1er

backend/app/core/config.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+from functools import lru_cache
+from pathlib import Path
+
+from pydantic import BaseModel
+
+CONFIG_PATH = Path(__file__).resolve().parent.parent.parent / "config_backend.json"
+# chemin vers la conf JSON partagée entre les composants backend
+
+
+class AppConfig(BaseModel):
+    env: str
+    version: str
+    base_url: str
+    log_level: str
+
+
+class ScrapeConfig(BaseModel):
+    interval_minutes: int
+    headless: bool
+    timeout_ms: int
+    retries: int
+    delay_range_ms: tuple[int, int]
+    user_agent: str
+    viewport: dict[str, int]
+    locale: str
+    timezone: str
+    proxy: str | None
+
+
+class TaxonomyConfig(BaseModel):
+    categories: list[str]
+    types_by_category: dict[str, list[str]]
+
+
+class BackendConfig(BaseModel):
+    app: AppConfig
+    scrape: ScrapeConfig
+    stores_enabled: list[str]
+    taxonomy: TaxonomyConfig
+
+
+@lru_cache(maxsize=1)
+def load_config() -> BackendConfig:
+    # on met en cache pour éviter de recharger le fichier à chaque requête
+    return BackendConfig.parse_file(CONFIG_PATH)

backend/app/core/logging.py

@@ -0,0 +1,20 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from loguru import logger
+
+LOG_DIR = Path(__file__).resolve().parent.parent.parent / "logs"
+# dossier de logs pour tracer les scrapes et erreurs
+LOG_DIR.mkdir(parents=True, exist_ok=True)
+LOG_FILE = LOG_DIR / "scrap.log"
+
+logger.add(
+    LOG_FILE,
+    rotation="10 MB",
+    retention="7 days",
+    level="INFO",
+    enqueue=True,
+    backtrace=True,
+    diagnose=True,
+)  # rotation simple pour ne pas gonfler les artefacts

backend/app/core/scheduler.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+
+from apscheduler.schedulers.background import BackgroundScheduler
+from apscheduler.triggers.interval import IntervalTrigger
+from loguru import logger
+
+from backend.app.core.config import load_config
+from backend.app.scraper.runner import scrape_all
+
+scheduler = BackgroundScheduler(timezone=load_config().scrape.timezone)
+"""Scheduler interne APScheduler, prêt à déclencher scrape_all selon la config."""
+
+
+def start_scheduler() -> None:
+    if scheduler.running:
+        return
+
+    config = load_config()
+    interval = config.scrape.interval_minutes
+    scheduler.add_job(
+        scrape_all,
+        trigger=IntervalTrigger(minutes=interval),
+        id="scheduled-scrape-all",
+        replace_existing=True,
+        next_run_time=None,
+    )
+    scheduler.start()
+    logger.info("Scheduler démarré avec un intervalle de %s minutes", interval)