RAAspotter_ppparis.py

from bs4 import BeautifulSoup
from urllib.parse import unquote

from RAAspotter import RAAspotter

class RAAspotter_ppparis(RAAspotter):

  # Config
  __RAA_PAGE     = 'https://www.prefecturedepolice.interieur.gouv.fr/actualites-et-presse/arretes/accueil-arretes'
  __WAIT_ELEMENT = 'block-decree-list-block'
  __USER_AGENT   = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'

  def __init__(self, data_dir):
    super().__init__(data_dir)
    self.user_agent = self.__USER_AGENT

  def get_raa(self, keywords):
    self.print_output('RAAspotter_ppparis')
    self.print_output(f'Termes recherchés: {keywords}')

    page_content = self.get_session()
    raa_elements = self.get_raa_elements(page_content)
    self.parse_raa(raa_elements, keywords.split(','))

  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.find_all('a', href=True):
      if a['href'].endswith('.pdf'):
        if a['href'].startswith('/'):
          url = 'https://www.prefecturedepolice.interieur.gouv.fr'+a['href']
        else:
          url = a['href']

        name = a.find('span').get_text()
        date = a.find('div', class_="field--type-datetime").get_text()

        filename = unquote(url.split('/')[-1])

        raa = RAAspotter.RAA(url, date, name, filename)
        elements.append(raa)
    return elements

  def get_session(self):
    return super().get_session(self.__RAA_PAGE, self.__WAIT_ELEMENT)