Commit a2c8fb9bcd189d6b9ed9c5f3a1c5cd2edf5b290e
Committed by
Philippe Lagadec
Philippe Lagadec
1 parent
014d3b47
Start creating parser for xls files e.g. for finding dde links
Showing
1 changed file
with
98 additions
and
0 deletions
oletools/xls_parser.py
0 → 100644
| 1 | +""" Parse xls up to some point | ||
| 2 | + | ||
| 3 | +Read storages, (sub-)streams, records from xls file | ||
| 4 | +""" | ||
| 5 | +# | ||
| 6 | +# === LICENSE ================================================================== | ||
| 7 | + | ||
| 8 | +# xls_parser is copyright (c) 2014-2017 Philippe Lagadec (http://www.decalage.info) | ||
| 9 | +# All rights reserved. | ||
| 10 | +# | ||
| 11 | +# Redistribution and use in source and binary forms, with or without modification, | ||
| 12 | +# are permitted provided that the following conditions are met: | ||
| 13 | +# | ||
| 14 | +# * Redistributions of source code must retain the above copyright notice, this | ||
| 15 | +# list of conditions and the following disclaimer. | ||
| 16 | +# * Redistributions in binary form must reproduce the above copyright notice, | ||
| 17 | +# this list of conditions and the following disclaimer in the documentation | ||
| 18 | +# and/or other materials provided with the distribution. | ||
| 19 | +# | ||
| 20 | +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND | ||
| 21 | +# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED | ||
| 22 | +# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE | ||
| 23 | +# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE | ||
| 24 | +# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL | ||
| 25 | +# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR | ||
| 26 | +# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | ||
| 27 | +# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, | ||
| 28 | +# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | ||
| 29 | +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | ||
| 30 | + | ||
| 31 | +from __future__ import print_function | ||
| 32 | + | ||
| 33 | +#------------------------------------------------------------------------------ | ||
| 34 | +# CHANGELOG: | ||
| 35 | +# 2017-11-02 v0.01 CH: - first version | ||
| 36 | + | ||
| 37 | +__version__ = '0.1' | ||
| 38 | + | ||
| 39 | +#------------------------------------------------------------------------------ | ||
| 40 | +# TODO: | ||
| 41 | +# everything | ||
| 42 | +# | ||
| 43 | +#------------------------------------------------------------------------------ | ||
| 44 | +# REFERENCES: | ||
| 45 | +# - [MS-XLS]: Excel Binary File Format (.xls) Structure Specification | ||
| 46 | +# https://msdn.microsoft.com/en-us/library/office/cc313154(v=office.14).aspx | ||
| 47 | +# - Understanding the Excel .xls Binary File Format | ||
| 48 | +# https://msdn.microsoft.com/en-us/library/office/gg615597(v=office.14).aspx | ||
| 49 | +# | ||
| 50 | +#--- IMPORTS ------------------------------------------------------------------ | ||
| 51 | + | ||
| 52 | +import sys | ||
| 53 | + | ||
| 54 | +# little hack to allow absolute imports even if oletools is not installed. | ||
| 55 | +# Copied from olevba.py | ||
| 56 | +_thismodule_dir = os.path.normpath(os.path.abspath(os.path.dirname(__file__))) | ||
| 57 | +_parent_dir = os.path.normpath(os.path.join(_thismodule_dir, '..')) | ||
| 58 | +if not _parent_dir in sys.path: | ||
| 59 | + sys.path.insert(0, _parent_dir) | ||
| 60 | + | ||
| 61 | +from oletools.thirdparty import olefile | ||
| 62 | + | ||
| 63 | + | ||
| 64 | +class XlsFile(olefile.OleFileIO): | ||
| 65 | + """ specialization of an OLE compound file """ | ||
| 66 | + | ||
| 67 | + def get_streams_recursive(self, storage=None): | ||
| 68 | + """ find all streams in all storages, depth-first """ | ||
| 69 | + if storage is None: | ||
| 70 | + storage = self | ||
| 71 | + print('Finding streams in ole file') | ||
| 72 | + for st in storage.listdir(streams=True, storages=True): | ||
| 73 | + st_type = self.get_type(st) | ||
| 74 | + if st_type == olefile.STGTY_STREAM: # a stream --> yield | ||
| 75 | + print('Checking stream {0}'.format(st)) | ||
| 76 | + yield st | ||
| 77 | + elif st_type == olefile.STGTY_STORAGE: # a storage --> recurse | ||
| 78 | + print('Recurse into storage {0}'.format(st)) | ||
| 79 | + for entry in self.get_streams_recursive(st): | ||
| 80 | + yield entry | ||
| 81 | + else: | ||
| 82 | + raise ValueError('unexpected type {0} for entry {1}' | ||
| 83 | + .format(st_type, st)) | ||
| 84 | + | ||
| 85 | + | ||
| 86 | +class XlsStream: | ||
| 87 | + """ specialization of an OLE (sub-)stream """ | ||
| 88 | + pass | ||
| 89 | + | ||
| 90 | + | ||
| 91 | +def test(filename): | ||
| 92 | + """ parse given file and print rough structure """ | ||
| 93 | + pass | ||
| 94 | + | ||
| 95 | +if __name__ == '__main__': | ||
| 96 | + """ parse all given file names and print rough structure """ | ||
| 97 | + for filename in sys.argv[1:]: | ||
| 98 | + test(filename) |