library/util/convert2pdf.py

#!/usr/bin/python3.6
# -*- coding: utf-8 -*-
# @Time    : 2021/3/15 9:19
# @Author  : lijunliang
# @Email   : lijunliang@topnet.net.cn
# @File    : convert2pdf.py
# @Software: PyCharm

import pdfkit
import subprocess
from loguru import logger
import os


def html2pdf(html: str, pdf_path: str):
    try:
        pdfkit.from_string(html, pdf_path)
    except Exception as e:
        logger.warning("html转pdf失败--->%s" % e)
        return False
    return True


def lib2pdf(file_path: str):
    '''
    doc,docx
    :param file_path: str
    :return:
    '''
    file_path = file_path.strip()
    out_dir = os.path.dirname(file_path)
    try:
        args = 'soffice  --headless --convert-to pdf:writer_pdf_Export %s --outdir %s' % (file_path, out_dir)
        output = subprocess.check_output(args, shell=True)
    except subprocess.CalledProcessError as e:
        logger.warning('转pdf出错---->%s' % e)
        return ''
    filePathList = file_path.split(".")
    filePathList[-1] = "pdf"
    pdfFileName = ".".join(filePathList)
    return pdfFileName


if __name__ == '__main__':
    # pdf_path = "../data/0.pdf"
    # html = open("../data/test.htm", "r").read()
    # pdf_data = html2pdf(html,pdf_path)
    # print(pdf_data)
    file_path = "../data/123.docx"
    pdf = lib2pdf(file_path)
    print(pdf)