Newer
Older
import os
import datetime
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
class Attrap_pref64(Attrap):
# Config
__HOST = 'https://www.pyrenees-atlantiques.gouv.fr'
__RAA_PAGE = {
'2024': f'{__HOST}/Publications/Recueil-des-actes-administratifs/Annee-2024',
'2023': f'{__HOST}/Publications/Recueil-des-actes-administratifs/Annee-2023',
'2022': f'{__HOST}/Publications/Recueil-des-actes-administratifs/Annee-2022',
'2021': f'{__HOST}/Publications/Recueil-des-actes-administratifs/Annee-2021',
'2020': f'{__HOST}/Publications/Recueil-des-actes-administratifs/Annee-2020',
'2019': f'{__HOST}/Publications/Recueil-des-actes-administratifs/Annee-2019'
}
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
full_name = 'Préfecture des Pyrénées-Atlantiques'
short_code = 'pref64'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
def get_raa(self, keywords):
year_pages_to_parse = []
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'])
pages_to_parse = []
# Pour chaque année, on cherche les sous-pages de mois
for year_page in year_pages_to_parse:
page_content = self.get_page(year_page, 'get').content
month_pages = self.get_sub_pages(
page_content,
'.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
)[::-1]
# Pour chaque page de mois, on récupère les liens vers des pages de RAA
for month_page in month_pages:
raa_links = self.get_sub_pages_with_pager(
month_page['url'],
'div.content-view-line div.class-file h2 a',
'ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next',
None,
self.__HOST
)[::-1]
# Pour chaque lien vers un RAA, on filtre ceux ne correspondant pas à la période analysée
for raa_link in raa_links:
guessed_date = Attrap.guess_date(raa_link['name'], 'n°[ 0-9-]* du ([0-9]*(?:er)? [a-zéû]* [0-9]*)')
if guessed_date >= self.not_before:
pages_to_parse.append(raa_link['url'])
# On parse les pages contenant des RAA
elements = []
for page in pages_to_parse:
page_content = self.get_page(page, 'get').content
for raa in self.get_raa_elements(page_content):
elements.append(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