Attrap_pref33.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref33(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.gironde.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs'
+    full_name = 'Préfecture de la Gironde'
+    short_code = 'pref33'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = 'Recueils{0,1} des [Aa]ctes [Aa]dministratifs de l\'année ([0-9]{4})'
+    Attrap_prefdpt.grey_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'
+    Attrap_prefdpt.grey_card['follow_link_on_unrecognised_date'] = False

Attrap_pref34.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref34(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.herault.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueils-des-actes-administratifs'
+    full_name = 'Préfecture de l\'Hérault'
+    short_code = 'pref34'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    year_regex = '(?:(?:Recueil des actes administratifs)|(?:Année))[ -]([0-9]{4})'
+    Attrap_prefdpt.white_card['regex']['year'] = year_regex
+    Attrap_prefdpt.grey_card['regex']['year'] = year_regex

Attrap_pref35.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref35(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.ille-et-vilaine.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
+    full_name = 'Préfecture d\'Ille-et-Vilaine'
+    short_code = 'pref35'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    year_regex = 'Recueil des actes administratifs ([0-9]{4})'
+    Attrap_prefdpt.white_card['regex']['year'] = year_regex
+
+    # On ajoute un widget de menu déroulant
+    Attrap_prefdpt.select_widgets.append(
+        Attrap_prefdpt.DptSelectWidget(
+            'menu_deroulant',
+            regex=year_regex,
+            css_path='div.fr-select-group select#Archives-des-RAA-liste-docs.fr-select',
+            type='year'
+        )
+    )

Attrap_pref38.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref38(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.isere.gouv.fr'
+    raa_page = f'{hostname}/Publications/RAA-Recueil-des-actes-administratifs'
+    full_name = 'Préfecture de l\'Isère'
+    short_code = 'pref38'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    year_regex = '(?:(?:[Rr]ecueils{0,1} des [Aa]ctes [Aa]dministratifs de la [Pp]réfecture de l\'Isère[ -]*)|(?:Année ))([0-9]{4})'
+    Attrap_prefdpt.grey_card['regex']['year'] = year_regex
+    Attrap_prefdpt.white_card['regex']['year'] = year_regex
+    Attrap_prefdpt.white_card['exclude'] = ['Vous recherchez "Le Journal officiel de la République française" ?']
+
+    # On ajoute un widget de menu déroulant
+    Attrap_prefdpt.select_widgets.append(
+        Attrap_prefdpt.DptSelectWidget(
+            'menu_deroulant',
+            regex='([0-9]{1,2}[er]{0,1} [a-zéû]* [0-9]{4})',
+            css_path='select#-liste-docs',
+            type='year-month-day'
+        )
+    )

Attrap_pref39.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref39(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = "https://www.jura.gouv.fr"
+    raa_page = f'{hostname}/Publications/Publications-legales/Recueil-des-Actes-Administratifs'
+    full_name = "Préfecture du Jura"
+    short_code = "pref39"
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = 'Année ([0-9]{4})'

Attrap_pref42.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref42(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.loire.gouv.fr'
+    raa_page = f'{hostname}/Publications/Publications-legales/Recueil-des-Actes-Administratifs'
+    full_name = 'Préfecture de la Loire'
+    short_code = 'pref42'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.white_card['regex']['year'] = '([0-9]{4})'

Attrap_pref44.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref44(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.loire-atlantique.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-RAA-en-Loire-Atlantique'
+    full_name = 'Préfecture de la Loire-Atlantique'
+    short_code = 'pref44'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'
+    Attrap_prefdpt.grey_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'
+    Attrap_prefdpt.grey_card['add_year_to_months'] = True

Attrap_pref49.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref49(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.maine-et-loire.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs'
+    full_name = 'Préfecture de Maine-et-Loire'
+    short_code = 'pref49'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = '.*([0-9]{4})'

Attrap_pref50.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref50(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.manche.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
+    full_name = 'Préfecture de la Manche'
+    short_code = 'pref50'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'

Attrap_pref52.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref52(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.haute-marne.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs-RAA'
+    full_name = 'Préfecture de la Haute-Marne'
+    short_code = 'pref52'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.white_card['regex']['year'] = 'Année ([0-9]{4})'

Attrap_pref54.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref54(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.meurthe-et-moselle.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
+    full_name = 'Préfecture de Meurthe-et-Moselle'
+    short_code = 'pref54'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.white_card['regex']['year'] = '([0-9]{4})'
+
+    # On ajoute un widget de menu déroulant
+    Attrap_prefdpt.select_widgets.append(
+        Attrap_prefdpt.DptSelectWidget(
+            'menu_deroulant',
+            regex='.* du ([0-9]*(?:er|ER)? [A-Za-zéÉûÛ]* [0-9]*)',
+            css_path='select#Liste-liste-docs',
+            type='year-month-day'
+        )
+    )

Attrap_pref55.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref55(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.meuse.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs-RAA'
+    full_name = 'Préfecture de la Meuse'
+    short_code = 'pref55'
+    timezone = 'Europe/Paris'
+
+    # On configure le widget de menu déroulant
+    Attrap_prefdpt.select_widgets.append(
+        Attrap_prefdpt.DptSelectWidget(
+            'menu_deroulant',
+            regex='RAA année ([0-9]{4})',
+            css_path='select#Liste-des-recueils-liste-docs',
+            type='year'
+        )
+    )

Attrap_pref59.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref59(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.nord.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueils-des-actes-administratifs/RAA-du-departement-du-Nord'
+    full_name = 'Préfecture du Nord'
+    short_code = 'pref59'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'
+    Attrap_prefdpt.grey_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'
+    Attrap_prefdpt.grey_card['add_year_to_months'] = True

Attrap_pref61.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref61(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.orne.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-Actes-Administratifs-RAA/Recueil-des-Actes-Administratifs-RAA'
+    full_name = 'Préfecture de l\'Orne'
+    short_code = 'pref61'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = 'Le Recueil des actes administratifs ([0-9]{4})'
+    Attrap_prefdpt.grey_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'
+    Attrap_prefdpt.grey_card['add_year_to_months'] = True
+    Attrap_prefdpt.white_card['regex']['month'] = '([A-Za-zéû]* [0-9]{4})'
+    Attrap_prefdpt.white_card['add_year_to_months'] = True

Attrap_pref62.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref62(Attrap_prefdpt):
+
+    # Config
+    hostname = 'https://www.pas-de-calais.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs'
+    full_name = 'Préfecture du Pas-de-Calais'
+    short_code = 'pref62'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.white_card['regex']['year'] = '([0-9]{4})'

Attrap_pref63.py

+from Attrap_prefdpt import Attrap_prefdpt
+
+
+class Attrap_pref63(Attrap_prefdpt):
+
+    # Configuration de la préfecture
+    hostname = 'https://www.puy-de-dome.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueils-des-actes-administratifs/Recueils-des-actes-administratifs-Puy-de-Dome'
+    full_name = 'Préfecture du Puy-de-Dôme'
+    short_code = 'pref63'
+    timezone = 'Europe/Paris'
+
+    # Configuration des widgets à analyser
+    Attrap_prefdpt.grey_card['regex']['year'] = '([0-9]{4})'

RAAspotter_pref31.py → Attrap_pref64.py

@@ -4,53 +4,58 @@ import datetime
 from bs4 import BeautifulSoup
 from urllib.parse import unquote
 
-from RAAspotter import RAAspotter
+from Attrap import Attrap
 
 
-class RAAspotter_pref31(RAAspotter):
+class Attrap_pref64(Attrap):
 
     # Config
-    __HOST = 'https://www.haute-garonne.gouv.fr'
-    __RAA_PAGE = f'{__HOST}/Publications/Recueil-des-Actes-Administratifs/Recueil-des-Actes-Administratifs-Haute-Garonne'
-    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
-    full_name = 'Préfecture de la Haute-Garonne'
-    short_code = 'pref31'
+    hostname = 'https://www.pyrenees-atlantiques.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 Pyrénées-Atlantiques'
+    short_code = 'pref64'
+    timezone = 'Europe/Paris'
 
     def __init__(self, data_dir):
-        super().__init__(data_dir, self.__USER_AGENT)
+        super().__init__(data_dir, self.user_agent)
+        self.set_sleep_time(30)
 
     def get_raa(self, keywords):
-        self.print_output('RAAspotter_pref31')
-        self.print_output(f'Termes recherchés: {keywords}')
-        self.print_output('')
-
-        # On cherche les pages de chaque mois
-        page_content = self.get_page(self.__RAA_PAGE, 'get').content
-        month_pages = self.get_sub_pages(
+        # On récupère les pages d'années
+        year_pages = []
+        page_content = self.get_page(self.raa_page, 'get').content
+        for year_page in 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,
+            'div.fr-card__body div.fr-card__content h2.fr-card__title a',
+            self.hostname,
             False
-        )[::-1]
-
-        pages_to_parse = []
-
-        # On filtre les pages de mois pour limiter le nombre de requêtes
-        for month_page in month_pages:
-            guessed_date = RAAspotter.guess_date(month_page['name'], '([a-zéû]* [0-9]{4})')
-            if guessed_date >= self.not_before.replace(day=1):
-                pages_to_parse.append(month_page['url'])
-
-        elements = []
-        # On parse les pages des mois qu'on veut analyser
-        for element in self.get_raa_with_pager(
-            pages_to_parse,
-            ".fr-pagination__link.fr-pagination__link--next",
-            self.__HOST
         ):
-            elements.append(element)
+            year = Attrap.guess_date(year_page['name'], '.* ([0-9]{4})').year
+            if year < 9999 and year >= self.not_before.year:
+                year_pages.append(year_page['url'])
+
+        # Pour chaque page d'année, on récupère les pages de mois
+        month_pages = []
+        for year_page in year_pages:
+            page_content = self.get_page(year_page, 'get').content
+            for month_page in self.get_sub_pages(
+                page_content,
+                'div.fr-card__body div.fr-card__content h2.fr-card__title a',
+                self.hostname,
+                False
+            ):
+                if Attrap.guess_date(month_page['name'], '(.*)').replace(day=1) >= self.not_before.replace(day=1):
+                    month_pages.append(month_page['url'])
+
+        # On récupère les RAA en suivant la navigation de chaque page de mois
+        elements = self.get_raa_with_pager(
+            month_pages[::-1],
+            'a.fr-pagination__link--next.fr-pagination__link--lg-label',
+            self.hostname
+        )[::-1]
 
-        self.parse_raa(elements, keywords.split(','))
+        self.parse_raa(elements, keywords)
         self.mailer()
 
     def get_raa_elements(self, page_content):
@@ -62,14 +67,14 @@ class RAAspotter_pref31(RAAspotter):
         for a in soup.select('div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link.menu-item-link'):
             if a.get('href') and a['href'].endswith('.pdf'):
                 if a['href'].startswith('/'):
-                    url = f"{self.__HOST}{a['href']}"
+                    url = f"{self.hostname}{a['href']}"
                 else:
                     url = a['href']
 
                 url = unquote(url)
-                name = a.get_text().strip().capitalize()
+                name = a.get_text().strip()
                 date = datetime.datetime.strptime(a['title'].split(' - ')[-1].strip(), '%d/%m/%Y')
 
-                raa = RAAspotter.RAA(url, date, name)
+                raa = Attrap.RAA(url, date, name, timezone=self.timezone)
                 elements.append(raa)
         return elements

RAAspotter_pref42.py → Attrap_pref65.py

 import os
 import datetime
-import re
 
 from bs4 import BeautifulSoup
 from urllib.parse import unquote
 
-from RAAspotter import RAAspotter
+from Attrap import Attrap
 
 
-class RAAspotter_pref42(RAAspotter):
+class Attrap_pref65(Attrap):
 
     # Config
-    __HOST = 'https://www.loire.gouv.fr'
-    __RAA_PAGE = f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs'
-    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
-    full_name = 'Préfecture de de la Loire'
-    short_code = 'pref42'
+    hostname = 'https://www.hautes-pyrenees.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-d-actes-administratifs'
+    user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
+    full_name = 'Préfecture des Hautes-Pyrénées'
+    short_code = 'pref65'
+    timezone = 'Europe/Paris'
 
     def __init__(self, data_dir):
-        super().__init__(data_dir, self.__USER_AGENT)
-        self.enable_tor(10)
+        super().__init__(data_dir, self.user_agent)
+        self.set_sleep_time(30)
 
     def get_raa(self, keywords):
-        self.print_output('RAAspotter_pref42')
-        self.print_output(f'Termes recherchés: {keywords}')
-        self.print_output('')
-
-        year_pages_to_parse = []
-
         # On détermine quelles pages d'année parser
+        pages_to_parse = []
         year_pages = self.get_sub_pages_with_pager(
-            self.__RAA_PAGE,
+            self.raa_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',
             '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.__HOST
+            self.hostname
         )
         for year_page in year_pages:
-            year = 9999
-            try:
-                year = int(re.search('([0-9]{4})', year_page['name'], re.IGNORECASE).group(1))
-                if year is None:
-                    year = 9999
-            except Exception as exc:
-                logger.warning(f"Impossible de deviner l\'année de la page {year_page['name']}")
-                year = 9999
-
-            if year >= self.not_before.year:
-                year_pages_to_parse.append(year_page['url'])
+            if Attrap.guess_date(year_page['name'].strip(), '.*([0-9]{4})').year >= self.not_before.year:
+                pages_to_parse.append(year_page['url'])
 
         elements = []
-        # Pour chaque année, on parse les RAA
-        for year_page in year_pages_to_parse:
-            page_content = self.get_page(year_page, 'get').content
-            for element in self.get_raa_elements(page_content)[::-1]:
+        for raa_page in pages_to_parse:
+            page_content = self.get_page(raa_page, 'get').content
+            for element in self.get_raa_elements(page_content):
                 elements.append(element)
 
-        # On parse les RAA
-        self.parse_raa(elements, keywords.split(','))
+        self.parse_raa(elements, keywords)
         self.mailer()
 
     def get_raa_elements(self, page_content):
@@ -65,11 +49,11 @@ class RAAspotter_pref42(RAAspotter):
         # 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'):
+        # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
+        for a in soup.select('a.fr-link.fr-link--download'):
             if a.get('href') and a['href'].endswith('.pdf'):
                 if a['href'].startswith('/'):
-                    url = f"{self.__HOST}{a['href']}"
+                    url = f"{self.hostname}{a['href']}"
                 else:
                     url = a['href']
 
@@ -77,6 +61,6 @@ class RAAspotter_pref42(RAAspotter):
                 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 = RAAspotter.RAA(url, date, name)
+                raa = Attrap.RAA(url, date, name, timezone=self.timezone)
                 elements.append(raa)
         return elements

RAAspotter_pref66.py → Attrap_pref66.py

@@ -6,35 +6,38 @@ import logging
 from bs4 import BeautifulSoup
 from urllib.parse import unquote
 
-from RAAspotter import RAAspotter
+from Attrap import Attrap
 
 logger = logging.getLogger(__name__)
 
 
-class RAAspotter_pref66(RAAspotter):
+class Attrap_pref66(Attrap):
 
     # Config
-    __HOST = 'https://www.pyrenees-orientales.gouv.fr'
-    __RAA_PAGE = {
-        '2024': f'{__HOST}/Publications/Le-recueil-des-actes-administratifs/Annee-2024',
-        '2023': f'{__HOST}/Publications/Le-recueil-des-actes-administratifs/Annee-2023',
-        '2022': f'{__HOST}/Publications/Le-recueil-des-actes-administratifs/Annee-2022',
-        '2021': f'{__HOST}/Publications/Le-recueil-des-actes-administratifs/Annee-2021',
-        '2020': f'{__HOST}/Publications/Le-recueil-des-actes-administratifs/Annee-2020',
-        '2019': f'{__HOST}/Publications/Le-recueil-des-actes-administratifs/Annee-2019'
-    }
-    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+    hostname = 'https://www.pyrenees-orientales.gouv.fr'
+    raa_page = f'{hostname}/Publications/Le-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 Pyrénées-Orientales'
     short_code = 'pref66'
+    timezone = 'Europe/Paris'
 
     def __init__(self, data_dir):
-        super().__init__(data_dir, self.__USER_AGENT)
-        self.enable_tor(10)
+        super().__init__(data_dir, self.user_agent)
+        self.set_sleep_time(30)
 
     def get_raa(self, keywords):
-        self.print_output('RAAspotter_pref66')
-        self.print_output(f'Termes recherchés: {keywords}')
-        self.print_output('')
+        # On détermine quelles pages d'année parser
+        year_pages = []
+        page_content = self.get_page(self.raa_page, 'get').content
+        for year_page in self.get_sub_pages(
+            page_content,
+            '.fr-table table tr td h3 a.fr-link',
+            self.hostname,
+            False
+        ):
+            year = Attrap.guess_date(year_page['name'].strip(), '.* ([0-9]{4})').year
+            if year < 9999 and year >= self.not_before.year:
+                year_pages.append([year_page['url'], year])
 
         elements = []
 
@@ -47,26 +50,18 @@ class RAAspotter_pref66(RAAspotter):
         # n'est pas exhaustif. On doit donc parser toutes les sous-pages de
         # 2024 puisqu'on ne peut se fier au tableau récapitulatif.
         # Grrr.
-        if self.not_before.year <= 2024:
-            for element in self.get_raa_elements_since_2024(self.__RAA_PAGE['2024']):
-                elements.append(element)
-        if self.not_before.year <= 2023:
-            for element in self.get_raa_elements_before_2024(self.__RAA_PAGE['2023']):
-                elements.append(element)
-        if self.not_before.year <= 2022:
-            for element in self.get_raa_elements_before_2024(self.__RAA_PAGE['2022']):
-                elements.append(element)
-        if self.not_before.year <= 2021:
-            for element in self.get_raa_elements_before_2024(self.__RAA_PAGE['2021']):
-                elements.append(element)
-        if self.not_before.year <= 2020:
-            for element in self.get_raa_elements_before_2024(self.__RAA_PAGE['2020']):
-                elements.append(element)
-        if self.not_before.year <= 2019:
-            for element in self.get_raa_elements_before_2024(self.__RAA_PAGE['2019']):
-                elements.append(element)
-
-        self.parse_raa(elements, keywords.split(','))
+        for year_page in year_pages:
+            url = year_page[0]
+            year = year_page[1]
+
+            if year >= 2024:
+                for element in self.get_raa_elements_since_2024(url):
+                    elements.append(element)
+            else:
+                for element in self.get_raa_elements_before_2024(url):
+                    elements.append(element)
+
+        self.parse_raa(elements, keywords)
         self.mailer()
 
     # On parse un lien d'avant 2024
@@ -93,7 +88,7 @@ class RAAspotter_pref66(RAAspotter):
                 if date >= self.not_before:
                     url = ''
                     if a['href'].startswith('/'):
-                        url = f"{self.__HOST}{a['href']}"
+                        url = f"{self.hostname}{a['href']}"
                     else:
                         url = a['href']
 
@@ -104,7 +99,7 @@ class RAAspotter_pref66(RAAspotter):
                     else:
                         name = a.get_text().replace('Télécharger ', '').strip()
 
-                    elements.append(RAAspotter.RAA(url, date, name))
+                    elements.append(Attrap.RAA(url, date, name))
         return elements
 
     # On parse les RAA depuis 2024
@@ -114,7 +109,7 @@ class RAAspotter_pref66(RAAspotter):
             '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.__HOST
+            self.hostname
         )[::-1]
 
         pages_to_parse = []
@@ -125,7 +120,7 @@ class RAAspotter_pref66(RAAspotter):
                 logger.warning(f"Attention, le lien vers {page['url']} n'est pas bon !")
             else:
                 if page['url'].startswith('/'):
-                    url = f"{self.__HOST}{page['url']}"
+                    url = f"{self.hostname}{page['url']}"
                 else:
                     url = page['url']
 
@@ -133,5 +128,5 @@ class RAAspotter_pref66(RAAspotter):
                 name = page['name'].replace('Télécharger ', '').strip()
                 date = datetime.datetime.strptime(page['details'].replace('Publié le ', '').strip(), '%d/%m/%Y')
 
-                elements.append(RAAspotter.RAA(url, date, name))
+                elements.append(Attrap.RAA(url, date, name, timezone=self.timezone))
         return elements

RAAspotter_pref69.py → Attrap_pref69.py

@@ -4,57 +4,45 @@ import datetime
 from bs4 import BeautifulSoup
 from urllib.parse import unquote
 
-from RAAspotter import RAAspotter
+from Attrap import Attrap
 
 
-class RAAspotter_pref69(RAAspotter):
+class Attrap_pref69(Attrap):
 
     # Config
-    __HOST = 'https://www.rhone.gouv.fr'
-    __RAA_PAGE = {
-        '2024': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2024',
-        '2023': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2023',
-        '2022': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2022',
-        '2021': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2021',
-        '2020': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2020',
-        '2019': f'{__HOST}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA/Recueils-de-2019'
-    }
-    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+    hostname = 'https://www.rhone.gouv.fr'
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-du-Rhone-RAA'
+    user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
     full_name = 'Préfecture du Rhône'
     short_code = 'pref69'
+    timezone = 'Europe/Paris'
 
     def __init__(self, data_dir):
-        super().__init__(data_dir, self.__USER_AGENT)
-        self.enable_tor(20)
+        super().__init__(data_dir, self.user_agent)
+        self.set_sleep_time(30)
 
     def get_raa(self, keywords):
-        self.print_output('RAAspotter_pref69')
-        self.print_output(f'Termes recherchés: {keywords}')
-        self.print_output('')
-
-        pages_to_parse = []
-        if self.not_before.year <= 2024:
-            pages_to_parse.append(self.__RAA_PAGE['2024'])
-        if self.not_before.year <= 2023:
-            pages_to_parse.append(self.__RAA_PAGE['2023'])
-        if self.not_before.year <= 2022:
-            pages_to_parse.append(self.__RAA_PAGE['2022'])
-        if self.not_before.year <= 2021:
-            pages_to_parse.append(self.__RAA_PAGE['2021'])
-        if self.not_before.year <= 2020:
-            pages_to_parse.append(self.__RAA_PAGE['2020'])
-        if self.not_before.year <= 2019:
-            pages_to_parse.append(self.__RAA_PAGE['2019'])
+        # On détermine quelles pages d'année parser
+        year_pages = []
+        page_content = self.get_page(self.raa_page, 'get').content
+        for year_page in self.get_sub_pages(
+            page_content,
+            'div.fr-card__body div.fr-card__content h2.fr-card__title a',
+            self.hostname,
+            False
+        ):
+            year = Attrap.guess_date(year_page['name'].strip(), '.* ([0-9]{4})').year
+            if year < 9999 and year >= self.not_before.year:
+                year_pages.append(year_page['url'])
 
         sub_pages_to_parse = []
-
-        for raa_page in pages_to_parse:
+        for raa_page in year_pages:
             sub_pages = self.get_sub_pages_with_pager(
                 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--next',
                 None,
-                self.__HOST)[::-1]
+                self.hostname)[::-1]
             for sub_page in sub_pages:
                 sub_pages_to_parse.append(sub_page['url'])
 
@@ -64,7 +52,7 @@ class RAAspotter_pref69(RAAspotter):
             for element in self.get_raa_elements(page_content)[::-1]:
                 elements.append(element)
 
-        self.parse_raa(elements, keywords.split(','))
+        self.parse_raa(elements, keywords)
         self.mailer()
 
     def get_raa_elements(self, page_content):
@@ -76,7 +64,7 @@ class RAAspotter_pref69(RAAspotter):
         for a in soup.select('a.fr-link.fr-link--download'):
             if a.get('href') and a['href'].endswith('.pdf'):
                 if a['href'].startswith('/'):
-                    url = f"{self.__HOST}{a['href']}"
+                    url = f"{self.hostname}{a['href']}"
                 else:
                     url = a['href']
 
@@ -84,6 +72,6 @@ class RAAspotter_pref69(RAAspotter):
                 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 = RAAspotter.RAA(url, date, name)
+                raa = Attrap.RAA(url, date, name, timezone=self.timezone)
                 elements.append(raa)
         return elements