import time
from time import sleep

import requests
from bs4 import BeautifulSoup
from openpyxl import Workbook


# Функция для парсинга страницы и сохранения данных в Excel
def parse_page(next_response, ws):
    soup = BeautifulSoup(next_response.content, 'html.parser')
    table = soup.find('table')

    rows = table.findAll('tr')

    for row in rows:
        cells = row.findAll('td')
        data = []
        for cell in cells:
            data.append(cell.text.strip())
        ws.append(data)


def main():
    session = requests.Session()

    # Создаем объект Workbook для создания Excel файла
    wb = Workbook()
    # Активируем лист
    ws = wb.active

    url = 'https://www.rst.gov.ru/portal/gost/home/activity/compliance/evaluationcompliance/AcknowledgementCorrespondence/safetycertificate018?portal:componentId=ff119059-8bd4-47fc-95f6-a70de17a4b3e&portal:isSecure=false&portal:portletMode=view&navigationalstate=JBPNS_rO0ABXdgAAhwYWdlU2l6ZQAAAAEAAjIwAAdvcmRlckJ5AAAAAQAYZGF0ZW9maXNzdWVvZmNlcnRpZmljYXRlAARmcm9tAAAAAQABMAAFb3JkZXIAAAABAARERVNDAAdfX0VPRl9f'
    response = session.get(url)
    soup = BeautifulSoup(response.content, 'html.parser')
    parse_page(response, ws)

    ccc = 0
    # Парсинг остальных страниц с помощью кнопки "вперед"
    while ccc <= 10000:
        next_button = soup.find('a', string='Вперед →')
        if next_button:
            next_page_url = next_button['href']
            next_response = session.get(next_page_url)
            soup = BeautifulSoup(next_response.content, 'html.parser')
            if next_response.status_code != 200:
                print(f'\n{next_response.url} - {next_response.status_code}\n')
                time.sleep(1)
                continue

            sleep(0.6)
            parse_page(next_response, ws)
            ccc += 1
            print(ccc)
        else:
            break

    # Сохраняем Excel файл
    wb.save('output.xlsx')


if __name__ == '__main__':
    main()