How to Save io.BytesIO pdfrw PDF into Django FileField

问题

What I am trying to do is basically:

Get PDF from URL
Modify it via pdfrw
Store it in memory as a BytesIO obj
Upload it into a Django FileField via Model.objects.create(form=pdf_file, name="Some name")

My issue is that when the create() method runs, it saves all of the fields except for the form.

helpers.py

import io
import tempfile
from contextlib import contextmanager

import requests
import pdfrw


@contextmanager
def as_file(url):
    with tempfile.NamedTemporaryFile(suffix='.pdf') as tfile:
        tfile.write(requests.get(url).content)
        tfile.flush()
        yield tfile.name


def write_fillable_pdf(input_pdf_path, output_pdf_path, data_dict):
    template_pdf = pdfrw.PdfReader(input_pdf_path)

    ## PDF is modified here

    buf = io.BytesIO()
    print(buf.getbuffer().nbytes). # Prints "0"!
    pdfrw.PdfWriter().write(buf, template_pdf)
    buf.seek(0)
    return buf

views.py

from django.core.files import File

class FormView(View):
    def get(self, request, *args, **kwargs):
        form_url = 'http://some-pdf-url.com'

        with as_file(form_url) as temp_form_path:
            submitted_form = write_fillable_pdf(temp_form_path, temp_form_path, {"name": "John Doe"})
            print(submitted_form.getbuffer().nbytes).  # Prints "994782"!
            FilledPDF.objects.create(form=File(submitted_form), name="Test PDF") 
        return render(request, 'index.html', {})

As you can see, print() gives out two different values as the BytesIO is populated, leading me to believe the increase in size means there is actually data in it. Is there a reason it is not saving properly into my django model instance? Also, if anyone knows a more efficient way to do this, please let me know!

回答1:

You can use ContentFile class in your code. I did modification accordingly in your view to save your file in filefield.

from django.core.files.base import ContentFile

class FormView(View):
    def get(self, request, *args, **kwargs):
        form_url = 'http://some-pdf-url.com'

        with as_file(form_url) as temp_form_path:
            submitted_form = write_fillable_pdf(temp_form_path, temp_form_path, {"name": "John Doe"})
            pdf_content = ContentFile(submitted_form.getvalue(), 'sample.pdf')
            FilledPDF.objects.create(form=pdf_content, name="Test PDF") 
        return render(request, 'index.html', {})

You can also use the save method to store file using the ContentFile class.

from django.core.files.base import ContentFile

    class FormView(View):
        def get(self, request, *args, **kwargs):
            form_url = 'http://some-pdf-url.com'

            with as_file(form_url) as temp_form_path:
                submitted_form = write_fillable_pdf(temp_form_path, temp_form_path, {"name": "John Doe"})
                pdf_content = ContentFile(submitted_form.getvalue())
                filled_pdf = FilledPDF()
                filled_pdf.name = "Test PDF"
                filled_pdf.form.save("sample.pdf", pdf_content, save=False)
                filled_pdf.save()
            return render(request, 'index.html', {})

回答2:

Here's the documentation on how to save a file to an object.

from django.core.files import File

filled_pdf = FilledPDF()
filled_pdf.form.save('test_pdf.pdf', File(submitted_form.getvalue()), save=True)

来源：https://stackoverflow.com/questions/60175556/how-to-save-io-bytesio-pdfrw-pdf-into-django-filefield

标签

python

django

pdf

bytesio

pdfrw