Implement license matcher about gimie HOT 2 CLOSED

import json
import requests

resp = requests.get("https://raw.githubusercontent.com/spdx/license-list-data/main/json/licenses.json")
all_licenses = json.loads(resp.text)

for i, lic in all_licenses['licenses']:
    r = requests.get(lic["detailsUrl"])
    lic["text"] = json.loads(r.text)["licenseText"]

with open('licenses.json', 'w') as fp:
    json.dump(all_licenses, fp)

import json
import pickle
from sklearn.feature_extraction.text import TfidfVectorizer

with open('licenses.json', 'r') as fp:
    all_licenses = json.load(fp)

corpus = [lic['text'] for lic in all_licenses['licenses']]
vectorizer = TfidfVectorizer()
tfidf = vectorizer.fit_transform(corpus)
pickle.dump(vectorizer, open('vectorizer.pickle', 'wb'))
pickle.dump(tfidf, open('tfidf.pickle', 'wb'))