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

108 lines
4.1 KiB
Python

#!/usr/bin/env python
# -*- coding: utf-8 -*-
9 years ago
import zipfile
from lxml import etree
import os
import uploader
from iso639 import languages as isoLanguages
def extractCover(zipFile, coverFile, coverpath, tmp_file_name):
if coverFile is None:
9 years ago
return None
else:
zipCoverPath = os.path.join(coverpath , coverFile).replace('\\','/')
cf = zipFile.read(zipCoverPath)
9 years ago
prefix = os.path.splitext(tmp_file_name)[0]
tmp_cover_name = prefix + '.' + os.path.basename(zipCoverPath)
9 years ago
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
}
epubZip = zipfile.ZipFile(tmp_file_path)
9 years ago
txt = epubZip.read('META-INF/container.xml')
9 years ago
tree = etree.fromstring(txt)
cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path', namespaces=ns)[0]
cf = epubZip.read(cfname)
9 years ago
tree = etree.fromstring(cf)
coverpath = os.path.dirname(cfname)
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
9 years ago
epub_metadata = {}
for s in ['title', 'description', 'creator', 'language']:
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"
if epub_metadata['description'] == "Unknown":
description = tree.xpath("//*[local-name() = 'description']/text()")
if len(description) > 0:
epub_metadata['description'] = description
else:
epub_metadata['description'] = ""
if epub_metadata['language'] == "Unknown":
8 years ago
epub_metadata['language'] = ""
else:
lang = epub_metadata['language'].split('-', 1)[0].lower()
if len(lang) == 2:
epub_metadata['language'] = isoLanguages.get(part1=lang).name
elif len(lang) == 3:
epub_metadata['language'] = isoLanguages.get(part3=lang).name
else:
epub_metadata['language'] = ""
9 years ago
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns)
coverfile = None
if len(coversection) > 0:
coverfile = extractCover(epubZip, coversection[0], coverpath, tmp_file_path)
9 years ago
else:
meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns)
if len(meta_cover) > 0:
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns)
if len(coversection) > 0:
filetype = coversection[0].rsplit('.', 1)[-1]
if filetype == "xhtml" or filetype == "html": #if cover is (x)html format
markup = epubZip.read(os.path.join(coverpath, coversection[0]))
markupTree = etree.fromstring(markup)
# no matter xhtml or html with no namespace
imgsrc = markupTree.xpath("//*[local-name() = 'img']/@src")
# imgsrc maybe startwith "../"" so fullpath join then relpath to cwd
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath, coversection[0])), imgsrc[0]))
coverfile = extractCover(epubZip, filename, "", tmp_file_path)
else:
coverfile = extractCover(epubZip, coversection[0], coverpath, tmp_file_path)
8 years ago
9 years ago
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.encode('utf-8').decode('utf-8'),
author=epub_metadata['creator'].encode('utf-8').decode('utf-8'),
cover=coverfile,
description=epub_metadata['description'],
tags="",
series="",
series_id="",
languages=epub_metadata['language'])