prefpaca: utilise Selenium

Les préfectures de régions utilisent Cloudflare depuis quelques jours :(

Attrap_prefpaca.py

@@ -12,7 +12,7 @@ class Attrap_prefpaca(Attrap):
     # Config
     hostname = 'https://www.prefectures-regions.gouv.fr'
     raa_page = f'{hostname}/provence-alpes-cote-dazur/Documents-publications'
-    user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
+    user_agent = 'Mozilla/5.0 (X11; Linux x86_64; rv:128.0) Gecko/20100101 Firefox/128.0'
     full_name = 'Préfecture de Provence-Alpes-Côte-d\'Azur'
     short_code = 'prefpaca'
     timezone = 'Europe/Paris'
@@ -22,14 +22,18 @@ class Attrap_prefpaca(Attrap):
         self.enable_tor(10)
 
     def get_raa(self, keywords):
+        # On récupère une session avec Selenium
+        page_content = self.get_session(self.raa_page, 'main', 6)
+
         # On récupère les pages d'années
         year_pages = []
         for year_page in self.get_sub_pages_with_pager(
-            self.raa_page,
+            page_content,
             'article.news-list-item header h2.news-list-title a',
             'article.article div.content-pagination ul.pagination li.next a',
             None,
-            self.hostname
+            self.hostname,
+            selenium=True
         ):
             year = Attrap.guess_date(year_page['name'].strip(), 'RAA ([0-9]{4})').year
             if year < 9999 and year >= self.not_before.year:
@@ -37,7 +41,7 @@ class Attrap_prefpaca(Attrap):
 
         elements = []
         for year_page in year_pages:
-            page_content = self.get_page(year_page, 'get').content
+            page_content = self.get_session(year_page, 'main', 6)
             for element in self.get_raa_elements(page_content):
                 elements.append(element)