基于Python制作一个词频统计工具的完整指南

python --version

def read_text(file_path):
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            return file.read()
    except FileNotFoundError:
        print("文件未找到，请检查路径！")
        return None

import re

def split_words(text):
    words = re.findall(r'\b\w+\b', text.lower())
    return words

from collections import defaultdict

def count_words(words):
    word_count = defaultdict(int)
    for word in words:
        word_count[word] += 1
    return word_count

def sort_and_print(word_count, top_n=10):
    sorted_words = sorted(word_count.items(), key=lambda x: x[1], reverse=True)
    for word, count in sorted_words[:top_n]:
        print(f"{word}: {count} 次")

def main():
    file_path = input("请输入文本文件路径（如 text.txt）：")
    text = read_text(file_path)
    if text is None:
        return

    words = split_words(text)
    word_count = count_words(words)
    sort_and_print(word_count)

import re
from collections import defaultdict

def read_text(file_path):
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            return file.read()
    except FileNotFoundError:
        print("文件未找到，请检查路径！")
        return None

def split_words(text):
    words = re.findall(r'\b\w+\b', text.lower())
    return words

def count_words(words):
    word_count = defaultdict(int)
    for word in words:
        word_count[word] += 1
    return word_count

def sort_and_print(word_count, top_n=10):
    sorted_words = sorted(word_count.items(), key=lambda x: x[1], reverse=True)
    for word, count in sorted_words[:top_n]:
        print(f"{word}: {count} 次")

def main():
    file_path = input("请输入文本文件路径（如 text.txt）：")
    text = read_text(file_path)
    if text is None:
        return

    words = split_words(text)
    word_count = count_words(words)
    sort_and_print(word_count)

if __name__ == "__main__":
    main()

Python is a great language. Python is easy to learn. Python is powerful.

python word_counter.py

请输入文本文件路径（如 text.txt）：text.txt

python: 3 次
is: 3 次
a: 1 次
great: 1 次
language: 1 次
easy: 1 次
to: 1 次
learn: 1 次
powerful: 1 次

def remove_stopwords(words):
    stopwords = {'a', 'an', 'the', 'is', 'and', 'or'}
    return [word for word in words if word not in stopwords]

import argparse

def parse_args():
    parser = argparse.ArgumentParser(description="词频统计工具")
    parser.add_argument("file_path", help="文本文件路径")
    parser.add_argument("--top", type=int, default=10, help="显示前 N 个高频词")
    return parser.parse_args()

if __name__ == "__main__":
    args = parse_args()
    text = read_text(args.file_path)
    if text is None:
        exit(1)
    words = split_words(text)
    word_count = count_words(words)
    sort_and_print(word_count, args.top)

python word_counter.py text.txt --top 5