898dd09d50
Introduces page-fetcher-api, a new internal ASP.NET Core service that centralises all web-page fetching through a single Playwright (headless Chromium) browser instance. All fetches are persisted to the pageFetcher SQL schema for auditing. New projects: - Apis/page-fetcher-api-models: FetchPageRequest, FetchPageResponse, IPageFetcherApiClient - Apis/page-fetcher-data: PageFetchDbContext, PageFetchEntity, InitialSchema migration (schema: pageFetcher) - Apis/page-fetcher-api: PlaywrightBrowserService (singleton), PageFetcherService, PageController Changes to existing services: - cv-matcher-api: JobTextExtractor now calls IPageFetcherApiClient instead of HttpClient - cv-search-job: HtmlJobSearcher uses IPageFetcherApiClient (removes inline Playwright); CvSearchJobTask fetches individual job pages and applies keyword pre-filter before LLM call; passes pre-fetched JobDescription to cv-matcher-api to skip re-fetch - common: add PageFetcherApiSettings - docker-compose.yml, build.yml: add new service + env vars for callers Closes #43 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
50 lines
1.8 KiB
C#
50 lines
1.8 KiB
C#
using Microsoft.Playwright;
|
|
|
|
namespace PageFetcherApi.Services;
|
|
|
|
/// <summary>
|
|
/// Singleton hosted service that owns the Playwright Chromium browser process for the lifetime of the application.
|
|
/// Launches the browser once at startup and exposes it for injection into <see cref="PageFetcherService"/>.
|
|
/// </summary>
|
|
public sealed class PlaywrightBrowserService : IHostedService, IAsyncDisposable
|
|
{
|
|
private IPlaywright? _playwright;
|
|
private IBrowser? _browser;
|
|
private readonly ILogger<PlaywrightBrowserService> _logger;
|
|
|
|
public PlaywrightBrowserService(ILogger<PlaywrightBrowserService> logger)
|
|
{
|
|
_logger = logger;
|
|
}
|
|
|
|
/// <summary>The running Chromium browser instance. Available after <see cref="StartAsync"/> completes.</summary>
|
|
public IBrowser Browser => _browser ?? throw new InvalidOperationException("Browser has not been started yet.");
|
|
|
|
/// <inheritdoc />
|
|
public async Task StartAsync(CancellationToken cancellationToken)
|
|
{
|
|
_logger.LogInformation("Launching Playwright Chromium browser...");
|
|
_playwright = await Playwright.CreateAsync();
|
|
_browser = await _playwright.Chromium.LaunchAsync(new BrowserTypeLaunchOptions
|
|
{
|
|
Headless = true,
|
|
Args = ["--no-sandbox", "--disable-setuid-sandbox", "--disable-dev-shm-usage"]
|
|
});
|
|
_logger.LogInformation("Playwright Chromium browser launched successfully.");
|
|
}
|
|
|
|
/// <inheritdoc />
|
|
public async Task StopAsync(CancellationToken cancellationToken)
|
|
{
|
|
_logger.LogInformation("Closing Playwright Chromium browser...");
|
|
if (_browser is not null) await _browser.CloseAsync();
|
|
}
|
|
|
|
/// <inheritdoc />
|
|
public async ValueTask DisposeAsync()
|
|
{
|
|
if (_browser is not null) await _browser.DisposeAsync();
|
|
_playwright?.Dispose();
|
|
}
|
|
}
|