from time import sleep
import requests
from bs4 import BeautifulSoup
from openpyxl import Workbook


def get_name(row):
    url = ''.join(map(lambda i: i.get('href'), row.find_all('a')))
    r = requests.get(url)
    soup = BeautifulSoup(r.text, 'html.parser')
    try:
        name = soup.find('div', string='Наименование').find_next('div').text.strip()
    except AttributeError:
        name = ''
        print(f'no name {r.url}')
    return name


# 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').find('tbody')

    rows = table.findAll('tr')

    for row in rows:
        name = get_name(row)
        cells = row.findAll('td')
        data = []
        for cell in cells:
            data.append(cell.text.strip())
        data.append(name)
        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 <= 2:
        next_button = soup.find('a', string='Вперед →')
        if next_button:
            next_page_url = next_button['href']
            next_response = session.get(next_page_url)

            sleep(0.6)
            try:
                parse_page(next_response, ws)
            except Exception as e:
                print(f'{next_response.url} - {next_response.status_code}\n{e}')
                continue
            soup = BeautifulSoup(next_response.content, 'html.parser')

            ccc += 1
            print(ccc)
        else:
            break

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


if __name__ == '__main__':
    main()