python word转pdf图片格式

import os
import sys
from PIL import Image
from docx2pdf import convert
from PyPDF2 import PdfFileReader, PdfFileWriter

# Convert word document to pdf
input_file = 'example.docx'
output_file = 'example.pdf'
convert(input_file, output_file)

# Convert pdf to png images
input_pdf = 'example.pdf'
output_folder = 'output_images'
if not os.path.exists(output_folder):
    os.makedirs(output_folder)

with open(input_pdf, 'rb') as pdf_file:
    pdf_reader = PdfFileReader(pdf_file)
    for page_num in range(pdf_reader.getNumPages()):
        page = pdf_reader.getPage(page_num)
        page_obj = page['/Resources']['/XObject'].getObject()
        if page_obj['/Subtype'] == '/Image':
            size = (page_obj['/Width'], page_obj['/Height'])
            data = page_obj.getData()
            mode = ''
            if page_obj['/ColorSpace'] == '/DeviceRGB':
                mode = 'RGB'
            else:
                mode = 'P'
            image = Image.frombytes(mode, size, data)
            output_path = os.path.join(output_folder, f'page{page_num}.png')
            image.save(output_path)

pip install PyPDF2 Pillow docx2pdf