Files
myAi/Jobs/cv-search-job/Services/HtmlJobSearcher.cs
T
claude e95ed36647 refactor: restructure solution into -models/-data/-api project taxonomy
Phases 1-10 of the planned refactoring:

Phase 1: rename shared-models -> common
  - namespace Shared.Models -> Common throughout
  - remove stale AspNetCore.Http.Features 5.0 reference

Phase 2: create shared-data with abstract BaseEntity
  - BaseEntity: required string Id { get; init; } + DateTime CreatedAt { get; init; }

Phase 3: rename myai-models -> myai-data
  - namespace MyAi.Models -> MyAi.Data
  - MigrationsAssembly("myai-data")

Phase 4: rename cv-search-models -> cv-search-data
  - namespace CvSearch.Models -> CvSearch.Data
  - move JobSearchSettings to cv-matcher-api-models
  - JobSearch*Entity now inherits BaseEntity

Phase 5: extract rag-data from rag-api
  - new project: Apis/rag-data with RagDbContext + entities + migrations
  - RagDocumentEntity inherits BaseEntity; cache entities use CacheKey PK
  - fix duplicate AddHttpClient<RagAiClient>/AddScoped registrations in rag-api
  - MigrationsAssembly("rag-data")

Phase 6: extract cv-matcher-data from cv-matcher-api
  - new project: Apis/cv-matcher-data with CvMatcherDbContext + entities + migrations
  - CvMatchResultEntity inherits BaseEntity; CvMatcherChatCacheEntity uses CacheKey PK
  - MigrationsAssembly("cv-matcher-data")

Phase 7: create empty cv-cleanup-job-models and cv-search-job-models

Phase 8: update all 5 Dockerfiles for renamed/new projects

Phase 9: reorganise .sln virtual folders (Apis/Jobs/Models/Data/Helpers)
  - update root CLAUDE.md with new project taxonomy and migration commands
  - update cv-matcher-api/CLAUDE.md and cv-search-job/CLAUDE.md

Phase 10: add Directory.Packages.props for centralised NuGet versions
  - remove Version= from all PackageReference elements in active .csproj files

No database changes. No runtime behaviour changes.
All MigrationId strings in __EFMigrationsHistory are unaffected.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-27 15:26:03 +03:00

87 lines
2.9 KiB
C#

using System.Text.RegularExpressions;
using System.Web;
using CvMatcher.Models.Settings;
using Microsoft.Extensions.Logging;
namespace CvSearchJob.Services;
public sealed class HtmlJobSearcher
{
private readonly HttpClient _http;
private readonly ILogger<HtmlJobSearcher> _logger;
public HtmlJobSearcher(HttpClient http, ILogger<HtmlJobSearcher> logger)
{
_http = http;
_logger = logger;
_http.Timeout = TimeSpan.FromSeconds(20);
_http.DefaultRequestHeaders.UserAgent.ParseAdd("Mozilla/5.0 (compatible; MyAi.ro CV-Search/1.0)");
}
public async Task<IReadOnlyList<string>> SearchJobUrlsAsync(
JobProviderConfig provider,
IReadOnlyList<string> cvKeywords,
CancellationToken ct)
{
var allKeywords = provider.InitialKeywords
.Concat(cvKeywords)
.Where(k => !string.IsNullOrWhiteSpace(k))
.Distinct(StringComparer.OrdinalIgnoreCase)
.ToList();
if (allKeywords.Count == 0)
return [];
var keywordsEncoded = HttpUtility.UrlEncode(string.Join(" ", allKeywords));
var searchUrl = provider.SearchUrlTemplate.Replace("{keywords}", keywordsEncoded);
string html;
try
{
html = await _http.GetStringAsync(searchUrl, ct);
}
catch (Exception ex)
{
_logger.LogWarning(ex, "Failed to fetch search results from {Provider} at {Url}", provider.Name, searchUrl);
return [];
}
var baseUri = new Uri(searchUrl);
var results = new List<string>();
var seen = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
// Match all anchor tags capturing href and inner text
var anchorPattern = new Regex(@"<a[^>]+href=[""']([^""']+)[""'][^>]*>(.*?)</a>",
RegexOptions.IgnoreCase | RegexOptions.Singleline);
foreach (Match match in anchorPattern.Matches(html))
{
if (results.Count >= provider.MaxResults) break;
var href = match.Groups[1].Value.Trim();
var anchorText = Regex.Replace(match.Groups[2].Value, "<[^>]+>", " ").Trim();
if (!href.Contains(provider.JobLinkContains, StringComparison.OrdinalIgnoreCase))
continue;
// Stage 2: anchor text must contain at least one CV keyword
if (!cvKeywords.Any(k => anchorText.Contains(k, StringComparison.OrdinalIgnoreCase)))
continue;
// Make absolute URL
if (!Uri.TryCreate(href, UriKind.Absolute, out var absoluteUri))
{
if (!Uri.TryCreate(baseUri, href, out absoluteUri))
continue;
}
var url = absoluteUri.GetLeftPart(UriPartial.Path);
if (seen.Add(url))
results.Add(url);
}
_logger.LogInformation("Provider {Provider}: found {Count} job URLs", provider.Name, results.Count);
return results;
}
}