pref971

Attrap_pref971.py

+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+import locale
+
+locale.setlocale(locale.LC_TIME, "fr_FR.UTF-8")
+
+
+# https://www.guadeloupe.gouv.fr/Publications/Le-Recueil-des-actes-administratifs/2021/Decembre
+
+
+class Attrap_pref971(Attrap):
+    months_fr = [
+        "Janvier",
+        "Fevrier",
+        "Mars",
+        "Avril",
+        "Mai",
+        "Juin",
+        "Juillet",
+        "Aout",
+        "Septembre",
+        "Octobre",
+        "Novembre",
+        "Decembre",
+    ]
+
+    # Config
+    __HOST = "https://www.guadeloupe.gouv.fr"
+    __RAA_PAGE = {
+        "2015": [],
+        "2016": [],
+        "2017": [],
+        "2018": [],
+        "2019": [],
+        "2020": [],
+        "2021": [],
+        "2022": [],
+        "2023": [],
+        "2024": [],
+    }
+    for year in range(2015, 2024):
+        for month in range(1, 12):
+            __RAA_PAGE[str(year)].append(
+                f"{__HOST}/Publications/Le-Recueil-des-actes-administratifs/{year}/{months_fr[month]}"
+            )
+    __USER_AGENT = (
+        "Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0"
+    )
+    full_name = "Préfecture de la Guadeloupe"
+    short_code = "pref971"
+
+    def __init__(self, data_dir):
+        super().__init__(data_dir, self.__USER_AGENT)
+        self.enable_tor(10)
+
+    def get_raa(self, keywords):
+        year_pages_to_parse = []
+        if self.not_before.year <= 2024:
+            for year_page in self.__RAA_PAGE["2024"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2023:
+            for year_page in self.__RAA_PAGE["2023"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2022:
+            for year_page in self.__RAA_PAGE["2022"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2021:
+            for year_page in self.__RAA_PAGE["2021"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2020:
+            for year_page in self.__RAA_PAGE["2020"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2019:
+            for year_page in self.__RAA_PAGE["2019"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2018:
+            for year_page in self.__RAA_PAGE["2018"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2017:
+            for year_page in self.__RAA_PAGE["2017"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2016:
+            for year_page in self.__RAA_PAGE["2016"]:
+                year_pages_to_parse.append(year_page)
+        if self.not_before.year <= 2015:
+            for year_page in self.__RAA_PAGE["2015"]:
+                year_pages_to_parse.append(year_page)
+
+        # On parse les pages contenant des RAA
+        elements = []
+        for year in self.__RAA_PAGE:
+            for page in self.__RAA_PAGE[year]:
+                page_content = self.get_page(page, "get").content
+                for raa in self.get_raa_elements(page_content):
+                    elements.append(raa)
+
+        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.get_text().replace("Télécharger ", "").strip()
+                date_str = a.find_all("span")[-1].get_text().split(" - ")[-1].strip()
+                date = datetime.datetime.strptime(date_str, "%d/%m/%Y")
+
+                raa = Attrap.RAA(url, date, name)
+                elements.append(raa)
+        return elements