# encoding:utf-8
import os
import re
import requests
import zipfile
import xml.dom.minidom

newfile = 'test.docx'


def create(newfile):
  """下载docx文件，并修改后缀为zip"""
  res = requests.get('https://www.cqjbfy.gov.cn/publiccenter/splc/mb/splc_gginfo.asp"""解压zip，并在work/temp/word/document.xml获取文本内容，进行正则替换标签等操作"""
  f = zipfile.ZipFile('test.zip', 'r')
  for file in f.namelist():
    f.extract(file, "temp/")
  
  f = xml.dom.minidom.parse('./temp/word/document.xml')
  
  txt = re.sub(r'</w:t></w:r></w:p>', '\n', f.toxml())
  print re.sub(r'<.*?>', '', txt)

if __name__ == '__main__':
  create(newfile)
  get_txt()