src/catalogue/management/commands/import_wl.py

   1 # -*- coding: utf-8 -*-
   2
   3 from collections import defaultdict
   4 import json
   5 from urllib.request import urlopen
   6
   7 from django.core.management.base import BaseCommand
   8 from django.core.management.color import color_style
   9 from django.db import transaction
  10 from librarian.dcparser import BookInfo
  11 from librarian import ParseError, ValidationError
  12
  13 from catalogue.models import Book
  14
  15
  16 WL_API = 'http://www.wolnelektury.pl/api/books/'
  17
  18
  19 class Command(BaseCommand):
  20     help = 'Imports XML files from WL.'
  21
  22     def add_arguments(self, parser):
  23         parser.add_argument('-q', '--quiet', action='store_false', dest='verbose', default=True,
  24             help='Less output')
  25
  26     def handle(self, *args, **options):
  27
  28         self.style = color_style()
  29
  30         verbose = options.get('verbose')
  31
  32         # Start transaction management.
  33         transaction.enter_transaction_management()
  34
  35         if verbose:
  36             print('Reading currently managed files (skipping hidden ones).')
  37         slugs = defaultdict(list)
  38         for b in Book.objects.exclude(slug__startswith='.').all():
  39             if verbose:
  40                 print(b.slug)
  41             text = b.materialize().encode('utf-8')
  42             try:
  43                 info = BookInfo.from_bytes(text)
  44             except (ParseError, ValidationError):
  45                 pass
  46             else:
  47                 slugs[info.slug].append(b)
  48
  49         book_count = 0
  50         commit_args = {
  51             "author_name": 'Platforma',
  52             "description": 'Automatycznie zaimportowane z Wolnych Lektur',
  53             "publishable": True,
  54         }
  55
  56         if verbose:
  57             print('Opening books list')
  58         for book in json.load(urlopen(WL_API)):
  59             book_detail = json.load(urlopen(book['href']))
  60             xml_text = urlopen(book_detail['xml']).read()
  61             info = BookInfo.from_bytes(xml_text)
  62             previous_books = slugs.get(info.slug)
  63             if previous_books:
  64                 if len(previous_books) > 1:
  65                     print(self.style.ERROR("There is more than one book "
  66                         "with slug %s:") % info.slug)
  67                 previous_book = previous_books[0]
  68                 comm = previous_book.slug
  69             else:
  70                 previous_book = None
  71                 comm = '*'
  72             print(book_count, info.slug , '-->', comm)
  73             Book.import_xml_text(xml_text, title=info.title[:255],
  74                 slug=info.slug[:128], previous_book=previous_book,
  75                 commit_args=commit_args)
  76             book_count += 1
  77
  78         # Print results
  79         print()
  80         print("Results:")
  81         print("Imported %d books from WL:" % (
  82                 book_count, ))
  83         print()
  84
  85
  86         transaction.commit()
  87         transaction.leave_transaction_management()
  88