feat(news): add scraper adapters, article deduplication, blocklist service, and remove tracked publish artifacts

This commit is contained in:
2026-08-24 21:35:33 +02:00
parent 44b161d509
commit 8112598602
400 changed files with 1812 additions and 113367 deletions
@@ -0,0 +1,24 @@
using System;
using System.Threading.Tasks;
using Microsoft.Playwright;
namespace FinlyticNews.Adapters.Scraping;
/// <summary>
/// Specialized article scraper adapter for DerAktionaer.de (DER AKTIONÄR).
/// </summary>
public class DerAktionaerScraperAdapter : ArticleScraperAdapter
{
public override string Hostname => "deraktionaer.de";
public override string ArticleBodySelector => "article#article-detail, div.article-body";
public override async Task<ScrapedArticleResult?> ExtractArticleContentAsync(IPage page)
{
await page.EvaluateAsync(@"() => {
document.querySelectorAll('.sp_message, .latest-release-item, .article-footer, .subscription-box').forEach(e => e.remove());
}");
return await base.ExtractArticleContentAsync(page);
}
}