From b5314cc54690708a20c1f50ce042a05a0a8b91fd Mon Sep 17 00:00:00 2001
From: Luc Pellissier <luc.pellissier@inria.fr>
Date: Sun, 9 Jun 2024 19:59:43 +0200
Subject: [PATCH] Draft Paris

---
 Attrap_pref75.py | 104 +++++++++++++++++++++++++++++++++++++++++++++++
 cli.py           |   1 +
 2 files changed, 105 insertions(+)
 create mode 100644 Attrap_pref75.py

diff --git a/Attrap_pref75.py b/Attrap_pref75.py
new file mode 100644
index 0000000..b35823d
--- /dev/null
+++ b/Attrap_pref75.py
@@ -0,0 +1,104 @@
+import os
+import datetime
+
+from bs4 import BeautifulSoup
+from urllib.parse import unquote
+
+from Attrap import Attrap
+
+
+class Attrap_pref75(Attrap):
+
+    # Les RAA de Paris sont sur le site de la préfecture de région
+    # Île-de-France. On ne prend en compte que les RAA départementaux.Tant qu'à
+    # y être, on prend les RAA du département et de la région.
+    
+    # Config
+    __HOST = 'https://www.prefectures-regions.gouv.fr'
+    __RAA_PAGE = {
+        '2024': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2024',
+        '2023': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2023',
+        '2022': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2022',
+        '2021': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2021',
+        '2020': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2020',
+        '2019': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2019',
+        '2018': f'{__HOST}/ile-de-france/ile-de-france/ile-de-france/Documents-publications/Recueil-des-actes-administratifs/Raa-du-departement-de-Paris-2018'
+        }
+    __USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
+    full_name = 'Préfecture de Paris'
+    short_code = 'pref75'
+
+    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 = []
+        
+        # Les RAA de Paris et de l'Île-de-France sont éparpillés sur des sous-pages par mois.
+        # Donc on parse la page principale à la recherche des sous-pages.
+
+        if self.not_before.year <= 2024:
+            year_pages_to_parse.append(self.__RAA_PAGE['2024'])
+        if self.not_before.year <= 2023:
+            year_pages_to_parse.append(self.__RAA_PAGE['2023'])
+        if self.not_before.year <= 2022:
+            year_pages_to_parse.append(self.__RAA_PAGE['2022'])
+        if self.not_before.year <= 2021:
+            year_pages_to_parse.append(self.__RAA_PAGE['2021'])
+        if self.not_before.year <= 2020:
+            year_pages_to_parse.append(self.__RAA_PAGE['2020'])
+        if self.not_before.year <= 2019:
+            year_pages_to_parse.append(self.__RAA_PAGE['2019'])
+
+        print(year_pages_to_parse)
+            
+        pages_to_parse = []
+        for year_page in year_pages_to_parse:
+            page_content = self.get_page(year_page, 'get').content
+            # print(page_content)
+            month_pages = self.get_sub_pages(
+                page_content,
+                'ol li a',
+                self.__HOST,
+                False
+            )[::-1]
+            print(month_pages)
+            for month_page in month_pages:
+                pages_to_parse.append(month_page['url'])
+
+        print(pages_to_parse)
+                
+        
+        elements = []
+        for page in pages_to_parse:
+            page_content = self.get_page(page, 'get').content
+            for element in self.get_raa_elements(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('main div.container.main-container div.col-main article.article div.texte div a.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')
+                guessed = Attrap.guess_date(a.get('href'),"([0-9]+.[0-9]+.[0-9]+)")"([0-9]+.[0-9]+.[0-9]+)")
+                print(guessed)
+                date = datetime.datetime.strptime(guessed, '%d.%m.%Y')
+
+                raa = Attrap.RAA(url, date, name)
+                elements.append(raa)
+        return elements
diff --git a/cli.py b/cli.py
index e40a01f..d3a99e8 100755
--- a/cli.py
+++ b/cli.py
@@ -60,6 +60,7 @@ available_administrations = [
     'pref66',
     'pref69',
     'pref73',
+    'pref75',
     'pref80',
     'pref81',
     'pref83',
-- 
GitLab