python doc转换成docx以及读取docx

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

# encoding=utf-8
import os
from shutil import copy
from win32com import client as wc

path_from_ = r"告"
path_to_ = r"新"


def doc_2_docx(path_from, path_to):
    """
    pass
    """
    word = wc.gencache.EnsureDispatch('kwps.application')
    files = os.listdir(path_from)
    for file in files:
        file_suf = file.split('.')
        if file_suf[1] == 'doc':
            filepath = path_from + '/' + file
            filepath_new = path_to + '/' + file_suf[0]+'.docx'
            doc = word.Documents.Open(filepath)
            doc.SaveAs2(filepath_new, 12)
            doc.Close()
        else:
            filepath = path_from + '/' + file
            filepath_new = path_to + '/' + file
            copy(filepath, filepath_new)

    word.Quit()


if __name__ == '__main__':
    doc_2_docx(path_from_, path_to_)

# -*- coding: utf-8 -*-
import os
import docx

path_from = r"新"

files = os.listdir(path_from)
for file in files:
    filepath = path_from + '/' + file
    doc = docx.Document(filepath)
    para_num = 0
    for para in doc.paragraphs:
        print(para.text)
        para_num += 1
        print('****************************************************')
    for i in range(len(doc.paragraphs)):
        print(str(i), doc.paragraphs[i].text)
    print('This document has ', para_num, ' paragraphs')

    break