pref09: utilise la classe générique de département

Attrap_pref09.py

-import os
-import datetime
+from Attrap_prefdpt import Attrap_prefdpt
 
-from bs4 import BeautifulSoup
-from urllib.parse import unquote
 
-from Attrap import Attrap
-
-
-class Attrap_pref09(Attrap):
+class Attrap_pref09(Attrap_prefdpt):
 
     # Config
     hostname = 'https://www.ariege.gouv.fr'
     raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-l-Ariege-a-partir-du-28-avril-2015'
-    user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
     full_name = 'Préfecture de l\'Ariège'
     short_code = 'pref09'
     timezone = 'Europe/Paris'
-
-    def __init__(self, data_dir):
-        super().__init__(data_dir, self.user_agent)
-        self.set_sleep_time(30)
-
-    def get_raa(self, keywords):
-        pages_to_parse = []
-
-        # Les RAA de l'Ariège sont éparpillés sur des sous-pages par mois.
-        # Donc on parse la page principale à la recherche des sous-pages.
-        sub_pages = self.get_sub_pages_with_pager(
-            self.raa_page,
-            'div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link',
-            'ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next',
-            'div.fr-card__body div.fr-card__content div.fr-card__end p.fr-card__detail',
-            self.hostname
-        )[::-1]
-
-        # On filtre par date les sous-pages pour limiter les requêtes
-        for sub_page in sub_pages:
-            guessed_date = datetime.datetime.strptime(sub_page['details'].replace('Publié le ', '').strip(), '%d/%m/%Y')
-            guessed_date.replace(day=1)
-            if guessed_date >= self.not_before:
-                pages_to_parse.append(sub_page['url'])
-
-        # On parse les pages contenant des RAA
-        elements = []
-        for page in pages_to_parse:
-            page_content = self.get_page(page, 'get').content
-            for element in self.get_raa_elements(page_content):
-                elements.append(element)
-
-        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')
-
-        # On récupère chaque balise a
-        for a in soup.select('div.fr-downloads-group.fr-downloads-group--bordered ul li a'):
-            if a.get('href') and a['href'].endswith('.pdf'):
-                if a['href'].startswith('/'):
-                    url = f"{self.hostname}{a['href']}"
-                else:
-                    url = a['href']
-
-                url = unquote(url)
-                name = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
-                date = datetime.datetime.strptime(a.find('span').get_text().split(' - ')[-1].strip(), '%d/%m/%Y')
-
-                raa = Attrap.RAA(url, date, name, timezone=self.timezone)
-                elements.append(raa)
-        return elements