Update main.py

main.py

@@ -159,31 +159,44 @@ def fetch_congress_scraped():
                 if len(title) < 15 or not is_relevant(title): continue
                 seen_links.add(full_url)
                 
-                # --- AGGRESSIVE DATE HUNTING ---
+                # --- UPGRADED DATE HUNTING (Container Search) ---
                 fmt_date = None
-                current_node = a_tag
                 
-                # Climb up the DOM tree up to 5 levels to find the date stamp
-                for _ in range(5):
-                    if current_node.parent:
-                        current_node = current_node.parent
-                        node_text = current_node.get_text(" ", strip=True)
-                        found_date = extract_robust_date([node_text])
-                        if found_date:
-                            fmt_date = found_date
-                            break
-                            
-                # If still no date, check previous text nodes entirely
+                # 1. Look for the entire row/article container (Catches sibling dates in Drupal!)
+                container = a_tag.find_parent(["article", "tr", "li"])
+                if not container:
+                    container = a_tag.find_parent("div", class_=re.compile(r"views-row|item|post", re.I))
+                    
+                if container:
+                    fmt_date = extract_robust_date([container.get_text(" ", strip=True)])
+                    
+                # 2. Fallback DOM climb
                 if not fmt_date:
-                    prev_text = a_tag.find_previous(string=True)
-                    fmt_date = extract_robust_date([prev_text]) if prev_text else None
-
-                # Only fallback to today if absolutely completely missing
-                fmt_date = fmt_date or datetime.now()
-                
+                    current_node = a_tag
+                    for _ in range(5):
+                        if current_node.parent:
+                            current_node = current_node.parent
+                            found_date = extract_robust_date([current_node.get_text(" ", strip=True)])
+                            if found_date:
+                                fmt_date = found_date
+                                break
+                                
+                # --- THE USER-FACING MISSING DATE FLAG ---
+                if not fmt_date:
+                    # We stop defaulting to today! Mark it explicitly for the user.
+                    display_time = "⚠️ DATE UNKNOWN"
+                    display_title = f"[DATE MISSING] {title}"
+                else:
+                    # If we found a date, run the age gate
+                    days_old = (datetime.now() - fmt_date).days
+                    if days_old > 60: continue
+                    display_time = "Published"
+                    display_title = title
+                    
                 results.append({
                     "source": name, "type": "Legislative Office Press Release", 
-                    "event_date": fmt_date, "time": "Published", "title": title, 
+                    "event_date": fmt_date, # This will be passed as None (Blank) instead of today
+                    "time": display_time, "title": display_title, 
                     "latest_action": "Web Publication", "link": full_url, "summary": "HTML Scrape"
                 })
             time.sleep(1)