Attrap_pref73.py

+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+
+class Attrap_pref73(Attrap):
+
+    # Config
+    __HOST = 'https://www.savoie.gouv.fr'
+    __RAA_PAGE = {
+        '2024': f'{__HOST}/Publications/Recueils-hebdomadaires-et-speciaux-des-actes-administratifs/2024',
+        '2023': f'{__HOST}/Publications/Recueils-hebdomadaires-et-speciaux-des-actes-administratifs/2023',
+        '2022': f'{__HOST}/Publications/Recueils-hebdomadaires-et-speciaux-des-actes-administratifs/2022',
+        '2021': f'{__HOST}/Publications/Recueils-hebdomadaires-et-speciaux-des-actes-administratifs/2021',
+        '2020': f'{__HOST}/Publications/Recueils-hebdomadaires-et-speciaux-des-actes-administratifs/2020',
+        '2019': f'{__HOST}/Publications/Recueils-hebdomadaires-et-speciaux-des-actes-administratifs/2019',
+    }
+    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+    full_name = 'Préfecture de la Savoie'
+    short_code = 'pref73'
+
+    def __init__(self, data_dir):
+        super().__init__(data_dir, self.__USER_AGENT)
+        self.enable_tor(10)
+
+    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'])
+
+        # On parse les pages contenant des RAA
+        elements = []
+        print(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)
+
+        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('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']}"
+                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)
+                elements.append(raa)
+        return elements

cli.py

@@ -59,6 +59,7 @@ available_administrations = [
     'pref65',
     'pref66',
     'pref69',
+    'pref73',
     'pref80',
     'pref81',
     'pref83',