Peter M. Groen / oletools

Commit 670d70755885e7e8c5c0e012ee23db95365d6121

Authored by Christian Herdtweck
1 parent 1665aeea

oleobj: make pylint and pep8 happier 

Most changes are just whitespace or line break or case changes. But:
- this did find an actual error (variable exc was used before creation)
- did move imports up between license and changelog (although I would prefer
it in its original place)
- removed the _ansi_ from read_*_ansi_string
- move logging constants from main to global scope
Inline Side-by-side
Showing 1 changed file with 160 additions and 121 deletions
oletools/oleobj.py
  View file @670d707
1 1 #!/usr/bin/env python
2   -from __future__ import print_function
3 2 """
4 3 oleobj.py
5 4  
6 5 oleobj is a Python script and module to parse OLE objects and files stored
7   -into various file formats such as RTF or MS Office documents (e.g. Word, Excel).
  6 +into various file formats such as RTF or MS Office documents
  7 +(e.g. Word, Excel).
8 8  
9 9 Author: Philippe Lagadec - http://www.decalage.info
10 10 License: BSD, see source code or documentation
... ... @@ -13,33 +13,63 @@ oleobj is part of the python-oletools package:
13 13 http://www.decalage.info/python/oletools
14 14 """
15 15  
16   -# === LICENSE ==================================================================
  16 +# === LICENSE =================================================================
17 17  
18 18 # oleobj is copyright (c) 2015-2017 Philippe Lagadec (http://www.decalage.info)
19 19 # All rights reserved.
20 20 #
21   -# Redistribution and use in source and binary forms, with or without modification,
22   -# are permitted provided that the following conditions are met:
  21 +# Redistribution and use in source and binary forms, with or without
  22 +# modification, are permitted provided that the following conditions are met:
23 23 #
24   -# * Redistributions of source code must retain the above copyright notice, this
25   -# list of conditions and the following disclaimer.
  24 +# * Redistributions of source code must retain the above copyright notice,
  25 +# this list of conditions and the following disclaimer.
26 26 # * Redistributions in binary form must reproduce the above copyright notice,
27 27 # this list of conditions and the following disclaimer in the documentation
28 28 # and/or other materials provided with the distribution.
29 29 #
30   -# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
31   -# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
32   -# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
33   -# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
34   -# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
35   -# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
36   -# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
37   -# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
38   -# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
39   -# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
40   -
41   -
42   -#------------------------------------------------------------------------------
  30 +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
  31 +# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  32 +# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  33 +# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
  34 +# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
  35 +# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
  36 +# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
  37 +# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
  38 +# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  39 +# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  40 +# POSSIBILITY OF SUCH DAMAGE.
  41 +
  42 +
  43 +# -- IMPORTS ------------------------------------------------------------------
  44 +
  45 +from __future__ import print_function
  46 +
  47 +import logging
  48 +import struct
  49 +import optparse
  50 +import os
  51 +import re
  52 +import sys
  53 +from zipfile import is_zipfile, ZipFile
  54 +
  55 +# IMPORTANT: it should be possible to run oletools directly as scripts
  56 +# in any directory without installing them with pip or setup.py.
  57 +# In that case, relative imports are NOT usable.
  58 +# And to enable Python 2+3 compatibility, we need to use absolute imports,
  59 +# so we add the oletools parent folder to sys.path (absolute+normalized path):
  60 +try:
  61 + from oletools.thirdparty import olefile
  62 +except ImportError:
  63 + PARENT_DIR = os.path.normpath(os.path.dirname(os.path.dirname(
  64 + os.path.abspath(__file__))))
  65 + if PARENT_DIR not in sys.path:
  66 + sys.path.insert(0, PARENT_DIR)
  67 + del PARENT_DIR
  68 + from oletools.thirdparty import olefile
  69 +from oletools.thirdparty import xglob
  70 +from ppt_record_parser import is_ppt, PptFile, PptRecordExOleVbaActiveXAtom
  71 +
  72 +# -----------------------------------------------------------------------------
43 73 # CHANGELOG:
44 74 # 2015-12-05 v0.01 PL: - first version
45 75 # 2016-06 PL: - added main and process_file (not working yet)
... ... @@ -51,12 +81,12 @@ http://www.decalage.info/python/oletools
51 81  
52 82 __version__ = '0.51'
53 83  
54   -#------------------------------------------------------------------------------
  84 +# -----------------------------------------------------------------------------
55 85 # TODO:
56 86 # + setup logging (common with other oletools)
57 87  
58 88  
59   -#------------------------------------------------------------------------------
  89 +# -----------------------------------------------------------------------------
60 90 # REFERENCES:
61 91  
62 92 # Reference for the storage of embedded OLE objects/files:
... ... @@ -67,38 +97,28 @@ __version__ = '0.51'
67 97 # TODO: oledump
68 98  
69 99  
70   -#--- IMPORTS ------------------------------------------------------------------
71   -
72   -import logging, struct, optparse, os, re, sys
  100 +# === LOGGING =================================================================
73 101  
74   -# IMPORTANT: it should be possible to run oletools directly as scripts
75   -# in any directory without installing them with pip or setup.py.
76   -# In that case, relative imports are NOT usable.
77   -# And to enable Python 2+3 compatibility, we need to use absolute imports,
78   -# so we add the oletools parent folder to sys.path (absolute+normalized path):
79   -_thismodule_dir = os.path.normpath(os.path.abspath(os.path.dirname(__file__)))
80   -# print('_thismodule_dir = %r' % _thismodule_dir)
81   -_parent_dir = os.path.normpath(os.path.join(_thismodule_dir, '..'))
82   -# print('_parent_dir = %r' % _thirdparty_dir)
83   -if not _parent_dir in sys.path:
84   - sys.path.insert(0, _parent_dir)
85   -
86   -from oletools.thirdparty.olefile import olefile
87   -from oletools.thirdparty.xglob import xglob
88   -from ppt_record_parser import is_ppt, PptFile, PptRecordExOleVbaActiveXAtom
  102 +DEFAULT_LOG_LEVEL = "warning"
  103 +LOG_LEVELS = {'debug': logging.DEBUG,
  104 + 'info': logging.INFO,
  105 + 'warning': logging.WARNING,
  106 + 'error': logging.ERROR,
  107 + 'critical': logging.CRITICAL}
89 108  
90   -# === LOGGING =================================================================
91 109  
92 110 class NullHandler(logging.Handler):
93 111 """
94 112 Log Handler without output, to avoid printing messages if logging is not
95 113 configured by the main application.
96 114 Python 2.7 has logging.NullHandler, but this is necessary for 2.6:
97   - see https://docs.python.org/2.6/library/logging.html#configuring-logging-for-a-library
  115 + see https://docs.python.org/2.6/library/logging.html section
  116 + configuring-logging-for-a-library
98 117 """
99 118 def emit(self, record):
100 119 pass
101 120  
  121 +
102 122 def get_logger(name, level=logging.CRITICAL+1):
103 123 """
104 124 Create a suitable logger object for this module.
... ... @@ -111,7 +131,7 @@ def get_logger(name, level=logging.CRITICAL+1):
111 131 # First, test if there is already a logger with the same name, else it
112 132 # will generate duplicate messages (due to duplicate handlers):
113 133 if name in logging.Logger.manager.loggerDict:
114   - #NOTE: another less intrusive but more "hackish" solution would be to
  134 + # NOTE: another less intrusive but more "hackish" solution would be to
115 135 # use getLogger then test if its effective level is not default.
116 136 logger = logging.getLogger(name)
117 137 # make sure level is OK:
... ... @@ -125,8 +145,10 @@ def get_logger(name, level=logging.CRITICAL+1):
125 145 logger.setLevel(level)
126 146 return logger
127 147  
  148 +
128 149 # a global logger object used for debugging:
129   -log = get_logger('oleobj')
  150 +log = get_logger('oleobj') # pylint: disable=invalid-name
  151 +
130 152  
131 153 def enable_logging():
132 154 """
... ... @@ -137,7 +159,7 @@ def enable_logging():
137 159 log.setLevel(logging.NOTSET)
138 160  
139 161  
140   -# === CONSTANTS ==============================================================
  162 +# === CONSTANTS ===============================================================
141 163  
142 164 # some str methods on Python 2.x return characters,
143 165 # while the equivalent bytes methods return integers on Python 3.x:
... ... @@ -146,18 +168,19 @@ if sys.version_info[0] <= 2:
146 168 NULL_CHAR = '\x00'
147 169 else:
148 170 # Python 3.x
149   - NULL_CHAR = 0
  171 + NULL_CHAR = 0 # pylint: disable=redefined-variable-type
  172 + xrange = range # pylint: disable=redefined-builtin, invalid-name
150 173  
151 174  
152   -# === GLOBAL VARIABLES =======================================================
  175 +# === GLOBAL VARIABLES ========================================================
153 176  
154 177 # struct to parse an unsigned integer of 32 bits:
155   -struct_uint32 = struct.Struct('<L')
156   -assert struct_uint32.size == 4 # make sure it matches 4 bytes
  178 +STRUCT_UINT32 = struct.Struct('<L')
  179 +assert STRUCT_UINT32.size == 4 # make sure it matches 4 bytes
157 180  
158 181 # struct to parse an unsigned integer of 16 bits:
159   -struct_uint16 = struct.Struct('<H')
160   -assert struct_uint16.size == 2 # make sure it matches 2 bytes
  182 +STRUCT_UINT16 = struct.Struct('<H')
  183 +assert STRUCT_UINT16.size == 2 # make sure it matches 2 bytes
161 184  
162 185 # max length of a zero-terminated ansi string. Not sure what this really is
163 186 STR_MAX_LEN = 1024
... ... @@ -173,7 +196,9 @@ RETURN_ERR_ARGS = 2 # reserve for OptionParser.parse_args
173 196 RETURN_ERR_STREAM = 4 # error opening/parsing a stream
174 197 RETURN_ERR_DUMP = 8 # error dumping data from stream to file
175 198  
176   -# === FUNCTIONS ==============================================================
  199 +
  200 +# === FUNCTIONS ===============================================================
  201 +
177 202  
178 203 def read_uint32(data, index):
179 204 """
... ... @@ -185,9 +210,9 @@ def read_uint32(data, index):
185 210 and the index to continue reading next time.
186 211 """
187 212 if index is None:
188   - value = struct_uint32.unpack(data.read(4))[0]
  213 + value = STRUCT_UINT32.unpack(data.read(4))[0]
189 214 else:
190   - value = struct_uint32.unpack(data[index:index+4])[0]
  215 + value = STRUCT_UINT32.unpack(data[index:index+4])[0]
191 216 index += 4
192 217 return (value, index)
193 218  
... ... @@ -202,19 +227,20 @@ def read_uint16(data, index):
202 227 and the index to continue reading next time.
203 228 """
204 229 if index is None:
205   - value = struct_uint16.unpack(data.read(2))[0]
  230 + value = STRUCT_UINT16.unpack(data.read(2))[0]
206 231 else:
207   - value = struct_uint16.unpack(data[index:index+2])[0]
  232 + value = STRUCT_UINT16.unpack(data[index:index+2])[0]
208 233 index += 2
209 234 return (value, index)
210 235  
211 236  
212   -def read_LengthPrefixedAnsiString(data, index):
  237 +def read_length_prefixed_string(data, index):
213 238 """
214 239 Read a length-prefixed ANSI string from data.
215 240  
216 241 :param data: bytes string or stream containing the data to be extracted.
217   - :param index: index in data where string size start or None if data is stream
  242 + :param index: index in data where string size start or None if data is
  243 + stream
218 244 :return: tuple (value, index) containing the read value (bytes string),
219 245 and the index to start reading from next time.
220 246 """
... ... @@ -236,20 +262,21 @@ def read_LengthPrefixedAnsiString(data, index):
236 262 return (ansi_string, index)
237 263  
238 264  
239   -def read_zero_terminated_ansi_string(data, index):
  265 +def read_zero_terminated_string(data, index):
240 266 """
241 267 Read a zero-terminated ANSI string from data
242 268  
243 269 Guessing that max length is 256 bytes.
244 270  
245 271 :param data: bytes string or stream containing an ansi string
246   - :param index: index at which the string should start or None if data is stream
  272 + :param index: index at which the string should start or None if data is
  273 + stream
247 274 :return: tuple (string, index) containing the read string (bytes string),
248 275 and the index to start reading from next time.
249 276 """
250 277 if index is None:
251 278 result = []
252   - for count in xrange(STR_MAX_LEN):
  279 + for _ in xrange(STR_MAX_LEN):
253 280 char = data.read(1)
254 281 if char == b'\x00':
255 282 return b''.join(result), index
... ... @@ -260,9 +287,10 @@ def read_zero_terminated_ansi_string(data, index):
260 287 return data[index:end_idx], end_idx+1 # return index after the 0-byte
261 288  
262 289  
263   -# === CLASSES ================================================================
  290 +# === CLASSES =================================================================
264 291  
265   -class OleNativeStream (object):
  292 +
  293 +class OleNativeStream(object):
266 294 """
267 295 OLE object contained into an OLENativeStream structure.
268 296 (see MS-OLEDS 2.3.6 OLENativeStream)
... ... @@ -272,7 +300,6 @@ class OleNativeStream (object):
272 300 TYPE_LINKED = 0x01
273 301 TYPE_EMBEDDED = 0x02
274 302  
275   -
276 303 def __init__(self, bindata=None, package=False):
277 304 """
278 305 Constructor for OleNativeStream.
... ... @@ -322,14 +349,14 @@ class OleNativeStream (object):
322 349 .format(self.native_data_size))
323 350 # I thought this might be an OLE type specifier ???
324 351 self.unknown_short, index = read_uint16(data, index)
325   - self.filename, index = read_zero_terminated_ansi_string(data, index)
  352 + self.filename, index = read_zero_terminated_string(data, index)
326 353 # source path
327   - self.src_path, index = read_zero_terminated_ansi_string(data, index)
328   - # TODO I bet these next 8 bytes are a timestamp => FILETIME from olefile
  354 + self.src_path, index = read_zero_terminated_string(data, index)
  355 + # TODO: I bet these 8 bytes are a timestamp ==> FILETIME from olefile
329 356 self.unknown_long_1, index = read_uint32(data, index)
330 357 self.unknown_long_2, index = read_uint32(data, index)
331 358 # temp path?
332   - self.temp_path, index = read_zero_terminated_ansi_string(data, index)
  359 + self.temp_path, index = read_zero_terminated_string(data, index)
333 360 # size of the rest of the data
334 361 try:
335 362 self.actual_size, index = read_uint32(data, index)
... ... @@ -338,7 +365,7 @@ class OleNativeStream (object):
338 365 else:
339 366 self.data = data[index:index+self.actual_size]
340 367 self.is_link = False
341   - # TODO: exception when size > remaining data
  368 + # TODO: there can be extra data, no idea what it is for
342 369 # TODO: SLACK DATA
343 370 except (IOError, struct.error): # no data to read actual_size
344 371 logging.debug('data is not embedded but only a link')
... ... @@ -347,7 +374,7 @@ class OleNativeStream (object):
347 374 self.data = None
348 375  
349 376  
350   -class OleObject (object):
  377 +class OleObject(object):
351 378 """
352 379 OLE 1.0 Object
353 380  
... ... @@ -359,13 +386,15 @@ class OleObject (object):
359 386 TYPE_LINKED = 0x01
360 387 TYPE_EMBEDDED = 0x02
361 388  
362   -
363 389 def __init__(self, bindata=None):
364 390 """
365 391 Constructor for OleObject.
366 392 If bindata is provided, it will be parsed using the parse() method.
367 393  
368   - :param bindata: bytes, OLE 1.0 Object structure containing an OLE object
  394 + :param bindata: bytes, OLE 1.0 Object structure containing OLE object
  395 +
  396 + Note: Code can easily by generalized to work with byte streams instead
  397 + of arrays just like in OleNativeStream.
369 398 """
370 399 self.ole_version = None
371 400 self.format_id = None
... ... @@ -374,6 +403,8 @@ class OleObject (object):
374 403 self.item_name = None
375 404 self.data = None
376 405 self.data_size = None
  406 + if bindata is not None:
  407 + self.parse(bindata)
377 408  
378 409 def parse(self, data):
379 410 """
... ... @@ -388,27 +419,29 @@ class OleObject (object):
388 419 # print("Parsing OLE object data:")
389 420 # print(hexdump3(data, length=16))
390 421 # Header: see MS-OLEDS 2.2.4 ObjectHeader
  422 + index = 0
391 423 self.ole_version, index = read_uint32(data, index)
392 424 self.format_id, index = read_uint32(data, index)
393   - log.debug('OLE version=%08X - Format ID=%08X' % (self.ole_version, self.format_id))
  425 + log.debug('OLE version=%08X - Format ID=%08X'
  426 + % (self.ole_version, self.format_id))
394 427 assert self.format_id in (self.TYPE_EMBEDDED, self.TYPE_LINKED)
395   - self.class_name, index = read_LengthPrefixedAnsiString(data, index)
396   - self.topic_name, index = read_LengthPrefixedAnsiString(data, index)
397   - self.item_name, index = read_LengthPrefixedAnsiString(data, index)
  428 + self.class_name, index = read_length_prefixed_string(data, index)
  429 + self.topic_name, index = read_length_prefixed_string(data, index)
  430 + self.item_name, index = read_length_prefixed_string(data, index)
398 431 log.debug('Class name=%r - Topic name=%r - Item name=%r'
399   - % (self.class_name, self.topic_name, self.item_name))
  432 + % (self.class_name, self.topic_name, self.item_name))
400 433 if self.format_id == self.TYPE_EMBEDDED:
401 434 # Embedded object: see MS-OLEDS 2.2.5 EmbeddedObject
402   - #assert self.topic_name != '' and self.item_name != ''
  435 + # assert self.topic_name != '' and self.item_name != ''
403 436 self.data_size, index = read_uint32(data, index)
404   - log.debug('Declared data size=%d - remaining size=%d' % (self.data_size, len(data)-index))
  437 + log.debug('Declared data size=%d - remaining size=%d'
  438 + % (self.data_size, len(data)-index))
405 439 # TODO: handle incorrect size to avoid exception
406 440 self.data = data[index:index+self.data_size]
407 441 assert len(self.data) == self.data_size
408 442 self.extra_data = data[index+self.data_size:]
409 443  
410 444  
411   -
412 445 def sanitize_filename(filename, replacement='_', max_length=200):
413 446 """compute basename of filename. Replaces all non-whitelisted characters.
414 447 The returned filename is always a basename of the file."""
... ... @@ -421,7 +454,7 @@ def sanitize_filename(filename, replacement=&#39;_&#39;, max_length=200):
421 454 while " " in sane_fname:
422 455 sane_fname = sane_fname.replace(' ', ' ')
423 456  
424   - if not len(filename):
  457 + if not filename:
425 458 sane_fname = 'NONAME'
426 459  
427 460 # limit filename length
... ... @@ -507,7 +540,7 @@ def find_ole(filename, data):
507 540 yield None # --> leads to non-0 return code but try next file first
508 541  
509 542  
510   -def process_file(container, filename, data, output_dir=None):
  543 +def process_file(filename, data, output_dir=None):
511 544 """ find embedded objects in given file
512 545  
513 546 if data is given (from xglob for encrypted zip files), then filename is
... ... @@ -530,8 +563,8 @@ def process_file(container, filename, data, output_dir=None):
530 563 fname_prefix = os.path.join(base_dir, sane_fname)
531 564  
532 565 # TODO: option to extract objects to files (false by default)
533   - print ('-'*79)
534   - print ('File: %r' % filename)
  566 + print('-'*79)
  567 + print('File: %r' % filename)
535 568 index = 1
536 569  
537 570 # do not throw errors but remember them and try continue with other streams
... ... @@ -553,10 +586,10 @@ def process_file(container, filename, data, output_dir=None):
553 586 stream = ole.openstream(path_parts)
554 587 print('extract file embedded in OLE object from stream %r:'
555 588 % stream_path)
556   - print ('Parsing OLE Package')
  589 + print('Parsing OLE Package')
557 590 opkg = OleNativeStream(stream)
558 591 # leave stream open until dumping is finished
559   - except Exception:
  592 + except Exception as exc:
560 593 log.warning('*** Not an OLE 1.0 Object ({0})'.format(exc))
561 594 err_stream = True
562 595 if stream is not None:
... ... @@ -568,9 +601,9 @@ def process_file(container, filename, data, output_dir=None):
568 601 log.debug('Object is not embedded but only linked to '
569 602 '- skip')
570 603 continue
571   - print ('Filename = %r' % opkg.filename)
572   - print ('Source path = %r' % opkg.src_path)
573   - print ('Temp path = %r' % opkg.temp_path)
  604 + print('Filename = %r' % opkg.filename)
  605 + print('Source path = %r' % opkg.src_path)
  606 + print('Temp path = %r' % opkg.temp_path)
574 607 if opkg.filename:
575 608 fname = '%s_%s' % (fname_prefix,
576 609 sanitize_filename(opkg.filename))
... ... @@ -579,10 +612,10 @@ def process_file(container, filename, data, output_dir=None):
579 612  
580 613 # dump
581 614 try:
582   - print ('saving to file %s' % fname)
  615 + print('saving to file %s' % fname)
583 616 with open(fname, 'wb') as writer:
584 617 n_dumped = 0
585   - next_size = min(DUMP_CHUNK_SIZE, opkg.actual_size)
  618 + next_size = min(DUMP_CHUNK_SIZE, opkg.actual_size)
586 619 while next_size:
587 620 data = stream.read(next_size)
588 621 writer.write(data)
... ... @@ -591,8 +624,8 @@ def process_file(container, filename, data, output_dir=None):
591 624 logging.warning('Wanted to read {0}, got {1}'
592 625 .format(next_size, len(data)))
593 626 break
594   - next_size = min(DUMP_CHUNK_SIZE,
595   - opkg.actual_size - n_dumped)
  627 + next_size = min(DUMP_CHUNK_SIZE,
  628 + opkg.actual_size - n_dumped)
596 629 did_dump = True
597 630 except Exception as exc:
598 631 log.warning('error dumping to {0} ({1})'
... ... @@ -605,23 +638,17 @@ def process_file(container, filename, data, output_dir=None):
605 638 return err_stream, err_dumping, did_dump
606 639  
607 640  
608   -#=== MAIN =================================================================
  641 +# === MAIN ====================================================================
  642 +
609 643  
610 644 def main():
611 645 """ main function, called when running this as script """
612 646 # print banner with version
613   - print ('oleobj %s - http://decalage.info/oletools' % __version__)
614   - print ('THIS IS WORK IN PROGRESS - Check updates regularly!')
615   - print ('Please report any issue at https://github.com/decalage2/oletools/issues')
616   - print ('')
617   -
618   - DEFAULT_LOG_LEVEL = "warning" # Default log level
619   - LOG_LEVELS = {'debug': logging.DEBUG,
620   - 'info': logging.INFO,
621   - 'warning': logging.WARNING,
622   - 'error': logging.ERROR,
623   - 'critical': logging.CRITICAL
624   - }
  647 + print('oleobj %s - http://decalage.info/oletools' % __version__)
  648 + print('THIS IS WORK IN PROGRESS - Check updates regularly!')
  649 + print('Please report any issue at '
  650 + 'https://github.com/decalage2/oletools/issues')
  651 + print('')
625 652  
626 653 usage = 'usage: %prog [options] <filename> [filename2 ...]'
627 654 parser = optparse.OptionParser(usage=usage)
... ... @@ -630,21 +657,31 @@ def main():
630 657 # parser.add_option('-c', '--csv', dest='csv',
631 658 # help='export results to a CSV file')
632 659 parser.add_option("-r", action="store_true", dest="recursive",
633   - help='find files recursively in subdirectories.')
634   - parser.add_option("-d", type="str", dest="output_dir",
635   - help='use specified directory to output files.', default=None)
636   - parser.add_option("-z", "--zip", dest='zip_password', type='str', default=None,
637   - help='if the file is a zip archive, open first file from it, using the provided password (requires Python 2.6+)')
638   - parser.add_option("-f", "--zipfname", dest='zip_fname', type='str', default='*',
639   - help='if the file is a zip archive, file(s) to be opened within the zip. Wildcards * and ? are supported. (default:*)')
640   - parser.add_option('-l', '--loglevel', dest="loglevel", action="store", default=DEFAULT_LOG_LEVEL,
641   - help="logging level debug/info/warning/error/critical (default=%default)")
  660 + help='find files recursively in subdirectories.')
  661 + parser.add_option("-d", type="str", dest="output_dir", default=None,
  662 + help='use specified directory to output files.')
  663 + parser.add_option("-z", "--zip", dest='zip_password', type='str',
  664 + default=None,
  665 + help='if the file is a zip archive, open first file from'
  666 + 'it, using the provided password (requires Python '
  667 + '2.6+)')
  668 + parser.add_option("-f", "--zipfname", dest='zip_fname', type='str',
  669 + default='*',
  670 + help='if the file is a zip archive, file(s) to be opened'
  671 + 'within the zip. Wildcards * and ? are supported. '
  672 + '(default:*)')
  673 + parser.add_option('-l', '--loglevel', dest="loglevel", action="store",
  674 + default=DEFAULT_LOG_LEVEL,
  675 + help='logging level debug/info/warning/error/critical '
  676 + '(default=%default)')
642 677  
643 678 # options for compatibility with ripOLE
644 679 parser.add_option('-i', '--more-input', type='str', default=None,
645   - help='Additional file to parse (same as positional arguments)')
  680 + help='Additional file to parse (same as positional '
  681 + 'arguments)')
646 682 parser.add_option('-v', '--verbose', action='store_true',
647   - help='verbose mode, set logging to DEBUG (overwrites -l)')
  683 + help='verbose mode, set logging to DEBUG '
  684 + '(overwrites -l)')
648 685  
649 686 (options, args) = parser.parse_args()
650 687 if options.more_input:
... ... @@ -653,7 +690,7 @@ def main():
653 690 options.loglevel = 'debug'
654 691  
655 692 # Print help if no arguments are passed
656   - if len(args) == 0:
  693 + if not args:
657 694 parser.print_help()
658 695 return RETURN_ERR_ARGS
659 696 for filename in args:
... ... @@ -674,13 +711,15 @@ def main():
674 711 any_err_dumping = False
675 712 any_did_dump = False
676 713  
677   - for container, filename, data in xglob.iter_files(args, recursive=options.recursive,
678   - zip_password=options.zip_password, zip_fname=options.zip_fname):
  714 + for container, filename, data in \
  715 + xglob.iter_files(args, recursive=options.recursive,
  716 + zip_password=options.zip_password,
  717 + zip_fname=options.zip_fname):
679 718 # ignore directory names stored in zip files:
680 719 if container and filename.endswith('/'):
681 720 continue
682 721 err_stream, err_dumping, did_dump = \
683   - process_file(container, filename, data, options.output_dir)
  722 + process_file(filename, data, options.output_dir)
684 723 any_err_stream |= err_stream
685 724 any_err_dumping |= err_dumping
686 725 any_did_dump |= did_dump
... ...