pref63: ajout de la préfecture du Puy-de-Dôme

.gitlab-ci.yml

@@ -168,6 +168,11 @@ test_pref62:
     PREF: "pref62"
   extends: .default_pref
 
+test_pref63:
+  variables:
+    PREF: "pref63"
+  extends: .default_pref
+
 test_pref64:
   variables:
     PREF: "pref64"

Attrap_pref63.py

+import os
+import datetime
+import re
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+
+class Attrap_pref63(Attrap):
+
+    # Config
+    __HOST = 'https://www.puy-de-dome.gouv.fr'
+    __RAA_PAGE = f'{__HOST}/Publications/Recueils-des-actes-administratifs/Recueils-des-actes-administratifs-Puy-de-Dome'
+    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+    full_name = 'Préfecture du Puy-de-Dôme'
+    short_code = 'pref63'
+
+    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 = []
+
+        # On détermine quelles pages d'année parser
+        page_content = self.get_page(self.__RAA_PAGE, 'get').content
+        year_pages = self.get_sub_pages(
+            page_content,
+            'div.fr-card.fr-card--sm.fr-card--grey.fr-enlarge-link div.fr-card__body div.fr-card__content h2.fr-card__title a',
+            self.__HOST,
+            False
+        )
+        for year_page in year_pages:
+            if not year_page['name'].strip() == 'Archives':
+                year = 9999
+                try:
+                    year = int(year_page['name'].strip())
+                except Exception as exc:
+                    logger.warning(f"Impossible de deviner l\'année de la page {year_page['name']}")
+                    year = 9999
+
+                if year >= self.not_before.year:
+                    year_pages_to_parse.append(year_page['url'])
+
+        elements = []
+        # Pour chaque année, on parse les RAA
+        for year_page in year_pages_to_parse:
+            page_content = self.get_page(year_page, 'get').content
+            for element in self.get_raa_elements(page_content):
+                elements.append(element)
+
+        # On parse les 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.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

Makefile

-make: ppparis pref04 pref05 pref06 pref09 pref13 pref31 pref33 pref34 pref35 pref38 pref42 pref44 pref59 pref62 pref64 pref65 pref66 pref69 pref80 pref81 pref83 pref87 pref976
+make: ppparis pref04 pref05 pref06 pref09 pref13 pref31 pref33 pref34 pref35 pref38 pref42 pref44 pref59 pref62 pref63 pref64 pref65 pref66 pref69 pref80 pref81 pref83 pref87 pref976
 ppparis:
 	bin/python3 cli.py ppparis
 pref04:
@@ -29,6 +29,8 @@ pref59:
 	bin/python3 cli.py pref59
 pref62:
 	bin/python3 cli.py pref62
+pref63:
+	bin/python3 cli.py pref63
 pref64:
 	bin/python3 cli.py pref64
 pref65:

cli.py

@@ -52,6 +52,7 @@ available_administrations = [
     'pref44',
     'pref59',
     'pref62',
+    'pref63',
     'pref64',
     'pref65',
     'pref66',