# -*- mode: python; coding: utf-8 -*- # Copyright (C) 2017-2019 by BDE ENS Paris-Saclay # SPDX-License-Identifier: GPL-3.0-or-later import json import urllib.request from django.forms import ModelForm from .scraper import BedetequeScraper class MediaAdminForm(ModelForm): def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) isbn_field = self.fields.get('isbn') if isbn_field: isbn_field.widget.template_name = "media/isbn_button.html" isbn_field.widget.attrs.update({'autofocus': 'autofocus'}) def download_data_bedeteque(self, isbn): """ Download data from bedeteque :return True if success """ scraper = BedetequeScraper() r = scraper.search_by_isbn(isbn) if not r: return False # If results, then take the most accurate data = scraper.scrap_bd_info(r[0]) self.cleaned_data.update(data) return True def download_data_openlibrary(self, isbn): """ Download data from openlibrary :return True if success """ api_url = "https://openlibrary.org/api/books?bibkeys=ISBN:{}" \ "&format=json&jscmd=data".format(isbn) with urllib.request.urlopen(api_url) as url: data = json.loads(url.read().decode()) if data and data['ISBN:' + isbn]: data = data['ISBN:' + isbn] if 'url' in data: # Fill the data self.cleaned_data['external_url'] = data['url'] if 'title' in data: self.cleaned_data['title'] = data['title'] if 'subtitle' in data: self.cleaned_data['subtitle'] = data['subtitle'] if 'number_of_pages' in data: self.cleaned_data['number_of_pages'] = \ data['number_of_pages'] return True return False def clean(self): """ If user fetch ISBN data, then download data before validating the form """ # TODO implement authors, side_identifier if "_continue" in self.request.POST: isbn = self.cleaned_data.get('isbn') if isbn: # ISBN is present, try with bedeteque scrap_result = self.download_data_bedeteque(isbn) if not scrap_result: # Try with OpenLibrary self.download_data_openlibrary(isbn) return super().clean()