pref05: utilise la classe générique de département

Attrap_pref05.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_pref05(Attrap):
+class Attrap_pref05(Attrap_prefdpt):
 
     # Config
     hostname = 'https://www.hautes-alpes.gouv.fr'
     raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
-    user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
     full_name = 'Préfecture des Hautes-Alpes'
     short_code = 'pref05'
     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):
-        year_pages_to_parse = []
-
-        # On détermine quelles pages d'année parser
-        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.hostname,
-            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'])
-
-        month_pages_to_parse = []
-        # Pour chaque année, on cherche les sous-pages de mois
-        for year_page in year_pages_to_parse:
-            page_content = self.get_page(year_page, 'get').content
-            month_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.hostname,
-                False
-            )[::-1]
-            for month_page in month_pages:
-                # On filtre les mois ne correspondant pas à la période analysée
-                guessed_date = Attrap.guess_date(month_page['name'], '(.*)')
-                if guessed_date.replace(day=1) >= self.not_before.replace(day=1):
-                    month_pages_to_parse.append(month_page['url'])
-
-        pages_to_parse = []
-        # Pour chaque page de mois, on cherche les pages de RAA
-        for month_page in month_pages_to_parse:
-            pages = self.get_sub_pages_with_pager(
-                month_page,
-                'div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link',
-                'nav.fr-pagination ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next.fr-pagination__link--lg-label',
-                'div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w div.fr-card__body div.fr-card__content div.fr-card__end p.fr-card__detail',
-                self.hostname
-            )[::-1]
-            for page in pages:
-                guessed_date = datetime.datetime.strptime(page['details'].replace('Publié le ', '').strip(), '%d/%m/%Y')
-                if guessed_date.replace(day=1) >= self.not_before.replace(day=1):
-                    pages_to_parse.append(page['url'])
-
-        elements = []
-        # On parse les pages contenant des RAA
-        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)
-
-        # On parse les RAA
-        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-grid-row 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
+    Attrap_prefdpt.grey_card['year'] = 'Année *([0-9]{4})'
+    Attrap_prefdpt.grey_card['month'] = '([A-Za-zéû]* *[0-9]{4})'