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>
2026-06-08 17:43:56 +03:00
parent 1222a86eb7
commit 898dd09d50
31 changed files with 1121 additions and 110 deletions
@@ -0,0 +1,59 @@
+using System;
+using Microsoft.EntityFrameworkCore.Migrations;
+
+#nullable disable
+
+namespace PageFetcher.Data.Migrations
+{
+    /// <inheritdoc />
+    public partial class InitialSchema : Migration
+    {
+        /// <inheritdoc />
+        protected override void Up(MigrationBuilder migrationBuilder)
+        {
+            migrationBuilder.EnsureSchema(
+                name: MigrationConstants.SchemaName);
+
+            migrationBuilder.CreateTable(
+                name: "PageFetches",
+                schema: MigrationConstants.SchemaName,
+                columns: table => new
+                {
+                    Id = table.Column<string>(type: "nvarchar(64)", maxLength: 64, nullable: false),
+                    Url = table.Column<string>(type: "nvarchar(2000)", maxLength: 2000, nullable: false),
+                    CallerService = table.Column<string>(type: "nvarchar(64)", maxLength: 64, nullable: false),
+                    HttpStatusCode = table.Column<int>(type: "int", nullable: true),
+                    Html = table.Column<string>(type: "nvarchar(max)", nullable: false),
+                    Text = table.Column<string>(type: "nvarchar(max)", nullable: false),
+                    DurationMs = table.Column<long>(type: "bigint", nullable: false),
+                    Success = table.Column<bool>(type: "bit", nullable: false),
+                    ErrorMessage = table.Column<string>(type: "nvarchar(2000)", maxLength: 2000, nullable: true),
+                    CreatedAt = table.Column<DateTime>(type: "datetime2", nullable: false, defaultValueSql: "SYSUTCDATETIME()")
+                },
+                constraints: table =>
+                {
+                    table.PrimaryKey("PK_PageFetches", x => x.Id);
+                });
+
+            migrationBuilder.CreateIndex(
+                name: "IX_PageFetches_CreatedAt",
+                schema: MigrationConstants.SchemaName,
+                table: "PageFetches",
+                column: "CreatedAt");
+
+            migrationBuilder.CreateIndex(
+                name: "IX_PageFetches_Url",
+                schema: MigrationConstants.SchemaName,
+                table: "PageFetches",
+                column: "Url");
+        }
+
+        /// <inheritdoc />
+        protected override void Down(MigrationBuilder migrationBuilder)
+        {
+            migrationBuilder.DropTable(
+                name: "PageFetches",
+                schema: MigrationConstants.SchemaName);
+        }
+    }
+}