python filter text files in folder(path match glob rule and content contains specified substring)

search-in-files.py

import os
import re
import glob
import traceback
import chardet
# import threading
from multiprocessing.dummy import Pool as ThreadPool
from operator import is_not
from functools import partial

def re_escape(rule):
    rule = rule.replace('[', r'\[')
    rule = rule.replace(']', r'\]')
    rule = rule.replace('(', r'\(')
    rule = rule.replace(')', r'\)')
    return rule

def file_list(folder, pattern):
    for root, dirnames, filenames in os.walk(folder):
        try:
            rule = os.path.join(re_escape(root), pattern)
            for filename in glob.iglob(rule, recursive=True):
                yield re.sub(r'(^[a-z]\:)([^\\])', r'\1\\\2', filename)
        except Exception as e:
            # import ipdb; ipdb.set_trace()
            traceback.print_exc()
            pass

def all_in(searchs, content):
    if not bool(searchs):
        return False
    is_in = True
    for item in searchs:
        is_in = is_in and item in content
        if not is_in:
            break
    return is_in

def do_search(filename):
    is_found = False
    if os.path.basename(filename) != '__init__.py':
        try:
            with open(filename, 'rb') as f:
                raw_content = f.read()
                # 检测编码
                detected = chardet.detect(raw_content)
                content = ''
                if isinstance(detected, dict) and 'encoding' in detected:
                    encoding = detected['encoding']
                    if encoding is not None:
                        content = raw_content.decode(encoding, 'ignore')
                if all_in(('jquery', 'execute', 'script'), content):
                    # print(filename)
                    is_found = True
                del content
        except Exception as e:
            # import ipdb; ipdb.set_trace()
            traceback.print_exc()
            pass
    if is_found:
        return filename

if __name__ == '__main__':
    folder = r'f:'
    pattern = '*.py'
    files = file_list(folder, pattern)
    tpool = ThreadPool(processes=20)
    # 启动任务
    tresult_proxy = tpool.map_async(do_search, files)
    # 关闭线程池
    tpool.close()
    # 等到线程池所有任务完成
    tpool.join()
    # 获取结果
    result = tresult_proxy.get()
    result = list(filter(partial(is_not, None), result))
    from pprint import pprint
    pprint(result)