RAAspotter_ppparis.py

from bs4 import BeautifulSoup
from urllib.parse import unquote

from RAAspotter import RAAspotter

class RAAspotter_ppparis(RAAspotter):

  def get_raa(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