olemeta.py
4.66 KB
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
#!/usr/bin/env python
"""
olemeta.py
olemeta is a script to parse OLE files such as MS Office documents (e.g. Word,
Excel), to extract all standard properties present in the OLE file.
Usage: olemeta.py <file>
olemeta project website: http://www.decalage.info/python/olemeta
olemeta is part of the python-oletools package:
http://www.decalage.info/python/oletools
"""
#=== LICENSE =================================================================
# olemeta is copyright (c) 2013-2016, Philippe Lagadec (http://www.decalage.info)
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without modification,
# are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
# list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#------------------------------------------------------------------------------
# CHANGELOG:
# 2013-07-24 v0.01 PL: - first version
# 2014-11-29 v0.02 PL: - use olefile instead of OleFileIO_PL
# - improved usage display
# 2015-12-29 v0.03 PL: - only display properties present in the file
# 2016-09-06 v0.50 PL: - added main entry point for setup.py
# 2016-10-25 PL: - fixed print for Python 3
# 2016-10-28 PL: - removed the UTF8 codec for console display
__version__ = '0.50'
#------------------------------------------------------------------------------
# TODO:
# + optparse
# + nicer output: table with fixed columns, datetime, etc
# + CSV output
# + option to only show available properties (by default)
#=== IMPORTS =================================================================
import sys, codecs
import thirdparty.olefile as olefile
from thirdparty.tablestream import tablestream
#=== MAIN =================================================================
def main():
try:
ole = olefile.OleFileIO(sys.argv[1])
except IndexError:
sys.exit(__doc__)
# parse and display metadata:
meta = ole.get_metadata()
# console output with UTF8 encoding:
# It looks like we do not need the UTF8 codec anymore, both for Python 2 and 3
console_utf8 = sys.stdout #codecs.getwriter('utf8')(sys.stdout)
# TODO: move similar code to a function
print('Properties from the SummaryInformation stream:')
t = tablestream.TableStream([21, 30], header_row=['Property', 'Value'], outfile=console_utf8)
for prop in meta.SUMMARY_ATTRIBS:
value = getattr(meta, prop)
if value is not None:
# TODO: pretty printing for strings, dates, numbers
# TODO: better unicode handling
# print('- %s: %s' % (prop, value))
# if isinstance(value, unicode):
# # encode to UTF8, avoiding errors
# value = value.encode('utf-8', errors='replace')
# else:
# value = str(value)
t.write_row([prop, value], colors=[None, 'yellow'])
t.close()
print('')
print('Properties from the DocumentSummaryInformation stream:')
t = tablestream.TableStream([21, 30], header_row=['Property', 'Value'], outfile=console_utf8)
for prop in meta.DOCSUM_ATTRIBS:
value = getattr(meta, prop)
if value is not None:
# TODO: pretty printing for strings, dates, numbers
# TODO: better unicode handling
# print('- %s: %s' % (prop, value))
# if isinstance(value, unicode):
# # encode to UTF8, avoiding errors
# value = value.encode('utf-8', errors='replace')
# else:
# value = str(value)
t.write_row([prop, value], colors=[None, 'yellow'])
t.close()
ole.close()
if __name__ == '__main__':
main()