ?ScrapingJob
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)->find($id);
+        $entity = $this->entityManager->getRepository(ScrapingJobEntity::class)
+            ->find($id);
+
+        return $entity?->toDomain();
     }
 
     public function findByChapterId(string $chapterId): ?ScrapingJob
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)
+        $entity = $this->entityManager->getRepository(ScrapingJobEntity::class)
             ->findOneBy(['chapterId' => $chapterId]);
+
+        return $entity?->toDomain();
     }
 
     public function findPendingJobs(): array
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)
+        $entities = $this->entityManager->getRepository(ScrapingJobEntity::class)
             ->createQueryBuilder('sj')
             ->where('sj.status = :status')
-            ->setParameter('status', 'pending')
+            ->setParameter('status', ScrapingStatus::PENDING->value)
             ->getQuery()
             ->getResult();
+
+        return array_map(fn(ScrapingJobEntity $entity) => $entity->toDomain(), $entities);
     }
 
     public function findInProgressJobs(): array
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)
+        $entities = $this->entityManager->getRepository(ScrapingJobEntity::class)
             ->createQueryBuilder('sj')
             ->where('sj.status = :status')
-            ->setParameter('status', 'in_progress')
+            ->setParameter('status', ScrapingStatus::IN_PROGRESS->value)
             ->getQuery()
             ->getResult();
+
+        return array_map(fn(ScrapingJobEntity $entity) => $entity->toDomain(), $entities);
     }
 } 

src/Domain/Scraping/Infrastructure/Service/Scraper/AbstractScraper.php

@@ -0,0 +1,94 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
+
+use App\Domain\Scraping\Domain\Contract\ScraperInterface;
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Event\PageScrapingProgressed;
+use App\Domain\Scraping\Domain\Event\ChapterScrapingCompleted;
+use App\Domain\Scraping\Domain\Event\ChapterScrapingStarted;
+use App\Domain\Scraping\Domain\Model\ScrapingProgress;
+use Symfony\Component\EventDispatcher\EventDispatcherInterface;
+use Symfony\Contracts\HttpClient\HttpClientInterface;
+
+abstract class AbstractScraper implements ScraperInterface
+{
+    public function __construct(
+        protected readonly HttpClientInterface $httpClient,
+        protected readonly EventDispatcherInterface $eventDispatcher,
+        protected readonly string $tempDir
+    ) {}
+
+    public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob
+    {
+        return new ScrapingJob(
+            uniqid('scraping_'),
+            $chapterId,
+            $sourceId
+        );
+    }
+
+    public function scrape(ScrapingJob $job): void
+    {
+        try {
+            $this->eventDispatcher->dispatch(new ChapterScrapingStarted($job->getId()));
+            
+            $tempDir = $this->createTempDirectory($job);
+            $pageData = $this->scrapePages($job);
+            
+            foreach ($pageData as $page) {
+                $this->downloadPage($job, $page, $tempDir);
+            }
+            
+            $job->complete();
+            
+            $this->eventDispatcher->dispatch(
+                new ChapterScrapingCompleted($job->getId(), $job->getPages())
+            );
+            
+            $this->cleanupTempDirectory($tempDir);
+            
+        } catch (\Exception $e) {
+            $job->fail();
+            throw $e;
+        }
+    }
+
+    abstract protected function scrapePages(ScrapingJob $job): array;
+
+    protected function createTempDirectory(ScrapingJob $job): string
+    {
+        $tempDir = $this->tempDir . '/' . uniqid('scraping_' . $job->getId() . '_');
+        if (!mkdir($tempDir) && !is_dir($tempDir)) {
+            throw new \RuntimeException("Failed to create temporary directory: $tempDir");
+        }
+        return $tempDir;
+    }
+
+    protected function cleanupTempDirectory(string $tempDir): void
+    {
+        if (is_dir($tempDir)) {
+            $files = new \RecursiveIteratorIterator(
+                new \RecursiveDirectoryIterator($tempDir, \RecursiveDirectoryIterator::SKIP_DOTS),
+                \RecursiveIteratorIterator::CHILD_FIRST
+            );
+
+            foreach ($files as $file) {
+                if ($file->isDir()) {
+                    rmdir($file->getRealPath());
+                } else {
+                    unlink($file->getRealPath());
+                }
+            }
+            rmdir($tempDir);
+        }
+    }
+
+    protected function dispatchProgressEvent(ScrapingJob $job, int $current, int $total): void
+    {
+        $progress = new ScrapingProgress($current, $total);
+        $this->eventDispatcher->dispatch(
+            new PageScrapingProgressed($job->getId(), $progress)
+        );
+    }
+} 

src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php

@@ -2,60 +2,62 @@
 
 namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
 
-use App\Domain\Scraping\Domain\Contract\ScraperInterface as ContractScraperInterface;
-use App\Domain\Scraping\Domain\Service\ScraperInterface;
 use App\Domain\Scraping\Domain\Model\ScrapingJob;
 use App\Domain\Scraping\Domain\Model\ValueObject\ImageUrl;
 use App\Domain\Scraping\Domain\Model\ValueObject\PageNumber;
-use App\Domain\Scraping\Domain\Event\PageScrapingProgressed;
-use App\Domain\Scraping\Domain\Event\ChapterScrapingCompleted;
 use Symfony\Component\DomCrawler\Crawler;
-use Symfony\Component\EventDispatcher\EventDispatcherInterface;
-use Symfony\Contracts\HttpClient\HttpClientInterface;
 
-class HtmlScraper implements ContractScraperInterface
+class HtmlScraper extends AbstractScraper
 {
-    public function __construct(
+    protected function scrapePages(ScrapingJob $job): array
-        private readonly HttpClientInterface $httpClient,
-        private readonly EventDispatcherInterface $eventDispatcher
-    ) {}
-
-    public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob
     {
-        return new ScrapingJob(
+        $url = $this->buildUrl($job);
-            uniqid('scraping_'),
-            $chapterId,
-            $sourceId
-        );
-    }
-
-    public function scrape(ScrapingJob $job): void
-    {
-        $url = $this->buildUrl($job); // À implémenter selon votre logique
         $response = $this->httpClient->request('GET', $url);
         
         $crawler = new Crawler($response->getContent());
-        $images = $crawler->filter('img.manga-page'); // Adapter selon le site cible
+        $images = $crawler->filter('img.manga-page'); // Adapter selon le site
         
-        $pageNumber = 1;
+        $pages = [];
-        $images->each(function (Crawler $image) use ($job, $pageNumber) {
+        $images->each(function (Crawler $image) use (&$pages) {
-            $imageUrl = new ImageUrl($image->attr('src'));
+            $pages[] = [
-            $job->addPage(new PageNumber($pageNumber), $imageUrl);
+                'url' => $image->attr('src'),
-            
+                'number' => count($pages) + 1
-            $this->eventDispatcher->dispatch(
+            ];
-                new PageScrapingProgressed($job->getId(), $job->getProgress())
-            );
-            
-            $pageNumber++;
         });
         
-        $this->eventDispatcher->dispatch(
+        return $pages;
-            new ChapterScrapingCompleted($job->getId(), $job->getPages())
+    }
+
+    protected function downloadPage(ScrapingJob $job, array $page, string $tempDir): void
+    {
+        $imageUrl = new ImageUrl($page['url']);
+        $pageNumber = new PageNumber($page['number']);
+        
+        $fileName = sprintf('%s/%03d.%s', 
+            $tempDir,
+            $pageNumber->getValue(),
+            $imageUrl->getExtension()
         );
+        
+        $response = $this->httpClient->request('GET', $imageUrl->getValue());
+        file_put_contents($fileName, $response->getContent());
+        
+        $job->addPage($pageNumber, $imageUrl);
+        $this->dispatchProgressEvent($job, $page['number'], count($pages));
     }
 
     public function supports(string $sourceType): bool
     {
         return $sourceType === 'html';
     }
-} 
+
+    private function buildUrl(ScrapingJob $job): string
+    {
+        // À implémenter selon votre logique de construction d'URL
+        // Vous aurez probablement besoin d'injecter un service pour récupérer les informations du chapitre
+        return sprintf('https://example.com/manga/%s/chapter/%s', 
+            $job->getMangaId(), 
+            $job->getChapterId()
+        );
+    }
+}

src/Domain/Scraping/Infrastructure/Service/Scraper/JavascriptScraper.php

@@ -0,0 +1,38 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
+
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use Symfony\Component\Panther\Client as PantherClient;
+
+class JavascriptScraper extends AbstractScraper
+{
+    protected function scrapePages(ScrapingJob $job): array
+    {
+        $client = PantherClient::createChromeClient();
+        try {
+            $url = $this->buildUrl($job);
+            $crawler = $client->request('GET', $url);
+            
+            // Attendre que les images soient chargées
+            $crawler->waitFor('img.manga-page');
+            
+            $pages = [];
+            $crawler->filter('img.manga-page')->each(function ($image) use (&$pages) {
+                $pages[] = [
+                    'url' => $image->attr('src'),
+                    'number' => count($pages) + 1
+                ];
+            });
+            
+            return $pages;
+        } finally {
+            $client->quit();
+        }
+    }
+
+    public function supports(string $sourceType): bool
+    {
+        return $sourceType === 'javascript';
+    }
+}