last

.env

@@ -0,0 +1,7 @@
+APP_ENV=development
+API_HOST=0.0.0.0
+API_PORT=8018
+FRONTEND_PORT=8081
+LOG_LEVEL=INFO
+DATABASE_URL=sqlite:///backend/data/suivi.db
+VITE_API_URL=/api

.gitignore

@@ -1,8 +1,8 @@
 .venv/
 __pycache__/
 *.pyc
-backend/data/
+#backend/data/
 backend/logs/
 frontend/node_modules/
 frontend/dist/
-.env
+#.env

backend/app/api/routes_config.py

@@ -1,16 +1,34 @@
 from __future__ import annotations
 
 import json
+import os
+import shutil
+from datetime import datetime
 from pathlib import Path
 
-from fastapi import APIRouter, Body, HTTPException
+from fastapi import APIRouter, Body, HTTPException, UploadFile, File
+from fastapi.responses import FileResponse
 
 from backend.app.core.config import BackendConfig, CONFIG_PATH, load_config
+from backend.app.db.database import DEFAULT_DATABASE_PATH
 
 router = APIRouter(prefix="/config", tags=["config"])
 
-# Chemin vers la config frontend
-FRONTEND_CONFIG_PATH = Path(__file__).resolve().parent.parent.parent.parent / "frontend" / "config_frontend.json"
+# Chemins possibles vers la config frontend (dev + docker)
+FRONTEND_CONFIG_PATH = (
+    Path(__file__).resolve().parent.parent.parent.parent / "frontend" / "public" / "config_frontend.json"
+)
+FRONTEND_CONFIG_FALLBACK_PATH = (
+    Path(__file__).resolve().parent.parent.parent.parent / "backend" / "config_frontend.json"
+)
+
+
+def _get_frontend_config_path() -> Path | None:
+    if FRONTEND_CONFIG_PATH.exists():
+        return FRONTEND_CONFIG_PATH
+    if FRONTEND_CONFIG_FALLBACK_PATH.exists():
+        return FRONTEND_CONFIG_FALLBACK_PATH
+    return None
 
 
 @router.get("/backend", response_model=BackendConfig)
@@ -23,8 +41,21 @@ def read_backend_config() -> BackendConfig:
 def update_backend_config(payload: dict = Body(...)) -> BackendConfig:
     current = load_config()
     try:
-        # validation via Pydantic avant écriture
-        updated = current.model_copy(update=payload)
+        # Fusion profonde des configs (nécessaire pour les modèles imbriqués Pydantic v2)
+        def deep_merge(base: dict, update: dict) -> dict:
+            result = base.copy()
+            for key, value in update.items():
+                if key in result and isinstance(result[key], dict) and isinstance(value, dict):
+                    result[key] = deep_merge(result[key], value)
+                else:
+                    result[key] = value
+            return result
+
+        # Convertir en dict, fusionner, puis revalider
+        current_dict = current.model_dump()
+        merged = deep_merge(current_dict, payload)
+        updated = BackendConfig.model_validate(merged)
+
         CONFIG_PATH.write_text(updated.model_dump_json(indent=2), encoding="utf-8")
         load_config.cache_clear()
         return load_config()
@@ -35,9 +66,10 @@ def update_backend_config(payload: dict = Body(...)) -> BackendConfig:
 @router.get("/frontend")
 def read_frontend_config() -> dict:
     """Retourne la configuration frontend."""
-    if not FRONTEND_CONFIG_PATH.exists():
+    config_path = _get_frontend_config_path()
+    if not config_path:
         raise HTTPException(status_code=404, detail="Config frontend introuvable")
-    return json.loads(FRONTEND_CONFIG_PATH.read_text(encoding="utf-8"))
+    return json.loads(config_path.read_text(encoding="utf-8"))
 
 
 @router.put("/frontend")
@@ -46,8 +78,9 @@ def update_frontend_config(payload: dict = Body(...)) -> dict:
     try:
         # Charger la config actuelle
         current = {}
-        if FRONTEND_CONFIG_PATH.exists():
-            current = json.loads(FRONTEND_CONFIG_PATH.read_text(encoding="utf-8"))
+        config_path = _get_frontend_config_path()
+        if config_path and config_path.exists():
+            current = json.loads(config_path.read_text(encoding="utf-8"))
 
         # Fusion profonde des configs
         def deep_merge(base: dict, update: dict) -> dict:
@@ -60,19 +93,87 @@ def update_frontend_config(payload: dict = Body(...)) -> dict:
             return result
 
         updated = deep_merge(current, payload)
-        FRONTEND_CONFIG_PATH.write_text(
-            json.dumps(updated, indent=2, ensure_ascii=False),
-            encoding="utf-8"
-        )
+        target_paths = []
+        if FRONTEND_CONFIG_PATH.parent.exists():
+            target_paths.append(FRONTEND_CONFIG_PATH)
+        if FRONTEND_CONFIG_FALLBACK_PATH.parent.exists():
+            target_paths.append(FRONTEND_CONFIG_FALLBACK_PATH)
+        if not target_paths:
+            target_paths.append(FRONTEND_CONFIG_FALLBACK_PATH)
 
-        # Mettre à jour aussi dans public/ pour le frontend dev
-        public_config = FRONTEND_CONFIG_PATH.parent / "public" / "config_frontend.json"
-        if public_config.parent.exists():
-            public_config.write_text(
+        for target in target_paths:
+            target.write_text(
                 json.dumps(updated, indent=2, ensure_ascii=False),
-                encoding="utf-8"
+                encoding="utf-8",
             )
 
         return updated
     except Exception as exc:
         raise HTTPException(status_code=400, detail=str(exc))
+
+
+# ==================== Database Backup ====================
+
+
+@router.get("/database/info")
+def database_info() -> dict:
+    """Retourne les informations sur la base de données."""
+    if not DEFAULT_DATABASE_PATH.exists():
+        raise HTTPException(status_code=404, detail="Base de données introuvable")
+
+    stat = DEFAULT_DATABASE_PATH.stat()
+    return {
+        "path": str(DEFAULT_DATABASE_PATH),
+        "filename": DEFAULT_DATABASE_PATH.name,
+        "size_bytes": stat.st_size,
+        "size_mb": round(stat.st_size / (1024 * 1024), 2),
+        "modified_at": datetime.fromtimestamp(stat.st_mtime).isoformat(),
+    }
+
+
+@router.get("/database/backup")
+def download_database():
+    """Télécharge une copie de la base de données."""
+    if not DEFAULT_DATABASE_PATH.exists():
+        raise HTTPException(status_code=404, detail="Base de données introuvable")
+
+    # Créer une copie temporaire pour éviter les problèmes de lock
+    backup_path = DEFAULT_DATABASE_PATH.parent / f"backup_{datetime.now().strftime('%Y%m%d_%H%M%S')}.db"
+    shutil.copy2(DEFAULT_DATABASE_PATH, backup_path)
+
+    return FileResponse(
+        path=backup_path,
+        filename=f"suivi_produit_backup_{datetime.now().strftime('%Y%m%d_%H%M%S')}.db",
+        media_type="application/x-sqlite3",
+        background=None,  # Nettoyer après envoi
+    )
+
+
+@router.post("/database/restore")
+async def restore_database(file: UploadFile = File(...)) -> dict:
+    """Restaure la base de données depuis un fichier uploadé."""
+    if not file.filename.endswith(".db"):
+        raise HTTPException(status_code=400, detail="Le fichier doit être un .db")
+
+    # Vérifier la taille (max 100MB)
+    content = await file.read()
+    if len(content) > 100 * 1024 * 1024:
+        raise HTTPException(status_code=400, detail="Fichier trop volumineux (max 100MB)")
+
+    # Créer un backup avant restauration
+    if DEFAULT_DATABASE_PATH.exists():
+        backup_before = DEFAULT_DATABASE_PATH.parent / f"before_restore_{datetime.now().strftime('%Y%m%d_%H%M%S')}.db"
+        shutil.copy2(DEFAULT_DATABASE_PATH, backup_before)
+
+    try:
+        # Écrire le nouveau fichier
+        with open(DEFAULT_DATABASE_PATH, "wb") as f:
+            f.write(content)
+
+        return {
+            "success": True,
+            "message": "Base de données restaurée avec succès",
+            "size_bytes": len(content),
+        }
+    except Exception as exc:
+        raise HTTPException(status_code=500, detail=f"Erreur lors de la restauration: {exc}")

backend/app/api/routes_products.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from fastapi import APIRouter, Depends, HTTPException, status
+from fastapi import APIRouter, Depends, HTTPException, Response, status
 from sqlalchemy.orm import Session
 
 from backend.app.api.deps import get_db
@@ -46,22 +46,25 @@ def update_product(product_id: int, payload: schemas.ProductUpdate, db: Session
     return crud.update_product(db, product, payload)
 
 
-@router.delete("/{product_id}", status_code=status.HTTP_204_NO_CONTENT)
-def delete_product(product_id: int, db: Session = Depends(get_db)) -> None:
+@router.delete("/{product_id}", status_code=status.HTTP_204_NO_CONTENT, response_model=None)
+def delete_product(product_id: int, db: Session = Depends(get_db)) -> Response:
     product = crud.get_product(db, product_id)
     if not product:
         raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Produit introuvable")
     # suppression définitive en base
     crud.remove_product(db, product)
+    return Response(status_code=status.HTTP_204_NO_CONTENT)
 
 
 @router.get("/{product_id}/snapshots", response_model=list[schemas.ProductSnapshotRead])
 def list_snapshots(
     product_id: int,
-    limit: int = 30,
+    days: int | None = None,
+    limit: int = 1000,
     db: Session = Depends(get_db),
 ) -> list[schemas.ProductSnapshotRead]:
+    """Retourne les snapshots d'un produit, filtrés par nombre de jours."""
     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)
+    return crud.list_snapshots(db, product_id, days=days, limit=limit)

backend/app/api/routes_scrape.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 from fastapi import APIRouter, BackgroundTasks, HTTPException
 from pydantic import BaseModel, HttpUrl
 
+from backend.app.core.scheduler import get_scheduler_status, trigger_next_run
 from backend.app.scraper.runner import scrape_all, scrape_preview, scrape_product
 
 router = APIRouter(prefix="/scrape", tags=["scrape"])
@@ -35,3 +36,15 @@ def trigger_single(product_id: int, background_tasks: BackgroundTasks):
 def trigger_all(background_tasks: BackgroundTasks):
     background_tasks.add_task(scrape_all)
     return {"statut": "planifie_tout"}
+
+
+@router.get("/scheduler/status")
+def scheduler_status():
+    """Retourne l'état actuel du scheduler de scraping automatique."""
+    return get_scheduler_status()
+
+
+@router.post("/scheduler/trigger")
+def scheduler_trigger():
+    """Force le prochain scrape planifié à s'exécuter maintenant."""
+    return trigger_next_run()

backend/app/api/routes_stats.py

@@ -0,0 +1,66 @@
+"""Endpoint pour les statistiques système."""
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+import psutil
+from fastapi import APIRouter
+from pydantic import BaseModel
+
+router = APIRouter(prefix="/stats", tags=["stats"])
+
+
+class SystemStats(BaseModel):
+    """Statistiques système."""
+
+    cpu_percent: float
+    memory_mb: float
+    memory_percent: float
+    data_size_mb: float
+
+
+def get_directory_size(path: Path) -> int:
+    """Calcule la taille totale d'un répertoire en bytes."""
+    total = 0
+    if path.exists() and path.is_dir():
+        for entry in path.rglob("*"):
+            if entry.is_file():
+                try:
+                    total += entry.stat().st_size
+                except (OSError, PermissionError):
+                    pass
+    return total
+
+
+@router.get("", response_model=SystemStats)
+def get_stats() -> SystemStats:
+    """Retourne les statistiques système du backend."""
+    # CPU et mémoire du process courant
+    process = psutil.Process(os.getpid())
+    cpu_percent = process.cpu_percent(interval=0.1)
+    memory_info = process.memory_info()
+    memory_mb = memory_info.rss / (1024 * 1024)
+
+    # Mémoire système totale pour calculer le pourcentage
+    total_memory = psutil.virtual_memory().total
+    memory_percent = (memory_info.rss / total_memory) * 100
+
+    # Taille des dossiers data et logs
+    base_path = Path("/app/backend")
+    if not base_path.exists():
+        # Fallback pour le développement local
+        base_path = Path(__file__).parent.parent.parent
+
+    data_path = base_path / "data"
+    logs_path = base_path / "logs"
+
+    data_size = get_directory_size(data_path) + get_directory_size(logs_path)
+    data_size_mb = data_size / (1024 * 1024)
+
+    return SystemStats(
+        cpu_percent=round(cpu_percent, 1),
+        memory_mb=round(memory_mb, 1),
+        memory_percent=round(memory_percent, 1),
+        data_size_mb=round(data_size_mb, 1),
+    )

backend/app/core/config.py

@@ -44,4 +44,4 @@ class BackendConfig(BaseModel):
 @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)
+    return BackendConfig.model_validate_json(CONFIG_PATH.read_text(encoding="utf-8"))

backend/app/core/scheduler.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from datetime import datetime, timedelta
+
 from apscheduler.schedulers.background import BackgroundScheduler
 from apscheduler.triggers.interval import IntervalTrigger
 from loguru import logger
@@ -17,12 +19,49 @@ def start_scheduler() -> None:
 
     config = load_config()
     interval = config.scrape.interval_minutes
+    # Premier run après l'intervalle défini (pas immédiatement au démarrage)
+    first_run = datetime.now() + timedelta(minutes=interval)
     scheduler.add_job(
         scrape_all,
         trigger=IntervalTrigger(minutes=interval),
         id="scheduled-scrape-all",
         replace_existing=True,
-        next_run_time=None,
+        next_run_time=first_run,
     )
     scheduler.start()
-    logger.info("Scheduler démarré avec un intervalle de %s minutes", interval)
+    logger.info("Scheduler démarré avec un intervalle de {} minutes (prochain run: {})", interval, first_run.strftime("%H:%M:%S"))
+
+
+def get_scheduler_status() -> dict:
+    """Retourne l'état actuel du scheduler."""
+    job = scheduler.get_job("scheduled-scrape-all")
+    config = load_config()
+
+    status = {
+        "running": scheduler.running,
+        "interval_minutes": config.scrape.interval_minutes,
+        "job_exists": job is not None,
+        "next_run_time": None,
+        "next_run_in_minutes": None,
+    }
+
+    if job and job.next_run_time:
+        status["next_run_time"] = job.next_run_time.isoformat()
+        # Calculer le temps restant
+        now = datetime.now(job.next_run_time.tzinfo)
+        delta = job.next_run_time - now
+        status["next_run_in_minutes"] = round(delta.total_seconds() / 60, 1)
+
+    return status
+
+
+def trigger_next_run() -> dict:
+    """Force le prochain scrape à s'exécuter maintenant."""
+    job = scheduler.get_job("scheduled-scrape-all")
+    if not job:
+        return {"success": False, "error": "Job non trouvé"}
+
+    # Modifier le job pour s'exécuter maintenant
+    scheduler.modify_job("scheduled-scrape-all", next_run_time=datetime.now())
+    logger.info("Prochain scrape programmé pour maintenant")
+    return {"success": True, "message": "Scrape programmé pour exécution immédiate"}

backend/app/db/crud.py

@@ -63,6 +63,7 @@ def create_product_with_snapshot(
         "description",
         "carateristique",
         "details",
+        "categorie_amazon",
     ]
     snapshot_data = {k: data_dict.pop(k) for k in snapshot_fields if k in data_dict}
 
@@ -118,15 +119,23 @@ def remove_product(db: Session, product: models.Product) -> None:
     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 list_snapshots(
+    db: Session, product_id: int, days: int | None = None, limit: int = 1000
+) -> list[models.ProductSnapshot]:
+    """Retourne les snapshots d'un produit, filtrés par nombre de jours si spécifié."""
+    from datetime import datetime, timedelta
+
+    query = db.query(models.ProductSnapshot).filter(
+        models.ProductSnapshot.produit_id == product_id
     )
 
+    # Filtrer par date si days est spécifié
+    if days is not None and days > 0:
+        cutoff_date = datetime.utcnow() - timedelta(days=days)
+        query = query.filter(models.ProductSnapshot.scrape_le >= cutoff_date)
+
+    return query.order_by(models.ProductSnapshot.scrape_le.desc()).limit(limit).all()
+
 
 def get_latest_snapshot(db: Session, product_id: int) -> models.ProductSnapshot | None:
     return (
@@ -215,6 +224,7 @@ def _enrich_product_with_snapshot(db: Session, product: models.Product) -> dict:
                 "description": snapshot.description,
                 "carateristique": carateristique,
                 "details": details,
+                "categorie_amazon": snapshot.categorie_amazon,
                 "dernier_scrape": snapshot.scrape_le,
                 "statut_scrap": snapshot.statut_scrap,
             }

backend/app/db/models.py

@@ -24,7 +24,7 @@ class Product(Base):
     cree_le = Column(DateTime, default=datetime.utcnow)
     modifie_le = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
 
-    snapshots = relationship("ProductSnapshot", back_populates="product")
+    snapshots = relationship("ProductSnapshot", back_populates="product", cascade="all, delete-orphan")
 
 
 class ScrapeRun(Base):
@@ -67,6 +67,7 @@ class ProductSnapshot(Base):
     description = Column(Text, nullable=True)
     carateristique = Column(Text, nullable=True)  # JSON object
     details = Column(Text, nullable=True)  # JSON object
+    categorie_amazon = Column(Text, nullable=True)  # Catégorie depuis breadcrumb Amazon
     chemin_json_brut = Column(Text, nullable=True)
     statut_scrap = Column(String(32), default="ok")
     message_erreur = Column(Text, nullable=True)

backend/app/db/schemas.py

@@ -1,9 +1,10 @@
 from __future__ import annotations
 
+import json
 from datetime import datetime
 from typing import Any, Optional
 
-from pydantic import BaseModel, HttpUrl
+from pydantic import BaseModel, ConfigDict, HttpUrl, field_validator
 
 
 class ProductBase(BaseModel):
@@ -30,13 +31,12 @@ class ProductUpdate(BaseModel):
 
 
 class ProductRead(ProductBase):
+    model_config = ConfigDict(from_attributes=True)
+
     id: int
     cree_le: datetime
     modifie_le: datetime
 
-    class Config:
-        orm_mode = True
-
 
 class ProductSnapshotBase(BaseModel):
     prix_actuel: Optional[float]
@@ -55,22 +55,48 @@ class ProductSnapshotBase(BaseModel):
     description: Optional[str] = None
     carateristique: Optional[dict[str, Any]] = None
     details: Optional[dict[str, Any]] = None
+    categorie_amazon: Optional[str] = None
     statut_scrap: Optional[str]
     message_erreur: Optional[str]
 
 
 class ProductSnapshotRead(ProductSnapshotBase):
+    model_config = ConfigDict(from_attributes=True)
+
     id: int
     produit_id: int
     scrape_le: datetime
 
-    class Config:
-        orm_mode = True
+    @field_validator("a_propos", mode="before")
+    @classmethod
+    def parse_a_propos(cls, v: Any) -> list[str] | None:
+        if v is None:
+            return None
+        if isinstance(v, str):
+            try:
+                return json.loads(v)
+            except json.JSONDecodeError:
+                return None
+        return v
+
+    @field_validator("carateristique", "details", mode="before")
+    @classmethod
+    def parse_json_dict(cls, v: Any) -> dict[str, Any] | None:
+        if v is None:
+            return None
+        if isinstance(v, str):
+            try:
+                return json.loads(v)
+            except json.JSONDecodeError:
+                return None
+        return v
 
 
 class ProductWithSnapshot(ProductBase):
     """Produit enrichi avec les données du dernier snapshot."""
 
+    model_config = ConfigDict(from_attributes=True)
+
     id: int
     cree_le: datetime
     modifie_le: datetime
@@ -92,12 +118,10 @@ class ProductWithSnapshot(ProductBase):
     description: Optional[str] = None
     carateristique: Optional[dict[str, Any]] = None
     details: Optional[dict[str, Any]] = None
+    categorie_amazon: Optional[str] = None
     dernier_scrape: Optional[datetime] = None
     statut_scrap: Optional[str] = None
 
-    class Config:
-        orm_mode = True
-
 
 class ProductCreateWithSnapshot(ProductBase):
     """Création d'un produit avec données de snapshot initiales (depuis preview)."""
@@ -119,3 +143,4 @@ class ProductCreateWithSnapshot(ProductBase):
     description: Optional[str] = None
     carateristique: Optional[dict[str, Any]] = None
     details: Optional[dict[str, Any]] = None
+    categorie_amazon: Optional[str] = None

backend/app/main.py

@@ -6,7 +6,7 @@ from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from dotenv import load_dotenv
 
-from backend.app.api import routes_config, routes_debug, routes_products, routes_scrape
+from backend.app.api import routes_config, routes_debug, routes_products, routes_scrape, routes_stats
 from backend.app.core.logging import logger
 from backend.app.core.scheduler import start_scheduler
 from backend.app.db.database import Base, engine
@@ -15,19 +15,26 @@ load_dotenv()
 
 app = FastAPI(title="suivi_produit")
 
+app_env = getenv("APP_ENV", "development")
+
 # CORS pour le frontend
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["http://localhost:5173", "http://127.0.0.1:5173"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
+cors_kwargs = {
+    "allow_credentials": True,
+    "allow_methods": ["*"],
+    "allow_headers": ["*"],
+}
+if app_env == "development":
+    cors_kwargs["allow_origin_regex"] = r"https?://(localhost|127\\.0\\.0\\.1|10\\.0\\.1\\.109)(:\\d+)?"
+else:
+    cors_kwargs["allow_origins"] = ["http://localhost:5173", "http://127.0.0.1:5173"]
+
+app.add_middleware(CORSMiddleware, **cors_kwargs)
 
 app.include_router(routes_products.router)
 app.include_router(routes_scrape.router)
 app.include_router(routes_config.router)
 app.include_router(routes_debug.router)
+app.include_router(routes_stats.router)
 
 
 @app.on_event("startup")