groove/Part-DB-server
1
0
Fork 0
mirror of https://github.com/Part-DB/Part-DB-server.git synced 2025-12-22 19:09:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use panther to retrieve more data from Aliexpress

Browse source
This commit is contained in:
Jan Böhmer 2025-03-25 23:14:58 +01:00
parent 2fdd837354
commit 3626570a0b
7 changed files with 331 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

49
src/Services/InfoProviderSystem/Providers/AliexpressProvider.php
View file

@ -25,15 +25,24 @@ namespace App\Services\InfoProviderSystem\Providers;
use App\Services\InfoProviderSystem\DTOs\PartDetailDTO;
use App\Services\InfoProviderSystem\DTOs\SearchResultDTO;
use Facebook\WebDriver\Chrome\ChromeOptions;
use Facebook\WebDriver\WebDriverDimension;
use Symfony\Component\DependencyInjection\Attribute\Autowire;
use Symfony\Component\DomCrawler\Crawler;
use Symfony\Component\Panther\Client;
use Symfony\Component\Panther\DomCrawler\Link;
use Symfony\Contracts\HttpClient\HttpClientInterface;
class AliexpressProvider implements InfoProviderInterface
{
public function __construct(private readonly HttpClientInterface $client)
{
private readonly string $chromiumDriverPath;
public function __construct(private readonly HttpClientInterface $client,
#[Autowire('%kernel.project_dir%')]
private readonly string $projectDir)
{
$this->chromiumDriverPath = $this->projectDir . '/drivers/chromedriver.exe';
}
public function getProviderInfo(): array
@ -125,18 +134,44 @@ class AliexpressProvider implements InfoProviderInterface
}
$product_page = $this->getBaseURL() . "/item/{$id}.html";
$response = $this->client->request('GET', $product_page );
//Create panther client
$chromeOptions = new ChromeOptions();
//Disable W3C mode, to avoid issues with getting html() from elements. See https://github.com/symfony/panther/issues/478
$chromeOptions->setExperimentalOption('w3c', false);
$client = Client::createChromeClient( $this->chromiumDriverPath, options: ['capabilities' => [ChromeOptions::CAPABILITY => $chromeOptions]]);
$client->manage()->deleteAllCookies();
$client->manage()->window()->setSize(new WebDriverDimension(1920, 1080));
$client->request('GET', $product_page );
//Dismiss cookie consent
$dom = $client->waitFor('div.global-gdpr-wrap button.btn-accept');
$dom->filter('div.global-gdpr-wrap button.btn-accept')->first()->click();
$dom = $client->waitFor('h1[data-pl="product-title"]');
$name = $dom->filter('h1[data-pl="product-title"]')->text();
//Click on the description button
$dom->filter('a[href="#nav-description"]')->first()->click();
//$client->clickLink('Übersicht');
$dom = $client->waitFor('#product-description');
$description = $dom->filter('#product-description')->html();
//Remove any script tags. This is just to prevent any weird output in the notes field, this is not really a security measure
$description = preg_replace('/<script\b[^>]*>(.*?)<\/script>/is', "", $description);
$content = $response->getContent();
$dom = new Crawler($content);
return new PartDetailDTO(
provider_key: $this->getProviderKey(),
provider_id: $id,
name: $dom->filter('h1[data-pl="product-title"]')->text(),
name: $name,
description: "",
provider_url: $product_page,
notes: $dom->filter('div[data-pl="product-description"]')->html(),
notes: $description,
);
}