scibs.py

scibs.py

import re

import requests
from bs4 import BeautifulSoup

HOST = 'www.vacances-scientifiques.com'
URI = f'https://{HOST}'
URL = f'{URI}/01-decembre-2022.html?lang=fr'

session = requests.Session()
data = session.get(URL).text
soup = BeautifulSoup(data, 'html.parser')
form = soup.find('form', method='post')
files = []

for input in form.find_all('input'):
    name = input.attrs.get('name')

    if not name:
        continue

    value = input.attrs.get('value', '')

    if (
        name == 'checkbox_1[]'
        and value == 'choix2'
    ):
        continue

    if name == 'email_1':
        value = '[email protected]'

    files.append((name, value))

prepared = requests.Request(
    'POST',
    URL + '#formulaire_formidable-65',
    files=files,
    headers={
        # Some of these are probably automatic, just figured I'd do as much like the browser as possible
        'Host': HOST,
        'Origin': URI,
        'Referer': URL,
        # Added a bunch of random headers, probably only one (or a few) of them is useful
        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:99.0) Gecko/20100101 Firefox/99.0',
        'Cookie': 'adv_search_mode=1; wishlist=0',
        'Upgrade-Insecure-Requests': '1',
        'Sec-Fetch-Dest': 'document',
        'Sec-Fetch-Mode': 'navigate',
        'Sec-Fetch-Site': 'same-origin',
        'Sec-Fetch-User': '?1',
        'Pragma': 'no-cache',
        'Cache-Control': 'no-cache',
    },
).prepare()
prepared.body = re.sub(b'; filename=.*', b'', prepared.body)
prepared.headers['Content-Length'] = str(len(prepared.body))
response = session.send(prepared)

response_soup = BeautifulSoup(response.text, 'html.parser')
assert not response_soup.find('form', method='post')