calibre-web/cps/fb2.py
OzzieIsaacs 93b19165cf Added polish in readme to supported UI languages
Handling of missing tags in fb import
naming of path is more imitating calibre (replacement of special characters, "pinyining" of author names if unidecode is available )
Sorting of authors (similar to calibre for jr./sr./I..IV endings)
bugfix pathseparator on windows and linux during upload
bugfix os.rename for authordir
publishing date on detailview is formated according to slected locale
filename on downloading from web ui is now correct displayed
added ids to html for testing
2017-02-15 18:09:17 +01:00

62 lines
1.9 KiB
Python

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import etree
import os
import uploader
import StringIO
def get_fb2_info(tmp_file_path, original_file_extension):
ns = {
'fb': 'http://www.gribuser.ru/xml/fictionbook/2.0',
'l': 'http://www.w3.org/1999/xlink',
}
fb2_file = open(tmp_file_path)
tree = etree.fromstring(fb2_file.read())
authors = tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:author', namespaces=ns)
def get_author(element):
last_name = element.xpath('fb:last-name/text()', namespaces=ns)
if len(last_name):
last_name = last_name[0]
else:
last_name = u''
middle_name = element.xpath('fb:middle-name/text()', namespaces=ns)
if len(middle_name):
middle_name = middle_name[0]
else:
middle_name = u''
first_name = element.xpath('fb:first-name/text()', namespaces=ns)
if len(first_name):
first_name = first_name[0]
else:
first_name = u''
return first_name + ' ' + middle_name + ' ' + last_name
author = unicode(", ".join(map(get_author, authors)))
title = tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:book-title/text()', namespaces=ns)
if len(title):
title = unicode(title[0])
else:
title = u''
description = tree.xpath('/fb:FictionBook/fb:description/fb:publish-info/fb:book-name/text()', namespaces=ns)
if len(description):
description = unicode(description[0])
else:
description = u''
return uploader.BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title.encode('utf-8').decode('utf-8'),
author=author.encode('utf-8').decode('utf-8'),
cover=None,
description=description,
tags="",
series="",
series_id="")