From c5070717b93dc52ce08081a550b7cc6a285299d1 Mon Sep 17 00:00:00 2001 From: Bastien Le Querrec <blq@laquadrature.net> Date: Tue, 7 Jan 2025 12:54:46 +0100 Subject: [PATCH] pref39: utilise prefdpt --- Attrap_pref39.py | 63 +++++------------------------------------------- 1 file changed, 6 insertions(+), 57 deletions(-) diff --git a/Attrap_pref39.py b/Attrap_pref39.py index c1cdc59..9f4ae76 100644 --- a/Attrap_pref39.py +++ b/Attrap_pref39.py @@ -1,66 +1,15 @@ -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_pref39(Attrap_prefdpt): - -class Attrap_pref39(Attrap): - - # Config + # Configuration de la préfecture hostname = "https://www.jura.gouv.fr" raa_page = f'{hostname}/Publications/Publications-legales/Recueil-des-Actes-Administratifs' - user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0' full_name = "Préfecture du Jura" short_code = "pref39" 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): - # On récupère les pages d'années - year_pages = [] - page_content = self.get_page(self.raa_page, 'get').content - for card 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(card['name'], '.* ([0-9]{4})').year >= self.not_before.year: - year_pages.append(card['url']) - - # On récupère tous les RAA en suivant la navigation - elements = self.get_raa_with_pager( - year_pages, - 'a.fr-pagination__link.fr-pagination__link--next', - self.hostname - ) - - 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('.fr-card__title a.fr-card__link.menu-item-link'): - 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.get_text().strip() - date = datetime.datetime.strptime(a['title'].split(' - ')[-1].strip(), '%d/%m/%Y') - - raa = Attrap.RAA(url, date, name, timezone=self.timezone) - elements.append(raa) - return elements + # Configuration des widgets à analyser + Attrap_prefdpt.grey_card['regex']['year'] = 'Année ([0-9]{4})' + #Attrap_prefdpt.white_card['css_path']['details'] = None -- GitLab