Python-Code

import json
from datetime import datetime
from pathlib import Path
import re
from typing import Literal
from typing import Union

import requests
from bs4 import BeautifulSoup
from strongtyping.strong_typing import match_typing

from playarounds.decorator import validate_docstr

ALLOWED_STATES = Literal[
    'Bayern',
    'Niedersachsen',
    'Baden-Württemberg',
    'Nordrhein-Westfalen',
    'Brandenburg',
    'Mecklenburg-Vorpommern',
    'Hessen',
    'Sachsen-Anhalt',
    'Rheinland-Pfalz',
    'Sachsen',
    'Thüringen',
    'Schleswig-Holstein',
    'Saarland',
    'Berlin',
    'Hamburg',
    'Bremen',
    ''
]

@match_typing
def get_holidays(*, year: int, state: ALLOWED_STATES = 'Alle', optional: str = None) -> None:
    data_file = Path('data.json')
    if not data_file.exists():
        raise RuntimeWarning('Please create at first the "data.json"')

    json_data = get_data(data_file)
    dates = [date for date in json_data.keys() if str(year) in date]

    if not dates:
        print('No data available')

    for date in dates:
        data = json_data[date]
        if optional is not None:
            if optional in data.get('optional', ''):
                print(f'{date}: {data["name"]}')
        else:
            state_info = [state.replace(',', '').strip() for state in data['states'].split()]
            if state in state_info or 'Alle' in state_info:
                print(f'{date}: {data["name"]}')


if __name__ == '__main__':
    get_holidays(year=2021, state='Berlin')
    """
    01.01.2021: Neujahr in Deutschland
    08.03.2021: Internationaler Frauentag
    02.04.2021: Karfreitag in Deutschland(Ostern in Deutschland)
    05.04.2021: Ostermontag in Deutschland(Ostern in Deutschland)
    01.05.2021: Tag der Arbeit in Deutschland
    13.05.2021: Christi Himmelfahrt in Deutschland
    24.05.2021: Pfingstmontag in Deutschland(Pfingsten in Deutschland)
    03.10.2021: Tag der Deutschen Einheit
    25.12.2021: 1. Weihnachtstag in Deutschland(Weihnachten in Deutschland)
    26.12.2021: 2. Weihnachtstag in Deutschland(Weihnachten in Deutschland)
    """

    get_holidays(year=2021, state='Bayern')
    """
    01.01.2021: Neujahr in Deutschland
    06.01.2021: Heilige Drei Könige
    02.04.2021: Karfreitag in Deutschland(Ostern in Deutschland)
    05.04.2021: Ostermontag in Deutschland(Ostern in Deutschland)
    01.05.2021: Tag der Arbeit in Deutschland
    13.05.2021: Christi Himmelfahrt in Deutschland
    24.05.2021: Pfingstmontag in Deutschland(Pfingsten in Deutschland)
    03.06.2021: Fronleichnam in Deutschland
    08.08.2021: Augsburger Friedensfest 
    15.08.2021: Mariä Himmelfahrt in Deutschland 
    03.10.2021: Tag der Deutschen Einheit
    01.11.2021: Allerheiligen in Deutschland
    25.12.2021: 1. Weihnachtstag in Deutschland(Weihnachten in Deutschland)
    26.12.2021: 2. Weihnachtstag in Deutschland(Weihnachten in Deutschland)
    """

    get_holidays(year=2021, optional='Rosenmontag')
    """
    15.02.2021: Rosenmontag
    """

    get_holidays(year=2021, state='Bayern', optional='Beamte')
    """
    24.12.2021: Heilig Abend
    31.12.2021: Silvester
    """

Python-Code

@match_typing
@validate_docstr
def get_feiertage_html(year: int = 2021) -> None:
    """
    :validate year: lambda x: 2014 <= x <= 2023
    :return:
    """
    resp = requests.get(f'https://www.ferienwiki.de/feiertage/{year}/de')
    html_file = Path('templates', f'feiertage_{year}.html')

    with html_file.open('w') as file:
        file.write(resp.content.decode('utf8'))


@match_typing
def get_data(data_file: Path) -> dict:
    if data_file.exists():
        with data_file.open('r') as file:
            data_set = json.load(file)
    else:
        data_set = {}
    return data_set


@match_typing
def write_data(data: dict):
    with Path('data.json').open('w') as file:
        json.dump(data, file)


@match_typing
def add_holiday(date: str, name: str, states: ALLOWED_STATES, optional_info: str = None):
    datetime.strptime(date, '%d.%m.%Y')  # to validate the date format, raises an error if wrong format
    data_file = Path('data.json')
    data = get_data(data_file)
    data[date] = {'name': name,
                  'states': states}
    if optional_info is not None:
        data['date']['optional'] = optional_info


@match_typing
def extract_and_save_data(filename: Union[str, Path]) -> None:
    td_tag = r'(<(\/)?td>)'
    data_file = Path('data.json')
    data = get_data(data_file)
    with Path(filename).open('r') as file:
        soup = BeautifulSoup(file.read(), 'html.parser')
        elements = soup.find_all('td')
        step = 4
        while step <= len(elements):
            date = ''
            name = ''
            state = ''
            for index, elem in enumerate(elements[step: step + 4]):
                elem = re.sub(td_tag, '', str(elem))
                sub_elem = BeautifulSoup(elem, 'html.parser', multi_valued_attributes=None).text
                if index == 0:
                    name = sub_elem
                elif index == 1:
                    date = sub_elem.split()[0]
                elif index == 2:
                    state = sub_elem
                else:
                    continue
            data[date] = {'name': name,
                          'states': state}
            step += 4
    write_data(data)


def extract_all_data() -> None:
    [extract_and_save_data(file) for file in Path('templates').glob('*.html')]