drop_weight_rewrite/data_do/读取docx.py

# -*- coding: utf-8 -*-

"""
@Time    :  2023/2/14 14:29
@Author  : 
@FileName: 
@Software: 
@Describe:
"""
# from zipfile import ZipFile
# from bs4 import BeautifulSoup
#
# document=ZipFile("../data/11篇/13139551_于丰源_在线考试系统-原文.docx")
# xml=document.read("word/document.xml")
# wordObj=BeautifulSoup(xml.decode("utf-8"))
# texts=wordObj.findAll("w:t")
# for text in texts:
#   print(text.text)

import docx
import win32com.client as wc
import operator
#doc文件另存为docx

# path = "E:\pycharm_workspace\drop_weight_rewrite\data\\11篇\\13138572_李菊_谈小学语文教学难点与创新-原文.doc"
# path_new = "E:\pycharm_workspace\drop_weight_rewrite\data\\11篇\\13138572_李菊_谈小学语文教学难点与创新-原文.docx"
# word = wc.Dispatch("Word.Application")
# doc = word.Documents.Open(path)
# # 12代表转换后为docx文件
# doc.SaveAs(path_new, 12)
# doc.Close
# word.Quit
#
# #读取转换后的docx
#
# file = docx.Document(path_new)
# for p in file.paragraphs:
#     print(p.text)

# from win32com import client as wc
# w = wc.Dispatch('Word.Application')
# # 或者使用下面的方法，使用启动独立的进程：
# # w = wc.DispatchEx('Word.Application')
# doc=w.Documents.Open(path)
# doc.SaveAs(path_new,16)#必须有参数16，否则会出错.


import os
from win32com import client as wc

def save_doc_to_docx(rawpath):  # doc转docx
    '''
    :param rawpath: 传入和传出文件夹的路径
    :return: None
    '''
    word = wc.Dispatch("Word.Application")
    # 不能用相对路径，老老实实用绝对路径
    # 需要处理的文件所在文件夹目录
    filenamelist = os.listdir(rawpath)
    for i in os.listdir(rawpath):
        # 找出文件中以.doc结尾并且不以~$开头的文件（~$是为了排除临时文件的）
        if i.endswith('.doc') and not i.startswith('~$'):
            print(i)
            # try
            # 打开文件
            doc = word.Documents.Open(rawpath + i)
            # # 将文件名与后缀分割
            rename = os.path.splitext(i)
            # 将文件另存为.docx
            doc.SaveAs(pathls + rename[0] + '.docx', 12)  # 12表示docx格式
            doc.Close()
    word.Quit()


if __name__ == '__main__':
    pathls = "E:\\pycharm_workspace\\drop_weight_rewrite\\data\\11篇\\"
    save_doc_to_docx(pathls)