python实现Pdf转Word

Python 专栏收录该内容
82 篇文章 16 订阅

python实现Pdf转Word

○ 运行 pip install -i https://pypi.doubanio.com/simple/ -r requirements.txt

○ 将需要转换的pdf文档复制到pdf文件夹

○ 运行 python mian.py

如下图所示:
在这里插入图片描述
全部代码请参考:

未完待续

mian.py 代码:

import os
from configparser import ConfigParser
from io import StringIO
from io import open
from concurrent.futures import ProcessPoolExecutor

from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from docx import Document


def read_from_pdf(file_path):
    with open(file_path, 'rb') as file:
        resource_manager = PDFResourceManager()
        return_str = StringIO()
        lap_params = LAParams()

        device = TextConverter(
            resource_manager, return_str, laparams=lap_params)
        process_pdf(resource_manager, device, file)
        device.close()

        content = return_str.getvalue()
        return_str.close()
        return content


def save_text_to_word(content, file_path):
    doc = Document()
    for line in content.split('\n'):
        paragraph = doc.add_paragraph()
        paragraph.add_run(remove_control_characters(line))
    doc.save(file_path)


def remove_control_characters(content):
    mpa = dict.fromkeys(range(32))
    return content.translate(mpa)


def pdf_to_word(pdf_file_path, word_file_path):
    content = read_from_pdf(pdf_file_path)
    save_text_to_word(content, word_file_path)


def main():
    config_parser = ConfigParser()
    config_parser.read('config.cfg')
    config = config_parser['default']

    tasks = []
    with ProcessPoolExecutor(max_workers=int(config['max_worker'])) as executor:
        for file in os.listdir(config['pdf_folder']):
            extension_name = os.path.splitext(file)[1]
            if extension_name != '.pdf':
                continue
            file_name = os.path.splitext(file)[0]
            pdf_file = config['pdf_folder'] + '/' + file
            word_file = config['word_folder'] + '/' + file_name + '.docx'
            print('正在处理: ', file)
            result = executor.submit(pdf_to_word, pdf_file, word_file)
            tasks.append(result)
    while True:
        exit_flag = True
        for task in tasks:
            if not task.done():
                exit_flag = False
        if exit_flag:
            print('完成')
            exit(0)


if __name__ == '__main__':
    main()
  • 11
    点赞
  • 1
    评论
  • 91
    收藏
  • 一键三连
    一键三连
  • 扫一扫,分享海报

©️2021 CSDN 皮肤主题: 精致技术 设计师:CSDN官方博客 返回首页
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、C币套餐、付费专栏及课程。

余额充值