From efbd7fac3e7f6776c3dd490c46fb5cd9256a6919 Mon Sep 17 00:00:00 2001
From: Bastien Le Querrec <blq@laquadrature.net>
Date: Fri, 3 Jan 2025 23:00:08 +0100
Subject: [PATCH] =?UTF-8?q?pref03:=20utilise=20la=20classe=20g=C3=A9n?=
=?UTF-8?q?=C3=A9rique=20de=20d=C3=A9partement?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
Attrap_pref03.py | 55 +++---------------------------------------------
1 file changed, 3 insertions(+), 52 deletions(-)
diff --git a/Attrap_pref03.py b/Attrap_pref03.py
index 2537b79..1880562 100644
--- a/Attrap_pref03.py
+++ b/Attrap_pref03.py
@@ -1,61 +1,12 @@
-import os
-import datetime
+from Attrap_prefdpt import Attrap_prefdpt
-from bs4 import BeautifulSoup
-from urllib.parse import unquote
-from Attrap import Attrap
-
-
-class Attrap_pref03(Attrap):
+class Attrap_pref03(Attrap_prefdpt):
# Config
hostname = 'https://www.allier.gouv.fr'
raa_page = f'{hostname}/Publications/Recueil-des-actes-administratifs-arretes'
- user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
full_name = 'Préfecture de l\'Allier'
short_code = 'pref03'
timezone = 'Europe/Paris'
-
- def __init__(self, data_dir):
- super().__init__(data_dir, self.user_agent)
- self.set_sleep_time(30)
-
- def get_raa(self, keywords):
- elements = []
- page_content = self.get_page(self.raa_page, 'get').content
- for sub_page in self.get_sub_pages(
- page_content,
- 'div.fr-card__body div.fr-card__content h2.fr-card__title a',
- self.hostname,
- False
- ):
- if Attrap.guess_date(sub_page['name'], '.* ([0-9]{4})').year >= self.not_before.year:
- sub_page_content = self.get_page(sub_page['url'], 'get').content
- for element in self.get_raa_elements(sub_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')
-
- # Pour chaque balise a, on regarde si c'est un PDF, et si oui on le
- # parse
- 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.hostname}{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, timezone=self.timezone)
- elements.append(raa)
- return elements
+ Attrap_prefdpt.grey_card['year'] = '([0-9]{4})'
\ No newline at end of file
--
GitLab