feat: implement background scheduler for job scraping with Gunicorn support

web/app.py

@@ -4,7 +4,7 @@ from flask_wtf import CSRFProtect
 from typing import Dict, List
 from datetime import datetime, timezone
 
-from web.craigslist import scraper
+from web.craigslist import scraper, start_scheduler_in_background
 from web.db import (
     db_init,
     delete_user_by_id,
@@ -60,6 +60,26 @@ app.static_folder = "static"
 csrf = CSRFProtect(app)
 
 
+def _scheduler_enabled() -> bool:
+    flag = (os.environ.get("SCRAPE_SCHEDULER_ENABLED") or "").strip().lower()
+    if flag not in {"1", "true", "yes", "on"}:
+        return False
+    # Avoid starting scheduler in Gunicorn workers (master hook handles it).
+    server_software = (os.environ.get("SERVER_SOFTWARE") or "").lower()
+    if "gunicorn" in server_software:
+        return False
+    # Avoid starting twice under Flask reloader.
+    if os.environ.get("FLASK_RUN_FROM_CLI") == "true" and os.environ.get("WERKZEUG_RUN_MAIN") != "true":
+        return False
+    return True
+
+
+@app.before_first_request
+def _start_scheduler_if_enabled():
+    if _scheduler_enabled():
+        start_scheduler_in_background()
+
+
 def require_admin():
     username = session.get('username')
     if not username: