From c75a25071b6ed8c43a9bc4a8e5df6d21b919d36e Mon Sep 17 00:00:00 2001
From: Bastien Le Querrec <blq@laquadrature.net>
Date: Tue, 19 Mar 2024 20:29:10 +0100
Subject: [PATCH] =?UTF-8?q?pref38:=20ajout=20de=20la=20pr=C3=A9fecture=20d?=
=?UTF-8?q?e=20l'Is=C3=A8re?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
Makefile | 4 +-
RAAspotter_pref38.py | 96 ++++++++++++++++++++++++++++++++++++++++++++
cli.py | 1 +
requirements.txt | 1 +
4 files changed, 101 insertions(+), 1 deletion(-)
create mode 100644 RAAspotter_pref38.py
diff --git a/Makefile b/Makefile
index 095b8db..37086af 100644
--- a/Makefile
+++ b/Makefile
@@ -1,10 +1,12 @@
-make: pref06 pref13 pref35 pref62 ppparis
+make: pref06 pref13 pref35 pref38 pref62 ppparis
pref06:
python cli.py --pref pref06
pref13:
python cli.py --pref pref13
pref35:
python cli.py --pref pref35
+pref38:
+ python cli.py --pref pref38
pref62:
python cli.py --pref pref62
ppparis:
diff --git a/RAAspotter_pref38.py b/RAAspotter_pref38.py
new file mode 100644
index 0000000..a7fed1a
--- /dev/null
+++ b/RAAspotter_pref38.py
@@ -0,0 +1,96 @@
+import os, sys, re
+import datetime
+import dateparser
+import logging
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from RAAspotter import RAAspotter
+
+logger = logging.getLogger(__name__)
+
+class RAAspotter_pref38(RAAspotter):
+
+ # Config
+ __HOST = 'https://www.isere.gouv.fr'
+ __RAA_PAGE = {'2024': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2024',
+ '2023': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2023',
+ '2022': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2022',
+ '2021': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Archives-des-recueils-des-actes-administratifs-de-la-prefecture-de-l-Isere-2021/Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2021',
+ '2020': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Archives-des-recueils-des-actes-administratifs-de-la-prefecture-de-l-Isere-2020/Recueils-des-Actes-Administratifs-de-la-Prefecture-de-l-Isere-2020',
+ '2019': f'{__HOST}/Publications/RAA-Recueil-des-actes-administratifs/Archives/Archives-des-Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2019/Archives-des-Recueils-des-Actes-Administratifs-de-la-prefecture-de-l-Isere-2019'}
+ __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+ full_name = 'Préfecture de l\'Isère'
+ short_code = 'pref38'
+
+ def __init__(self, data_dir):
+ super().__init__(data_dir, self.__USER_AGENT)
+ self.enable_tor(20)
+
+ def get_raa(self, keywords):
+ self.print_output('RAAspotter_pref38')
+ self.print_output(f'Termes recherchés: {keywords}')
+ self.print_output('')
+
+ 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'])
+
+ for raa_page in pages_to_parse:
+ page_content = self.get_page(raa_page, 'get').content
+ raa_elements = self.get_raa_elements(page_content, raa_page)
+ self.parse_raa(raa_elements, keywords.split(','))
+ self.mailer()
+
+ def get_raa_elements(self, page_content, raa_page):
+ elements = []
+ # On charge le parser
+ soup = BeautifulSoup(page_content, 'html.parser')
+
+ # On récupère le select qui contient la liste des RAA
+ select_list = soup.select('select#-liste-docs')[0]
+ # On analyse chaque résultat
+ for option in select_list.find_all('option'):
+ if not option['value'] == "":
+ guessed_date = datetime.datetime(9999, 1, 1)
+ try:
+ # Pour chaque RAA listé, on essaie de deviner sa date à partir de son nom, et si elle correspond à la plage
+ # demandée, on poursuit l'analyse
+ search = re.search('.* n°[ 0-9]* du ([0-9]*(?:er)? [a-zéû]* [0-9]*)', option['title'], re.IGNORECASE)
+ guessed_date = dateparser.parse(search.group(1))
+ except Exception as exc:
+ logger.warning(f"Impossible de deviner la date du RAA {option['title']} : {exc}")
+
+ # Si la date estimée correspond à la plage d'analyse, on demande au serveur les détails du RAA
+ if guessed_date >= self.not_before:
+ page_content = self.get_page(raa_page, 'post', {'-liste-docs':option['value']}).content
+ # On parse la page de détails pour obtenir les propriétés du RAA
+ soup = BeautifulSoup(page_content, 'html.parser')
+ a = soup.select('div.liste_deroulante a.fr-link.fr-link--download')[0]
+
+ # Si la page contient une balise a qui renvoie vers un pdf, c'est qu'on a obtenu les détails du RAA demandé, donc on le parse
+ 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')
+ filename = url.split('/')[-1]
+
+ raa = RAAspotter.RAA(url, date, name, filename)
+ elements.append(raa)
+ return elements
diff --git a/cli.py b/cli.py
index 5816df4..8776b02 100755
--- a/cli.py
+++ b/cli.py
@@ -38,6 +38,7 @@ available_prefs = [
'pref06',
'pref13',
'pref35',
+ 'pref38',
'pref62',
'ppparis'
]
diff --git a/requirements.txt b/requirements.txt
index 0ae92bc..6558ead 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,3 +5,4 @@ pdfminer.six
requests
stem
Mastodon.py
+dateparser
--
GitLab