')
c2.properties.append('rendition:layout-pre-paginated rendition:orientation-landscape rendition:spread-none')
# add all the items
book.add_item(c1)
book.add_item(c2)
book.toc = ( (epub.Section('Languages'),
(c1, c2)),
)
style = '''
@namespace epub "http://www.idpf.org/2007/ops";
body {
font-family: Cambria, Liberation Serif, Bitstream Vera Serif, Georgia, Times, Times New Roman, serif;
}
h2 {
text-align: left;
text-transform: uppercase;
font-weight: 200;
}
ol {
list-style-type: none;
}
ol > li:first-child {
margin-top: 0.3em;
}
nav[epub|type~='toc'] > ol > li > ol {
list-style-type:square;
}
nav[epub|type~='toc'] > ol > li > ol > li {
margin-top: 0.3em;
}
'''
nav_css = epub.EpubItem(uid="style_nav", file_name="style/nav.css", media_type="text/css", content=style)
book.add_item(nav_css)
# this should be maybe add by default or something
book.add_item(epub.EpubNcx())
nav = epub.EpubNav()
nav.add_item(nav_css)
book.add_item(nav)
# this probably is not correct. should be able to define other properties also
book.spine = ['cover', 'nav', c1, c2]
# write book to the file
epub.write_epub('test.epub', book)
print '------------'
for x in nav.get_links_of_type('text/css'):
print x
python-ebooklib-0.15~ds0.orig/tests/epub_parse.py 0000644 0001750 0001750 00000000715 12326461175 022043 0 ustar alessio alessio import sys
import ebooklib
from ebooklib import epub
from ebooklib.utils import debug
book = epub.read_epub(sys.argv[1])
debug(book.metadata)
debug(book.spine)
debug(book.toc)
#for it in book.items:
# debug( it.get_type())
for x in book.get_items_of_type(ebooklib.ITEM_IMAGE):
debug( x)
from ebooklib.plugins import standard, tidyhtml
opts = {'plugins': [standard.SyntaxPlugin(), tidyhtml.TidyPlugin()]}
epub.write_epub('test.epub', book, opts)
python-ebooklib-0.15~ds0.orig/MANIFEST.in 0000644 0001750 0001750 00000000070 12326461175 017732 0 ustar alessio alessio include *.txt
include *.md
recursive-include docs *.txt
python-ebooklib-0.15~ds0.orig/AUTHORS.txt 0000644 0001750 0001750 00000000115 12326461175 020062 0 ustar alessio alessio Aleksandar Erkalovic
Borko Jandras
python-ebooklib-0.15~ds0.orig/docs/ 0000700 0001750 0001750 00000000000 12330427407 017110 5 ustar alessio alessio python-ebooklib-0.15~ds0.orig/docs/modules.rst 0000644 0001750 0001750 00000000073 12326461175 021331 0 ustar alessio alessio Modules
=======
.. toctree::
:maxdepth: 4
ebooklib
python-ebooklib-0.15~ds0.orig/docs/Makefile 0000644 0001750 0001750 00000012704 12326461175 020573 0 ustar alessio alessio # Makefile for Sphinx documentation
#
# You can set these variables from the command line.
SPHINXOPTS =
SPHINXBUILD = sphinx-build
PAPER =
BUILDDIR = _build
# Internal variables.
PAPEROPT_a4 = -D latex_paper_size=a4
PAPEROPT_letter = -D latex_paper_size=letter
ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
# the i18n builder cannot share the environment and doctrees with the others
I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
help:
@echo "Please use \`make ' where is one of"
@echo " html to make standalone HTML files"
@echo " dirhtml to make HTML files named index.html in directories"
@echo " singlehtml to make a single large HTML file"
@echo " pickle to make pickle files"
@echo " json to make JSON files"
@echo " htmlhelp to make HTML files and a HTML help project"
@echo " qthelp to make HTML files and a qthelp project"
@echo " devhelp to make HTML files and a Devhelp project"
@echo " epub to make an epub"
@echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
@echo " latexpdf to make LaTeX files and run them through pdflatex"
@echo " text to make text files"
@echo " man to make manual pages"
@echo " texinfo to make Texinfo files"
@echo " info to make Texinfo files and run them through makeinfo"
@echo " gettext to make PO message catalogs"
@echo " changes to make an overview of all changed/added/deprecated items"
@echo " linkcheck to check all external links for integrity"
@echo " doctest to run all doctests embedded in the documentation (if enabled)"
clean:
-rm -rf $(BUILDDIR)/*
html:
$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
@echo
@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
dirhtml:
$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
@echo
@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
singlehtml:
$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
@echo
@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
pickle:
$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
@echo
@echo "Build finished; now you can process the pickle files."
json:
$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
@echo
@echo "Build finished; now you can process the JSON files."
htmlhelp:
$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
@echo
@echo "Build finished; now you can run HTML Help Workshop with the" \
".hhp project file in $(BUILDDIR)/htmlhelp."
qthelp:
$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
@echo
@echo "Build finished; now you can run "qcollectiongenerator" with the" \
".qhcp project file in $(BUILDDIR)/qthelp, like this:"
@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/EBookLib.qhcp"
@echo "To view the help file:"
@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/EBookLib.qhc"
devhelp:
$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
@echo
@echo "Build finished."
@echo "To view the help file:"
@echo "# mkdir -p $$HOME/.local/share/devhelp/EBookLib"
@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/EBookLib"
@echo "# devhelp"
epub:
$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
@echo
@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
latex:
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
@echo
@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
@echo "Run \`make' in that directory to run these through (pdf)latex" \
"(use \`make latexpdf' here to do that automatically)."
latexpdf:
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
@echo "Running LaTeX files through pdflatex..."
$(MAKE) -C $(BUILDDIR)/latex all-pdf
@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
text:
$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
@echo
@echo "Build finished. The text files are in $(BUILDDIR)/text."
man:
$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
@echo
@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
texinfo:
$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
@echo
@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
@echo "Run \`make' in that directory to run these through makeinfo" \
"(use \`make info' here to do that automatically)."
info:
$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
@echo "Running Texinfo files through makeinfo..."
make -C $(BUILDDIR)/texinfo info
@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
gettext:
$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
@echo
@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
changes:
$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
@echo
@echo "The overview file is in $(BUILDDIR)/changes."
linkcheck:
$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
@echo
@echo "Link check complete; look for any errors in the above output " \
"or in $(BUILDDIR)/linkcheck/output.txt."
doctest:
$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
@echo "Testing of doctests in the sources finished, look at the " \
"results in $(BUILDDIR)/doctest/output.txt."
python-ebooklib-0.15~ds0.orig/docs/ebooklib.rst 0000644 0001750 0001750 00000000745 12326461175 021455 0 ustar alessio alessio ebooklib Package
================
:mod:`ebooklib` Package
-----------------------
.. automodule:: ebooklib
:members:
:undoc-members:
:show-inheritance:
:mod:`epub` Module
------------------
.. automodule:: ebooklib.epub
:members:
:undoc-members:
:show-inheritance:
:mod:`utils` Module
-------------------
.. automodule:: ebooklib.utils
:members:
:undoc-members:
:show-inheritance:
Subpackages
-----------
.. toctree::
ebooklib.plugins
python-ebooklib-0.15~ds0.orig/docs/index.rst 0000644 0001750 0001750 00000001573 12326461175 020776 0 ustar alessio alessio .. EBookLib documentation master file, created by
sphinx-quickstart on Fri Apr 25 11:49:49 2014.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
Welcome to EBookLib's documentation!
====================================
EbookLib is a Python library for managing EPUB2/EPUB3 and Kindle files. It's capable of reading and writing EPUB files programmatically (Kindle support is under development).
The API is designed to be as simple as possible, while at the same time making complex things possible too. It has support for covers, table of contents, spine, guide, metadata and more. EbookLib works with Python 2.7 and Python 3.3.
Homepage: https://github.com/aerkalov/ebooklib/
.. toctree::
:maxdepth: 4
modules
Indices and tables
==================
* :ref:`genindex`
* :ref:`modindex`
* :ref:`search`
python-ebooklib-0.15~ds0.orig/docs/_static/ 0000700 0001750 0001750 00000000000 12326462732 020543 5 ustar alessio alessio python-ebooklib-0.15~ds0.orig/docs/_static/README 0000644 0001750 0001750 00000000115 12326461175 021432 0 ustar alessio alessio For some reason, readthedocs.org expects a docs/_static/ directory to exist.
python-ebooklib-0.15~ds0.orig/docs/conf.py 0000644 0001750 0001750 00000022141 12326461175 020426 0 ustar alessio alessio # -*- coding: utf-8 -*-
#
# EBookLib documentation build configuration file, created by
# sphinx-quickstart on Fri Apr 25 11:49:49 2014.
#
# This file is execfile()d with the current directory set to its containing dir.
#
# Note that not all possible configuration values are present in this
# autogenerated file.
#
# All configuration values have a default; values that are commented out
# serve to show the default.
import sys, os
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
sys.path.insert(0, os.path.abspath('..'))
# -- General configuration -----------------------------------------------------
# If your documentation needs a minimal Sphinx version, state it here.
#needs_sphinx = '1.0'
# Add any Sphinx extension module names here, as strings. They can be extensions
# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
extensions = ['sphinx.ext.autodoc', 'sphinx.ext.doctest', 'sphinx.ext.intersphinx', 'sphinx.ext.todo', 'sphinx.ext.coverage', 'sphinx.ext.viewcode']
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# The suffix of source filenames.
source_suffix = '.rst'
# The encoding of source files.
#source_encoding = 'utf-8-sig'
# The master toctree document.
master_doc = 'index'
# General information about the project.
project = u'EBookLib'
copyright = u'2013, Aleksandar Erkalovic'
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The short X.Y version.
version = '0.15'
# The full version, including alpha/beta/rc tags.
release = '0.15'
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
#language = None
# There are two options for replacing |today|: either, you set today to some
# non-false value, then it is used:
#today = ''
# Else, today_fmt is used as the format for a strftime call.
#today_fmt = '%B %d, %Y'
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
exclude_patterns = ['_build']
# The reST default role (used for this markup: `text`) to use for all documents.
#default_role = None
# If true, '()' will be appended to :func: etc. cross-reference text.
#add_function_parentheses = True
# If true, the current module name will be prepended to all description
# unit titles (such as .. function::).
#add_module_names = True
# If true, sectionauthor and moduleauthor directives will be shown in the
# output. They are ignored by default.
#show_authors = False
# The name of the Pygments (syntax highlighting) style to use.
pygments_style = 'sphinx'
# A list of ignored prefixes for module index sorting.
#modindex_common_prefix = []
# -- Options for HTML output ---------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
html_theme = 'default'
# Theme options are theme-specific and customize the look and feel of a theme
# further. For a list of options available for each theme, see the
# documentation.
#html_theme_options = {}
# Add any paths that contain custom themes here, relative to this directory.
#html_theme_path = []
# The name for this set of Sphinx documents. If None, it defaults to
# " v documentation".
#html_title = None
# A shorter title for the navigation bar. Default is the same as html_title.
#html_short_title = None
# The name of an image file (relative to this directory) to place at the top
# of the sidebar.
#html_logo = None
# The name of an image file (within the static path) to use as favicon of the
# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
# pixels large.
#html_favicon = None
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static']
# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
# using the given strftime format.
#html_last_updated_fmt = '%b %d, %Y'
# If true, SmartyPants will be used to convert quotes and dashes to
# typographically correct entities.
#html_use_smartypants = True
# Custom sidebar templates, maps document names to template names.
#html_sidebars = {}
# Additional templates that should be rendered to pages, maps page names to
# template names.
#html_additional_pages = {}
# If false, no module index is generated.
#html_domain_indices = True
# If false, no index is generated.
#html_use_index = True
# If true, the index is split into individual pages for each letter.
#html_split_index = False
# If true, links to the reST sources are added to the pages.
#html_show_sourcelink = True
# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
#html_show_sphinx = True
# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
#html_show_copyright = True
# If true, an OpenSearch description file will be output, and all pages will
# contain a tag referring to it. The value of this option must be the
# base URL from which the finished HTML is served.
#html_use_opensearch = ''
# This is the file name suffix for HTML files (e.g. ".xhtml").
#html_file_suffix = None
# Output file base name for HTML help builder.
htmlhelp_basename = 'EBookLibdoc'
# -- Options for LaTeX output --------------------------------------------------
latex_elements = {
# The paper size ('letterpaper' or 'a4paper').
#'papersize': 'letterpaper',
# The font size ('10pt', '11pt' or '12pt').
#'pointsize': '10pt',
# Additional stuff for the LaTeX preamble.
#'preamble': '',
}
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title, author, documentclass [howto/manual]).
latex_documents = [
('index', 'EBookLib.tex', u'EBookLib Documentation',
u'Aleksandar Erkalovic', 'manual'),
]
# The name of an image file (relative to this directory) to place at the top of
# the title page.
#latex_logo = None
# For "manual" documents, if this is true, then toplevel headings are parts,
# not chapters.
#latex_use_parts = False
# If true, show page references after internal links.
#latex_show_pagerefs = False
# If true, show URL addresses after external links.
#latex_show_urls = False
# Documents to append as an appendix to all manuals.
#latex_appendices = []
# If false, no module index is generated.
#latex_domain_indices = True
# -- Options for manual page output --------------------------------------------
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
('index', 'ebooklib', u'EBookLib Documentation',
[u'Aleksandar Erkalovic'], 1)
]
# If true, show URL addresses after external links.
#man_show_urls = False
# -- Options for Texinfo output ------------------------------------------------
# Grouping the document tree into Texinfo files. List of tuples
# (source start file, target name, title, author,
# dir menu entry, description, category)
texinfo_documents = [
('index', 'EBookLib', u'EBookLib Documentation',
u'Aleksandar Erkalovic', 'EBookLib', 'Python library for EPUB and Kindle formats.',
'Miscellaneous'),
]
# Documents to append as an appendix to all manuals.
#texinfo_appendices = []
# If false, no module index is generated.
#texinfo_domain_indices = True
# How to display URL addresses: 'footnote', 'no', or 'inline'.
#texinfo_show_urls = 'footnote'
# -- Options for Epub output ---------------------------------------------------
# Bibliographic Dublin Core info.
epub_title = u'EBookLib'
epub_author = u'Aleksandar Erkalovic'
epub_publisher = u'Aleksandar Erkalovic'
epub_copyright = u'2013, Aleksandar Erkalovic'
# The language of the text. It defaults to the language option
# or en if the language is not set.
#epub_language = ''
# The scheme of the identifier. Typical schemes are ISBN or URL.
#epub_scheme = ''
# The unique identifier of the text. This can be a ISBN number
# or the project homepage.
#epub_identifier = ''
# A unique identification for the text.
#epub_uid = ''
# A tuple containing the cover image and cover page html template filenames.
#epub_cover = ()
# HTML files that should be inserted before the pages created by sphinx.
# The format is a list of tuples containing the path and title.
#epub_pre_files = []
# HTML files shat should be inserted after the pages created by sphinx.
# The format is a list of tuples containing the path and title.
#epub_post_files = []
# A list of files that should not be packed into the epub file.
#epub_exclude_files = []
# The depth of the table of contents in toc.ncx.
#epub_tocdepth = 3
# Allow duplicate toc entries.
#epub_tocdup = True
# Example configuration for intersphinx: refer to the Python standard library.
intersphinx_mapping = {'http://docs.python.org/': None}
python-ebooklib-0.15~ds0.orig/docs/ebooklib.plugins.rst 0000644 0001750 0001750 00000001372 12326461175 023132 0 ustar alessio alessio plugins Package
===============
:mod:`base` Module
------------------
.. automodule:: ebooklib.plugins.base
:members:
:undoc-members:
:show-inheritance:
:mod:`booktype` Module
----------------------
.. automodule:: ebooklib.plugins.booktype
:members:
:undoc-members:
:show-inheritance:
:mod:`sourcecode` Module
------------------------
.. automodule:: ebooklib.plugins.sourcecode
:members:
:undoc-members:
:show-inheritance:
:mod:`standard` Module
----------------------
.. automodule:: ebooklib.plugins.standard
:members:
:undoc-members:
:show-inheritance:
:mod:`tidyhtml` Module
----------------------
.. automodule:: ebooklib.plugins.tidyhtml
:members:
:undoc-members:
:show-inheritance:
python-ebooklib-0.15~ds0.orig/CHANGES.TXT 0000644 0001750 0001750 00000000000 12326461175 017636 0 ustar alessio alessio python-ebooklib-0.15~ds0.orig/.gitignore 0000644 0001750 0001750 00000000150 12326461175 020163 0 ustar alessio alessio #ignore these in git listings
EbookLib.egg-info
dist
build
*.pyc
*~
.emacs*
.DS_Store
.swp
\#*#
.#*
\#*
python-ebooklib-0.15~ds0.orig/MANIFEST 0000644 0001750 0001750 00000000132 12326461175 017324 0 ustar alessio alessio # file GENERATED by distutils, do NOT edit
setup.py
ebooklib/__init__.py
ebooklib/epub.py
python-ebooklib-0.15~ds0.orig/ebooklib/ 0000700 0001750 0001750 00000000000 12326462732 017753 5 ustar alessio alessio python-ebooklib-0.15~ds0.orig/ebooklib/epub.py 0000644 0001750 0001750 00000114667 12326461175 021311 0 ustar alessio alessio # This file is part of EbookLib.
# Copyright (c) 2013 Aleksandar Erkalovic
#
# EbookLib is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# EbookLib is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with EbookLib. If not, see .
import sys
import os.path
import zipfile
import io
import six
import mimetypes
import logging
try:
from urllib.parse import unquote
except ImportError:
from urllib import unquote
from lxml import etree
import ebooklib
from ebooklib.utils import parse_string, parse_html_string
# This really should not be here
mimetypes.init()
# Version of EPUB library
VERSION = (0, 15, 0)
NAMESPACES = {'XML': 'http://www.w3.org/XML/1998/namespace',
'EPUB': 'http://www.idpf.org/2007/ops',
'DAISY': 'http://www.daisy.org/z3986/2005/ncx/',
'OPF': 'http://www.idpf.org/2007/opf',
'CONTAINERNS': 'urn:oasis:names:tc:opendocument:xmlns:container',
'DC': "http://purl.org/dc/elements/1.1/",
'XHTML': 'http://www.w3.org/1999/xhtml'}
# XML Templates
CONTAINER_PATH = 'META-INF/container.xml'
CONTAINER_XML = '''
'''
NCX_XML = '''
'''
NAV_XML = ''''''
CHAPTER_XML = ''''''
COVER_XML = '''
'''
IMAGE_MEDIA_TYPES = ['image/jpeg', 'image/jpg', 'image/png', 'image/svg+xml']
## TOC elements
class Section(object):
def __init__(self, title):
self.title = title
class Link(object):
def __init__(self, href, title, uid=None):
self.href = href
self.title = title
self.uid = uid
## Exceptions
class EpubException(Exception):
def __init__(self, code, msg):
self.code = code
self.msg = msg
def __str__(self):
return repr(self.msg)
## Items
class EpubItem(object):
def __init__(self, uid=None, file_name='', media_type='', content=''):
self.id = uid
self.file_name = file_name
self.media_type = media_type
self.content = content
self.is_linear = True
self.book = None
def get_id(self):
return self.id
def get_name(self):
return self.file_name
def get_type(self):
"""
Guess type according to the file extension. Not the best way to do it, but works for now.
"""
_, ext = os.path.splitext(self.get_name())
ext = ext.lower()
for uid, ext_list in six.iteritems(ebooklib.EXTENSIONS):
if ext in ext_list:
return uid
return ebooklib.ITEM_UNKNOWN
def get_content(self, default=''):
return self.content or default
def set_content(self, content):
self.content = content
def __str__(self):
return '' % self.id
class EpubNcx(EpubItem):
def __init__(self, uid='ncx', file_name='toc.ncx'):
super(EpubNcx, self).__init__(uid=uid, file_name=file_name, media_type="application/x-dtbncx+xml")
def __str__(self):
return '' % self.id
class EpubCover(EpubItem):
def __init__(self, uid='cover-img', file_name=''):
super(EpubCover, self).__init__(uid=uid, file_name=file_name)
def __str__(self):
return '' % (self.id, self.file_name)
class EpubHtml(EpubItem):
_template_name = 'chapter'
def __init__(self, uid=None, file_name='', media_type='', content=None, title='', lang=None):
super(EpubHtml, self).__init__(uid, file_name, media_type, content)
self.title = title
self.lang = lang
self.links = []
self.properties = []
def is_chapter(self):
return True
def get_type(self):
return ebooklib.ITEM_DOCUMENT
def set_language(self, lang):
self.lang = lang
def get_language(self):
return self.lang
def add_link(self, **kwgs):
self.links.append(kwgs)
def get_links(self):
return (link for link in self.links)
def get_links_of_type(self, link_type):
return (link for link in self.links if link.get('type', '') == link_type)
def add_item(self, item):
if item.get_type() == ebooklib.ITEM_STYLE:
self.add_link(href=item.get_name(), rel="stylesheet", type="text/css")
if item.get_type() == ebooklib.ITEM_SCRIPT:
self.add_link(href=item.get_name(), type="text/javascript")
def get_body_content(self):
content = self.get_content()
try:
html_tree = parse_html_string(self.content)
except:
return ''
html_root = html_tree.getroottree()
if len(html_root.find('body')) != 0:
body = html_tree.find('body')
tree_str = etree.tostring(body, pretty_print=True, encoding='utf-8', xml_declaration=False)
# this is so stupid
if tree_str.startswith(''):
n = tree_str.rindex('')
return tree_str[7:n]
return tree_str
return ''
def get_content(self, default=None):
tree = parse_string(self.book.get_template(self._template_name))
tree_root = tree.getroot()
tree_root.set('lang', self.lang or self.book.language)
tree_root.attrib['{%s}lang' % NAMESPACES['XML']] = self.lang or self.book.language
# add to the head also
#
try:
html_tree = parse_html_string(self.content)
except:
return ''
html_root = html_tree.getroottree()
# create and populate head
_head = etree.SubElement(tree_root, 'head')
if self.title != '':
_title = etree.SubElement(_head, 'title')
_title.text = self.title
for lnk in self.links:
_lnk = etree.SubElement(_head, 'link', lnk)
# this should not be like this
# head = html_root.find('head')
# if head is not None:
# for i in head.getchildren():
# if i.tag == 'title' and self.title != '':
# continue
# _head.append(i)
# create and populate body
_body = etree.SubElement(tree_root, 'body')
body = html_tree.find('body')
if body is not None:
for i in body.getchildren():
_body.append(i)
tree_str = etree.tostring(tree, pretty_print=True, encoding='utf-8', xml_declaration=True)
return tree_str
def __str__(self):
return '' % (self.id, self.file_name)
class EpubCoverHtml(EpubHtml):
def __init__(self, uid='cover', file_name='cover.xhtml', image_name='', title='Cover'):
super(EpubCoverHtml, self).__init__(uid=uid, file_name=file_name, title=title)
self.image_name = image_name
self.is_linear = False
def is_chapter(self):
return False
def get_content(self):
self.content = self.book.get_template('cover')
tree = parse_string(super(EpubCoverHtml, self).get_content())
tree_root = tree.getroot()
images = tree_root.xpath('//xhtml:img', namespaces={'xhtml': NAMESPACES['XHTML']})
images[0].set('src', self.image_name)
images[0].set('alt', self.title)
tree_str = etree.tostring(tree, pretty_print=True, encoding='utf-8', xml_declaration=True)
return tree_str
def __str__(self):
return '' % (self.id, self.file_name)
class EpubNav(EpubHtml):
def __init__(self, uid='nav', file_name='nav.xhtml', media_type="application/xhtml+xml"):
super(EpubNav, self).__init__(uid=uid, file_name=file_name, media_type=media_type)
def is_chapter(self):
return False
def __str__(self):
return '' % (self.id, self.file_name)
class EpubImage(EpubItem):
def __init__(self):
super(EpubImage, self).__init__()
def get_type(self):
return ebooklib.ITEM_IMAGE
def __str__(self):
return '' % (self.id, self.file_name)
## EpubBook
class EpubBook(object):
def __init__(self):
self.EPUB_VERSION = None
self.reset()
# we should have options here
def reset(self):
"Initialises all needed variables to default values"
self.uid = ''
self.metadata = {}
self.items = []
self.spine = []
self.guide = []
self.toc = []
self.IDENTIFIER_ID = 'id'
self.FOLDER_NAME = 'EPUB'
self._id_html = 0
self._id_image = 0
self._id_static = 0
self.title = ''
self.language = 'en'
self.templates = {'ncx': NCX_XML,
'nav': NAV_XML,
'chapter': CHAPTER_XML,
'cover': COVER_XML}
self.add_metadata('OPF', 'generator', '', {'name': 'generator', 'content': 'Ebook-lib %s' % '.'.join([str(s) for s in VERSION])})
def set_identifier(self, uid):
"Sets unique id for this epub"
self.uid = uid
self.add_metadata('DC', 'identifier', self.uid, {'id': self.IDENTIFIER_ID})
def set_title(self, title):
"Set title. You can set multiple titles."
self.title = title
self.add_metadata('DC', 'title', self.title)
def set_language(self, lang):
"Set language for this epub. You can set multiple languages."
self.language = lang
self.add_metadata('DC', 'language', lang)
def set_cover(self, file_name, content, create_page=True):
"Set cover and create cover document if needed."
# as it is now, it can only be called once
c0 = EpubCover(file_name=file_name)
c0.content = content
self.add_item(c0)
if create_page:
c1 = EpubCoverHtml(image_name=file_name)
self.add_item(c1)
self.add_metadata(None, 'meta', '', {'name': 'cover', 'content': 'cover-img'})
def add_author(self, author, file_as=None, role=None, uid='creator'):
"Add author for this document"
self.add_metadata('DC', 'creator', author, {'id': uid})
if file_as:
self.add_metadata(None, 'meta', file_as, {'refines': '#'+uid,
'property': 'file-as',
'scheme': 'marc:relators'})
if role:
self.add_metadata(None, 'meta', role, {'refines': '#'+uid,
'property': 'role',
'scheme': 'marc:relators'})
def add_metadata(self, namespace, name, value, others = None):
"Add metadata"
if namespace in NAMESPACES:
namespace = NAMESPACES[namespace]
if namespace not in self.metadata:
self.metadata[namespace] = {}
if name not in self.metadata[namespace]:
self.metadata[namespace][name] = []
self.metadata[namespace][name].append(( value, others))
def get_metadata(self, namespace, name):
"Retrieve metadata"
if namespace in NAMESPACES:
namespace = NAMESPACES[namespace]
return self.metadata[namespace][name]
def add_item(self, item):
if item.media_type == '':
(has_guessed, media_type) = mimetypes.guess_type(item.get_name().lower())
if has_guessed:
if media_type is not None:
item.media_type = media_type
else:
item.media_type = has_guessed
else:
item.media_type = 'application/octet-stream'
if not item.get_id():
# make chapter_, image_ and static_ configurable
if isinstance(item, EpubHtml):
item.id = 'chapter_%d' % self._id_html
self._id_html += 1
elif isinstance(item, EpubImage):
item.id = 'image_%d' % self._id_image
self._id_image += 1
else:
item.id = 'static_%d' % self._id_image
self._id_image += 1
item.book = self
self.items.append(item)
return item
def get_item_with_id(self, uid):
for item in self.get_items():
if item.id == uid:
return item
return None
def get_item_with_href(self, href):
for item in self.get_items():
if item.get_name() == href:
return item
return None
def get_items(self):
return (item for item in self.items)
def get_items_of_type(self, item_type):
return (item for item in self.items if item.get_type() == item_type)
def get_items_of_media_type(self, media_type):
return (item for item in self.items if item.media_type == media_type)
def set_template(self, name, value):
self.templates[name] = value
def get_template(self, name):
return self.templates.get(name)
###########################################################################################################
class EpubWriter(object):
DEFAULT_OPTIONS = {'epub2_guide': True,
'epub3_landmark': True,
'landmark_title': 'Guide'
}
def __init__(self, name, book, options = None):
self.file_name = name
self.book = book
self.options = dict(self.DEFAULT_OPTIONS)
if options:
self.options.update(options)
def process(self):
# should cache this html parsing so we don't do it for every plugin
for plg in self.options.get('plugins', []):
if hasattr(plg, 'before_write'):
plg.before_write(self.book)
for item in self.book.get_items():
if isinstance(item, EpubHtml):
for plg in self.options.get('plugins', []):
if hasattr(plg, 'html_before_write'):
plg.html_before_write(self.book, item)
def _write_container(self):
container_xml = CONTAINER_XML % { 'folder_name' : self.book.FOLDER_NAME }
self.out.writestr(CONTAINER_PATH, container_xml)
def _write_opf_file(self):
root = etree.Element('package',
{'xmlns' : NAMESPACES['OPF'],
'unique-identifier' : self.book.IDENTIFIER_ID,
'version' : '3.0'})
root.attrib['prefix'] = 'rendition: http://www.ipdf.org/vocab/rendition/#'
## METADATA
nsmap = {'dc': NAMESPACES['DC'], 'opf': NAMESPACES['OPF']}
# This is really not needed
# problem is uppercase/lowercase
# for ns_name, values in six.iteritems(self.book.metadata):
# if ns_name:
# for n_id, ns_url in six.iteritems(NAMESPACES):
# if ns_name == ns_url:
# nsmap[n_id.lower()] = NAMESPACES[n_id]
metadata = etree.SubElement(root, 'metadata', nsmap = nsmap)
import datetime
el = etree.SubElement(metadata, 'meta', {'property':'dcterms:modified'})
el.text = datetime.datetime.now().strftime('%Y-%m-%dT%H:%M:%SZ')
for ns_name, values in six.iteritems(self.book.metadata):
if ns_name == NAMESPACES['OPF']:
for values in values.values():
for v in values:
try:
el = etree.SubElement(metadata, 'meta', v[1])
if v[0]:
el.text = v[0]
except ValueError:
logging.error('Could not create metadata.')
else:
for name, values in six.iteritems(values):
for v in values:
try:
if ns_name:
el = etree.SubElement(metadata, '{%s}%s' % (ns_name, name), v[1])
else:
el = etree.SubElement(metadata, '%s' % name, v[1])
el.text = v[0]
except ValueError:
logging.error('Could not create metadata "{}".'.format(name))
# MANIFEST
manifest = etree.SubElement(root, 'manifest')
_ncx_id = None
# mathml, scripted, svg, remote-resources, and switch
# nav
# cover-image
for item in self.book.get_items():
if isinstance(item, EpubNav):
etree.SubElement(manifest, 'item', {'href': item.get_name(),
'id': item.id,
'media-type': item.media_type,
'properties': 'nav'})
elif isinstance(item, EpubNcx):
_ncx_id = item.id
etree.SubElement(manifest, 'item', {'href': item.file_name,
'id': item.id,
'media-type': item.media_type})
elif isinstance(item, EpubCover):
etree.SubElement(manifest, 'item', {'href': item.file_name,
'id': item.id,
'media-type': item.media_type,
'properties': 'cover-image'})
else:
opts = {'href': item.file_name,
'id': item.id,
'media-type': item.media_type}
if hasattr(item, 'properties') and len(item.properties) > 0:
opts['properties' ] = ' '.join(item.properties)
etree.SubElement(manifest, 'item', opts)
# SPINE
spine = etree.SubElement(root, 'spine', {'toc': _ncx_id or 'ncx'})
for _item in self.book.spine:
# this is for now
# later we should be able to fetch things from tuple
is_linear = True
if isinstance(_item, tuple):
item = _item[0]
if len(_item) > 1:
if _item[1] == 'no':
is_linear = False
else:
item = _item
if isinstance(item, EpubHtml):
opts = {'idref': item.get_id()}
if not item.is_linear or not is_linear:
opts['linear'] = 'no'
elif isinstance(item, EpubItem):
opts = {'idref': item.get_id()}
if not item.is_linear or not is_linear:
opts['linear'] = 'no'
else:
opts = {'idref': item}
try:
itm = self.book.get_item_with_id(item)
if not itm.is_linear or not is_linear:
opts['linear'] = 'no'
except:
pass
etree.SubElement(spine, 'itemref', opts)
# GUIDE
# - http://www.idpf.org/epub/20/spec/OPF_2.0.1_draft.htm#Section2.6
if len(self.book.guide) > 0 and self.options.get('epub2_guide'):
guide = etree.SubElement(root, 'guide', {})
for item in self.book.guide:
if 'item' in item:
chap = item.get('item')
if chap:
_href = chap.file_name
_title = chap.title
else:
_href = item.get('href', '')
_title = item.get('title', '')
ref = etree.SubElement(guide, 'reference', {'type': item.get('type', ''),
'title': _title,
'href': _href})
tree_str = etree.tostring(root, pretty_print=True, encoding='utf-8', xml_declaration=True)
self.out.writestr('%s/content.opf' % self.book.FOLDER_NAME, tree_str)
def _get_nav(self, item):
# just a basic navigation for now
ncx = parse_string(self.book.get_template('nav'))
root = ncx.getroot()
root.set('lang', self.book.language)
root.attrib['{%s}lang' % NAMESPACES['XML']] = self.book.language
head = etree.SubElement(root, 'head')
title = etree.SubElement(head, 'title')
title.text = self.book.title
# for now this just handles css files and ignores others
for _link in item.links:
_lnk = etree.SubElement(head, 'link', {"href":_link.get('href', ''), "rel":"stylesheet", "type":"text/css"})
body = etree.SubElement(root, 'body')
nav = etree.SubElement(body, 'nav', {'{%s}type' % NAMESPACES['EPUB']: 'toc', 'id': 'id'})
content_title = etree.SubElement(nav, 'h2')
content_title.text = self.book.title
def _create_section(itm, items):
ol = etree.SubElement(itm, 'ol')
for item in items:
if isinstance(item, tuple) or isinstance(item, list):
li = etree.SubElement(ol, 'li')
a = etree.SubElement(li, 'span')
a.text = item[0].title
_create_section(li, item[1])
elif isinstance(item, Link):
li = etree.SubElement(ol, 'li')
a = etree.SubElement(li, 'a', {'href': item.href})
a.text = item.title
elif isinstance(item, EpubHtml):
li = etree.SubElement(ol, 'li')
a = etree.SubElement(li, 'a', {'href': item.file_name})
a.text = item.title
_create_section(nav, self.book.toc)
# LANDMARKS / GUIDE
# - http://www.idpf.org/epub/30/spec/epub30-contentdocs.html#sec-xhtml-nav-def-types-landmarks
if len(self.book.guide) > 0 and self.options.get('epub3_landmark'):
guide_nav = etree.SubElement(body, 'nav', {'{%s}type' % NAMESPACES['EPUB']: 'landmarks'})
guide_content_title = etree.SubElement(guide_nav, 'h2')
guide_content_title.text = self.options.get('landmark_title', 'Guide')
guild_ol = etree.SubElement(guide_nav, 'ol')
for elem in self.book.guide:
li_item = etree.SubElement(guild_ol, 'li')
if 'item' in elem:
chap = elem.get('item', None)
if chap:
_href = chap.file_name
_title = chap.title
else:
_href = elem.get('href', '')
_title = elem.get('title', '')
a_item = etree.SubElement(li_item, 'a', {'{%s}type' % NAMESPACES['EPUB']: elem.get('type', ''), 'href': _href})
a_item.text = _title
tree_str = etree.tostring(root, pretty_print=True, encoding='utf-8', xml_declaration=True)
return tree_str
def _get_ncx(self):
# we should be able to setup language for NCX as also
ncx = parse_string(self.book.get_template('ncx'))
root = ncx.getroot()
head = etree.SubElement(root, 'head')
# get this id
uid = etree.SubElement(head, 'meta', {'content': self.book.uid, 'name': 'dtb:uid'})
uid = etree.SubElement(head, 'meta', {'content': '0', 'name': 'dtb:depth'})
uid = etree.SubElement(head, 'meta', {'content': '0', 'name': 'dtb:totalPageCount'})
uid = etree.SubElement(head, 'meta', {'content': '0', 'name': 'dtb:maxPageNumber'})
doc_title = etree.SubElement(root, 'docTitle')
title = etree.SubElement(doc_title, 'text')
title.text = self.book.title
# doc_author = etree.SubElement(root, 'docAuthor')
# author = etree.SubElement(doc_author, 'text')
# author.text = 'Name of the person'
# For now just make a very simple navMap
nav_map = etree.SubElement(root, 'navMap')
def _create_section(itm, items, uid):
for item in items:
if isinstance(item, tuple) or isinstance(item, list):
section, subsection = item[0], item[1]
np = etree.SubElement(itm, 'navPoint', {'id': 'sep_%d' % uid})
nl = etree.SubElement(np, 'navLabel')
nt = etree.SubElement(nl, 'text')
nt.text = section.title
# CAN NOT HAVE EMPTY SRC HERE
nc = etree.SubElement(np, 'content', {'src': ''})
#uid += 1
uid = _create_section(np, subsection, uid+1)
elif isinstance(item, Link):
_parent = itm
_content = _parent.find('content')
if _content != None:
if _content.get('src') == '':
_content.set('src', item.href)
np = etree.SubElement(itm, 'navPoint', {'id': item.uid})
nl = etree.SubElement(np, 'navLabel')
nt = etree.SubElement(nl, 'text')
nt.text = item.title
nc = etree.SubElement(np, 'content', {'src': item.href})
elif isinstance(item, EpubHtml):
_parent = itm
_content = _parent.find('content')
if _content != None:
if _content.get('src') == '':
_content.set('src', item.file_name)
np = etree.SubElement(itm, 'navPoint', {'id': item.get_id()})
nl = etree.SubElement(np, 'navLabel')
nt = etree.SubElement(nl, 'text')
nt.text = item.title
nc = etree.SubElement(np, 'content', {'src': item.file_name})
return uid
_create_section(nav_map, self.book.toc, 0)
tree_str = etree.tostring(root, pretty_print=True, encoding='utf-8', xml_declaration=True)
return tree_str
def _write_items(self):
for item in self.book.get_items():
if isinstance(item, EpubNcx):
self.out.writestr('%s/%s' % (self.book.FOLDER_NAME, item.file_name), self._get_ncx())
elif isinstance(item, EpubNav):
self.out.writestr('%s/%s' % (self.book.FOLDER_NAME, item.file_name), self._get_nav(item))
else:
self.out.writestr('%s/%s' % (self.book.FOLDER_NAME, item.file_name), item.get_content())
def write(self):
# check for the option allowZip64
self.out = zipfile.ZipFile(self.file_name, 'w', zipfile.ZIP_DEFLATED)
self.out.writestr('mimetype', 'application/epub+zip', compress_type=zipfile.ZIP_STORED)
self._write_container()
self._write_opf_file()
self._write_items()
self.out.close()
###########################################################################################################
class EpubReader(object):
DEFAULT_OPTIONS = {}
def __init__(self, epub_file_name, options = None):
self.file_name = epub_file_name
self.book = EpubBook()
self.zf = None
self.opf_file = ''
self.opf_dir = ''
self.options = dict(self.DEFAULT_OPTIONS)
if options:
self.options.update(options)
def process(self):
# should cache this html parsing so we don't do it for every plugin
for plg in self.options.get('plugins', []):
if hasattr(plg, 'after_read'):
plg.after_read(self.book)
for item in self.book.get_items():
if isinstance(item, EpubHtml):
for plg in self.options.get('plugins', []):
if hasattr(plg, 'html_after_read'):
plg.html_after_read(self.book, item)
def load(self):
self._load()
return self.book
def read_file(self, name):
# Raises KeyError
return self.zf.read(name)
def _load_container(self):
meta_inf = self.read_file('META-INF/container.xml')
tree = parse_string(meta_inf)
for root_file in tree.findall('//xmlns:rootfile[@media-type]', namespaces = {'xmlns': NAMESPACES['CONTAINERNS']}):
if root_file.get('media-type') == "application/oebps-package+xml":
self.opf_file = root_file.get('full-path')
self.opf_dir = os.path.dirname(self.opf_file)
def _load_metadata(self):
container_root = self.container.getroot()
# get epub version
self.book.version = container_root.get('version', None)
# get unique-identifier
if container_root.get('unique-identifier', None):
self.book.IDENTIFIER_ID = container_root.get('unique-identifier')
# get xml:lang
# get metadata
metadata = self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'metadata'))
nsmap = metadata.nsmap
nstags = dict((k, '{%s}' % v) for k, v in six.iteritems(nsmap))
default_ns = nstags.get(None, '')
nsdict = dict((v, {}) for v in nsmap.values())
def add_item(ns, tag, value, extra):
if ns not in nsdict:
nsdict[ns] = {}
values = nsdict[ns].setdefault(tag, [])
values.append((value, extra))
for t in metadata:
if not etree.iselement(t):
continue
if t.tag == default_ns + 'meta':
name = t.get('name')
others = dict((k, v) for k, v in t.items())
if name and ':' in name:
prefix, name = name.split(':', 1)
else:
prefix = None
add_item(t.nsmap.get(prefix, prefix), name, t.text, others)
else:
tag = t.tag[t.tag.rfind('}') + 1:]
if (t.prefix and t.prefix.lower() == 'dc') and tag == 'identifier':
_id = t.get('id', None)
if _id:
self.book.IDENTIFIER_ID = _id
others = dict((k, v) for k, v in t.items())
add_item(t.nsmap[t.prefix], tag, t.text, others)
self.book.metadata = nsdict
titles = self.book.get_metadata('DC', 'title')
if len(titles) > 0:
self.book.title = titles[0][0]
for value, others in self.book.get_metadata("DC", "identifier"):
if others.get("id") == self.book.IDENTIFIER_ID:
self.book.uid = value
def _load_manifest(self):
for r in self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'manifest')):
if r is not None and r.tag != '{%s}item' % NAMESPACES['OPF']:
continue
media_type = r.get('media-type')
_properties = r.get('properties', '')
if _properties:
properties = _properties.split(' ')
else:
properties = []
# people use wrong content types
if media_type == 'image/jpg':
media_type = 'image/jpeg'
if media_type == 'application/x-dtbncx+xml':
ei = EpubNcx(uid=r.get('id'), file_name=unquote(r.get('href')))
ei.content = self.read_file(os.path.join(self.opf_dir, ei.file_name))
elif media_type == 'application/xhtml+xml':
if 'nav' in properties:
ei = EpubNav(uid=r.get('id'), file_name=unquote(r.get('href')))
ei.content = self.read_file(os.path.join(self.opf_dir, r.get('href')))
elif 'cover' in properties:
ei = EpubCoverHtml()
ei.content = self.read_file(os.path.join(self.opf_dir, unquote(r.get('href'))))
else:
ei = EpubHtml()
ei.id = r.get('id')
ei.file_name = unquote(r.get('href'))
ei.media_type = media_type
ei.content = self.read_file(os.path.join(self.opf_dir, ei.get_name()))
ei.properties = properties
elif media_type in IMAGE_MEDIA_TYPES:
if 'cover-image' in properties:
ei = EpubCover(uid=r.get('id'), file_name=unquote(r.get('href')))
ei.media_type = media_type
ei.content = self.read_file(os.path.join(self.opf_dir, ei.get_name()))
else:
ei = EpubImage()
ei.id = r.get('id')
ei.file_name = unquote(r.get('href'))
ei.media_type = media_type
ei.content = self.read_file(os.path.join(self.opf_dir, ei.get_name()))
else:
# different types
ei = EpubItem()
ei.id = r.get('id')
ei.file_name = unquote(r.get('href'))
ei.media_type = media_type
ei.content = self.read_file(os.path.join(self.opf_dir, ei.get_name()))
# r.get('properties')
self.book.add_item(ei)
def _parse_ncx(self, data):
tree = parse_string(data);
tree_root = tree.getroot()
nav_map = tree_root.find('{%s}navMap' % NAMESPACES['DAISY'])
def _get_children(elems, n, nid):
label, content = '', ''
children = []
_id = ''
for a in elems.getchildren():
if a.tag == '{%s}navLabel' % NAMESPACES['DAISY']:
label = a.getchildren()[0].text
if a.tag == '{%s}content' % NAMESPACES['DAISY']:
content = a.get('src')
if a.tag == '{%s}navPoint' % NAMESPACES['DAISY']:
children.append(_get_children(a, n+1, a.get('id', '')))
if len(children) > 0:
if n == 0:
return children
return (Section(label),
children)
else:
return (Link(content, label, nid))
self.book.toc = _get_children(nav_map, 0, '')
def _parse_nav(self, data, base_path):
html_node = parse_html_string(data)
nav_node = html_node.xpath("//nav[@*='toc']")[0]
def parse_list(list_node):
items = []
for item_node in list_node.findall("li"):
sublist_node = item_node.find("ol")
link_node = item_node.find("a")
if sublist_node is not None:
title = item_node[0].text
children = parse_list(sublist_node)
items.append((Section(title), children))
elif link_node is not None:
title = link_node.text
href = os.path.normpath(os.path.join(base_path, link_node.get("href")))
items.append(Link(href, title))
return items
self.book.toc = parse_list(nav_node.find("ol"))
def _load_spine(self):
spine = self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'spine'))
self.book.spine = [(t.get('idref'), t.get('linear', 'yes')) for t in spine]
toc = spine.get('toc', '')
# should read ncx or nav file
if toc:
try:
ncxFile = self.read_file(os.path.join(self.opf_dir, self.book.get_item_with_id(toc).get_name()))
except KeyError:
raise EpubError(-1, 'Can not find ncx file.')
self._parse_ncx(ncxFile)
def _load_guide(self):
guide = self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'guide'))
if guide is not None:
self.book.guide = [{'href': t.get('href'), 'title': t.get('title'), 'type': t.get('type')} for t in guide]
def _load_opf_file(self):
try:
s = self.read_file(self.opf_file)
except KeyError:
raise EpubError(-1, 'Can not find container file')
self.container = parse_string(s)
self._load_metadata()
self._load_manifest()
self._load_spine()
self._load_guide()
# read nav file if found
#
if not self.book.toc:
nav_item = next((item for item in self.book.items if isinstance(item, EpubNav)), None)
if nav_item:
self._parse_nav(nav_item.content, os.path.dirname(nav_item.file_name))
def _load(self):
try:
self.zf = zipfile.ZipFile(self.file_name, 'r', compression = zipfile.ZIP_DEFLATED, allowZip64 = True)
except zipfile.BadZipfile as bz:
raise EpubException(0, 'Bad Zip file')
except zipfile.LargeZipFile as bz:
raise EpubException(1, 'Large Zip file')
# 1st check metadata
self._load_container()
self._load_opf_file()
self.zf.close()
## WRITE
def write_epub(name, book, options = None):
epub = EpubWriter(name, book, options)
epub.process()
try:
epub.write()
except IOError:
pass
## READ
def read_epub(name, options = None):
reader = EpubReader(name, options)
book = reader.load()
reader.process()
return book
python-ebooklib-0.15~ds0.orig/ebooklib/__init__.py 0000644 0001750 0001750 00000002545 12326461175 022104 0 ustar alessio alessio # This file is part of EbookLib.
# Copyright (c) 2013 Aleksandar Erkalovic
#
# EbookLib is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# EbookLib is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with EbookLib. If not, see .
# Version of ebook library
VERSION = (0, 15, 0)
# LIST OF POSSIBLE ITEMS
ITEM_UNKNOWN = 0
ITEM_IMAGE = 1
ITEM_STYLE = 2
ITEM_SCRIPT = 3
ITEM_NAVIGATION = 4
ITEM_VECTOR = 5
ITEM_FONT = 6
ITEM_VIDEO = 7
ITEM_AUDIO = 8
ITEM_DOCUMENT = 9
# EXTENSION MAPPER
EXTENSIONS = {ITEM_IMAGE: ['.jpg', '.jpeg', '.gif', '.tiff', '.tif', '.png'],
ITEM_STYLE: ['.css'],
ITEM_VECTOR: ['.svg'],
ITEM_FONT: ['.otf', '.woff'],
ITEM_SCRIPT: ['.js'],
ITEM_NAVIGATION: ['.ncx'],
ITEM_VIDEO: ['.mov', '.mp4', '.avi'],
ITEM_AUDIO: ['.mp3', '.ogg']
}
python-ebooklib-0.15~ds0.orig/ebooklib/plugins/ 0000700 0001750 0001750 00000000000 12326462732 021434 5 ustar alessio alessio python-ebooklib-0.15~ds0.orig/ebooklib/plugins/sourcecode.py 0000644 0001750 0001750 00000004661 12326461175 024162 0 ustar alessio alessio # This file is part of EbookLib.
# Copyright (c) 2013 Aleksandar Erkalovic
#
# EbookLib is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# EbookLib is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with EbookLib. If not, see .
from ebooklib.plugins.base import BasePlugin
from ebooklib.utils import parse_html_string
class SourceHighlighter(BasePlugin):
def __init__(self):
pass
def html_before_write(self, book, chapter):
from lxml import etree, html
from pygments import highlight
from pygments.formatters import HtmlFormatter
from ebooklib import epub
try:
tree = parse_html_string(chapter.content)
except:
return
root = tree.getroottree()
had_source = False
if len(root.find('body')) != 0:
body = tree.find('body')
# check for embeded source
for source in body.xpath('//pre[contains(@class,"source-")]'):
css_class = source.get('class')
source_text = (source.text or '') + ''.join([html.tostring(child) for child in source.iterchildren()])
if 'source-python' in css_class:
from pygments.lexers import PythonLexer
# _text = highlight(source_text, PythonLexer(), HtmlFormatter(linenos="inline"))
_text = highlight(source_text, PythonLexer(), HtmlFormatter())
if 'source-css' in css_class:
from pygments.lexers import CssLexer
_text = highlight(source_text, CssLexer(), HtmlFormatter())
_parent = source.getparent()
_parent.replace(source, etree.XML(_text))
had_source = True
if had_source:
chapter.add_link(href="style/code.css", rel="stylesheet", type="text/css")
chapter.content = etree.tostring(tree, pretty_print=True, encoding='utf-8')
python-ebooklib-0.15~ds0.orig/ebooklib/plugins/tidyhtml.py 0000644 0001750 0001750 00000004302 12326461175 023655 0 ustar alessio alessio # This file is part of EbookLib.
# Copyright (c) 2013 Aleksandar Erkalovic
#
# EbookLib is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# EbookLib is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with EbookLib. If not, see .
import six
import subprocess
from ebooklib.plugins.base import BasePlugin
from ebooklib.utils import parse_html_string
# Recommend usage of
# - https://github.com/w3c/tidy-html5
def tidy_cleanup(content, **extra):
cmd = []
for k, v in six.iteritems(extra):
cmd.append('--%s' % k)
if v:
cmd.append(v)
# must parse all other extra arguments
try:
p = subprocess.Popen(['tidy']+cmd, shell=False,
stdin=subprocess.PIPE, stdout=subprocess.PIPE,
stderr=subprocess.PIPE, close_fds=True)
except OSError:
return (3, None)
p.stdin.write(content)
(cont, p_err) = p.communicate()
# 0 - all ok
# 1 - there were warnings
# 2 - there were errors
# 3 - exception
return (p.returncode, cont)
class TidyPlugin(BasePlugin):
NAME = 'Tidy HTML'
OPTIONS = {'utf8': None,
'tidy-mark': 'no'
}
def __init__(self, extra = {}):
self.options = dict(self.OPTIONS)
self.options.update(extra)
def html_before_write(self, book, chapter):
if not chapter.content:
return None
(_, chapter.content) = tidy_cleanup(chapter.content, **self.options)
return chapter.content
def html_after_read(self, book, chapter):
if not chapter.content:
return None
(_, chapter.content) = tidy_cleanup(chapter.content, **self.options)
return chapter.content
python-ebooklib-0.15~ds0.orig/ebooklib/plugins/base.py 0000644 0001750 0001750 00000003012 12326461175 022726 0 ustar alessio alessio # This file is part of EbookLib.
# Copyright (c) 2013 Aleksandar Erkalovic
#
# EbookLib is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# EbookLib is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with EbookLib. If not, see .
class BasePlugin(object):
def before_write(self, book):
"Processing before save"
return True
def after_write(self, book):
"Processing after save"
return True
def before_read(self, book):
"Processing before save"
return True
def after_read(self, book):
"Processing after save"
return True
def item_after_read(self, book, item):
"Process general item after read."
return True
def item_before_write(self, book, item):
"Process general item before write."
return True
def html_after_read(self, book, chapter):
"Processing HTML before read."
return True
def html_before_write(self, book, chapter):
"Processing HTML before save."
return True
python-ebooklib-0.15~ds0.orig/ebooklib/plugins/__init__.py 0000644 0001750 0001750 00000000000 12326461175 023545 0 ustar alessio alessio python-ebooklib-0.15~ds0.orig/ebooklib/plugins/booktype.py 0000644 0001750 0001750 00000010627 12326461175 023662 0 ustar alessio alessio # This file is part of EbookLib.
# Copyright (c) 2013 Aleksandar Erkalovic
#
# EbookLib is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# EbookLib is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with EbookLib. If not, see .
from ebooklib.plugins.base import BasePlugin
from ebooklib.utils import parse_html_string
class BooktypeLinks(BasePlugin):
NAME = 'Booktype Links'
def __init__(self, booktype_book):
self.booktype_book = booktype_book
def html_before_write(self, book, chapter):
from lxml import etree
try:
from urlparse import urlparse, urljoin
except ImportError:
from urllib.parse import urlparse, urljoin
try:
tree = parse_html_string(chapter.content)
except:
return
root = tree.getroottree()
if len(root.find('body')) != 0:
body = tree.find('body')
# should also be aware to handle
# ../chapter/
# ../chapter/#reference
# ../chapter#reference
for _link in body.xpath('//a'):
# This is just temporary for the footnotes
if _link.get('href', '').find('InsertNoteID') != -1:
_ln = _link.get('href', '')
i = _ln.find('#')
_link.set('href', _ln[i:]);
continue
_u = urlparse(_link.get('href', ''))
# Let us care only for internal links at the moment
if _u.scheme == '':
if _u.path != '':
_link.set('href', '%s.xhtml' % _u.path)
if _u.fragment != '':
_link.set('href', urljoin(_link.get('href'), '#%s' % _u.fragment))
if _link.get('name') != None:
_link.set('id', _link.get('name'))
etree.strip_attributes(_link, 'name')
chapter.content = etree.tostring(tree, pretty_print=True, encoding='utf-8')
class BooktypeFootnotes(BasePlugin):
NAME = 'Booktype Footnotes'
def __init__(self, booktype_book):
self.booktype_book = booktype_book
def html_before_write(self, book, chapter):
from lxml import etree
from ebooklib import epub
try:
tree = parse_html_string(chapter.content)
except:
return
root = tree.getroottree()
if len(root.find('body')) != 0:
body = tree.find('body')
# 1
#
