60 lines
1.9 KiB
Python
60 lines
1.9 KiB
Python
"""
|
|
Pipeline de persistence pour les snapshots de scraping.
|
|
|
|
Ne doit jamais bloquer le pipeline principal si la DB est indisponible.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Optional
|
|
|
|
from sqlalchemy.exc import SQLAlchemyError
|
|
|
|
from pricewatch.app.core.config import AppConfig, get_config
|
|
from pricewatch.app.core.logging import get_logger
|
|
from pricewatch.app.core.schema import ProductSnapshot
|
|
from pricewatch.app.db.connection import get_session
|
|
from pricewatch.app.db.repository import ProductRepository
|
|
|
|
logger = get_logger("scraping.pipeline")
|
|
|
|
|
|
class ScrapingPipeline:
|
|
"""Orchestration de persistence DB pour un ProductSnapshot."""
|
|
|
|
def __init__(self, config: Optional[AppConfig] = None) -> None:
|
|
self.config = config
|
|
|
|
def process_snapshot(
|
|
self,
|
|
snapshot: ProductSnapshot,
|
|
save_to_db: bool = True,
|
|
apply_classification: bool = True,
|
|
) -> Optional[int]:
|
|
"""
|
|
Persiste un snapshot en base si active.
|
|
|
|
Retourne l'id produit si sauve, sinon None.
|
|
"""
|
|
app_config = self.config or get_config()
|
|
if not save_to_db or not app_config.enable_db:
|
|
logger.debug("Persistence DB desactivee")
|
|
return None
|
|
|
|
try:
|
|
with get_session(app_config) as session:
|
|
repo = ProductRepository(session)
|
|
if apply_classification:
|
|
repo.apply_classification(snapshot)
|
|
product_id = repo.safe_save_snapshot(snapshot)
|
|
session.commit()
|
|
return product_id
|
|
except SQLAlchemyError as exc:
|
|
snapshot.add_note(f"Persistence DB echouee: {exc}")
|
|
logger.error(f"Persistence DB echouee: {exc}")
|
|
return None
|
|
except Exception as exc:
|
|
snapshot.add_note(f"Erreur pipeline DB: {exc}")
|
|
logger.error(f"Erreur pipeline DB: {exc}")
|
|
return None
|