フォルダの中のファイルに日本語を抽出する

[yuhope]

# This is a sample Python script.
import os
import re

# 対象パス<---input please
dir_path: str = "/Users/aoyamanozomu/PycharmProjects/test"


def findAll(dir_path: object) -> object:
    for root, dirs, files in os.walk(dir_path):
        print('directory:', root)
        for subdir in dirs:
            print('sub directory:', os.path.join(root, subdir))
        for file in files:
            print('file :', os.path.join(root, file))
            print_japanese(file)


def print_japanese(filename):
    print(f'File: {filename}')
    with open(dir_path + '/' + filename, 'r') as f:
        content = f.read()
    # find japanese
    pattern = re.compile(r'[\u3000-\u303F\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF]+')
    matches = re.findall(pattern, content)
    for match in matches:
        print(match)


# Press the green button in the gutter to run the script.
if __name__ == '__main__':
    findAll(dir_path)

[drinker]

@yuhope ありがとう