Newer
Older
import os
import datetime
from bs4 import BeautifulSoup
from urllib.parse import unquote
import logging
from Attrap import Attrap
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
class Attrap_pref94(Attrap):
# Config
__HOST = 'https://www.val-de-marne.gouv.fr'
__RAA_PAGE = f'{__HOST}/Publications/Publications-legales/RAA-Recueil-des-actes-administratifs'
__USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0'
full_name = 'Préfecture du Val-de-Marne'
short_code = 'pref94'
def __init__(self, data_dir):
super().__init__(data_dir, self.__USER_AGENT)
self.enable_tor(10)
def get_raa(self, keywords):
elements = []
page_content = self.get_page(self.__RAA_PAGE, 'get').content
for sub_page in self.get_sub_pages(
page_content,
'div.fr-card__body div.fr-card__content h2.fr-card__title a',
self.__HOST,
False
):
if Attrap.guess_date(sub_page['name'], '([0-9]{4})$').year >= self.not_before.year:
sub_page_content = self.get_page(sub_page['url'], 'get').content
for element in self.get_raa_elements(sub_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('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