feat: scraping endpoints, job persistence, firsts unit tests, legacy entities usage

This commit is contained in:
ext.jeremy.guillot@maxicoffee.domains
2025-02-07 11:56:51 +01:00
parent c55cd62ec7
commit 0374ab0e46
34 changed files with 348 additions and 326 deletions

View File

@@ -0,0 +1,21 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Handler;
use App\Domain\Scraping\Application\Command\ScrapeChapter;
use App\Domain\Scraping\Application\CommandHandler\ScrapeChapterHandler;
use Symfony\Component\Messenger\Attribute\AsMessageHandler;
#[AsMessageHandler]
class SymfonyScrapeChapterHandler
{
public function __construct(
private ScrapeChapterHandler $handler
) {
}
public function __invoke(ScrapeChapter $command): void
{
$this->handler->handle($command);
}
}

View File

@@ -1,23 +0,0 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Persistence;
use App\Domain\Scraping\Domain\Contract\Repository\MangaRepositoryInterface;
use App\Domain\Scraping\Domain\Model\Manga;
use App\Domain\Scraping\Infrastructure\Persistence\Entity\MangaEntity;
use Doctrine\ORM\EntityManagerInterface;
class DoctrineMangaRepository implements MangaRepositoryInterface
{
public function __construct(
private readonly EntityManagerInterface $entityManager
) {
}
public function getById(string $id): ?Manga
{
$manga = $this->entityManager->getRepository(MangaEntity::class)->find($id);
return $manga ? $manga->toDomain() : null;
}
}

View File

@@ -1,27 +0,0 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Persistence;
use App\Domain\Scraping\Domain\Model\Source;
use App\Domain\Scraping\Domain\Repository\SourceRepositoryInterface;
use Doctrine\ORM\EntityManagerInterface;
use App\Domain\Scraping\Infrastructure\Persistence\Entity\SourceEntity as SourceEntityEntity;
class DoctrineSourceRepository implements SourceRepositoryInterface
{
public function __construct(
private readonly EntityManagerInterface $entityManager
) {
}
public function getById(string $id): ?Source
{
$sourceEntity = $this->entityManager->getRepository(SourceEntityEntity::class)->find($id);
if (!$sourceEntity) {
return null;
}
return $sourceEntity->toDomain();
}
}

View File

@@ -1,75 +0,0 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Persistence\Entity;
use App\Domain\Scraping\Domain\Model\Manga;
use Doctrine\DBAL\Types\Types;
use Doctrine\ORM\Mapping as ORM;
#[ORM\Entity]
#[ORM\Table(name: 'mangas')]
class MangaEntity
{
#[ORM\Id]
#[ORM\Column(type: 'string', length: 36)]
private string $id;
#[ORM\Column(length: 255)]
private string $title;
#[ORM\Column(length: 255, unique: true)]
private string $slug;
#[ORM\Column(length: 255, nullable: true)]
private ?string $imageUrl = null;
#[ORM\Column(nullable: true)]
private ?int $publicationYear = null;
#[ORM\Column(type: Types::TEXT, nullable: true)]
private ?string $description = null;
#[ORM\Column(type: Types::ARRAY, nullable: true)]
private ?array $genres = null;
#[ORM\Column(type: 'datetime_immutable')]
private \DateTimeImmutable $createdAt;
#[ORM\Column(nullable: true)]
private ?float $rating = null;
#[ORM\Column(length: 255, nullable: true)]
private ?string $author = null;
#[ORM\Column(length: 255, nullable: true)]
private ?string $status = null;
#[ORM\Column]
private bool $monitored;
public static function fromDomain(Manga $manga): self
{
$entity = new self();
$entity->id = $manga->getId();
$entity->title = $manga->getTitle();
$entity->slug = $manga->getSlug();
$entity->description = $manga->getDescription();
$entity->author = $manga->getAuthor();
return $entity;
}
public function toDomain(): Manga
{
$manga = new Manga(
$this->id,
$this->title,
$this->slug,
$this->description,
$this->author
);
return $manga;
}
}

View File

@@ -14,7 +14,7 @@ class ScrapingJobEntity
private string $id;
#[ORM\Column(type: 'string')]
private string $chapterId;
private string $chapterNumber;
#[ORM\Column(type: 'string')]
private string $mangaId;
@@ -38,7 +38,7 @@ class ScrapingJobEntity
{
$entity = new self();
$entity->id = $job->getId();
$entity->chapterId = $job->getChapterId();
$entity->chapterNumber = $job->getChapterNumber();
$entity->mangaId = $job->getMangaId();
$entity->sourceId = $job->getSourceId();
$entity->pages = $job->getPages();
@@ -52,10 +52,10 @@ class ScrapingJobEntity
public function toDomain(): ScrapingJob
{
$job = new ScrapingJob(
$this->id,
$this->chapterId,
$this->mangaId,
$this->sourceId
id: $this->id,
mangaId: $this->mangaId,
chapterNumber: $this->chapterNumber,
sourceId: $this->sourceId
);
return $job;

View File

@@ -1,65 +0,0 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Persistence\Entity;
use App\Domain\Scraping\Domain\Model\Source;
use Doctrine\ORM\Mapping as ORM;
#[ORM\Entity]
#[ORM\Table(name: 'sources')]
class SourceEntity
{
#[ORM\Id]
#[ORM\Column(type: 'string', length: 36)]
private string $id;
#[ORM\Column(type: 'string', nullable: true)]
private ?string $name = null;
#[ORM\Column(type: 'text', nullable: true)]
private ?string $description = null;
#[ORM\Column(type: 'string')]
private string $baseUrl;
#[ORM\Column(type: 'json')]
private array $scrappingParameters = [];
#[ORM\Column(type: 'boolean')]
private bool $isActive;
#[ORM\Column(type: 'datetime_immutable')]
private \DateTimeImmutable $createdAt;
#[ORM\Column(type: 'datetime_immutable')]
private \DateTimeImmutable $updatedAt;
public static function fromDomain(Source $source): self
{
$entity = new self();
$entity->id = $source->getId();
$entity->name = $source->getName();
$entity->description = $source->getDescription();
$entity->baseUrl = $source->getBaseUrl();
$entity->scrappingParameters = $source->getScrappingParameters();
$entity->isActive = $source->isActive();
$entity->createdAt = $source->getCreatedAt();
$entity->updatedAt = $source->getUpdatedAt();
return $entity;
}
public function toDomain(): Source
{
return new Source(
$this->id,
$this->name ?? '',
$this->description ?? '',
$this->baseUrl,
$this->scrappingParameters,
$this->isActive,
$this->createdAt,
$this->updatedAt
);
}
}

View File

@@ -0,0 +1,30 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Persistence;
use App\Domain\Scraping\Domain\Contract\Repository\MangaRepositoryInterface;
use App\Domain\Scraping\Domain\Model\Manga;
use App\Entity\Manga as EntityManga;
use Doctrine\ORM\EntityManagerInterface;
readonly class LegacyMangaRepository implements MangaRepositoryInterface
{
public function __construct(
private EntityManagerInterface $entityManager
) {
}
public function getById(string $id): ?Manga
{
/** @var EntityManga|null $mangaEntity */
$mangaEntity = $this->entityManager->getRepository(EntityManga::class)->find($id);
return $mangaEntity ? new Manga(
$mangaEntity->getId(),
$mangaEntity->getTitle(),
$mangaEntity->getSlug(),
$mangaEntity->getDescription(),
$mangaEntity->getAuthor(),
) : null;
}
}

View File

@@ -0,0 +1,49 @@
<?php
namespace App\Domain\Scraping\Infrastructure\Persistence;
use App\Domain\Scraping\Domain\Contract\Repository\SourceRepositoryInterface;
use App\Domain\Scraping\Domain\Exception\SourceNotFoundException;
use App\Domain\Scraping\Domain\Model\Source;
use App\Domain\Scraping\Domain\Model\ValueObject\SourceId;
use App\Entity\ContentSource;
use DateTimeImmutable;
use Doctrine\ORM\EntityManagerInterface;
readonly class LegacySourceRepository implements SourceRepositoryInterface
{
public function __construct(
private EntityManagerInterface $entityManager
) {
}
/**
* @throws SourceNotFoundException
*/
public function getById(string $id): Source
{
/** @var ContentSource|null $source */
$source = $this->entityManager->getRepository(ContentSource::class)->find($id);
if (!$source) {
throw new SourceNotFoundException("Source not found");
}
return new Source(
id: new SourceId($source->getId()),
name: $source->getCleanBaseUrl(),
description: 'Legacy Source: ' . $source->getBaseUrl(),
baseUrl: $source->getBaseUrl(),
scrappingParameters: [
'imageSelector' => $source->getImageSelector(),
'nextPageSelector' => $source->getNextPageSelector(),
'chapterUrlFormat' => $source->getChapterUrlFormat(),
'scrapingType' => $source->getScrapingType(),
'chapterSelector' => $source->getChapterSelector()
],
isActive: true,
createdAt: new DateTimeImmutable(),
updatedAt: new DateTimeImmutable()
);
}
}

View File

@@ -3,11 +3,12 @@
namespace App\Domain\Scraping\Infrastructure\Service;
use Symfony\Contracts\HttpClient\HttpClientInterface;
use App\Domain\Scraping\Domain\Contract\Service\ImageDownloader as ImageDownloaderInterface;
class ImageDownloader
readonly class ImageDownloader implements ImageDownloaderInterface
{
public function __construct(
private readonly HttpClientInterface $httpClient
private HttpClientInterface $httpClient
) {
}

View File

@@ -2,9 +2,7 @@
namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
use App\Domain\Scraping\Domain\Contract\ScraperInterface;
use App\Domain\Scraping\Domain\Event\ChapterScrapingCompleted;
use App\Domain\Scraping\Domain\Event\ChapterScrapingStarted;
use App\Domain\Scraping\Domain\Contract\Service\ScraperInterface;
use App\Domain\Scraping\Domain\Event\PageScrapingProgressed;
use App\Domain\Scraping\Domain\Model\ScrapingJob;
use App\Domain\Scraping\Domain\Model\ScrapingProgress;
@@ -22,16 +20,6 @@ abstract class AbstractScraper implements ScraperInterface
) {
}
public function createScrapingJob(string $mangaId, string $chapterId, string $sourceId): ScrapingJob
{
return new ScrapingJob(
Uuid::uuid4()->toString(),
$mangaId,
$chapterId,
$sourceId,
);
}
abstract public function scrape(ScrapingJob $job): void;
abstract protected function scrapePages(ScrapingJob $job, Source $source): array;

View File

@@ -2,11 +2,14 @@
namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
use App\Domain\Scraping\Domain\Contract\Repository\MangaRepositoryInterface;
use App\Domain\Scraping\Domain\Contract\Repository\ScrapingJobRepositoryInterface;
use App\Domain\Scraping\Domain\Model\ScrapingJob;
use App\Domain\Scraping\Domain\Model\Source;
use App\Domain\Scraping\Domain\Model\ValueObject\ImageUrl;
use App\Domain\Scraping\Domain\Model\ValueObject\PageNumber;
use App\Domain\Scraping\Domain\Repository\SourceRepositoryInterface;
use App\Domain\Scraping\Domain\Contract\Repository\SourceRepositoryInterface;
use App\Domain\Scraping\Domain\Model\ValueObject\ChapterUrl;
use Symfony\Component\DomCrawler\Crawler;
use Symfony\Contracts\HttpClient\HttpClientInterface;
use Symfony\Component\Messenger\MessageBusInterface;
@@ -18,7 +21,9 @@ class HtmlScraper extends AbstractScraper
ImageDownloader $imageDownloader,
MessageBusInterface $eventBus,
private readonly HttpClientInterface $httpClient,
private readonly SourceRepositoryInterface $sourceRepository
private readonly SourceRepositoryInterface $sourceRepository,
private readonly MangaRepositoryInterface $mangaRepository,
private readonly ScrapingJobRepositoryInterface $scrapingJobRepository,
) {
parent::__construct($imageDownloader, $eventBus);
}
@@ -48,21 +53,25 @@ class HtmlScraper extends AbstractScraper
}
$job->complete();
$this->scrapingJobRepository->save($job);
} catch (\Exception $e) {
$job->fail();
$this->scrapingJobRepository->save($job);
throw $e;
} finally {
$this->cleanupTempFiles($tempDir);
}
}
protected function scrapePages(ScrapingJob $job, Source $sourceConfig): array
protected function scrapePages(ScrapingJob $job, Source $source): array
{
if (!$sourceConfig['next_page_selector']) {
return $this->scrapeVerticalReader($job, $sourceConfig);
$scrappingParameters = $source->getScrappingParameters();
if (!$scrappingParameters['nextPageSelector']) {
return $this->scrapeVerticalReader($job, $source);
}
return $this->scrapeHorizontalReader($job, $sourceConfig);
return $this->scrapeHorizontalReader($job, $source);
}
private function scrapeVerticalReader(ScrapingJob $job, Source $sourceConfig): array
@@ -70,7 +79,7 @@ class HtmlScraper extends AbstractScraper
$html = $this->fetchHtml($this->buildChapterUrl($job, $sourceConfig));
$crawler = new Crawler($html);
return $crawler->filter($sourceConfig['image_selector'])
return $crawler->filter($sourceConfig->getScrappingParameters()['imageSelector'])
->each(function ($node) {
return $this->cleanImageUrl(
$node->attr('src') ?: $node->attr('data-src')
@@ -87,13 +96,20 @@ class HtmlScraper extends AbstractScraper
$html = $this->fetchHtml($currentUrl);
$crawler = new Crawler($html);
$imageUrl = $crawler->filter($sourceConfig['image_selector'])
->attr('src') ?: $crawler->filter($sourceConfig['image_selector'])
$imageUrl = $crawler->filter($sourceConfig->getScrappingParameters()['imageSelector'])
->attr('src') ?: $crawler->filter($sourceConfig->getScrappingParameters()['imageSelector'])
->attr('data-src');
if (!preg_match('/^https?:\/\//', $imageUrl)) {
$urlComponents = parse_url($sourceConfig->getScrappingParameters()['chapterUrlFormat']);
$scheme = $urlComponents['scheme'];
$host = $urlComponents['host'];
$imageUrl = $scheme.'://'.$host.'/'.ltrim($imageUrl, '/');
}
$pages[] = $this->cleanImageUrl($imageUrl);
$nextLink = $crawler->filter($sourceConfig['next_page_selector']);
$nextLink = $crawler->filter($sourceConfig->getScrappingParameters()['nextPageSelector']);
$currentUrl = $nextLink->count() > 0 ? $nextLink->attr('href') : null;
}
@@ -120,10 +136,9 @@ class HtmlScraper extends AbstractScraper
private function buildChapterUrl(ScrapingJob $job, Source $sourceConfig): string
{
return sprintf(
$sourceConfig->getBaseUrl(),
$job->getChapterId()
);
$manga = $this->mangaRepository->getById($job->getMangaId());
$chapterUrl = new ChapterUrl($sourceConfig->getScrappingParameters()['chapterUrlFormat'], $manga->getSlug(), $job->getChapterNumber());
return $chapterUrl->getUrl();
}
public function supports(string $sourceType): bool