import logging
import os

import openpyxl
import requests
from tqdm import tqdm


def get_data():
    logging.basicConfig(
        level=logging.INFO
    )
    if not os.path.exists('images'):
        os.mkdir('images')
    book = openpyxl.Workbook()
    for sheet in book.worksheets:
        sheet.append(['Название', 'Описание', 'Идентификатор', 'Учредитель', 'Сокращенное название',
                      'Тип собственности', 'КОПУК', 'Тип по профилю', 'ОГРН', 'ИНН', 'Юр. адрес',
                      'Фактическое нахождение', 'Телефон', 'Email', 'Сайт', 'Руководитель', 'ОКПО',
                      'Путь до фотографий'])
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:103.0) Gecko/20100101 Firefox/103.0',
        'Accept': 'application/json, text/plain, */*',
        'Accept-Language': 'ru-RU,ru;q=0.8,en-US;q=0.5,en;q=0.3',
        'Connection': 'keep-alive',
        'Referer': 'https://goskatalog.ru/portal/',
        'Sec-Fetch-Dest': 'empty',
        'Sec-Fetch-Mode': 'cors',
        'Sec-Fetch-Site': 'same-origin',
    }
    params = {
        'cacheEnabled': 'true',
        'limit': '20000',
        'offset': '0',
        'publicationLimit': 'false',
    }
    r = requests.get('https://goskatalog.ru/muzfo-rest/rest/museums', params=params, headers=headers)
    data = r.json()
    museums = data.get('museums')
    for museum in tqdm(museums[:100]):
        try:
            inn = okpo = ogrn = address = mail = number = website = actual_address = headmaster = own_type = '-'
            i = 1
            id = museum.get('id')
            url = f'https://goskatalog.ru/muzfo-rest/rest/museums/{id}'
            r = requests.get(url, headers=headers)
            data = r.json()
            title = data.get('name')  # название
            abbreviation = data.get('abbreviation')  # сокращенное название
            annotation = data.get('annotation')  # описание
            if annotation == None:
                annotation = '-'
            else:
                annotation = annotation.replace('\n', '').replace('\r', '').replace('\t', '').strip()
            founder = data.get('founder')  # основатель
            kopuk = data.get('code')  # копук
            unic_identifier = data.get('fullUin')  # уникальный идентификатор
            # with open('data2.json', 'w', encoding='utf-8') as file:
            #     json.dump(data, file, indent=4, ensure_ascii=False)

            identifiers = data.get('identifiers')
            for identifier in identifiers:
                name = identifier.get('type')
                value = identifier.get('value')
                if name == 'INN':
                    inn = value  # инн
                elif name == 'OKPO':
                    okpo = value  # окпо
                elif name == 'OGRN':
                    ogrn = value  # огрн

            contacts = data.get('contacts')
            for contact in contacts:
                value = contact.get('contactValue')
                if '@' in value:
                    mail = value
                elif '+7' in value:
                    number = value
                elif 'http' in value:
                    website = value
                elif 'ул' in value or 'д' in value:
                    if address != '-':
                        if value != address:
                            actual_address = value
                            continue
                    address = value

            if actual_address == '-':
                actual_address = address

            images = data.get('images')

            file_title = title.replace('\\', '.') \
                             .replace('"', '').replace('|', '').replace('*', 'x').replace(':', '') \
                             .replace('?', '.').replace('<', '').replace('>', '').replace('/', '.') \
                             .replace('\n', '')[:200]
            for image in images:
                code = image.get('code')
                id = image.get('id')
                image_url = f'https://goskatalog.ru/muzfo-imaginator/rest/images/public/350/{code}/{id}.jpg'
                r = requests.get(image_url)
                with open(f'images/{file_title}_{i}.jpg', 'wb') as file:
                    file.write(r.content)
                i += 1

            profile_type = data.get('types')[0].get('name')  # тип по профилю

            employees = data.get('employees')
            for employee in employees:
                if employee.get('roleId') == 1:
                    headmaster = employee.get('name')  # руководитель

            ownershipid = data.get('ownershipId')
            if ownershipid == 3:
                own_type = 'Муниципальная'
            elif ownershipid == 2:
                own_type = 'Субъекта РФ'
            elif ownershipid == 1:
                own_type = 'Федеральная'

            if annotation != '-':
                logging.info(annotation + '\n')

            for sheet in book.worksheets:
                sheet.append([title, annotation, unic_identifier, founder, abbreviation,
                              own_type, kopuk, profile_type, ogrn, inn, address,
                              actual_address, number, mail, website, headmaster, okpo, f'images/{file_title}'])
        except Exception as e:
            print(e)
        finally:
            book.save('data.xlsx')


def main():
    get_data()


if __name__ == '__main__':
    main()