pref976: détecte l'URL de l'année voulue automatiquement

Attrap_pref976.py

@@ -11,15 +11,7 @@ class Attrap_pref976(Attrap):
 
     # Config
     hostname = 'https://www.mayotte.gouv.fr'
-    raa_page = {
-        'default': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A',
-        '2024': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2024',
-        '2023': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2023',
-        '2022': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2022',
-        '2021': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2021',
-        '2020': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2020',
-        '2019': f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A/RAA-2019'
-    }
+    raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-R.A.A'
     user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
     full_name = 'Préfecture de Mayotte'
     short_code = 'pref976'
@@ -30,24 +22,23 @@ class Attrap_pref976(Attrap):
         self.set_sleep_time(30)
 
     def get_raa(self, keywords):
-        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'])
-
-        sub_pages_to_parse = [self.raa_page['default']]
+        year_pages_to_parse = []
+
+        # On récupère les pages d'années
+        page_content = self.get_page(self.raa_page, 'get').content
+        for card 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(card['name'], '([0-9]{4})').year >= self.not_before.year:
+                year_pages_to_parse.append(card['url'])
+
+        pages_to_parse = [self.raa_page]
 
         # Pour chaque année, on cherche les sous-pages de mois
-        for raa_page in pages_to_parse:
+        for raa_page in year_pages_to_parse:
             page_content = self.get_page(raa_page, 'get').content
             month_pages = self.get_sub_pages(
                 page_content,
@@ -59,7 +50,7 @@ class Attrap_pref976(Attrap):
             # On regarde aussi si sur la page de l'année il n'y aurait pas un
             # RAA mal catégorisé
             for page_to_parse in self.find_raa_card(raa_page):
-                sub_pages_to_parse.append(page_to_parse)
+                pages_to_parse.append(page_to_parse)
 
             # Pour chaque mois, on cherche les pages des RAA
             for month_page in month_pages:
@@ -68,11 +59,11 @@ class Attrap_pref976(Attrap):
                     month_page['url'],
                     year
                 ):
-                    sub_pages_to_parse.append(page_to_parse)
+                    pages_to_parse.append(page_to_parse)
 
         # On parse les pages contenant des RAA
         elements = []
-        for page in sub_pages_to_parse:
+        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)