forked from DidierStevens/DidierStevensSuite
-
Notifications
You must be signed in to change notification settings - Fork 0
/
file-magic.py
1494 lines (1310 loc) · 62.9 KB
/
file-magic.py
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python
from __future__ import print_function
__description__ = 'Essentialy a wrapper for file (libmagic)'
__author__ = 'Didier Stevens'
__version__ = '0.0.4'
__date__ = '2018/10/27'
"""
Source code put in public domain by Didier Stevens, no Copyright
https://DidierStevens.com
Use at your own risk
History:
2017/01/28: start
2017/04/24: 0.0.2 added support for multiple files; options -o -r -n
2017/05/09: refactoring, manpage
2017/12/30: added option -c
2018/02/18: added option -j
2018/02/20: tested on Kali
2018/06/29: switched to python-magic-bin for Windows; refactoring based on binary file template
2018/07/01: updated man
2018/07/02: added option -v
2018/07/07: updated CheckJSON to version 2
2018/07/08: merged with binary template
2018/07/10: updated man
2018/10/26: 0.0.3 updated cOutput
2018/10/27: 0.0.4 added option -C
Todo:
"""
import optparse
import sys
import os
import zipfile
import binascii
import random
import gzip
import collections
import glob
import textwrap
import re
import struct
import string
import math
import fnmatch
import json
import time
import hashlib
if sys.version_info[0] >= 3:
from io import BytesIO as DataIO
else:
from cStringIO import StringIO as DataIO
if sys.version_info[0] >= 3:
from io import StringIO
else:
from cStringIO import StringIO
try:
import magic
except:
pass
def PrintManual():
manual = r'''
Manual:
This tool is a wrapper for the file command (libmagic), used to determine file types based on file content.
file-magic.py can do the same as file: determine the file type of a single file.
Example:
C:\Demo>file-magic.py EICARgen.exe
PE32 executable for MS Windows (console) Intel 80386 32-bit
Unlike file, file-magic.py also accepts a file from stdin, it can determine the file type of a file contained in a (password protected) ZIP file, ... This tool is very versatile when it comes to handling files, later full details will be provided.
By default, file-magic will read up to 1MB from the file to identify. To change this limit, use option -b (buffersize).
As shown in the previous example, for a single file, file-magic.py outputs the file type only.
When given multiple files, file-magic will output the filename and the file type (separated by a tab character).
Example:
C:\Demo>file-magic.py *.*
20160805-090019.png PNG image, 692 x 357, 8-bit/color RGBA, non-interlaced
EICARgen.exe PE32 executable for MS Windows (console) Intel 80386 32-bit
f0bbe894f6e71690f80866b3c218f3330af8c0d5c6c6660963ace57fa6a1d592.vir.zip VBE file (encoded VBScript)
file-magic.def ASCII text
file-magic.py a python script text executable
magic.def magic text file for file(1) cmd
To output only the filename, use option -n. To output only the file type, use option -t.
file-magic.py can also produce a CSV file using option -c:
C:\Demo>file-magic.py -c *.*
Filename;Magic
20160805-090019.png;PNG image, 692 x 357, 8-bit/color RGBA, non-interlaced
EICARgen.exe;PE32 executable for MS Windows (console) Intel 80386 32-bit
f0bbe894f6e71690f80866b3c218f3330af8c0d5c6c6660963ace57fa6a1d592.vir.zip;VBE file (encoded VBScript)
file-magic.def;ASCII text
file-magic.py;a python script text executable
magic.def;magic text file for file(1) cmd
This CSV file has a header and 2 fields: the filename and the type of the file.
Option -r (regex) can be used to filter the output based on the file type. If the provided regular expression matches (ignoring case) the determined file type, the file will be outputed.
Example:
C:\Demo>file-magic.py -r pe32 *.*
EICARgen.exe PE32 executable for MS Windows (console) Intel 80386 32-bit
If the regular expression contains a capture group (), then the outputed file type is the capture group.
Option -v can be used to invert the selection when a regular expression is used: all file types that do not match the regular expression are selected.
When combining option -n with option -r, a list of names of files of a particular type will be produced, which can be used for further processing.
Output can be written to a file using option -o.
Option -s (scan) is experimental: the type of the provided file will be determined repeatedly, byte per byte. The goal is to find embedded files.
Example using -r:
C:\Demo>file-magic.py -s -r pe32 png-exe.bin
0000346e: PE32 executable for MS Windows (console) Intel 80386 32-bit
file-magic.py requires the python-magic module (installed with 1) Windows/OSX: pip install python-magic-bin 2) Linux: pip install python-magic).
On Windows, this requires VC Runtime 2015.
file-magic.py can use optional magic definitions. These are contained in file file-magic.def in the same folder as file-magic.py.
To restrict identification to these custom definitions, use option -C.
As stated at the beginning of this manual, this tool is very versatile when it comes to handling files. This will be explained now.
This tool reads files in binary mode. It can read files from disk, from standard input (stdin) and from "generated" files via the command line.
It can also partially read files (this is done with the cut operator).
If no file arguments are provided to this tool, it will read data from standard input (stdin). This way, this tool can be used in a piped chain of commands, like this:
oledump.py -s 4 -d sample.doc.vir | tool.py
When one or more file arguments are provided to this tool, it will read the files and process the content.
How the files are read, depends on the type of file arguments that are provided. File arguments that start with character @ or # have special meaning, and will be explained later.
If a file argument does not start with @ or #, it is considered to be a file on disk and the content will be read from disk.
If the file is not a compressed file, the binary content of the file is read from disk for processing.
Compressed files are solely recognized based on their extension: .zip and .gz.
If a file argument with extension .gz is provided, the tool will decompress the gzip file in memory and process the decompressed content. No checks are made to ensure that the file with extension .gz is an actual gzip compressed file.
If a file argument with extension .zip is provided and it contains a single file, the tool will extract the file from the ZIP file in memory and process the decompressed content. No checks are made to ensure that the file with extension .zip is an actual ZIP compressed file.
Password protected ZIP files can be processed too. The tool uses password 'infected' (without quotes) as default password. A different password can be provided using option --password.
Example:
tool.py sample.zip
To prevent the tool from decompressing .zip or .gz files, but to process the compressed file itself, use option --noextraction.
File arguments that start with character @ ("here files"), are read as text files that contain file arguments (one per line) to be processed.
For example, we take a text file with filename list.txt and following content:
sample-1.bin
sample-5.bin
sample-7.bin
When using this file (list.txt) in the following command:
tool.py @list.txt
the tool will process the following files: sample-1.bin, sample-5.bin and sample-7.bin.
A single @ character as filename is a here file read from stdin.
Wildcards are supported too. The classic *, ? and [] wildcard characters are supported. For example, use the following command to process all .exe and .dll files in the Windows directory:
tool.py C:\Windows\*.exe C:\Windows\*.dll
To prevent the tool from processing file arguments with wildcard characters or special initial characters (@ and #) differently, but to process them as normal files, use option --literalfilenames.
The content of folders can be processed too: use option --recursedir and provide folder names as argument. Wildcards and here files (for folder names) can be used too.
File arguments that start with character # have special meaning. These are not processed as actual files on disk (except when option --literalfilenames is used), but as file arguments that specify how to "generate" the file content.
File arguments that start with #, #h#, #b# or #e# are used to "generate" the file content.
Arguments that start with #c# are not file arguments, but cut operators (explained later).
Generating the file content with a # file argument means that the file content is not read from disk, but generated in memory based on the characteristics provided via the file argument.
When a file argument starts with # (and not with #h#, #b#, #e# or #c#), all characters that follow the # character specify the content of the generated file.
For example, file argument #ABCDE specifies a file containing exactly 5 bytes: ASCII characters A, B, C, D and E.
Thus the following command:
tool.py #ABCDE
will make the tool process data with binary content ABCDE. #ABCDE is not an actual file written on disk, but it is a notational convention to provide data via the command line.
Since this notation can not be used to specify all possible byte values, hexadecimal encoding (#h#) and BASE64 encoding (#b#) notation is supported too.
For example, #h#4142434445 is an hexadecimal notation that generates data ABCDE. Hexadecimal notation allows the generation of non-printable characters for example, like NULL bytes: #h#00
File argument #b#QUJDREU= is another example, this time BASE64 notation, that generates data ABCDE.
File arguments that start with #e# are a notational convention to use expressions to generate data. An expression is a single function/string or the concatenation of several functions/strings (using character + as concatenation operator).
Strings can be characters enclosed by single quotes ('example') or hexadecimal strings prefixed by 0x (0xBEEF).
4 functions are available: random, loremipsum, repeat and chr.
Function random takes exactly one argument: an integer (with value 1 or more). Integers can be specified using decimal notation or hexadecimal notation (prefix 0x).
The random function generates a sequence of bytes with a random value (between 0 and 255), the argument specifies how many bytes need to be generated. Remark that the random number generator that is used is just the Python random number generator, not a cryptographic random number generator.
Example:
tool.py #e#random(100)
will make the tool process data consisting of a sequence of 100 random bytes.
Function loremipsum takes exactly one argument: an integer (with value 1 or more).
The loremipsum function generates "lorem ipsum" text (fake latin), the argument specifies the number of sentences to generate.
Example: #e#loremipsum(2) generates this text:
Ipsum commodo proin pulvinar hac vel nunc dignissim neque eget odio erat magna lorem urna cursus fusce facilisis porttitor congue eleifend taciti. Turpis duis suscipit facilisi tristique dictum praesent natoque sem mi egestas venenatis per dui sit sodales est condimentum habitasse ipsum phasellus non bibendum hendrerit.
Function chr takes one argument or two arguments.
chr with one argument takes an integer between 0 and 255, and generates a single byte with the value specified by the integer.
chr with two arguments takes two integers between 0 and 255, and generates a byte sequence with the values specified by the integers.
For example #e#chr(0x41,0x45) generates data ABCDE.
Function repeat takes two arguments: an integer (with value 1 or more) and a byte sequence. This byte sequence can be a quoted string of characters (single quotes), like 'ABCDE' or an hexadecimal string prefixed with 0x, like 0x4142434445.
The repeat function will create a sequence of bytes consisting of the provided byte sequence (the second argument) repeated as many times as specified by the first argument.
For example, #e#repeat(3, 'AB') generates byte sequence ABABAB.
When more than one function needs to be used, the byte sequences generated by the functions can be concatenated with the + operator.
For example, #e#repeat(10,0xFF)+random(100) will generate a byte sequence of 10 FF bytes followed by 100 random bytes.
The cut argument (or cut operator) allows for the partial selection of the content of a file. This argument starts with #c# followed by a "cut-expression". Use this expression to "cut out" part of the content.
The cut-argument must be put in front of a file argument, like in this example:
tool.py #c#0:100l data.bin
With these arguments, tool.py will only process the first 100 bytes (0:100l) of file data.bin.
A cut argument is applied to all file arguments that follow it. Example:
tool.py #c#0:100l data-1.bin data-2.bin
With these arguments, tool.py will only process the first 100 bytes (0:100l) of file data-1.bin and the first 100 bytes file data-2.bin.
More than one cut argument can be used, like in this example:
tool.py #c#0:100l data-1.bin #c#0:200l data-2.bin
With these arguments, tool.py will only process the first 100 bytes (0:100l) of file data-1.bin and the first 200 bytes (0:200l) of file data-2.bin.
A cut-expression is composed of 2 terms separated by a colon (:), like this:
termA:termB
termA and termB can be:
- nothing (an empty string)
- a positive decimal number; example: 10
- an hexadecimal number (to be preceded by 0x); example: 0x10
- a case sensitive string to search for (surrounded by square brackets and single quotes); example: ['MZ']
- an hexadecimal string to search for (surrounded by square brackets); example: [d0cf11e0]
If termA is nothing, then the cut section of bytes starts with the byte at position 0.
If termA is a number, then the cut section of bytes starts with the byte at the position given by the number (first byte has index 0).
If termA is a string to search for, then the cut section of bytes starts with the byte at the position where the string is first found. If the string is not found, the cut is empty (0 bytes).
If termB is nothing, then the cut section of bytes ends with the last byte.
If termB is a number, then the cut section of bytes ends with the byte at the position given by the number (first byte has index 0).
When termB is a number, it can have suffix letter l. This indicates that the number is a length (number of bytes), and not a position.
termB can also be a negative number (decimal or hexademical): in that case the position is counted from the end of the file. For example, :-5 selects the complete file except the last 5 bytes.
If termB is a string to search for, then the cut section of bytes ends with the last byte at the position where the string is first found. If the string is not found, the cut is empty (0 bytes).
No checks are made to assure that the position specified by termA is lower than the position specified by termB. This is left up to the user.
Search string expressions (ASCII and hexadecimal) can be followed by an instance (a number equal to 1 or greater) to indicate which instance needs to be taken. For example, ['ABC']2 will search for the second instance of string 'ABC'. If this instance is not found, then nothing is selected.
Search string expressions (ASCII and hexadecimal) can be followed by an offset (+ or - a number) to add (or substract) an offset to the found instance. For example, ['ABC']+3 will search for the first instance of string 'ABC' and then select the bytes after ABC (+ 3).
Finally, search string expressions (ASCII and hexadecimal) can be followed by an instance and an offset.
Examples:
This cut-expression can be used to dump the first 256 bytes of a PE file located inside the file content: ['MZ']:0x100l
This cut-expression can be used to dump the OLE file located inside the file content: [d0cf11e0]:
With option --jsoninput, the tool will parse the output produced by another tool using option --jsonoutput.
Example:
zipdump.py --jsonoutput Book1.xlsm | file-magic.py --jsoninput
[Content_Types].xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
_rels/.rels XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/_rels/workbook.xml.rels XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/workbook.xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/drawings/drawing1.xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/worksheets/_rels/sheet1.xml.rels XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/theme/theme1.xml XML 1.0 document, UTF-8 Unicode text, with very long lines, with CRLF line terminators
xl/styles.xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/worksheets/sheet1.xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/vbaProject.bin Composite Document File V2 Document, Cannot read section info
xl/drawings/vmlDrawing1.vml ASCII text, with CRLF line terminators
docProps/app.xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
xl/ctrlProps/ctrlProp1.xml XML 1.0 document, ASCII text, with CRLF line terminators
docProps/core.xml XML 1.0 document, ASCII text, with very long lines, with CRLF line terminators
In this example, zipdump is used to produce JSON data with the content of each file contained inside file Book1.xlsm (a ZIP container), which is then consumed by file-magic.py to identify (libmagic) the type of each file.
Option --checkfilenames directs the tool to check the provided files prior to processing. This involves checking if the files exist and are regular files (e.g. not folders).
With option --ignoreprocessingerrors, the tool will continue processing the next file when an error occurs while processing the current file. Files that can not be opened will always be skipped to move to the next file.
Option --logfile direct the tool to create a logfile, and option --logcomment can be used to add a comment to the log file. The log file will contain metadata and a list of processed files, it does not contain processing results.
It is best to use this option when option --ignoreprocessingerrors is used, to have a record of file processing errors.
'''
for line in manual.split('\n'):
print(textwrap.fill(line, 79))
DEFAULT_SEPARATOR = ','
QUOTE = '"'
def PrintError(*args, **kwargs):
print(*args, file=sys.stderr, **kwargs)
#Convert 2 Bytes If Python 3
def C2BIP3(string):
if sys.version_info[0] > 2:
return bytes([ord(x) for x in string])
else:
return string
#Convert 2 Integer If Python 2
def C2IIP2(data):
if sys.version_info[0] > 2:
return data
else:
return ord(data)
# CIC: Call If Callable
def CIC(expression):
if callable(expression):
return expression()
else:
return expression
# IFF: IF Function
def IFF(expression, valueTrue, valueFalse):
if expression:
return CIC(valueTrue)
else:
return CIC(valueFalse)
#-BEGINCODE cBinaryFile------------------------------------------------------------------------------
#import random
#import binascii
#import zipfile
#import gzip
#import sys
#if sys.version_info[0] >= 3:
# from io import BytesIO as DataIO
#else:
# from cStringIO import StringIO as DataIO
def LoremIpsumSentence(minimum, maximum):
words = ['lorem', 'ipsum', 'dolor', 'sit', 'amet', 'consectetur', 'adipiscing', 'elit', 'etiam', 'tortor', 'metus', 'cursus', 'sed', 'sollicitudin', 'ac', 'sagittis', 'eget', 'massa', 'praesent', 'sem', 'fermentum', 'dignissim', 'in', 'vel', 'augue', 'scelerisque', 'auctor', 'libero', 'nam', 'a', 'gravida', 'odio', 'duis', 'vestibulum', 'vulputate', 'quam', 'nec', 'cras', 'nibh', 'feugiat', 'ut', 'vitae', 'ornare', 'justo', 'orci', 'varius', 'natoque', 'penatibus', 'et', 'magnis', 'dis', 'parturient', 'montes', 'nascetur', 'ridiculus', 'mus', 'curabitur', 'nisl', 'egestas', 'urna', 'iaculis', 'lectus', 'maecenas', 'ultrices', 'velit', 'eu', 'porta', 'hac', 'habitasse', 'platea', 'dictumst', 'integer', 'id', 'commodo', 'mauris', 'interdum', 'malesuada', 'fames', 'ante', 'primis', 'faucibus', 'accumsan', 'pharetra', 'aliquam', 'nunc', 'at', 'est', 'non', 'leo', 'nulla', 'sodales', 'porttitor', 'facilisis', 'aenean', 'condimentum', 'rutrum', 'facilisi', 'tincidunt', 'laoreet', 'ultricies', 'neque', 'diam', 'euismod', 'consequat', 'tempor', 'elementum', 'lobortis', 'erat', 'ligula', 'risus', 'donec', 'phasellus', 'quisque', 'vivamus', 'pellentesque', 'tristique', 'venenatis', 'purus', 'mi', 'dictum', 'posuere', 'fringilla', 'quis', 'magna', 'pretium', 'felis', 'pulvinar', 'lacinia', 'proin', 'viverra', 'lacus', 'suscipit', 'aliquet', 'dui', 'molestie', 'dapibus', 'mollis', 'suspendisse', 'sapien', 'blandit', 'morbi', 'tellus', 'enim', 'maximus', 'semper', 'arcu', 'bibendum', 'convallis', 'hendrerit', 'imperdiet', 'finibus', 'fusce', 'congue', 'ullamcorper', 'placerat', 'nullam', 'eros', 'habitant', 'senectus', 'netus', 'turpis', 'luctus', 'volutpat', 'rhoncus', 'mattis', 'nisi', 'ex', 'tempus', 'eleifend', 'vehicula', 'class', 'aptent', 'taciti', 'sociosqu', 'ad', 'litora', 'torquent', 'per', 'conubia', 'nostra', 'inceptos', 'himenaeos']
sample = random.sample(words, random.randint(minimum, maximum))
sample[0] = sample[0].capitalize()
return ' '.join(sample) + '.'
def LoremIpsum(sentences):
return ' '.join([LoremIpsumSentence(15, 30) for i in range(sentences)])
STATE_START = 0
STATE_IDENTIFIER = 1
STATE_STRING = 2
STATE_SPECIAL_CHAR = 3
STATE_ERROR = 4
FUNCTIONNAME_REPEAT = 'repeat'
FUNCTIONNAME_RANDOM = 'random'
FUNCTIONNAME_CHR = 'chr'
FUNCTIONNAME_LOREMIPSUM = 'loremipsum'
def Tokenize(expression):
result = []
token = ''
state = STATE_START
while expression != '':
char = expression[0]
expression = expression[1:]
if char == "'":
if state == STATE_START:
state = STATE_STRING
elif state == STATE_IDENTIFIER:
result.append([STATE_IDENTIFIER, token])
state = STATE_STRING
token = ''
elif state == STATE_STRING:
result.append([STATE_STRING, token])
state = STATE_START
token = ''
elif char >= '0' and char <= '9' or char.lower() >= 'a' and char.lower() <= 'z':
if state == STATE_START:
token = char
state = STATE_IDENTIFIER
else:
token += char
elif char == ' ':
if state == STATE_IDENTIFIER:
result.append([STATE_IDENTIFIER, token])
token = ''
state = STATE_START
elif state == STATE_STRING:
token += char
else:
if state == STATE_IDENTIFIER:
result.append([STATE_IDENTIFIER, token])
token = ''
state = STATE_START
result.append([STATE_SPECIAL_CHAR, char])
elif state == STATE_STRING:
token += char
else:
result.append([STATE_SPECIAL_CHAR, char])
token = ''
if state == STATE_IDENTIFIER:
result.append([state, token])
elif state == STATE_STRING:
result = [[STATE_ERROR, 'Error: string not closed', token]]
return result
def ParseFunction(tokens):
if len(tokens) == 0:
print('Parsing error')
return None, tokens
if tokens[0][0] == STATE_STRING or tokens[0][0] == STATE_IDENTIFIER and tokens[0][1].startswith('0x'):
return [[FUNCTIONNAME_REPEAT, [[STATE_IDENTIFIER, '1'], tokens[0]]], tokens[1:]]
if tokens[0][0] != STATE_IDENTIFIER:
print('Parsing error')
return None, tokens
function = tokens[0][1]
tokens = tokens[1:]
if len(tokens) == 0:
print('Parsing error')
return None, tokens
if tokens[0][0] != STATE_SPECIAL_CHAR or tokens[0][1] != '(':
print('Parsing error')
return None, tokens
tokens = tokens[1:]
if len(tokens) == 0:
print('Parsing error')
return None, tokens
arguments = []
while True:
if tokens[0][0] != STATE_IDENTIFIER and tokens[0][0] != STATE_STRING:
print('Parsing error')
return None, tokens
arguments.append(tokens[0])
tokens = tokens[1:]
if len(tokens) == 0:
print('Parsing error')
return None, tokens
if tokens[0][0] != STATE_SPECIAL_CHAR or (tokens[0][1] != ',' and tokens[0][1] != ')'):
print('Parsing error')
return None, tokens
if tokens[0][0] == STATE_SPECIAL_CHAR and tokens[0][1] == ')':
tokens = tokens[1:]
break
tokens = tokens[1:]
if len(tokens) == 0:
print('Parsing error')
return None, tokens
return [[function, arguments], tokens]
def Parse(expression):
tokens = Tokenize(expression)
if len(tokens) == 0:
print('Parsing error')
return None
if tokens[0][0] == STATE_ERROR:
print(tokens[0][1])
print(tokens[0][2])
print(expression)
return None
functioncalls = []
while True:
functioncall, tokens = ParseFunction(tokens)
if functioncall == None:
return None
functioncalls.append(functioncall)
if len(tokens) == 0:
return functioncalls
if tokens[0][0] != STATE_SPECIAL_CHAR or tokens[0][1] != '+':
print('Parsing error')
return None
tokens = tokens[1:]
def InterpretInteger(token):
if token[0] != STATE_IDENTIFIER:
return None
try:
return int(token[1])
except:
return None
def Hex2Bytes(hexadecimal):
if len(hexadecimal) % 2 == 1:
hexadecimal = '0' + hexadecimal
try:
return binascii.a2b_hex(hexadecimal)
except:
return None
def InterpretHexInteger(token):
if token[0] != STATE_IDENTIFIER:
return None
if not token[1].startswith('0x'):
return None
bytes = Hex2Bytes(token[1][2:])
if bytes == None:
return None
integer = 0
for byte in bytes:
integer = integer * 0x100 + C2IIP2(byte)
return integer
def InterpretNumber(token):
number = InterpretInteger(token)
if number == None:
return InterpretHexInteger(token)
else:
return number
def InterpretBytes(token):
if token[0] == STATE_STRING:
return token[1]
if token[0] != STATE_IDENTIFIER:
return None
if not token[1].startswith('0x'):
return None
return Hex2Bytes(token[1][2:])
def CheckFunction(functionname, arguments, countarguments, maxcountarguments=None):
if maxcountarguments == None:
if countarguments == 0 and len(arguments) != 0:
print('Error: function %s takes no arguments, %d are given' % (functionname, len(arguments)))
return True
if countarguments == 1 and len(arguments) != 1:
print('Error: function %s takes 1 argument, %d are given' % (functionname, len(arguments)))
return True
if countarguments != len(arguments):
print('Error: function %s takes %d arguments, %d are given' % (functionname, countarguments, len(arguments)))
return True
else:
if len(arguments) < countarguments or len(arguments) > maxcountarguments:
print('Error: function %s takes between %d and %d arguments, %d are given' % (functionname, countarguments, maxcountarguments, len(arguments)))
return True
return False
def CheckNumber(argument, minimum=None, maximum=None):
number = InterpretNumber(argument)
if number == None:
print('Error: argument should be a number: %s' % argument[1])
return None
if minimum != None and number < minimum:
print('Error: argument should be minimum %d: %d' % (minimum, number))
return None
if maximum != None and number > maximum:
print('Error: argument should be maximum %d: %d' % (maximum, number))
return None
return number
def Interpret(expression):
functioncalls = Parse(expression)
if functioncalls == None:
return None
decoded = ''
for functioncall in functioncalls:
functionname, arguments = functioncall
if functionname == FUNCTIONNAME_REPEAT:
if CheckFunction(functionname, arguments, 2):
return None
number = CheckNumber(arguments[0], minimum=1)
if number == None:
return None
bytes = InterpretBytes(arguments[1])
if bytes == None:
print('Error: argument should be a byte sequence: %s' % arguments[1][1])
return None
decoded += number * bytes
elif functionname == FUNCTIONNAME_RANDOM:
if CheckFunction(functionname, arguments, 1):
return None
number = CheckNumber(arguments[0], minimum=1)
if number == None:
return None
decoded += ''.join([chr(random.randint(0, 255)) for x in range(number)])
elif functionname == FUNCTIONNAME_LOREMIPSUM:
if CheckFunction(functionname, arguments, 1):
return None
number = CheckNumber(arguments[0], minimum=1)
if number == None:
return None
decoded += LoremIpsum(number)
elif functionname == FUNCTIONNAME_CHR:
if CheckFunction(functionname, arguments, 1, 2):
return None
number = CheckNumber(arguments[0], minimum=1, maximum=255)
if number == None:
return None
if len(arguments) == 1:
decoded += chr(number)
else:
number2 = CheckNumber(arguments[1], minimum=1, maximum=255)
if number2 == None:
return None
if number < number2:
decoded += ''.join([chr(n) for n in range(number, number2 + 1)])
else:
decoded += ''.join([chr(n) for n in range(number, number2 - 1, -1)])
else:
print('Error: unknown function: %s' % functionname)
return None
return decoded
FCH_FILENAME = 0
FCH_DATA = 1
FCH_ERROR = 2
def FilenameCheckHash(filename, literalfilename):
if literalfilename:
return FCH_FILENAME, filename
elif filename.startswith('#h#'):
result = Hex2Bytes(filename[3:])
if result == None:
return FCH_ERROR, 'hexadecimal'
else:
return FCH_DATA, result
elif filename.startswith('#b#'):
try:
return FCH_DATA, binascii.a2b_base64(filename[3:])
except:
return FCH_ERROR, 'base64'
elif filename.startswith('#e#'):
result = Interpret(filename[3:])
if result == None:
return FCH_ERROR, 'expression'
else:
return FCH_DATA, result
elif filename.startswith('#'):
return FCH_DATA, C2BIP3(filename[1:])
else:
return FCH_FILENAME, filename
def AnalyzeFileError(filename):
PrintError('Error opening file %s' % filename)
PrintError(sys.exc_info()[1])
try:
if not os.path.exists(filename):
PrintError('The file does not exist')
elif os.path.isdir(filename):
PrintError('The file is a directory')
elif not os.path.isfile(filename):
PrintError('The file is not a regular file')
except:
pass
class cBinaryFile:
def __init__(self, filename, zippassword='infected', noextraction=False, literalfilename=False):
self.filename = filename
self.zippassword = zippassword
self.noextraction = noextraction
self.literalfilename = literalfilename
self.oZipfile = None
self.extracted = False
self.fIn = None
fch, data = FilenameCheckHash(self.filename, self.literalfilename)
if fch == FCH_ERROR:
line = 'Error %s parsing filename: %s' % (data, self.filename)
raise Exception(line)
try:
if self.filename == '':
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY)
self.fIn = sys.stdin
elif fch == FCH_DATA:
self.fIn = DataIO(data)
elif not self.noextraction and self.filename.lower().endswith('.zip'):
self.oZipfile = zipfile.ZipFile(self.filename, 'r')
if len(self.oZipfile.infolist()) == 1:
self.fIn = self.oZipfile.open(self.oZipfile.infolist()[0], 'r', self.zippassword)
self.extracted = True
else:
self.oZipfile.close()
self.oZipfile = None
self.fIn = open(self.filename, 'rb')
elif not self.noextraction and self.filename.lower().endswith('.gz'):
self.fIn = gzip.GzipFile(self.filename, 'rb')
self.extracted = True
else:
self.fIn = open(self.filename, 'rb')
except:
AnalyzeFileError(self.filename)
raise
def close(self):
if self.fIn != sys.stdin and self.fIn != None:
self.fIn.close()
if self.oZipfile != None:
self.oZipfile.close()
def read(self, size=None):
try:
fRead = self.fIn.buffer
except:
fRead = self.fIn
if size == None:
return fRead.read()
else:
return fRead.read(size)
def Data(self):
data = self.fIn.read()
self.close()
return data
#-ENDCODE cBinaryFile--------------------------------------------------------------------------------
def File2Strings(filename):
try:
if filename == '':
f = sys.stdin
else:
f = open(filename, 'r')
except:
return None
try:
return map(lambda line:line.rstrip('\n'), f.readlines())
except:
return None
finally:
if f != sys.stdin:
f.close()
def ProcessAt(argument):
if argument.startswith('@'):
strings = File2Strings(argument[1:])
if strings == None:
raise Exception('Error reading %s' % argument)
else:
return strings
else:
return [argument]
def Glob(filename):
filenames = glob.glob(filename)
if len(filenames) == 0:
return [filename]
else:
return filenames
class cExpandFilenameArguments():
def __init__(self, filenames, literalfilenames=False, recursedir=False, checkfilenames=False, expressionprefix=None):
self.containsUnixShellStyleWildcards = False
self.warning = False
self.message = ''
self.filenameexpressions = []
self.expressionprefix = expressionprefix
self.literalfilenames = literalfilenames
expression = ''
if len(filenames) == 0:
self.filenameexpressions = [['', '']]
elif literalfilenames:
self.filenameexpressions = [[filename, ''] for filename in filenames]
elif recursedir:
for dirwildcard in filenames:
if expressionprefix != None and dirwildcard.startswith(expressionprefix):
expression = dirwildcard[len(expressionprefix):]
else:
if dirwildcard.startswith('@'):
for filename in ProcessAt(dirwildcard):
self.filenameexpressions.append([filename, expression])
elif os.path.isfile(dirwildcard):
self.filenameexpressions.append([dirwildcard, expression])
else:
if os.path.isdir(dirwildcard):
dirname = dirwildcard
basename = '*'
else:
dirname, basename = os.path.split(dirwildcard)
if dirname == '':
dirname = '.'
for path, dirs, files in os.walk(dirname):
for filename in fnmatch.filter(files, basename):
self.filenameexpressions.append([os.path.join(path, filename), expression])
else:
for filename in list(collections.OrderedDict.fromkeys(sum(map(self.Glob, sum(map(ProcessAt, filenames), [])), []))):
if expressionprefix != None and filename.startswith(expressionprefix):
expression = filename[len(expressionprefix):]
else:
self.filenameexpressions.append([filename, expression])
self.warning = self.containsUnixShellStyleWildcards and len(self.filenameexpressions) == 0
if self.warning:
self.message = "Your filename argument(s) contain Unix shell-style wildcards, but no files were matched.\nCheck your wildcard patterns or use option literalfilenames if you don't want wildcard pattern matching."
return
if self.filenameexpressions == [] and expression != '':
self.filenameexpressions = [['', expression]]
if checkfilenames:
self.CheckIfFilesAreValid()
def Glob(self, filename):
if not ('?' in filename or '*' in filename or ('[' in filename and ']' in filename)):
return [filename]
self.containsUnixShellStyleWildcards = True
return glob.glob(filename)
def CheckIfFilesAreValid(self):
valid = []
doesnotexist = []
isnotafile = []
for filename, expression in self.filenameexpressions:
hashfile = False
try:
hashfile = FilenameCheckHash(filename, self.literalfilenames)[0] == FCH_DATA
except:
pass
if filename == '' or hashfile:
valid.append([filename, expression])
elif not os.path.exists(filename):
doesnotexist.append(filename)
elif not os.path.isfile(filename):
isnotafile.append(filename)
else:
valid.append([filename, expression])
self.filenameexpressions = valid
if len(doesnotexist) > 0:
self.warning = True
self.message += 'The following files do not exist and will be skipped: ' + ' '.join(doesnotexist) + '\n'
if len(isnotafile) > 0:
self.warning = True
self.message += 'The following files are not regular files and will be skipped: ' + ' '.join(isnotafile) + '\n'
def Filenames(self):
if self.expressionprefix == None:
return [filename for filename, expression in self.filenameexpressions]
else:
return self.filenameexpressions
def CheckJSON(stringJSON):
try:
object = json.loads(stringJSON)
except:
print('Error parsing JSON')
print(sys.exc_info()[1])
return None
if not isinstance(object, dict):
print('Error JSON is not a dictionary')
return None
if not 'version' in object:
print('Error JSON dictionary has no version')
return None
if object['version'] != 2:
print('Error JSON dictionary has wrong version')
return None
if not 'id' in object:
print('Error JSON dictionary has no id')
return None
if object['id'] != 'didierstevens.com':
print('Error JSON dictionary has wrong id')
return None
if not 'type' in object:
print('Error JSON dictionary has no type')
return None
if object['type'] != 'content':
print('Error JSON dictionary has wrong type')
return None
if not 'fields' in object:
print('Error JSON dictionary has no fields')
return None
if not 'name' in object['fields']:
print('Error JSON dictionary has no name field')
return None
if not 'content' in object['fields']:
print('Error JSON dictionary has no content field')
return None
if not 'items' in object:
print('Error JSON dictionary has no items')
return None
for item in object['items']:
item['content'] = binascii.a2b_base64(item['content'])
return object['items']
CUTTERM_NOTHING = 0
CUTTERM_POSITION = 1
CUTTERM_FIND = 2
CUTTERM_LENGTH = 3
def Replace(string, dReplacements):
if string in dReplacements:
return dReplacements[string]
else:
return string
def ParseCutTerm(argument):
if argument == '':
return CUTTERM_NOTHING, None, ''
oMatch = re.match(r'\-?0x([0-9a-f]+)', argument, re.I)
if oMatch == None:
oMatch = re.match(r'\-?(\d+)', argument)
else:
value = int(oMatch.group(1), 16)
if argument.startswith('-'):
value = -value
return CUTTERM_POSITION, value, argument[len(oMatch.group(0)):]
if oMatch == None:
oMatch = re.match(r'\[([0-9a-f]+)\](\d+)?([+-]\d+)?', argument, re.I)
else:
value = int(oMatch.group(1))
if argument.startswith('-'):
value = -value
return CUTTERM_POSITION, value, argument[len(oMatch.group(0)):]
if oMatch == None:
oMatch = re.match(r"\[\'(.+?)\'\](\d+)?([+-]\d+)?", argument)
else:
if len(oMatch.group(1)) % 2 == 1:
raise Exception("Uneven length hexadecimal string")
else:
return CUTTERM_FIND, (binascii.a2b_hex(oMatch.group(1)), int(Replace(oMatch.group(2), {None: '1'})), int(Replace(oMatch.group(3), {None: '0'}))), argument[len(oMatch.group(0)):]
if oMatch == None:
return None, None, argument
else:
return CUTTERM_FIND, (oMatch.group(1), int(Replace(oMatch.group(2), {None: '1'})), int(Replace(oMatch.group(3), {None: '0'}))), argument[len(oMatch.group(0)):]
def ParseCutArgument(argument):
type, value, remainder = ParseCutTerm(argument.strip())
if type == CUTTERM_NOTHING:
return CUTTERM_NOTHING, None, CUTTERM_NOTHING, None
elif type == None:
if remainder.startswith(':'):
typeLeft = CUTTERM_NOTHING
valueLeft = None
remainder = remainder[1:]
else:
return None, None, None, None
else:
typeLeft = type
valueLeft = value
if typeLeft == CUTTERM_POSITION and valueLeft < 0:
return None, None, None, None
if typeLeft == CUTTERM_FIND and valueLeft[1] == 0:
return None, None, None, None
if remainder.startswith(':'):
remainder = remainder[1:]
else:
return None, None, None, None
type, value, remainder = ParseCutTerm(remainder)
if type == CUTTERM_POSITION and remainder == 'l':
return typeLeft, valueLeft, CUTTERM_LENGTH, value
elif type == None or remainder != '':
return None, None, None, None
elif type == CUTTERM_FIND and value[1] == 0:
return None, None, None, None
else:
return typeLeft, valueLeft, type, value
def Find(data, value, nth):
position = -1
while nth > 0:
position = data.find(value, position + 1)
if position == -1:
return -1
nth -= 1
return position
def CutData(stream, cutArgument):
if cutArgument == '':
return stream
typeLeft, valueLeft, typeRight, valueRight = ParseCutArgument(cutArgument)
if typeLeft == None:
return stream
if typeLeft == CUTTERM_NOTHING:
positionBegin = 0
elif typeLeft == CUTTERM_POSITION:
positionBegin = valueLeft
elif typeLeft == CUTTERM_FIND:
positionBegin = Find(stream, valueLeft[0], valueLeft[1])
if positionBegin == -1:
return ''
positionBegin += valueLeft[2]
else:
raise Exception("Unknown value typeLeft")
if typeRight == CUTTERM_NOTHING:
positionEnd = len(stream)
elif typeRight == CUTTERM_POSITION and valueRight < 0:
positionEnd = len(stream) + valueRight
elif typeRight == CUTTERM_POSITION:
positionEnd = valueRight + 1
elif typeRight == CUTTERM_LENGTH:
positionEnd = positionBegin + valueRight
elif typeRight == CUTTERM_FIND:
positionEnd = Find(stream, valueRight[0], valueRight[1])
if positionEnd == -1:
return ''
else: