# This file is part of EbookLib. # Copyright (c) 2013 Aleksandar Erkalovic # # EbookLib is free software: you can redistribute it and/or modify # it under the terms of the GNU Affero General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # EbookLib is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU Affero General Public License for more details. # # You should have received a copy of the GNU Affero General Public License # along with EbookLib. If not, see . import io import mimetypes from lxml import etree mimetype_initialised = False def debug(obj): import pprint pp = pprint.PrettyPrinter(indent=4) pp.pprint(obj) def parse_string(s): try: tree = etree.parse(io.BytesIO(s.encode('utf-8'))) except: tree = etree.parse(io.BytesIO(s)) return tree def parse_html_string(s): from lxml import html utf8_parser = html.HTMLParser(encoding='utf-8') html_tree = html.document_fromstring(s, parser=utf8_parser) return html_tree def guess_type(extenstion): global mimetype_initialised if not mimetype_initialised: mimetypes.init() mimetypes.add_type('application/xhtml+xml', '.xhtml') mimetype_initialised = True return mimetypes.guess_type(extenstion)