From 4ff5d3ee79000bfdfd5427715319d3c053af8744 Mon Sep 17 00:00:00 2001
From: gilles <gil.soulier@gmail.com>
Date: Sun, 18 Jan 2026 19:33:04 +0100
Subject: [PATCH] feat: auto-scrape on product creation and update product data
 (Step 4)

- Add automatic scraping when creating a new product
- Update product title and image from scraped data
- Add GET /products/{id}/snapshots endpoint for price history
- Add list_snapshots and get_latest_snapshot to CRUD

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---
 backend/app/api/routes_products.py | 27 +++++++++++++++++++++++----
 backend/app/db/crud.py             | 19 +++++++++++++++++++
 backend/app/scraper/runner.py      | 17 +++++++++++++++++
 3 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/backend/app/api/routes_products.py b/backend/app/api/routes_products.py
index b27d446..896ba33 100644
--- a/backend/app/api/routes_products.py
+++ b/backend/app/api/routes_products.py
@@ -1,10 +1,11 @@
 from __future__ import annotations
 
-from fastapi import APIRouter, Depends, HTTPException, status
+from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException, status
 from sqlalchemy.orm import Session
 
 from backend.app.api.deps import get_db
 from backend.app.db import crud, schemas
+from backend.app.scraper.runner import scrape_product
 
 router = APIRouter(prefix="/products", tags=["products"])
 
@@ -16,9 +17,15 @@ def list_products(skip: int = 0, limit: int = 50, db: Session = Depends(get_db))
 
 
 @router.post("", response_model=schemas.ProductRead, status_code=status.HTTP_201_CREATED)
-def create_product(payload: schemas.ProductCreate, db: Session = Depends(get_db)) -> schemas.ProductRead:
-    # création de produit rigoureuse via Pydantic
-    return crud.create_product(db, payload)
+def create_product(
+    payload: schemas.ProductCreate,
+    background_tasks: BackgroundTasks,
+    db: Session = Depends(get_db),
+) -> schemas.ProductRead:
+    product = crud.create_product(db, payload)
+    # Déclenche automatiquement le scraping après création
+    background_tasks.add_task(scrape_product, product.id)
+    return product
 
 
 @router.get("/{product_id}", response_model=schemas.ProductRead)
@@ -45,3 +52,15 @@ def delete_product(product_id: int, db: Session = Depends(get_db)) -> None:
         raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Produit introuvable")
     # suppression définitive en base
     crud.remove_product(db, product)
+
+
+@router.get("/{product_id}/snapshots", response_model=list[schemas.ProductSnapshotRead])
+def list_snapshots(
+    product_id: int,
+    limit: int = 30,
+    db: Session = Depends(get_db),
+) -> list[schemas.ProductSnapshotRead]:
+    product = crud.get_product(db, product_id)
+    if not product:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Produit introuvable")
+    return crud.list_snapshots(db, product_id, limit=limit)
diff --git a/backend/app/db/crud.py b/backend/app/db/crud.py
index 8cdbe9a..00954bd 100644
--- a/backend/app/db/crud.py
+++ b/backend/app/db/crud.py
@@ -43,3 +43,22 @@ def update_product(db: Session, product: models.Product, changes: schemas.Produc
 def remove_product(db: Session, product: models.Product) -> None:
     db.delete(product)
     db.commit()
+
+
+def list_snapshots(db: Session, product_id: int, limit: int = 30) -> list[models.ProductSnapshot]:
+    return (
+        db.query(models.ProductSnapshot)
+        .filter(models.ProductSnapshot.produit_id == product_id)
+        .order_by(models.ProductSnapshot.scrape_le.desc())
+        .limit(limit)
+        .all()
+    )
+
+
+def get_latest_snapshot(db: Session, product_id: int) -> models.ProductSnapshot | None:
+    return (
+        db.query(models.ProductSnapshot)
+        .filter(models.ProductSnapshot.produit_id == product_id)
+        .order_by(models.ProductSnapshot.scrape_le.desc())
+        .first()
+    )
diff --git a/backend/app/scraper/runner.py b/backend/app/scraper/runner.py
index d1a8574..7402762 100644
--- a/backend/app/scraper/runner.py
+++ b/backend/app/scraper/runner.py
@@ -53,6 +53,20 @@ def _save_debug_artifacts(page, product_id: int) -> tuple[Path, Path]:
     return screenshot_path, html_path
 
 
+def _update_product_from_scrape(
+    session: Session,
+    product: models.Product,
+    data: dict,
+) -> None:
+    """Met à jour le produit avec les données scrappées (titre, image)."""
+    if data.get("titre") and not product.titre:
+        product.titre = data["titre"]
+    if data.get("url_image_principale") and not product.url_image:
+        product.url_image = data["url_image_principale"]
+    session.add(product)
+    session.commit()
+
+
 def _create_snapshot(
     session: Session,
     product: models.Product,
@@ -62,6 +76,9 @@ def _create_snapshot(
     raw_json_path: Path | None,
     error_message: str | None = None,
 ) -> None:
+    # Mettre à jour le produit avec titre/image si manquants
+    _update_product_from_scrape(session, product, data)
+
     snapshot = models.ProductSnapshot(
         produit_id=product.id,
         run_scrap_id=run.id,