feat: add page-fetcher-api — centralised Playwright page fetcher
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>
This commit is contained in:
@@ -0,0 +1,45 @@
|
||||
using Microsoft.EntityFrameworkCore;
|
||||
using PageFetcher.Data.Entities;
|
||||
|
||||
namespace PageFetcher.Data;
|
||||
|
||||
/// <summary>
|
||||
/// EF Core DbContext for the <c>pageFetcher</c> schema.
|
||||
/// Owns the <c>PageFetches</c> audit table.
|
||||
/// </summary>
|
||||
public sealed class PageFetchDbContext : DbContext
|
||||
{
|
||||
public const string SchemaName = MigrationConstants.SchemaName;
|
||||
public const string MigrationTableName = MigrationConstants.MigrationTableName;
|
||||
|
||||
public PageFetchDbContext(DbContextOptions<PageFetchDbContext> options) : base(options) { }
|
||||
|
||||
public DbSet<PageFetchEntity> PageFetches => Set<PageFetchEntity>();
|
||||
|
||||
protected override void OnConfiguring(DbContextOptionsBuilder optionsBuilder)
|
||||
{
|
||||
base.OnConfiguring(optionsBuilder);
|
||||
optionsBuilder.UseSqlServer(x => x.MigrationsHistoryTable(MigrationTableName, SchemaName));
|
||||
}
|
||||
|
||||
protected override void OnModelCreating(ModelBuilder modelBuilder)
|
||||
{
|
||||
modelBuilder.HasDefaultSchema(SchemaName);
|
||||
|
||||
modelBuilder.Entity<PageFetchEntity>(entity =>
|
||||
{
|
||||
entity.ToTable("PageFetches");
|
||||
entity.HasKey(x => x.Id);
|
||||
entity.Property(x => x.Id).HasMaxLength(64);
|
||||
entity.Property(x => x.Url).HasMaxLength(2000).IsRequired();
|
||||
entity.Property(x => x.CallerService).HasMaxLength(64).IsRequired();
|
||||
entity.Property(x => x.Html).IsRequired();
|
||||
entity.Property(x => x.Text).IsRequired();
|
||||
entity.Property(x => x.ErrorMessage).HasMaxLength(2000);
|
||||
entity.Property(x => x.CreatedAt).HasDefaultValueSql("SYSUTCDATETIME()");
|
||||
|
||||
entity.HasIndex(x => x.Url);
|
||||
entity.HasIndex(x => x.CreatedAt);
|
||||
});
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user