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 from util import makedirs
  17
  18
  19 class GandalfEpub(packagers.EpubPackager):
  20     cover = cover.GandalfCover
  21
  22
  23 class GandalfPdf(packagers.PdfPackager):
  24     cover = cover.GandalfCover
  25
  26
  27 class BookotekaEpub(packagers.EpubPackager):
  28     cover = cover.BookotekaCover
  29
  30
  31 class PrestigioEpub(packagers.EpubPackager):
  32     cover = cover.PrestigioCover
  33     flags = ('less-advertising',)
  34
  35
  36 class PrestigioPdf(packagers.PdfPackager):
  37     cover = cover.PrestigioCover
  38     flags = ('less-advertising',)
  39
  40
  41 class Virtualo(packagers.Packager):
  42     @staticmethod
  43     def utf_trunc(text, limit):
  44         """ truncates text to at most `limit' bytes in utf-8 """
  45         if text is None:
  46             return text
  47         if len(text.encode('utf-8')) > limit:
  48             newlimit = limit - 3
  49             while len(text.encode('utf-8')) > newlimit:
  50                 text = text[:(newlimit - len(text.encode('utf-8'))) / 4]
  51             text += '...'
  52         return text
  53
  54     @classmethod
  55     def prepare(cls, input_filenames, output_dir='', verbose=False):
  56         from lxml import etree
  57         from librarian import DirDocProvider, ParseError
  58         from librarian.parser import WLDocument
  59         from copy import deepcopy
  60         import os.path
  61
  62         xml = etree.fromstring("""<?xml version="1.0" encoding="utf-8"?>
  63             <products xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"></products>""")
  64         product = etree.fromstring("""<product>
  65                 <publisherProductId></publisherProductId>
  66                 <title></title>
  67                 <info></info>
  68                 <description></description>
  69                 <authors>
  70                     <author>
  71                         <names>Jan</names>
  72                         <lastName>Kowalski</lastName>
  73                     </author>
  74                 </authors>
  75                 <price>0.0</price>
  76                 <language>PL</language>
  77             </product>""")
  78
  79         try:
  80             for main_input in input_filenames:
  81                 if verbose:
  82                     print main_input
  83                 path, fname = os.path.realpath(main_input).rsplit('/', 1)
  84                 provider = DirDocProvider(path)
  85                 slug, ext = os.path.splitext(fname)
  86
  87                 outfile_dir = os.path.join(output_dir, slug)
  88                 makedirs(os.path.join(output_dir, slug))
  89
  90                 doc = WLDocument.from_file(main_input, provider=provider)
  91                 info = doc.book_info
  92
  93                 product_elem = deepcopy(product)
  94                 product_elem[0].text = cls.utf_trunc(slug, 100)
  95                 product_elem[1].text = cls.utf_trunc(info.title, 255)
  96                 product_elem[2].text = cls.utf_trunc(info.description, 255)
  97                 product_elem[3].text = cls.utf_trunc(info.source_name, 3000)
  98                 product_elem[4][0][0].text = cls.utf_trunc(u' '.join(info.author.first_names), 100)
  99                 product_elem[4][0][1].text = cls.utf_trunc(info.author.last_name, 100)
 100                 xml.append(product_elem)
 101
 102                 cover.VirtualoCover(info).save(os.path.join(outfile_dir, slug+'.jpg'))
 103                 outfile = os.path.join(outfile_dir, '1.epub')
 104                 outfile_sample = os.path.join(outfile_dir, '1.sample.epub')
 105                 doc.save_output_file(doc.as_epub(), output_path=outfile)
 106                 doc.save_output_file(doc.as_epub(doc, sample=25), output_path=outfile_sample)
 107                 outfile = os.path.join(outfile_dir, '1.mobi')
 108                 outfile_sample = os.path.join(outfile_dir, '1.sample.mobi')
 109                 doc.save_output_file(doc.as_mobi(cover=cover.VirtualoCover), output_path=outfile)
 110                 doc.save_output_file(
 111                     doc.as_mobi(doc, cover=cover.VirtualoCover, sample=25),
 112                     output_path=outfile_sample)
 113         except ParseError, e:
 114             print '%(file)s:%(name)s:%(message)s' % {
 115                 'file': main_input,
 116                 'name': e.__class__.__name__,
 117                 'message': e.message
 118             }
 119
 120         xml_file = open(os.path.join(output_dir, 'import_products.xml'), 'w')
 121         xml_file.write(etree.tostring(xml, pretty_print=True, encoding=unicode).encode('utf-8'))
 122         xml_file.close()