choix-spe/datareader.py

import requests, json, jaro, zipfile, os

#Get the name from the web site parcourstup 
r = requests.get("https://ressource.parcoursup.fr/data/files.xml")
name = r.content[102:135].decode()
print(f"https://ressource.parcoursup.fr/data/{name}.zip")

# Download the dataset if it doesn't already exist
if not os.path.exists(name):
    r = requests.get(f"https://ressource.parcoursup.fr/data/{name}.zip")
    with open('data.zip', 'wb') as file:
        file.write(r.content)
    with zipfile.ZipFile('data.zip', 'r') as zip_ref:
        zip_ref.extractall()

# Load database
print("Loading database ...")
with open(name, "r") as file:
    database = json.loads(file.read())

def get_formations(prompt: str):
    indices = [max([(jaro.jaro_winkler_metric(actual_word, word), index) for word, index in database["lexique"]["index"].items()], key=lambda x: x[0])[1] for actual_word in prompt.split()]
    return [f"{formation['nm']} - {list(formation['recS'].keys())[-1]}" for formation in database["formations"].values() if all([str(index) in formation["recW"] for index in indices])]

print(get_formations(input("Votre projet > ")))