Files
myAi/Apis/page-fetcher-api/Controllers/PageController.cs
T
claude 898dd09d50 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

48 lines
1.9 KiB
C#

using Microsoft.AspNetCore.Mvc;
using PageFetcher.Models;
using PageFetcherApi.Services;
using Swashbuckle.AspNetCore.Annotations;
namespace PageFetcherApi.Controllers;
/// <summary>
/// Handles page-fetch requests: navigates to the URL via Playwright and returns rendered HTML and extracted text.
/// </summary>
[ApiController]
[Route("api/page")]
public sealed class PageController : ControllerBase
{
private readonly PageFetcherService _service;
private readonly ILogger<PageController> _logger;
public PageController(PageFetcherService service, ILogger<PageController> logger)
{
_service = service;
_logger = logger;
}
/// <summary>
/// Fetches a web page via headless Chromium.
/// Returns rendered HTML and extracted plain text.
/// </summary>
[HttpPost("fetch")]
[SwaggerOperation(Summary = "Fetch a web page", Description = "Navigates to the given URL using Playwright, returns rendered HTML and stripped plain text.")]
[SwaggerResponse(StatusCodes.Status200OK, "Page fetched successfully", typeof(FetchPageResponse))]
[SwaggerResponse(StatusCodes.Status400BadRequest, "Invalid or non-HTTP(S) URL")]
public async Task<ActionResult<FetchPageResponse>> Fetch([FromBody] FetchPageRequest request, CancellationToken ct)
{
if (string.IsNullOrWhiteSpace(request.Url))
return BadRequest(new { Error = "Url is required." });
if (!Uri.TryCreate(request.Url, UriKind.Absolute, out var uri) ||
(uri.Scheme != Uri.UriSchemeHttp && uri.Scheme != Uri.UriSchemeHttps))
return BadRequest(new { Error = "Url must be an absolute HTTP or HTTPS URL." });
_logger.LogInformation("Fetch request: {Url} | caller={Caller} | waitFor={WaitFor}",
request.Url, request.CallerService, request.WaitFor);
var result = await _service.FetchAsync(request, ct);
return Ok(result);
}
}