Attrap_pref06.py

import os
import datetime

from bs4 import BeautifulSoup
from urllib.parse import unquote

from Attrap import Attrap


class Attrap_pref06(Attrap):

    # Config
    __HOST = 'https://www.alpes-maritimes.gouv.fr'
    __RAA_PAGE = f'{__HOST}/Publications/Recueil-des-actes-administratifs-RAA'
    __USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; 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.set_sleep_time(30)

    def get_raa(self, keywords):
        # On détermine quelles pages d'année parser
        year_pages_to_parse = []
        page_content = self.get_page(self.__RAA_PAGE, 'get').content
        year_pages = self.get_sub_pages(
            page_content,
            '.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link div.fr-card__body div.fr-card__content h2.fr-card__title a',
            self.__HOST,
            False
        )
        for year_page in year_pages:
            if int(year_page['name'].replace('Année ', '').strip()) >= self.not_before.year:
                year_pages_to_parse.append(year_page['url'])

        # Pour chaque année, on récupère les pages de chaque catégorie (RAA mensuels, spéciaux ou spécifiques)
        pages_to_parse = []
        for year_page in year_pages_to_parse:
            page_content = self.get_page(year_page, 'get').content
            pages = self.get_sub_pages(
                page_content,
                '.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link div.fr-card__body div.fr-card__content h2.fr-card__title a',
                self.__HOST,
                False
            )
            for page in pages:
                pages_to_parse.append(page['url'])

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

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