import xlsxwriter
import subprocess
import os
import docx
import sys
import re

def remove_doc_special_tag():
  for filename in os.listdir(path):
    otherName = re.sub("[\s+\!\/_,$%^*(+\"\')]+|[+——()", "",filename) 
    os.rename(os.path.join(path,filename),os.path.join(path,otherName))

path='/Users/cavin/Desktop/files'
for filename in os.listdir(path):
  ...具体逻辑...

if filename.endswith('.doc'):
  subprocess.call('textutil -convert docx {0}'.format(fullname),shell=True)
  fullname=fullname[:-4]+".docx"
  sheetModel= etl_word_files(fullname)#解析文本逻辑
  subprocess.call('rm {0}'.format(fullname),shell=True) #移除转换的文件

doc = docx.Document(fullname)
for para in doc.paragraphs:
  print(para.text)
  ...具体解析逻辑...

workbook = xlsxwriter.Workbook('report_list.xlsx')
worksheet = workbook.add_worksheet('list')
worksheet.write(0,0, '序号') 
worksheet.write(0,1, '姓名') 
worksheet.write(0,2, '性别') 
worksheet.write(0,3, '年龄') 
worksheet.write(0,4, '籍贯') 
worksheet.write(0,5, '目前所在地') 
worksheet.write(0,6, '学历')
worksheet.write(0,7, '学校')
worksheet.write(0,8, '公司')
worksheet.write(0,9, '职位')
worksheet.write(0,10, '文档链接')

worksheet.write(index,10, '=HYPERLINK(\"./'+filename+'\",\"附件\")')