feat: caché de contenido de fuentes — reutiliza URLs scrapeadas en últimos 7 días

2026-05-06 07:05:41 +00:00
parent aa83cfacbd
commit 82e614e285
2 changed files with 30 additions and 0 deletions
@@ -414,6 +414,23 @@ class ExhaustiveScraper:
            source_id = source["id"]

            try:
+                try:
+                    cached = await self.db.get_cached_content(url)
+                except Exception as cache_err:
+                    logger.warning("Cache lookup failed", url=url, error=str(cache_err))
+                    cached = None
+
+                if cached:
+                    logger.debug("Cache hit", url=url)
+                    await self.db.save_source_content(source_id, cached)
+                    await self.db.update_source(
+                        source_id,
+                        status="scraped",
+                        scraped_at=time.time(),
+                        word_count=len(cached.split()),
+                    )
+                    return 0
+
                if source_type == "youtube":
                    content, title = await fetch_with_retry(
                        lambda: self._extract_youtube(url), url