You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
parallel-library/cps/epub.py

69 lines
2.0 KiB
Python

#!/usr/bin/env python
# -*- coding: utf-8 -*-
9 years ago
import zipfile
from lxml import etree
import os
import uploader
9 years ago
def extractCover(zip, coverFile, tmp_file_name):
if coverFile is None:
9 years ago
return None
else:
cf = zip.read("OPS/" + coverFile)
prefix = os.path.splitext(tmp_file_name)[0]
tmp_cover_name = prefix + "." + coverFile
image = open(tmp_cover_name, 'wb')
image.write(cf)
image.close()
return tmp_cover_name
def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
ns = {
'n': 'urn:oasis:names:tc:opendocument:xmlns:container',
'pkg': 'http://www.idpf.org/2007/opf',
'dc': 'http://purl.org/dc/elements/1.1/'
9 years ago
}
zip = zipfile.ZipFile(tmp_file_path)
txt = zip.read('META-INF/container.xml')
tree = etree.fromstring(txt)
cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path', namespaces=ns)[0]
9 years ago
cf = zip.read(cfname)
tree = etree.fromstring(cf)
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
9 years ago
epub_metadata = {}
for s in ['title', 'description', 'creator']:
tmp = p.xpath('dc:%s/text()' % s, namespaces=ns)
if len(tmp) > 0:
epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0]
9 years ago
else:
epub_metadata[s] = "Unknown"
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover']/@href", namespaces=ns)
if len(coversection) > 0:
9 years ago
coverfile = extractCover(zip, coversection[0], tmp_file_path)
else:
coverfile = None
if epub_metadata['title'] is None:
title = original_file_name
else:
title = epub_metadata['title']
return uploader.BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title,
author=epub_metadata['creator'],
cover=coverfile,
description=epub_metadata['description'],
tags="",
series="",
9 years ago
series_id="")