update the scrapper.py

scraper.py

@@ -24,9 +24,15 @@ def scrape_and_store(db: Session, req: ScrapeRequest) -> List[ScrapedPost]:
     # 2) normalize quickly
     normalized = parse_boxapi_items_fast(raw_items)
 
-    # 3) apply cursor filter if provided
-    if req.since_taken_at:
-        normalized = [n for n in normalized if n["taken_at"] < req.since_taken_at]
+    # 3) apply cursor filter if provided (safe, optional)
+    since_ts = getattr(req, "since_taken_at", None)
+    if since_ts:
+        try:
+            since_ts = int(since_ts)
+            normalized = [n for n in normalized if (n.get("taken_at") or 0) > since_ts]
+        except Exception:
+            # If since_taken_at is invalid, ignore it
+            pass
 
     # 4) filter already-seen
     ids_in_order = [n["ig_post_id"] for n in normalized if n.get("ig_post_id")]
@@ -102,9 +108,8 @@ def scrape_and_store(db: Session, req: ScrapeRequest) -> List[ScrapedPost]:
             media_type=item["media_type"],
             caption=item["caption"],
             thumbnail_url=final_thumbnail,
-            remote_urls=item["remote_urls"],  # Return remote URLs for async processing
-            taken_at=item["taken_at"],
-            code=item.get("code")
+            local_media=media_urls,  # Return S3 URLs only
+            created_at=datetime.fromtimestamp(item["taken_at"])
         ))
 
         new_post_count += 1