[Python]借助python-docx进行文档的自动化金融数字脱敏并保留原格式

最新推荐文章于 2024-09-11 21:00:20 发布

鲸落914315

最新推荐文章于 2024-09-11 21:00:20 发布

阅读量927

点赞数 1

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/xiaohundan127/article/details/90672984

博客提到一份完整的116页文档处理大概需4秒，但存在很多for循环，代码美观度欠佳，主要围绕文档处理和代码形式展开。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

这份是比较完整的版本，116页的文档大概4秒左右，但是有很多for循环，大概是很不美观了。

# coding=utf8

import os
import re
import datetime
from win32com import client
from docx import Document
import pywintypes


CommaNumberPattern = re.compile(u'\d{1,3}([,，]\d\d\d)*([.]\d\d)')
NumberPattern = re.compile(u'[0-9]')


def doc_to_docx(path):

    filenames = os.listdir(path)
    doc_filenames = [os.path.join(path, filename) for filename in filenames if os.path.splitext(filename)[1] == '.doc']

    if len(doc_filenames) != 0:
        for doc_file in doc_filenames:
            try:
                word = client.Dispatch('Word.Application')
                doc = word.Documents.Open(doc_file)
                doc.SaveAs(os.path.splitext(doc_file)[0] + ".docx", 16)
                doc.Close()
                word.Quit()
                os.remove(doc_file)
            except pywintypes.com_error:
                print(doc_file, '文件异常，请手动转换')


def replace_comma_number(file_path, file_out_path):
    document = Document(file_path)
    for paragraph in document.paragraphs:
        for inline in paragraph.runs:
            if not re.search(CommaNumberPattern, inline.text) is None:
                inline.text = re.sub(NumberPattern, '1', inline.text)

    for table in document.tables:
        for row in table.rows:
            for cell in row.cells:
                cell_text = ''.join([paragraph.text for paragraph in cell.paragraphs])
                if re.search(CommaNumberPattern, cell_text):
                    for inline in cell.paragraphs[0].runs:
                        inline.text = re.sub(NumberPattern, '1', inline.text)

    document.save(file_out_path)


if __name__ == "__main__":

    path = 'C:\\Users\\cn190441\\PycharmProjects\\KPMG_NLP\\Num_replace\\original_doc'
    out_path = 'C:\\Users\\cn190441\\PycharmProjects\\KPMG_NLP\\Num_replace\\output'

    doc_to_docx(path)
    filenames = os.listdir(path)

    time = datetime.datetime.now()
    print('There is {} files in all.'.format(len(filenames)))
    for file in filenames:
        replace_comma_number(os.path.join(path, file), os.path.join(out_path, file))
    print('Time Consumption: {}'.format(datetime.datetime.now() - time))