fetch.py

import json
import urllib.request
import unidecode
import pathlib

def slugify(s):
    s = unidecode.unidecode(s).lower().replace(' ', '+')
    return s

def create_dir(d):
    pathlib.Path(d).mkdir(parents=True, exist_ok=True)

def fetch_deputes(group):
    content = urllib.request.urlopen("https://www.nosdeputes.fr/groupe/" + group + "/json").read().decode('utf-8')
    elements = json.loads(content)
    return elements['deputes']

def fetch_interventions(name):
    slug = slugify(name)
    create_dir(slug)
    content = urllib.request.urlopen("https://www.nosdeputes.fr/recherche/?object_name=Intervention&format=json&count=10000&tag=parlementaire=" + slug).read().decode('utf-8')
    elements = json.loads(content)
    for e in elements['results']:
        url = e['document_url']
        urllib.request.urlretrieve(url, slug + '/' + str(e['document_id']))
        
    return elements

groups = ['LREM', 'MODEM', 'UAI', 'NG', 'LR', 'LFI', 'GDR', 'NI']

for g in groups:
    deputes = fetch_deputes(g)
    for d in deputes:
        print(fetch_interventions(d['depute']['nom']))