小工具：从多文件中收集字符串

"""
# reCollectString.py
# 收集指定路径下、指定后缀文件中的匹配字符串，并记录文件名和行号。
# 适用于Python3
# 要处理的文件编码应为：utf-8（无签名）
"""
import os, re

# 要处理的文件所在路径
DIR = "./workDir"
# 要处理的文件后缀列表
EXT = ['.txt', ".md"]
# 输出文件（含路径）
OUT_FILE = "./out.txt"
# 要查找的字符串（正则表达式），请按需设置
r = re.compile(r'\[.*?\]')

with open(OUT_FILE, "w", encoding="utf-8") as outFile:
    filesNum = 1
    for root, __, files in os.walk(DIR):
        lesson_cut_file_list = [x for x in files if os.path.splitext(x)[1] in EXT]
        for file in lesson_cut_file_list:
            with open(os.path.join(root, file), "r", encoding="utf-8") as f:
                # for line in f.readlines():
                for index, line in enumerate(f):
                    lineStrip = line.strip()
                    finds = r.findall(lineStrip)
                    if finds:
                        for i in finds:
                            outLine = "{path}\t{index}\t{string}\n".format(path=os.path.join(root, file), index=index + 1, string=i)
                            if outLine:
                                outFile.write(outLine)
            print(filesNum, "files done.")
            filesNum += 1