遍历目录正则匹配文本.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# Copyright © 2021, All rights reserved.
# Author: Eric <wendachen@flickering.ai>

from pathlib import Path
import re
import json

dir_path = '/Users/har/Documents/Github/online-tools'
match_list = []
pattern = "\"(https://cdn.jsdelivr.net/.*?)\""
for file in Path(dir_path).rglob("*"):
    if file.is_dir():
        continue
    is_in_hide_folder = False
    for p in file.parents:
        if p.name.startswith('.'):
            is_in_hide_folder = True
            break
    if is_in_hide_folder:
        continue

    try:
        with open(file, "r+", encoding='utf-8') as f:
            origin_data = f.read()
            match_list += re.findall(pattern, origin_data)
    except UnicodeDecodeError:
        continue
print(list(set(match_list)))