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/fb2.py

40 lines
1.3 KiB
Python

#!/usr/bin/env python
# -*- coding: utf-8 -*-
8 years ago
from lxml import etree
import os
import uploader
# ToDo: Check usage of original_file_name
8 years ago
def get_fb2_info(tmp_file_path, original_file_name, original_file_extension):
ns = {
'fb': 'http://www.gribuser.ru/xml/fictionbook/2.0',
'l': 'http://www.w3.org/1999/xlink',
8 years ago
}
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)
8 years ago
def get_author(element):
return element.xpath('fb:first-name/text()', namespaces=ns)[0] + ' ' + element.xpath('fb:middle-name/text()',
namespaces=ns)[0] + ' ' + element.xpath('fb:last-name/text()', namespaces=ns)[0]
8 years ago
author = ", ".join(map(get_author, authors))
title = unicode(tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:book-title/text()', namespaces=ns)[0])
description = unicode(tree.xpath('/fb:FictionBook/fb:description/fb:publish-info/fb:book-name/text()',
namespaces=ns)[0])
8 years ago
return uploader.BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title,
author=author,
cover=None,
description=description,
tags="",
series="",
8 years ago
series_id="")