librarian/partners.py

   1 # -*- coding: utf-8 -*-
   2 #
   3 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
   4 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
   5 #
   6
   7 """
   8 Classes for packaging ebooks for some old partners.
   9 These should be removed from librarian to separate package,
  10 along with custom cover images etc.
  11
  12 New partners shouldn't be added here, but in the partners repository.
  13 """
  14
  15 from librarian import packagers, cover
  16
  17 class GandalfEpub(packagers.EpubPackager):
  18     cover = cover.GandalfCover
  19
  20 class GandalfPdf(packagers.PdfPackager):
  21     cover = cover.GandalfCover
  22
  23 class BookotekaEpub(packagers.EpubPackager):
  24     cover = cover.BookotekaCover
  25
  26 class PrestigioEpub(packagers.EpubPackager):
  27     cover = cover.PrestigioCover
  28     flags = ('less-advertising',)
  29
  30 class PrestigioPdf(packagers.PdfPackager):
  31     cover = cover.PrestigioCover
  32     flags = ('less-advertising',)
  33
  34
  35 class Virtualo(packagers.Packager):
  36     @staticmethod
  37     def utf_trunc(text, limit):
  38         """ truncates text to at most `limit' bytes in utf-8 """
  39         if text is None:
  40             return text
  41         if len(text.encode('utf-8')) > limit:
  42             newlimit = limit - 3
  43             while len(text.encode('utf-8')) > newlimit:
  44                 text = text[:(newlimit - len(text.encode('utf-8'))) / 4]
  45             text += '...'
  46         return text
  47
  48     @classmethod
  49     def prepare(cls, input_filenames, output_dir='', verbose=False):
  50         from lxml import etree
  51         from librarian import DirDocProvider, ParseError
  52         from librarian.parser import WLDocument
  53         from copy import deepcopy
  54         import os
  55         import os.path
  56
  57         xml = etree.fromstring("""<?xml version="1.0" encoding="utf-8"?>
  58             <products xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"></products>""")
  59         product = etree.fromstring("""<product>
  60                 <publisherProductId></publisherProductId>
  61                 <title></title>
  62                 <info></info>
  63                 <description></description>
  64                 <authors>
  65                     <author>
  66                         <names>Jan</names>
  67                         <lastName>Kowalski</lastName>
  68                     </author>
  69                 </authors>
  70                 <price>0.0</price>
  71                 <language>PL</language>
  72             </product>""")
  73
  74         try:
  75             for main_input in input_filenames:
  76                 if verbose:
  77                     print main_input
  78                 path, fname = os.path.realpath(main_input).rsplit('/', 1)
  79                 provider = DirDocProvider(path)
  80                 slug, ext = os.path.splitext(fname)
  81
  82                 outfile_dir = os.path.join(output_dir, slug)
  83                 os.makedirs(os.path.join(output_dir, slug))
  84
  85                 doc = WLDocument.from_file(main_input, provider=provider)
  86                 info = doc.book_info
  87
  88                 product_elem = deepcopy(product)
  89                 product_elem[0].text = cls.utf_trunc(slug, 100)
  90                 product_elem[1].text = cls.utf_trunc(info.title, 255)
  91                 product_elem[2].text = cls.utf_trunc(info.description, 255)
  92                 product_elem[3].text = cls.utf_trunc(info.source_name, 3000)
  93                 product_elem[4][0][0].text = cls.utf_trunc(u' '.join(info.author.first_names), 100)
  94                 product_elem[4][0][1].text = cls.utf_trunc(info.author.last_name, 100)
  95                 xml.append(product_elem)
  96
  97                 cover.VirtualoCover(info).save(os.path.join(outfile_dir, slug+'.jpg'))
  98                 outfile = os.path.join(outfile_dir, '1.epub')
  99                 outfile_sample = os.path.join(outfile_dir, '1.sample.epub')
 100                 doc.save_output_file(doc.as_epub(),
 101                         output_path=outfile)
 102                 doc.save_output_file(doc.as_epub(doc, sample=25),
 103                         output_path=outfile_sample)
 104                 outfile = os.path.join(outfile_dir, '1.mobi')
 105                 outfile_sample = os.path.join(outfile_dir, '1.sample.mobi')
 106                 doc.save_output_file(doc.as_mobi(cover=cover.VirtualoCover),
 107                         output_path=outfile)
 108                 doc.save_output_file(
 109                         doc.as_mobi(doc, cover=cover.VirtualoCover, sample=25),
 110                         output_path=outfile_sample)
 111         except ParseError, e:
 112             print '%(file)s:%(name)s:%(message)s' % {
 113                 'file': main_input,
 114                 'name': e.__class__.__name__,
 115                 'message': e.message
 116             }
 117
 118         xml_file = open(os.path.join(output_dir, 'import_products.xml'), 'w')
 119         xml_file.write(etree.tostring(xml, pretty_print=True, encoding=unicode).encode('utf-8'))
 120         xml_file.close()