InformationCollector/main.py

import csv, os, re, sys, argparse
from logger import *
from datetime import datetime
import pandas as pd


   
parse = argparse.ArgumentParser(
    description="Программа для сбора информации из csv файлов")
parse.add_argument('-p', '--path', help='Указать в какой директории искать',
                   default=os.path.dirname(sys.argv[0]))
parse.add_argument('-e', '--open_encoding',
                   help='Указать в какой кодировке открывать', default='utf-16')
args = parse.parse_args()

print(args)
LIST_BAD_ADAPTER = ['Wireless', 'Bluetooth', 'Wireless', 'WiFi',
                    'Kaspersky', 'VirtualBox', 'TAP-Windows',
                    'Wintun', '802.11', 'VMware', 'VPN', 'Wi-Fi',
                    '1394', 'Mobile']

# Количетсво интерфейсов по умолчанию
COUNT_INTERFACE = 1


def check_correct_controller(name) -> bool:
    return any(ext not in name for ext in LIST_BAD_ADAPTER)


class ObjectReady:
    def get_len_dict(self) -> int:
        return len(self.__dict__)

    def get_row(self) -> str:
        return self.__dict__


def get_paths() -> list:
    list_path = []
    for root, _, files in os.walk(args.path):
        list_path += [
            F"{root}/{file}" for file in files if file.split('.')[-1] == 'csv' and "result" not in file]
    return list_path


def convert_mb_to_gb(val: str) -> str:
    numbers = int(''.join([x for x in val if x.isdigit()]))
    return str(round(numbers/1024, 1))+' GB'


def get_ser_motherboard(row: list) -> str:
    try:
        return row if row not in ['To be filled by O.E.M.', 'Default string'] else None
    except IndexError:
        pass


def get_data_from_file(path: str, obj: ObjectReady) -> None:
    global COUNT_INTERFACE
    
    with open(path, 'r', encoding=args.open_encoding) as file:
        
        cs = csv.reader(file, delimiter=',')

        next(cs)
        line_info_computers = next(cs)
        obj.os = line_info_computers[7]
        obj.cpu = line_info_computers[13]
        obj.ram = convert_mb_to_gb(line_info_computers[14])
        obj.motherboard = None
        obj.count_interface = 0
        count_interface = 0
        
        for line in cs:
            data = list(pd.Series(line))
            if data[0] == '6200':
                obj.motherboard = get_ser_motherboard(data[6])

            if data[0] == '2600' and len(data) > 2 and check_correct_controller(data[3]):
                setattr(obj, F'ip{count_interface+1}', data[6].split(' ')[0])
                setattr(obj, F'mac{count_interface+1}', data[-3])
                count_interface += 1

        # Увеличиваем значение если количестов интерфейсов больше в этой строке
        obj.count_interface = count_interface
        if count_interface > COUNT_INTERFACE:
            COUNT_INTERFACE = count_interface

        file.close()


def get_ready_information() -> list[ObjectReady]:
    list_objects = []
    for path in get_paths():
        
        obj = ObjectReady()
        obj.frame = os.path.basename(os.path.dirname(path))
        obj.cabinet = re.findall(
            r"\/([\w+?\ ?[а-яА-Я]+\ ?|\w+?\ ?[a-zA-Z]+\ ?|\d+])[\.|\,]", path)[-1]

        try:
            get_data_from_file(path, obj)
        except UnicodeDecodeError as ude:
            logger.error(F"{path} --> {ude}\n")
        except UnicodeError as er:
            logger.error(F"{path} --> {er}\n")
        except StopIteration as si:
            logger.error(F"{path} --> Пустой файл или тмпо того\n")

        list_objects.append(obj)
    return list_objects


def create_csv(list_obj: list[ObjectReady]) -> None:
    namefile = F"result-{datetime.today().strftime('%Y-%m-%d-%H.%M.%S')}.xlsx"
    data = [row.get_row() for row in list_obj]
    df = pd.DataFrame(data=data)
    df.to_excel(namefile, index= False)
    
if __name__ == '__main__':
    create_logger()
    
    logger.info("Start programm")
    logger.info(F"Base dir: {args.path}")
    
    create_csv(get_ready_information())
    logger.info("Stop programm")