使用Python将.doc转换为.pdf

我曾经使用该解决方案，但需要搜索所有.docx、.dotm、.docm、.odt、.doc或.rtf文件，然后将它们全部转换为.pdf（使用Python 3.7.5版本）。希望这能够起作用...

import os
import win32com.client

wdFormatPDF = 17

for root, dirs, files in os.walk(r'your directory here'):
    for f in files:

        if  f.endswith(".doc")  or f.endswith(".odt") or f.endswith(".rtf"):
            try:
                print(f)
                in_file=os.path.join(root,f)
                word = win32com.client.Dispatch('Word.Application')
                word.Visible = False
                doc = word.Documents.Open(in_file)
                doc.SaveAs(os.path.join(root,f[:-4]), FileFormat=wdFormatPDF)
                doc.Close()
                word.Quit()
                word.Visible = True
                print ('done')
                os.remove(os.path.join(root,f))
                pass
            except:
                print('could not open')
                # os.remove(os.path.join(root,f))
        elif f.endswith(".docx") or f.endswith(".dotm") or f.endswith(".docm"):
            try:
                print(f)
                in_file=os.path.join(root,f)
                word = win32com.client.Dispatch('Word.Application')
                word.Visible = False
                doc = word.Documents.Open(in_file)
                doc.SaveAs(os.path.join(root,f[:-5]), FileFormat=wdFormatPDF)
                doc.Close()
                word.Quit()
                word.Visible = True
                print ('done')
                os.remove(os.path.join(root,f))
                pass
            except:
                print('could not open')
                # os.remove(os.path.join(root,f))
        else:
            pass

使用try和except是为了那些我无法读取的文档，它不会退出代码直到最后一个文档。

你应该从调查所谓的虚拟 PDF 打印驱动程序开始。一旦你找到了一个，你就应该能够编写批处理文件，将你的 DOC 文件打印成 PDF 文件。你可能也可以用 Python 来做这个（设置打印机驱动程序输出并在 MSWord 中发出文档/打印命令，后者可以使用命令行 AFAIR）。

import docx2txt
from win32com import client

import os

files_from_folder = r"c:\\doc"

directory = os.fsencode(files_from_folder)

amount = 1

word = client.DispatchEx("Word.Application")
word.Visible = True

for file in os.listdir(directory):
    filename = os.fsdecode(file)
    print(filename)

    if filename.endswith('docx'):
        text = docx2txt.process(os.path.join(files_from_folder, filename))

        print(f'{filename} transfered ({amount})')
        amount += 1
        new_filename = filename.split('.')[0] + '.txt'

        try:
            with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
                t.write(text)
        except:
            os.mkdir(files_from_folder + r'\txt_files')
            with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
                t.write(text)
    elif filename.endswith('doc'):
        doc = word.Documents.Open(os.path.join(files_from_folder, filename))
        text = doc.Range().Text
        doc.Close()

        print(f'{filename} transfered ({amount})')
        amount += 1
        new_filename = filename.split('.')[0] + '.txt'

        try:
            with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
                t.write(text)
        except:
            os.mkdir(files_from_folder + r'\txt_files')
            with open(os.path.join(files_from_folder + r'\txt_files', new_filename), 'w', encoding='utf-8') as t:
                t.write(text)
word.Quit()

源代码，请见此处：

https://neculaifantanaru.com/en/python-full-code-how-to-convert-doc-and-docx-files-to-pdf-from-the-folder.html

我建议您忽略您的主管，使用具有Python API的OpenOffice。 OpenOffice内置了对Python的支持，并且有人为此创建了一个特定的库（PyODConverter）。
如果他对输出不满意，请告诉他用Word可能需要花费您数周的时间。