enhance article handling with index page detection and query improvements

2026-04-17 01:02:39 +01:00
parent b298be6108
commit 01bc624a24
4 changed files with 86 additions and 43 deletions
@@ -557,6 +557,7 @@ async function crawlSite(site) {
          url: canonicalUrl,
          source: normalizedSite.name,
          pubDate: selectPubDate(meta, jsonLdArticle, html),
+          isIndexPage: !isArticleCandidate,
        });
      }
    }