Sincronización incremental desde SMB con smbprotocol en Linux: autenticación NTLM y control de logs

pip install smbprotocol sqlalchemy pydantic python-dotenv

import logging

# Silenciar smbprotocol
logging.getLogger('smbprotocol').setLevel(logging.WARNING)
logging.getLogger('smbprotocol.connection').setLevel(logging.WARNING)
logging.getLogger('smbprotocol.session').setLevel(logging.WARNING)

# Tu logger
logger = logging.getLogger('sync_smb')
logger.setLevel(logging.INFO)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
logger.addHandler(handler)

from datetime import datetime
from sqlalchemy import create_engine, Column, String, DateTime, Integer
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker

Base = declarative_base()

class SyncedFile(Base):
    __tablename__ = 'synced_files'
    
    filename = Column(String, primary_key=True)
    md5_hash = Column(String)
    file_size = Column(Integer)
    last_modified = Column(DateTime)
    sync_timestamp = Column(DateTime, default=datetime.utcnow)

engine = create_engine('sqlite:///smb_sync.db')
Base.metadata.create_all(engine)
Session = sessionmaker(bind=engine)

from smbprotocol.session import Session
from smbprotocol.tree import TreeConnect
import socket

username = "DOMINIO\\usuario"  # Formato NETBIOS\usuario
password = "contraseña"
host = "192.168.x.x"
share = "compartido"

# Conexión básica
connection = smbprotocol.connection.Connection(
    uuid.uuid4(),
    host,
    445,
)
connection.connect()

session = Session(connection, username, password)
session.connect()

tree = TreeConnect(session, f"\\\\{host}\\{share}")
tree.connect()

import hashlib
from pathlib import Path

def get_file_hash(file_data):
    """Calcula MD5 de contenido en bytes"""
    return hashlib.md5(file_data).hexdigest()

def sync_smb_share(local_path: Path):
    session = Session()
    remote_files = {}
    
    # Listar archivos del share
    directory = tree.open_file(share, FileAttributes.DIRECTORY, CreateOptions.FILE_DIRECTORY_FILE)
    
    for file_info in directory.query_directory():
        if file_info.file_attributes & FileAttributes.DIRECTORY:
            continue  # Ignorar carpetas por ahora
        
        filename = file_info.file_name
        remote_files[filename] = {
            'size': file_info.end_of_file,
            'modified': file_info.change_time.timestamp()
        }
    
    # Leer archivos nuevos o modificados
    local_db = session.query(SyncedFile).all()
    local_files = {f.filename: f for f in local_db}
    
    for filename, info in remote_files.items():
        # Nuevo o modificado
        if filename not in local_files or local_files[filename].file_size != info['size']:
            logger.info(f"Descargando: {filename}")
            
            file_obj = tree.open_file(filename)
            content = b""
            for chunk in file_obj:
                content += chunk
            
            md5 = get_file_hash(content)
            (local_path / filename).write_bytes(content)
            
            # Actualizar BD
            sync_record = local_files.get(filename) or SyncedFile()
            sync_record.filename = filename
            sync_record.md5_hash = md5
            sync_record.file_size = info['size']
            sync_record.last_modified = datetime.fromtimestamp(info['modified'])
            
            session.merge(sync_record)
            session.commit()
    
    # Detectar eliminados
    for filename in local_files:
        if filename not in remote_files:
            logger.warning(f"Archivo eliminado en remoto: {filename}")
            (local_path / filename).unlink(missing_ok=True)
            session.query(SyncedFile).filter_by(filename=filename).delete()
            session.commit()
    
    tree.close()
    session.close()

if __name__ == "__main__":
    sync_smb_share(Path("/mnt/sync"))

0 */4 * * * /usr/bin/python3 /opt/sync_smb/sync.py >> /var/log/smb_sync.log 2>&1