Newer
Older
import os
import re
import datetime
import logging
from bs4 import BeautifulSoup
from urllib.parse import unquote
from Attrap import Attrap
logger = logging.getLogger(__name__)
class Attrap_pref33(Attrap):
# Config
__HOST = 'https://www.gironde.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Recueil-des-Actes-Administratifs'
__USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; rv:109.0) Gecko/20100101 Firefox/115.0'
full_name = 'Préfecture de la Gironde'
short_code = 'pref33'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.set_sleep_time(30)
26
27
28
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
102
103
104
105
106
107
108
def get_raa(self, keywords):
pages_to_parse = []
# Parfois un RAA est mal catégorisé et se retrouve sur la page racine, donc on la parse
pages_to_parse.append(self.__RAA_PAGE)
# On détermine quelles pages d'année parser
year_pages_to_parse = []
page_content = self.get_page(self.__RAA_PAGE, 'get').content
year_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
)
for year_page in year_pages:
year = 9999
try:
year = int(re.search('.*([0-9]{4})', year_page['name'].strip(), re.IGNORECASE).group(1))
if year is None:
year = 9999
except Exception as exc:
logger.warning(f"Impossible de deviner l\'année de la page {year_page['name']}")
year = 9999
if year >= self.not_before.year:
year_pages_to_parse.append(year_page['url'])
# Pour chaque année, on cherche les sous-pages de mois
month_pages_to_parse = []
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]
for month_page in month_pages:
guessed_date = Attrap.guess_date(month_page['name'], '([a-zéû]* [0-9]{4})')
if guessed_date >= self.not_before.replace(day=1):
pages_to_parse.append(month_page['url'])
# On parse les pages sélectionnées
elements = self.get_raa_with_pager(
pages_to_parse,
"ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next.fr-pagination__link--lg-label",
self.__HOST
)[::-1]
self.parse_raa(elements, keywords)
self.mailer()
def get_raa_elements(self, page_content):
elements = []
# On récupère chaque carte avec un RAA
for card in BeautifulSoup(page_content, 'html.parser').select('div.fr-card.fr-card--horizontal div.fr-card__body div.fr-card__content'):
# On récupère le lien
links = card.select('h2.fr-card__title a.fr-card__link.menu-item-link')
# On récupère la date
dates_raw = card.select('div.fr-card__end p.fr-card__detail')
# Si on a toutes les infos, on continue
if links and links[0] and dates_raw and dates_raw[0]:
a = links[0]
date_raw = dates_raw[0]
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.get_text().strip()
date = datetime.datetime.strptime(date_raw.get_text().replace('Publié le', '').strip(), '%d/%m/%Y')
raa = Attrap.RAA(url, date, name)
elements.append(raa)
return elements