Skip to content
Extraits de code Groupes Projets
Sélectionner une révision Git
  • main par défaut protégée
  • pref19
2 résultats
Blame Lien permanent
Attrap_pref42.py 3,00 Kio
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
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 






import os
import datetime
import re

from bs4 import BeautifulSoup
from urllib.parse import unquote

from Attrap import Attrap


class Attrap_pref42(Attrap):

    # Config
    hostname = 'https://www.loire.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 de la Loire'
    short_code = 'pref42'
    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):
        year_pages_to_parse = []

        # On détermine quelles pages d'année parser
        year_pages = self.get_sub_pages_with_pager(
            self.raa_page,
            'div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w div.fr-card__body div.fr-card__content h2.fr-card__title a.fr-card__link',
            'ul.fr-pagination__list li a.fr-pagination__link.fr-pagination__link--next.fr-pagination__link--lg-label',
            'div.fr-card.fr-card--horizontal.fr-card--sm.fr-enlarge-link.fr-mb-3w div.fr-card__body div.fr-card__content div.fr-card__end p.fr-card__detail',
            self.hostname
        )
        for year_page in year_pages:
            year = 9999
            try:
                year = int(re.search('([0-9]{4})', year_page['name'], 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'])

        elements = []
        # Pour chaque année, on parse les RAA
        for year_page in year_pages_to_parse:
            page_content = self.get_page(year_page, 'get').content
            for element in self.get_raa_elements(page_content)[::-1]:
                elements.append(element)

        # On parse les 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('div.fr-downloads-group.fr-downloads-group--bordered ul li a'):
            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.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, timezone=self.timezone)
                elements.append(raa)
        return elements