colgora/Mangarr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: suite du passage en DDD de Scraping

Browse Source
This commit is contained in:
ext.jeremy.guillot@maxicoffee.domains
2025-02-01 13:59:37 +01:00
committed by ThysTips
parent 0e3d72cc5e
commit 97d7bcf061
4 changed files with 190 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php
View File

@@ -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(
private readonly HttpClientInterface $httpClient,
private readonly EventDispatcherInterface $eventDispatcher
) {}
public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob
protected function scrapePages(ScrapingJob $job): array
{
return new ScrapingJob(
uniqid('scraping_'),
$chapterId,
$sourceId
);
}
public function scrape(ScrapingJob $job): void
{
$url = $this->buildUrl($job); // À implémenter selon votre logique
$url = $this->buildUrl($job);
$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;
$images->each(function (Crawler $image) use ($job, $pageNumber) {
$imageUrl = new ImageUrl($image->attr('src'));
$job->addPage(new PageNumber($pageNumber), $imageUrl);
$this->eventDispatcher->dispatch(
new PageScrapingProgressed($job->getId(), $job->getProgress())
);
$pageNumber++;
$pages = [];
$images->each(function (Crawler $image) use (&$pages) {
$pages[] = [
'url' => $image->attr('src'),
'number' => count($pages) + 1
];
});
$this->eventDispatcher->dispatch(
new ChapterScrapingCompleted($job->getId(), $job->getPages())
return $pages;
}
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()
);
}
}