在python中生成pdf文件校验和时排除元数据

我打算在文件上生成一个校验和,然后将校验和作为文件本身的元数据。然而,我面临的问题是,元数据放入文件之前和之后生成的校验和是不同的,我意识到这是因为文件中的元数据发生了更改。这就是我在python 3中对pypdf2所做的:

import os
import sys
import time
import hashlib

from PyPDF2 import PdfFileReader, PdfFileWriter
from PyPDF2.generic import NameObject, createStringObject

1。函数生成文件的md5校验和

def md5_checksum(filePath):
    try:
        with open(filePath, 'rb') as file:
            m = hashlib.md5()
            while True:
                data = file.read(8192)
                if not data:
                    break

                m.update(data)

            return m.hexdigest()
    except IOError:
        print('[ERROR][NOT FOUND]: ' + filePath)
        return 'NULL'
    finally:
        file.close()

2。函数将元数据嵌入到pdf文件中

def embedd_metadata_file(file_in, file_out, metadatas):
    with open(file_in, 'rb') as fin:
        pdf = PdfFileReader(fin)
        writer = PdfFileWriter()
        metadata = writer._info.getObject()
        info = pdf.documentInfo

        for page in range(pdf.getNumPages()):
            writer.addPage(pdf.getPage(page))

        for key in info:
            metadata.update({NameObject(key): createStringObject(info[key])})

        for key in metadatas:
            metadata.update({NameObject(key): createStringObject(str(metadatas[key]))})

        metadata.update({
            NameObject('/Pages'): createStringObject(str(pdf.getNumPages()))
        })

        with open(file_out, 'wb') as fout:
            writer.write(fout)

    fin.close()
    fout.close()

    os.unlink(file_in)
    os.rename(file_out, file_in)

    pdf = PdfFileReader(open(file_in, 'rb'))
    return pdf.getDocumentInfo()

三。调用函数

file = 'example.pdf'
file_in = os.path.join(DIR, file)
file_out = os.path.join(DIR, file + '.OUT.pdf')

checksum = md5_checksum(file_in)
metadata = embedd_metadata_file(file_in, file_out, {
    '/MD5Checksum': checksum,
    '/ISBN': 'xxx-xxxx-xxxxxxx-xxx',
    '/eISBN': 'xxx-xxxx-xxxxxxx-xxx,
    '/Title': 'Blablablabla',
    '/Size': '2.3 MB',
    '/Author': 'Some Author',
    '/Copyright': 'Blabla Blablabla',
    '/Version': '2',
    '/Publisher': 'Blablablabla Blabla'
})

问题是,如何将校验和作为元数据文件而不改变文件本身的校验和?任何帮助我都很感激。