Djnago rest framework html/url в docx

Я создаю Django API, который конвертирует любой URL или HTML файл в pdf и Docx. Реализованный ниже код уже конвертирует в формат pdf с помощью пакета pdfkit. Я использую python-docx для генерации в Docx, но я не знаю, как с этим работать. Я хотел бы получить любую поддержку, пожалуйста. У меня нет глубоких знаний, и любая помощь будет оценена по достоинству.

Вот мой convert.py файл:

import io
from pydoc import doc
from tempfile import NamedTemporaryFile
from typing import IO
from urllib.parse import urlparse

import pdfkit

from docx import Document


class ConvertingError(Exception):
  """
    This exception represents an error during converting.
    In example, when Host of a url is unreachable.

    In other words, this is a wrapper for wkhtmltopdf errors.
  """
  pass


 def url_to_pdf(url: str) -> IO:
   """Fetch HTML from url and convert the page to pdf,"""
    with NamedTemporaryFile('w+b') as tmpf:
      try:
          pdfkit.from_url(url, tmpf.name)
      except OSError as e:
         raise ConvertingError from e
      pdf = io.BytesIO(tmpf.read())
    return pdf

 def html_to_pdf(html: str) -> IO:
     """Convert HTML string to pdf."""
     with NamedTemporaryFile('w+b') as tmpf:
       try:
          pdfkit.from_string(html, tmpf.name)
       except OSError as e:
          raise ConvertingError from e
       pdf = io.BytesIO(tmpf.read())
     return pdf


 def filename_from_url(url: str) -> str:
   """
      Generate pdf filename using a hostname of a URL.
      If no hostname is provided, return 'default.pdf' as filename.
   """
   parsed = urlparse(URL)
   return (parsed.hostname or 'default') + '.pdf'

 def url_to_docx(url: str) -> IO:
    pass

 def html_to_docx(html: str) -> IO:
    pass

И мой views.py файл

from fileinput import filename
from typing import IO

from django.http import FileResponse
from rest_framework.exceptions import ValidationError
from rest_framework.parsers import MultiPartParser
from rest_framework.viewsets import ViewSet

from .converter import filename_from_url, html_to_pdf, url_to_pdf, ConvertingError, 
  url_to_docx, html_to_docx
from .serializers import HtmlFileInputSerializer, UrlInputSerializer

def generate_from_html(self, request):
   serializer = HtmlFileInputSerializer(data=request.data)
   serializer.is_valid(raise_exception=True)

   file: IO = serializer.validated_data['file']
   content = str(file.read())
   try:
      pdf = html_to_pdf(content)
   except ConvertingError:
      raise ValidationError('The file is of inappropriate type or corrupted.')

   response = FileResponse(pdf)
   response["Content-Type"] = 'application/pdf'
   return response

   def generate_docx_from_html(self, request):
      pass


 # class UrlConverterViewSet(ViewSet):

def generate_from_url(self, request):
    serializer = UrlInputSerializer(data=request.data)
    serializer.is_valid(raise_exception=True)

    url: str = serializer.validated_data['url']
    try:
       pdf = url_to_pdf(URL)
    except ConvertingError:
       raise ValidationError('The url is invalid or unreachable.')
    filename = serializer.validated_data.get('filename') or filename_from_url(URL)

    response = FileResponse(pdf, filename=filename)
    response["Content-Type"] = 'application/pdf'
    return response

def generate_docx_from_url(self, request):
    pass

class GeneratePdf(ViewSet):
    # generate pdf view from html file and URL 
    parser_classes = (MultiPartParser,)

    def create(self, request):
       if request.data.get('file'):
          return generate_from_html(self, request)
       elif request.data.get('url'):
          return generate_from_url(self, request)

       else:
          raise ValidationError('The file or url is invalid or unreachable.')
   

Вернуться на верх