/usr/share/pyshared/weboob/tools/parsers/iparser.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 54 55 56 57 58 59 60 61 62 63 | # -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Romain Bignon
#
# 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/>.
import re
__all__ = ['IParser', 'RawParser']
class IParser(object):
def parse(self, data, encoding=None):
"""
Parse a HTML document with a specific encoding to get a tree.
@param data [str] HTML document
@param encoding [str] encoding to use
@return an object with the structured document
"""
raise NotImplementedError()
def tostring(self, elem):
"""
Get HTML string from an element.
"""
raise NotImplementedError()
def tocleanstring(self, elem):
"""
Get a clean string from an element.
"""
return self.strip(self.tostring(elem))
def strip(self, data):
"""
Strip a HTML string.
"""
p = re.compile(r'<.*?>')
return p.sub(' ', data).strip()
class RawParser(IParser):
def parse(self, data, encoding=None):
return data.read()
def tostring(self, elem):
return elem
|