I wrote a Python script to scrape and convert to JSON the most common words in German and French from the legal codex of the Canton Bern (Belex). Adding this content for a lawmakers remix of the FastType game by Solomon Shalom Lijo. Try it above! Click on the yellow tab to switch modes.

from collections import Counter
import string
import re

# Load text file
file_path = "belex-fr.txt"
with open(file_path, "r") as file:
    text = file.read()

# Remove punctuation
text = re.sub(f"[{string.punctuation}]", "", text)

# Tokenize the text
tokens = text.split()

# Remove short words
tokens = [word for word in tokens if len(word)>6]

tokens1w = []
tokens1l = []
for word in tokens:
    if not word.lower() in tokens1l:
        tokens1w.append(word)
        tokens1l.append(word.lower)


# Create a dictionary with word frequencies
word_freq = Counter(tokens1w)

# Print the dictionary
print(word_freq)

Counter({'autorités': 106, 'communes': 89, 'Conseil': 81, 'Conseilexécutif': 71, 'données': 44, 'peuvent': 39, 'Constitution': 36, 'bernoises': 36, 'Recueil': 35, 'personne': 34, 'personnes': 33, 'prestations': 31, 'membres': 31, 'officiel': 31, 'cantonales': 30, 'présente': 27, 'législation': 26, 'dautres': 26, 'publication': 26, 'vigueur': 24, 'cantonale': 22, 'ressources': 22, 'électoral': 21, 'publiques': 21, 'liberté': 20, 'compétences': 20, 'protection': 20, 'populaire': 19, 'législatifs': 19, 'mesures': 18, 'surveillance': 18, 'dispositions': 18, 'Confédération': 17, 'cantonal': 17, 'manière': 17, 'législatif': 17, 'particulier': 16, 'notamment': 16, 'traitement': 16, 'ladministration': 16, 'larticle': 16, 'électronique': 16, ...

del word_freq.most_common()[0]
del word_freq.most_common()[1]
del word_freq.most_common()[2]

words = [k for k,i in word_freq.most_common() if i<50]
words

['données',
 'peuvent',
 'Constitution',
 'bernoises',
 'Recueil',
 'personne',

...

import json
output_json = "franz.json"
with open(output_json, "w", encoding="utf-8") as json_file:
    json.dump(words, json_file, indent=4)