pdf_title_image/doc2pdf.py

#!/usr/bin/python
# -*- coding=utf-8 -*-
# @Create Time:		2024-08-22 14:50:03
# @Last Modified time: 2024-12-02 16:58:14
import logging
import subprocess

from win32com.client import Dispatch, constants, gencache


def doc2pdf(src: str, dst: str):
    if os.path.exists(dst):
        return True

    word = Dispatch('Word.Application')
    # word = gencache.EnsureDispatch('Word.Application')
    try:
        # 打开文件
        doc = word.Documents.Open(src, ReadOnly=1)
        # 转换文件
        # doc.ExportAsFixedFormat(dst,
        #                         constants.wdExportFormatPDF,
        #                         Item=constants.wdExportDocumentWithMarkup,
        #                         CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
        doc.SaveAs(f'{dst}.pdf', 17)
        doc.Close()
        logging.info('转换成功')
    except Exception:
        doc.Close()
        logging.exception("转换失败")
    finally:
        word.Quit(constants.wdDoNotSaveChanges)


def doc2pdf_linux(src: str, dst: str):
    """
    允许的文档格式：doc，docx
    需要在linux中下载好libreoffice
    """
    #  注意cmd中的libreoffice要和linux中安装的一致
    cmd = 'libreoffice --headless --convert-to pdf'.split() + [src] + ['--outdir'] + [dst]
    # cmd = 'libreoffice6.2 --headless --convert-to pdf'.split() + [src]
    p = subprocess.Popen(cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
    p.wait(timeout=30)  # 停顿30秒等待转化
    stdout, stderr = p.communicate()
    if stderr:
        raise subprocess.SubprocessError(stderr)


if __name__ == '__main__':
    import os
    from glob import glob

    # for wordpath in glob('./data/0预审查初审详审测试数据/*/*.doc*'):
    for wordpath in glob('./工程量清单（含采购文件和技术规范）/*/*/*.doc*'):
        wordpath = os.path.abspath(wordpath)
        filename = ''.join(wordpath.split('\\')[-1].split('.')[:-1])
        pdfpath = os.path.join('\\'.join(wordpath.split('\\')[:-2]), filename)
        pdfpath = os.path.abspath(pdfpath)
        print(wordpath)
        print(pdfpath)
        doc2pdf(wordpath, pdfpath)