pref13: n'analyse que les 5 dernières années disponibles

RAAspotter_pref13.py

@@ -9,7 +9,12 @@ class RAAspotter_pref13(RAAspotter):
 
   # Config
   __HOST       = 'https://www.bouches-du-rhone.gouv.fr'
-  __RAA_PAGE   = f'{__HOST}/Publications/RAA-et-Archives'
+  __RAA_PAGE   = [f'{__HOST}/Publications/RAA-et-Archives/RAA-2024',
+                  f'{__HOST}/Publications/RAA-et-Archives/RAA-2023',
+                  f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2022',
+                  f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2021',
+                  f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2020',
+                  f'{__HOST}/Publications/RAA-et-Archives/Archives-RAA-des-Bouches-du-Rhone/RAA-2019']
   __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
 
   def __init__(self, data_dir):
@@ -20,13 +25,10 @@ class RAAspotter_pref13(RAAspotter):
     self.print_output('RAAspotter_pref13')
     self.print_output(f'Termes recherchés: {keywords}')
 
-    page_content = self.get_page(self.__RAA_PAGE).content
-    sub_pages = self.get_sub_pages(page_content, 'div.fr-card__body div.fr-card__content h2.fr-card__title a', self.__HOST)
-    raa_elements = []
-    for page in sub_pages:
-      for element in self.get_raa_elements(self.get_page(page).content):
-        raa_elements.append(element)
-    self.parse_raa(raa_elements, keywords.split(','))
+    for raa_page in self.__RAA_PAGE:
+      page_content = self.get_page(raa_page).content
+      raa_elements = self.get_raa_elements(page_content)
+      self.parse_raa(raa_elements, keywords.split(','))
 
   def get_raa_elements(self, page_content):
     elements = []
@@ -34,15 +36,15 @@ class RAAspotter_pref13(RAAspotter):
     soup = BeautifulSoup(page_content, 'html.parser')
 
     # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
-    for a in soup.find_all('a', href=True):
+    for a in soup.find_all('a', href=True, class_='fr-link--download'):
       if a['href'].endswith('.pdf'):
         if a['href'].startswith('/'):
           url = f"{self.__HOST}{a['href']}"
         else:
           url = a['href']
 
-        name     = unquote(url.split('/')[-1])
-        date     = "date non renseignée"
+        name     = a.find('span').previous_sibling.replace('Télécharger ', '').strip()
+        date     = a.find('span').get_text().split(' - ')[-1].strip()
         filename = unquote(url.split('/')[-1])
 
         raa = RAAspotter.RAA(url, date, name, filename)