Most common words from WhatsApp export

main.py

from collections import Counter
import re
import nltk
from nltk.corpus import stopwords
import re

import ssl

try:
    _create_unverified_https_context = ssl._create_unverified_context
except AttributeError:
    pass
else:
    ssl._create_default_https_context = _create_unverified_https_context
nltk.download('stopwords')

def load_text_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        text = file.read()
    text = re.sub(r"^\d{2}\/\d{2}\/\d{4}, \d{2}:\d{2} - [\w -]+:", "", text, flags=re.M)
    text = re.sub(r"<Media omitted>", "", text)
    text = re.sub(r"(?:https?://)?(?:[\w]+\.)(?:\.?[\w]{2,})+", "", text)
    return text

def find_most_common_words(text, n):
    words = re.findall(r'\b\w+\b', text.lower())
    stop_words = set(stopwords.words('english'))
    filtered_words = [word for word in words if word not in stop_words]
    word_counts = Counter(filtered_words)
    most_common_words = word_counts.most_common(n)
    return most_common_words

if __name__ == "__main__":
    text = load_text_file("corpus.txt")
    common_words = find_most_common_words(text, 50)

    print(f"\nTop 50 most common words (excluding stop words):")
    for word, count in common_words:
        print(f"{word}: {count}")