RAAspotter_pref06.py

import os
import datetime

from bs4 import BeautifulSoup
from urllib.parse import unquote

from RAAspotter import RAAspotter


class RAAspotter_pref06(RAAspotter):

    # Config
    __HOST = 'https://www.alpes-maritimes.gouv.fr'
    __RAA_PAGE = {
        '2024': [
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2024/Recueils-mensuels',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2024/Recueils-speciaux',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2024/Recueils-specifiques'
        ],
        '2023': [
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2023/Recueils-mensuels',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2023/Recueils-speciaux',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2023/Recueils-specifiques'
        ],
        '2022': [
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2022/Recueils-mensuels',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2022/Recueils-speciaux',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2022/Recueils-specifiques'
        ],
        '2021': [
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2021/Recueils-mensuels',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2021/Recueils-speciaux',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2021/Recueils-specifiques'
        ],
        '2020': [
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2020/Recueils-mensuels',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2020/Recueils-speciaux',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2020/Recueils-specifiques'
        ],
        '2019': [
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2019/Recueils-mensuels',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2019/Recueils-speciaux',
            f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA/Annee-2019/Recueils-specifiques'
        ]
    }
    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
    full_name = 'Préfecture des Alpes-Maritimes'
    short_code = 'pref06'

    def __init__(self, data_dir):
        super().__init__(data_dir, self.__USER_AGENT)
        self.enable_tor(20)

    def get_raa(self, keywords):
        self.print_output('RAAspotter_pref06')
        self.print_output(f'Termes recherchés: {keywords}')
        self.print_output('')

        pages_to_parse = []
        if self.not_before.year <= 2024:
            for page in self.__RAA_PAGE['2024']:
                pages_to_parse.append(page)
        if self.not_before.year <= 2023:
            for page in self.__RAA_PAGE['2023']:
                pages_to_parse.append(page)
        if self.not_before.year <= 2022:
            for page in self.__RAA_PAGE['2022']:
                pages_to_parse.append(page)
        if self.not_before.year <= 2021:
            for page in self.__RAA_PAGE['2021']:
                pages_to_parse.append(page)
        if self.not_before.year <= 2020:
            for page in self.__RAA_PAGE['2020']:
                pages_to_parse.append(page)
        if self.not_before.year <= 2019:
            for page in self.__RAA_PAGE['2019']:
                pages_to_parse.append(page)

        elements = self.get_raa_with_pager(
            pages_to_parse,
            ".fr-pagination__link.fr-pagination__link--next",
            self.__HOST
        )
        self.parse_raa(elements, keywords.split(','))
        self.mailer()

    def get_raa_elements(self, page_content):
        elements = []
        # On charge le parser
        soup = BeautifulSoup(page_content, 'html.parser')

        # Pour chaque élément fr-card__content, on cherche sa balise a, et si
        # c'est un PDF on le parse
        cards = soup.find_all('div', class_='fr-card__content')
        for card in cards:
            a = card.find('a')
            if a['href'].endswith('.pdf'):
                if a['href'].startswith('/'):
                    url = f"{self.__HOST}{a['href']}"
                else:
                    url = a['href']

                url = unquote(url)
                name = a.get_text().strip()
                date = datetime.datetime.strptime(card.find('p', class_='fr-card__detail').get_text().replace('Publié le ', '').strip(), '%d/%m/%Y')
                filename = url.split('/')[-1]

                raa = RAAspotter.RAA(url, date, name, filename)
                elements.append(raa)
        return elements