Jura

Attrap_pref39.py

+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+
+class Attrap_pref39(Attrap):
+
+    # Config
+    __HOST = 'https://www.jura.gouv.fr'
+    __RAA_PAGE = {
+        '2024': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2024',
+        '2023': f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueil-des-actes-administratifs-2023',
+        '2022': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2022',
+        '2021': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2021',
+        '2020': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2020',
+        '2019': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2019',
+        '2018': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2018',
+        '2017': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2017',
+        '2016': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2016',
+        '2015': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2015',
+        '2011': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2011',
+        '2010': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2010',
+        '2009': f'{__HOST}/Publications/Publications-legales/Recueil-des-Actes-Administratifs/Annee-2009',
+    }
+    __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 du Jura'
+    short_code = 'pref39'
+
+    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'])
+        if self.not_before.year <= 2018:
+            pages_to_parse.append(self.__RAA_PAGE['2018'])
+        if self.not_before.year <= 2017:
+            pages_to_parse.append(self.__RAA_PAGE['2017'])
+        if self.not_before.year <= 2016:
+            pages_to_parse.append(self.__RAA_PAGE['2016'])
+        if self.not_before.year <= 2015:
+            pages_to_parse.append(self.__RAA_PAGE['2015'])
+        if self.not_before.year <= 2011:
+            pages_to_parse.append(self.__RAA_PAGE['2011'])
+        if self.not_before.year <= 2010:
+            pages_to_parse.append(self.__RAA_PAGE['2010'])
+        if self.not_before.year <= 2009:
+            pages_to_parse.append(self.__RAA_PAGE['2009'])
+
+        elements = []
+        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)
+
+        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-card__link'):
+            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.get_text().strip()
+                date_str = name.strip('RAA-39-').split(" ")[0]
+                try:
+                    date = datetime.datetime.strptime(date_str.strip('_'), '%Y-%m-0%d')
+                except ValueError:
+                    date = datetime.datetime.strptime(date_str.strip('_'), '%Y_%m_0%d')
+                raa = Attrap.RAA(url, date, name)
+                elements.append(raa)
+        return elements