/usr/share/pyshared/weboob/tools/parsers/html5libparser.py is in python-weboob-core 0.g-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | # -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Romain Bignon, Christophe Benz
#
# This file is part of weboob.
#
# weboob 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.
#
# weboob 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 weboob. If not, see <http://www.gnu.org/licenses/>.
from html5lib import treebuilders, HTMLParser
try:
from xml.etree import cElementTree as ElementTree
except ImportError:
from xml.etree import ElementTree
from .iparser import IParser
__all__ = ['Html5libParser']
class Html5libParser(HTMLParser, IParser):
"""
Parser using html5lib.
Note that it is not available on every systems.
"""
# Default implementation for each type of API.
defaults = {'etree': ElementTree}
def __init__(self, api='etree'):
# if no default implementation is defined for this api, set it to None
# to let getTreeBuilder() using the corresponding implementation.
implementation = self.defaults.get(api, None)
HTMLParser.__init__(self, tree=treebuilders.getTreeBuilder(api, implementation))
def parse(self, data, encoding):
return HTMLParser.parse(self, data, encoding=encoding)
def tostring(self, element):
return element.toxml()
|