fix: remove stale mark_notified import, full main.py scheduler refactor, fix scraper datetime+image extraction

worker/src/scraper.py

@@ -78,11 +78,26 @@ def extract_ad_fields(ad_dict: dict[str, Any]) -> dict[str, Any]:
 
     # Published time from CHANGED_String or PUBLISHED_String (ISO 8601)
     published_raw = attrs.get("PUBLISHED_String") or attrs.get("CHANGED_String")
-    published_at: str | None = None
+    published_at: datetime | None = None
     if published_raw:
         try:
-            dt = datetime.fromisoformat(published_raw.replace("Z", "+00:00"))
-            published_at = dt.isoformat()
+            published_at = datetime.fromisoformat(published_raw.replace("Z", "+00:00"))
+        except (ValueError, TypeError):
+            pass
+
+    # Main image from the first advertImage entry
+    images = ad_dict.get("advertImageList", {}).get("advertImage", [])
+    main_image_url: str | None = None
+    if images and isinstance(images[0], dict):
+        main_image_url = images[0].get("referenceImageUrl")
+
+    postcode = attrs.get("POSTCODE")
+
+    modified_raw = attrs.get("CHANGED_String")
+    modified_at: datetime | None = None
+    if modified_raw:
+        try:
+            modified_at = datetime.fromisoformat(modified_raw.replace("Z", "+00:00"))
         except (ValueError, TypeError):
             pass
 
@@ -93,4 +108,7 @@ def extract_ad_fields(ad_dict: dict[str, Any]) -> dict[str, Any]:
         "location": location,
         "url": url,
         "published_at": published_at,
+        "main_image_url": main_image_url,
+        "postcode": postcode,
+        "modified_at": modified_at,
     }