两行Python代码实现pdf转word功能

pip install --index https://pypi.mirrors.ustc.edu.cn/simple/ python-office

import office
office.pdf.pdf2docx(file_path = 'test.pdf')

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()

#-*- coding: UTF-8 -*- 
#!/usr/bin/python
#-*- coding: utf-8 -*-
import sys
import importlib
importlib.reload(sys)
from pdfminer.pdfparser import PDFParser,PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import *
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
import os
#设置工作目录文件夹
os.chdir(r'c:/users/dicey/desktop/codes/pdf-docx')
#解析pdf文件函数
def parse(pdf_path):
 fp = open('diya.pdf', 'rb') # 以二进制读模式打开
 # 用文件对象来创建一个pdf文档分析器
 parser = PDFParser(fp)
 # 创建一个PDF文档
 doc = PDFDocument()
 # 连接分析器 与文档对象
 parser.set_document(doc)
 doc.set_parser(parser)
 # 提供初始化密码
 # 如果没有密码 就创建一个空的字符串
 doc.initialize()
 # 检测文档是否提供txt转换，不提供就忽略
 if not doc.is_extractable:
  raise PDFTextExtractionNotAllowed
 else:
  # 创建PDf 资源管理器 来管理共享资源
  rsrcmgr = PDFResourceManager()
  # 创建一个PDF设备对象
  laparams = LAParams()
  device = PDFPageAggregator(rsrcmgr, laparams=laparams)
  # 创建一个PDF解释器对象
  interpreter = PDFPageInterpreter(rsrcmgr, device)
  # 用来计数页面，图片，曲线，figure，水平文本框等对象的数量
  num_page, num_image, num_curve, num_figure, num_TextBoxHorizontal = 0, 0, 0, 0, 0
  # 循环遍历列表，每次处理一个page的内容
  for page in doc.get_pages(): # doc.get_pages() 获取page列表
   num_page += 1 # 页面增一
   interpreter.process_page(page)
   # 接受该页面的LTPage对象
   layout = device.get_result()
   for x in layout:
    if isinstance(x,LTImage): # 图片对象
     num_image += 1
    if isinstance(x,LTCurve): # 曲线对象
     num_curve += 1
    if isinstance(x,LTFigure): # figure对象
     num_figure += 1
    if isinstance(x, LTTextBoxHorizontal): # 获取文本内容
     num_TextBoxHorizontal += 1 # 水平文本框对象增一
     # 保存文本内容
     with open(r'test2.doc', 'a',encoding='utf-8') as f: #生成doc文件的文件名及路径
      results = x.get_text()
      f.write(results)
      f.write('\n')
  print('对象数量：\n','页面数：%s\n'%num_page,'图片数：%s\n'%num_image,'曲线数：%s\n'%num_curve,'水平文本框：%s\n'
    %num_TextBoxHorizontal)

if __name__ == '__main__':
 pdf_path = r'diya.pdf' #pdf文件路径及文件名
 parse(pdf_path)