/usr/share/pyshared/weboob/tools/parsers/__init__.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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | # -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Christophe Benz, 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 logging
__all__ = ['get_parser', 'NoParserFound']
class NoParserFound(Exception):
pass
def load_lxml():
from .lxmlparser import LxmlHtmlParser
return LxmlHtmlParser
def load_lxmlsoup():
from .lxmlsoupparser import LxmlSoupParser
return LxmlSoupParser
def load_html5lib():
from .html5libparser import Html5libParser
return Html5libParser
def load_elementtidy():
from .elementtidyparser import ElementTidyParser
return ElementTidyParser
def load_builtin():
from .htmlparser import HTMLParser
return HTMLParser
def load_json():
# This parser doesn't read HTML, don't include it in the
# preference_order default value below.
from .jsonparser import JsonParser
return JsonParser
def load_csv():
# This parser doesn't read HTML, don't include it in the
# preference_order default value below.
from .csvparser import CsvParser
return CsvParser
def load_raw():
# This parser doesn't read HTML, don't include it in the
# preference_order default value below.
from .iparser import RawParser
return RawParser
def get_parser(preference_order=('lxml', 'lxmlsoup')):
"""
Get a parser from a preference order list.
This allows Weboob to run on systems without lxml, which is the default parser.
Return a parser implementing IParser.
"""
if not isinstance(preference_order, (tuple, list)):
preference_order = [preference_order]
for kind in preference_order:
if not 'load_%s' % kind in globals():
continue
try:
return globals()['load_%s' % kind]()
except ImportError:
logging.debug('%s is not installed.' % kind)
raise NoParserFound("No parser found (%s)" % ','.join(preference_order))
|