2017-01-29 20:06:08 +00:00
|
|
|
#!/usr/bin/env python
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
2016-06-05 19:28:30 +00:00
|
|
|
import zipfile
|
|
|
|
from lxml import etree
|
|
|
|
import os
|
|
|
|
import uploader
|
2017-03-02 14:57:02 +00:00
|
|
|
from iso639 import languages as isoLanguages
|
2016-12-23 08:53:39 +00:00
|
|
|
|
2017-03-31 14:52:25 +00:00
|
|
|
|
|
|
|
def extractCover(zipFile, coverFile, coverpath, tmp_file_name):
|
2016-12-23 08:53:39 +00:00
|
|
|
if coverFile is None:
|
2016-06-05 19:28:30 +00:00
|
|
|
return None
|
|
|
|
else:
|
2017-02-24 19:20:41 +00:00
|
|
|
zipCoverPath = os.path.join(coverpath , coverFile).replace('\\','/')
|
2017-03-31 14:52:25 +00:00
|
|
|
cf = zipFile.read(zipCoverPath)
|
2016-06-05 19:28:30 +00:00
|
|
|
prefix = os.path.splitext(tmp_file_name)[0]
|
2017-02-24 19:20:41 +00:00
|
|
|
tmp_cover_name = prefix + '.' + os.path.basename(zipCoverPath)
|
2016-06-05 19:28:30 +00:00
|
|
|
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 = {
|
2016-12-23 08:53:39 +00:00
|
|
|
'n': 'urn:oasis:names:tc:opendocument:xmlns:container',
|
|
|
|
'pkg': 'http://www.idpf.org/2007/opf',
|
|
|
|
'dc': 'http://purl.org/dc/elements/1.1/'
|
2016-06-05 19:28:30 +00:00
|
|
|
}
|
|
|
|
|
2017-03-31 14:52:25 +00:00
|
|
|
epubZip = zipfile.ZipFile(tmp_file_path)
|
2016-06-05 19:28:30 +00:00
|
|
|
|
2017-03-31 14:52:25 +00:00
|
|
|
txt = epubZip.read('META-INF/container.xml')
|
2016-06-05 19:28:30 +00:00
|
|
|
tree = etree.fromstring(txt)
|
2016-12-23 08:53:39 +00:00
|
|
|
cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path', namespaces=ns)[0]
|
2017-03-31 14:52:25 +00:00
|
|
|
cf = epubZip.read(cfname)
|
2016-06-05 19:28:30 +00:00
|
|
|
tree = etree.fromstring(cf)
|
|
|
|
|
2017-03-31 14:52:25 +00:00
|
|
|
coverpath = os.path.dirname(cfname)
|
2017-02-24 19:20:41 +00:00
|
|
|
|
2016-12-23 08:53:39 +00:00
|
|
|
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
|
2016-06-05 19:28:30 +00:00
|
|
|
|
|
|
|
epub_metadata = {}
|
2017-03-03 04:46:19 +00:00
|
|
|
|
2017-07-31 06:46:29 +00:00
|
|
|
for s in ['title', 'description', 'creator', 'language', 'subject']:
|
2016-12-23 08:53:39 +00:00
|
|
|
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]
|
2016-06-05 19:28:30 +00:00
|
|
|
else:
|
|
|
|
epub_metadata[s] = "Unknown"
|
2017-03-04 07:37:30 +00:00
|
|
|
|
2017-07-31 06:46:29 +00:00
|
|
|
if epub_metadata['subject'] == "Unknown":
|
|
|
|
epub_metadata['subject'] = ''
|
|
|
|
|
2017-03-04 07:37:30 +00:00
|
|
|
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":
|
2017-03-30 19:17:18 +00:00
|
|
|
epub_metadata['language'] = ""
|
2017-03-04 07:37:30 +00:00
|
|
|
else:
|
|
|
|
lang = epub_metadata['language'].split('-', 1)[0].lower()
|
2017-03-02 15:15:15 +00:00
|
|
|
if len(lang) == 2:
|
2017-03-04 07:37:30 +00:00
|
|
|
epub_metadata['language'] = isoLanguages.get(part1=lang).name
|
2017-03-02 15:15:15 +00:00
|
|
|
elif len(lang) == 3:
|
2017-03-04 07:37:30 +00:00
|
|
|
epub_metadata['language'] = isoLanguages.get(part3=lang).name
|
2017-03-02 15:15:15 +00:00
|
|
|
else:
|
2017-03-04 07:37:30 +00:00
|
|
|
epub_metadata['language'] = ""
|
2016-06-05 19:28:30 +00:00
|
|
|
|
2017-02-24 19:20:41 +00:00
|
|
|
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns)
|
2017-03-02 16:27:54 +00:00
|
|
|
coverfile = None
|
2016-12-23 08:53:39 +00:00
|
|
|
if len(coversection) > 0:
|
2017-03-31 14:52:25 +00:00
|
|
|
coverfile = extractCover(epubZip, coversection[0], coverpath, tmp_file_path)
|
2016-06-05 19:28:30 +00:00
|
|
|
else:
|
2017-03-04 07:48:59 +00:00
|
|
|
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:
|
2017-03-31 14:52:25 +00:00
|
|
|
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]))
|
2017-03-04 07:48:59 +00:00
|
|
|
markupTree = etree.fromstring(markup)
|
2017-03-31 14:52:25 +00:00
|
|
|
# no matter xhtml or html with no namespace
|
2017-03-04 07:48:59 +00:00
|
|
|
imgsrc = markupTree.xpath("//*[local-name() = 'img']/@src")
|
2017-03-31 14:52:25 +00:00
|
|
|
# imgsrc maybe startwith "../"" so fullpath join then relpath to cwd
|
2017-03-04 07:48:59 +00:00
|
|
|
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath, coversection[0])), imgsrc[0]))
|
2017-03-31 14:52:25 +00:00
|
|
|
coverfile = extractCover(epubZip, filename, "", tmp_file_path)
|
2017-03-04 07:48:59 +00:00
|
|
|
else:
|
2017-03-31 14:52:25 +00:00
|
|
|
coverfile = extractCover(epubZip, coversection[0], coverpath, tmp_file_path)
|
2017-03-30 19:17:18 +00:00
|
|
|
|
2017-04-23 06:22:10 +00:00
|
|
|
if not epub_metadata['title']:
|
2016-06-05 19:28:30 +00:00
|
|
|
title = original_file_name
|
|
|
|
else:
|
|
|
|
title = epub_metadata['title']
|
|
|
|
|
|
|
|
return uploader.BookMeta(
|
2016-12-23 08:53:39 +00:00
|
|
|
file_path=tmp_file_path,
|
|
|
|
extension=original_file_extension,
|
2017-02-04 13:28:18 +00:00
|
|
|
title=title.encode('utf-8').decode('utf-8'),
|
|
|
|
author=epub_metadata['creator'].encode('utf-8').decode('utf-8'),
|
2016-12-23 08:53:39 +00:00
|
|
|
cover=coverfile,
|
|
|
|
description=epub_metadata['description'],
|
2017-07-31 06:46:29 +00:00
|
|
|
tags=epub_metadata['subject'].encode('utf-8').decode('utf-8'),
|
2016-12-23 08:53:39 +00:00
|
|
|
series="",
|
2017-03-02 11:59:35 +00:00
|
|
|
series_id="",
|
2017-03-04 07:37:30 +00:00
|
|
|
languages=epub_metadata['language'])
|