/
iocextract.py
762 lines (627 loc) · 23.4 KB
/
iocextract.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
"""Extract and optionally refang Indicators of Compromise (IOCs) from text.
All methods return iterator objects, not lists. If for some reason you need
a list, do e.g.: ``list(extract_iocs(my_data))``.
Otherwise, you can iterate over the objects (e.g. in a ``for`` loop) normally.
Each object yielded from the generators will by of type :class:`str`.
"""
import io
import sys
import itertools
import argparse
import binascii
import base64
try:
# python3
from urllib.parse import urlparse, unquote
unicode = str
except ImportError:
from urlparse import urlparse
from urllib import unquote
import ipaddress
import regex as re
# Reusable end punctuation regex.
END_PUNCTUATION = r"[\.\?>\"'\)!,}:;\u201d\u2019\uff1e\uff1c\]]*"
# Reusable regex for symbols commonly used to defang.
SEPARATOR_DEFANGS = r"[\(\)\[\]{}<>\\]"
# Split URLs on some characters that may be valid, but may also be garbage.
URL_SPLIT_STR = r"[>\"'\),};]"
# Get basic url format, including a few obfuscation techniques, main anchor is the uri scheme.
GENERIC_URL_RE = re.compile(r"""
(
# Scheme.
[fhstu]\S\S?[px]s?
# One of these delimiters/defangs.
(?:
:\/\/|
:\\\\|
:?__
)
# Any number of defang characters.
(?:
\x20|
""" + SEPARATOR_DEFANGS + r"""
)*
# Domain/path characters.
\w
\S+?
# CISCO ESA style defangs followed by domain/path characters.
(?:\x20[\/\.][^\.\/\s]\S*?)*
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.IGNORECASE | re.VERBOSE | re.UNICODE)
# Get some obfuscated urls, main anchor is brackets around the period.
BRACKET_URL_RE = re.compile(r"""
\b
(
[\.\:\/\\\w\[\]\(\)-]+
(?:
\x20?
[\(\[]
\x20?
\.
\x20?
[\]\)]
\x20?
\S*?
)+
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.VERBOSE | re.UNICODE)
# Get some obfuscated urls, main anchor is backslash before a period.
BACKSLASH_URL_RE = re.compile(r"""
\b
(
[\:\/\\\w\[\]\(\)-]+
(?:
\x20?
\\?\.
\x20?
\S*?
)*?
(?:
\x20?
\\\.
\x20?
\S*?
)
(?:
\x20?
\\?\.
\x20?
\S*?
)*
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.VERBOSE | re.UNICODE)
# Get hex-encoded urls.
HEXENCODED_URL_RE = re.compile(r"""
(
[46][86]
(?:[57]4)?
[57]4[57]0
(?:[57]3)?
3a2f2f
(?:2[356def]|3[0-9adf]|[46][0-9a-f]|[57][0-9af])+
)
(?:[046]0|2[0-2489a-c]|3[bce]|[57][b-e]|[8-f][0-9a-f]|0a|0d|09|[
\x5b-\x5d\x7b\x7d\x0a\x0d\x20
]|$)
""", re.IGNORECASE | re.VERBOSE)
# Get urlencoded urls.
URLENCODED_URL_RE = re.compile(r"""
(s?[hf]t?tps?%3A%2F%2F\w[\w%-]*?)(?:[^\w%-]|$)
""", re.IGNORECASE | re.VERBOSE)
# Get base64-encoded urls.
B64ENCODED_URL_RE = re.compile(r"""
(
# b64re '([hH][tT][tT][pP][sS]|[hH][tT][tT][pP]|[fF][tT][pP])://'
# Modified to ignore whitespace.
(?:
[\x2b\x2f-\x39A-Za-z]\s*[\x2b\x2f-\x39A-Za-z]\s*[\x31\x35\x39BFJNRVZdhlptx]\s*[Gm]\s*[Vd]\s*[FH]\s*[A]\s*\x36\s*L\s*y\s*[\x2b\x2f\x38-\x39]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x2b\x2f-\x39A-Za-z]\s*[\x31\x35\x39BFJNRVZdhlptx]\s*[Io]\s*[Vd]\s*[FH]\s*[R]\s*[Qw]\s*[O]\s*i\s*\x38\s*v\s*[\x2b\x2f-\x39A-Za-z]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x2b\x2f-\x39A-Za-z]\s*[\x31\x35\x39BFJNRVZdhlptx]\s*[Io]\s*[Vd]\s*[FH]\s*[R]\s*[Qw]\s*[Uc]\s*[z]\s*o\s*v\s*L\s*[\x2b\x2f-\x39w-z]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x30\x32EGUWkm]\s*[Z]\s*[\x30U]\s*[Uc]\s*[D]\s*o\s*v\s*L\s*[\x2b\x2f-\x39w-z]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x30\x32EGUWkm]\s*[h]\s*[\x30U]\s*[Vd]\s*[FH]\s*[A]\s*\x36\s*L\s*y\s*[\x2b\x2f\x38-\x39]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x30\x32EGUWkm]\s*[h]\s*[\x30U]\s*[Vd]\s*[FH]\s*[B]\s*[Tz]\s*[O]\s*i\s*\x38\s*v\s*[\x2b\x2f-\x39A-Za-z]\s*|
[RZ]\s*[ln]\s*[R]\s*[Qw]\s*[O]\s*i\s*\x38\s*v\s*[\x2b\x2f-\x39A-Za-z]\s*|
[Sa]\s*[FH]\s*[R]\s*[\x30U]\s*[Uc]\s*[D]\s*o\s*v\s*L\s*[\x2b\x2f-\x39w-z]\s*|
[Sa]\s*[FH]\s*[R]\s*[\x30U]\s*[Uc]\s*[FH]\s*[M]\s*\x36\s*L\s*y\s*[\x2b\x2f\x38-\x39]\s*
)
# Up to 260 characters (pre-encoding, reasonable URL length).
[A-Za-z0-9+/=\s]{1,357}
)
(?=[^A-Za-z0-9+/=\s]|$)
""", re.VERBOSE)
# Get some valid obfuscated ip addresses.
IPV4_RE = re.compile(r"""
(?:^|
(?![^\d\.])
)
(?:
(?:[1-9]?\d|1\d\d|2[0-4]\d|25[0-5])
[\[\(\\]*?\.[\]\)]*?
){3}
(?:[1-9]?\d|1\d\d|2[0-4]\d|25[0-5])
(?:(?=[^\d\.])|$)
""", re.VERBOSE)
# Experimental IPv6 regex, will not catch everything but should be sufficent for now.
IPV6_RE = re.compile(r"""
\b(?:[a-f0-9]{1,4}:|:){2,7}(?:[a-f0-9]{1,4}|:)\b
""", re.IGNORECASE | re.VERBOSE)
# Capture email addresses including common defangs.
EMAIL_RE = re.compile(r"""
(
[a-z0-9_.+-]+
[\(\[{\x20]*
(?:@|\Wat\W)
[\)\]}\x20]*
[a-z0-9-]+
(?:
(?:
(?:
\x20*
""" + SEPARATOR_DEFANGS + r"""
\x20*
)*
\.
(?:
\x20*
""" + SEPARATOR_DEFANGS + r"""
\x20*
)*
|
\W+dot\W+
)
[a-z0-9-]+?
)+
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.IGNORECASE | re.VERBOSE | re.UNICODE)
MD5_RE = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{32})(?:[^a-fA-F\d]|\b)")
SHA1_RE = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{40})(?:[^a-fA-F\d]|\b)")
SHA256_RE = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{64})(?:[^a-fA-F\d]|\b)")
SHA512_RE = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{128})(?:[^a-fA-F\d]|\b)")
# YARA regex.
YARA_PARSE_RE = re.compile(r"""
(?:^|\s)
(
(?:
\s*?import\s+?"[^\r\n]*?[\r\n]+|
\s*?include\s+?"[^\r\n]*?[\r\n]+|
\s*?//[^\r\n]*[\r\n]+|
\s*?/\*.*?\*/\s*?
)*
(?:
\s*?private\s+|
\s*?global\s+
)*
rule\s*?
\w+\s*?
(?:
:[\s\w]+
)?
\s+\{
.*?
condition\s*?:
.*?
\s*\}
)
(?:$|\s)
""", re.MULTILINE | re.DOTALL | re.VERBOSE)
def extract_iocs(data, refang=False, strip=False):
"""Extract all IOCs.
Results are returned as an itertools.chain iterable object which
lazily provides the results of the other extract_* generators.
:param data: Input text
:param bool refang: Refang output?
:param bool strip: Strip possible garbage from the end of URLs
:rtype: :py:func:`itertools.chain`
"""
return itertools.chain(
extract_urls(data, refang=refang, strip=strip),
extract_ips(data, refang=refang),
extract_emails(data, refang=refang),
extract_hashes(data),
extract_yara_rules(data)
)
def extract_urls(data, refang=False, strip=False):
"""Extract URLs.
:param data: Input text
:param bool refang: Refang output?
:param bool strip: Strip possible garbage from the end of URLs
:rtype: :py:func:`itertools.chain`
"""
return itertools.chain(
extract_unencoded_urls(data, refang=refang, strip=strip),
extract_encoded_urls(data, refang=refang, strip=strip),
)
def extract_unencoded_urls(data, refang=False, strip=False):
"""Extract only unencoded URLs.
:param data: Input text
:param bool refang: Refang output?
:param bool strip: Strip possible garbage from the end of URLs
:rtype: Iterator[:class:`str`]
"""
unencoded_urls = itertools.chain(
GENERIC_URL_RE.finditer(data),
BRACKET_URL_RE.finditer(data),
BACKSLASH_URL_RE.finditer(data),
)
for url in unencoded_urls:
if refang:
url = refang_url(url.group(1))
else:
url = url.group(1)
if strip:
url = re.split(URL_SPLIT_STR, url)[0]
yield url
def extract_encoded_urls(data, refang=False, strip=False):
"""Extract only encoded URLs.
:param data: Input text
:param bool refang: Decode output?
:param bool strip: Strip possible garbage from the end of URLs
:rtype: Iterator[:class:`str`]
"""
for url in HEXENCODED_URL_RE.finditer(data):
if refang:
yield binascii.unhexlify(url.group(1)).decode('utf-8')
else:
yield url.group(1)
for url in URLENCODED_URL_RE.finditer(data):
if refang:
yield unquote(url.group(1))
else:
yield url.group(1)
for url in B64ENCODED_URL_RE.finditer(data):
# Strip whitespace.
url = ''.join(url.group(1).split())
# Truncate the string if it's not a multiple of 3 bytes long.
# We don't care about the end of the string since it's probably garbage.
if len(url) % 4:
url = url[:-(len(url) % 4)]
if refang:
# Decode base64.
url = base64.b64decode(url).decode('utf-8', 'replace')
# Remove the first 1-2 bytes if we got back extra leading characters from the base64.
# The only valid starts are "http" or "ftp", so look for h/f case insensitive.
url = url[re.search('[hHfF]', url).start():]
# Stop at the first whitespace or non-unicode character.
url = url.split(u'\ufffd')[0].\
split()[0]
if strip:
url = re.split(URL_SPLIT_STR, url)[0]
yield url
def extract_ips(data, refang=False):
"""Extract IP addresses.
Includes both IPv4 and IPv6 addresses.
:param data: Input text
:param bool refang: Refang output?
:rtype: :py:func:`itertools.chain`
"""
return itertools.chain(
extract_ipv4s(data, refang=refang),
extract_ipv6s(data),
)
def extract_ipv4s(data, refang=False):
"""Extract IPv4 addresses.
:param data: Input text
:param bool refang: Refang output?
:rtype: Iterator[:class:`str`]
"""
for ip_address in IPV4_RE.finditer(data):
if refang:
yield refang_ipv4(ip_address.group(0))
else:
yield ip_address.group(0)
def extract_ipv6s(data):
"""Extract IPv6 addresses.
Not guaranteed to catch all valid IPv6 addresses.
:param data: Input text
:rtype: Iterator[:class:`str`]
"""
for ip_address in IPV6_RE.finditer(data):
yield ip_address.group(0)
def extract_emails(data, refang=False):
"""Extract email addresses.
:param data: Input text
:param bool refang: Refang output?
:rtype: Iterator[:class:`str`]
"""
for email in EMAIL_RE.finditer(data):
if refang:
email = refang_email(email.group(1))
else:
email = email.group(1)
yield email
def extract_hashes(data):
"""Extract MD5/SHA hashes.
Results are returned as an itertools.chain iterable object which
lazily provides the results of the other extract_*_hashes generators.
:param data: Input text
:rtype: :py:func:`itertools.chain`
"""
return itertools.chain(
extract_md5_hashes(data),
extract_sha1_hashes(data),
extract_sha256_hashes(data),
extract_sha512_hashes(data)
)
def extract_md5_hashes(data):
"""Extract MD5 hashes.
:param data: Input text
:rtype: Iterator[:class:`str`]
"""
for md5 in MD5_RE.finditer(data):
yield md5.group(1)
def extract_sha1_hashes(data):
"""Extract SHA1 hashes.
:param data: Input text
:rtype: Iterator[:class:`str`]
"""
for sha1 in SHA1_RE.finditer(data):
yield sha1.group(1)
def extract_sha256_hashes(data):
"""Extract SHA256 hashes.
:param data: Input text
:rtype: Iterator[:class:`str`]
"""
for sha256 in SHA256_RE.finditer(data):
yield sha256.group(1)
def extract_sha512_hashes(data):
"""Extract SHA512 hashes.
:param data: Input text
:rtype: Iterator[:class:`str`]
"""
for sha512 in SHA512_RE.finditer(data):
yield sha512.group(1)
def extract_yara_rules(data):
"""Extract YARA rules.
:param data: Input text
:rtype: Iterator[:class:`str`]
"""
for yara_rule in YARA_PARSE_RE.finditer(data):
yield yara_rule.group(1).strip()
def extract_custom_iocs(data, regex_list):
"""Extract using custom regex strings.
Will always yield only the first *group* match from each regex.
Always use a single capture group! Do this::
[
r'(my regex)', # This yields 'my regex' if the pattern matches.
r'my (re)gex', # This yields 're' if the pattern matches.
]
NOT this::
[
r'my regex', # BAD! This doesn't yield anything.
r'(my) (re)gex', # BAD! This yields 'my' if the pattern matches.
]
For complicated regexes, you can combine capture and non-capture groups,
like this::
[
r'(?:my|your) (re)gex', # This yields 're' if the pattern matches.
]
Note the (?: ) syntax for noncapture groups vs the ( ) syntax for the capture
group.
:param data: Input text
:param regex_list: List of strings to treat as regex and match against data.
:rtype: Iterator[:class:`str`]
"""
# Compile all the regex strings first, so we can error out quickly.
regex_objects = []
for regex_string in regex_list:
regex_objects.append(re.compile(regex_string))
# Iterate over regex objects, running each against input data.
for regex_object in regex_objects:
for ioc in regex_object.finditer(data):
yield ioc.group(1)
def _is_ipv6_url(url):
"""URL network location is an IPv6 address, not a domain.
:param url: String URL
:rtype: bool
"""
# Fix urlparse exception.
parsed = urlparse(url)
# Handle RFC 2732 IPv6 URLs with and without port, as well as non-RFC IPv6 URLs.
if ']:' in parsed.netloc:
ipv6 = ':'.join(parsed.netloc.split(':')[:-1])
else:
ipv6 = parsed.netloc
try:
ipaddress.IPv6Address(unicode(ipv6.replace('[', '').replace(']', '')))
except ValueError:
return False
return True
def _refang_common(ioc):
"""Remove artifacts from common defangs.
:param ioc: String IP/Email Address or URL netloc.
:rtype: str
"""
return ioc.replace('[dot]', '.').\
replace('(dot)', '.').\
replace('[.]', '.').\
replace('(', '').\
replace(')', '').\
replace(',', '.').\
replace(' ', '').\
replace(u'\u30fb', '.')
def refang_email(email):
"""Refang an email address.
:param email: String email address.
:rtype: str
"""
# Check for ' at ' and ' dot ' first.
email = re.sub('\W[aA][tT]\W', '@', email.lower())
email = re.sub('\W*[dD][oO][tT]\W*', '.', email)
# Then do other char replaces.
return _refang_common(email).replace('[', '').\
replace(']', '').\
replace('{', '').\
replace('}', '').\
replace('{', '')
def refang_url(url):
"""Refang a URL.
:param url: String URL
:rtype: str
"""
# First fix urlparse errors.
# Fix ipv6 parsing exception.
if '[.' in url and '[.]' not in url:
url = url.replace('[.', '[.]')
if '.]' in url and '[.]' not in url:
url = url.replace('.]', '[.]')
if '[dot' in url and '[dot]' not in url:
url = url.replace('[dot', '[.]')
if 'dot]' in url and '[dot]' not in url:
url = url.replace('dot]', '[.]')
if '[/]' in url:
url = url.replace('[/]', '/')
# Since urlparse expects a scheme, make sure one exists.
if '//' not in url:
if '__' in url[:8]:
# Support http__domain and http:__domain.
if ':__' in url[:8]:
url = url.replace(':__', '://', 1)
else:
url = url.replace('__', '://', 1)
elif '\\\\' in url[:8]:
# Support http:\\domain.
url = url.replace('\\\\', '//', 1)
else:
# Support no-protocol.
url = 'http://' + url
# Refang (/), since it's not entirely in the netloc.
url = url.replace('(/)', '/')
# Refang some backslash-escaped characters.
url = url.replace('\.', '.').\
replace('\(', '(').\
replace('\[', '[').\
replace('\)', ')').\
replace('\]', ']')
try:
_ = urlparse(url)
except ValueError:
# Last resort on ipv6 fail.
url = url.replace('[', '').replace(']', '')
# Now use urlparse and continue processing.
parsed = urlparse(url)
# Handle URLs with no scheme / obfuscated scheme.
# Note: ParseResult._replace is a public member, this is safe.
if parsed.scheme not in ['http', 'https', 'ftp']:
if parsed.scheme.strip('s') in ['ftx', 'fxp']:
parsed = parsed._replace(scheme='ftp')
url = parsed.geturl().replace('ftp:///', 'ftp://')
else:
parsed = parsed._replace(scheme='http')
url = parsed.geturl().replace('http:///', 'http://')
try:
_ = urlparse(url)
except ValueError:
# Last resort on ipv6 fail.
url = url.replace('[', '').replace(']', '')
parsed = urlparse(url)
# Remove artifacts from common defangs.
parsed = parsed._replace(netloc=_refang_common(parsed.netloc))
parsed = parsed._replace(path=parsed.path.replace('[.]', '.'))
# Fix example[.]com, but keep RFC 2732 URLs intact.
if not _is_ipv6_url(url):
parsed = parsed._replace(netloc=parsed.netloc.replace('[', '').replace(']', ''))
return parsed.geturl()
def refang_ipv4(ip_address):
"""Refang an IPv4 address.
:param ip_address: String IPv4 address.
:rtype: str
"""
return _refang_common(ip_address).replace('[', '').\
replace(']', '').\
replace('\\', '')
def defang(ioc):
"""Defang a URL, domain, or IPv4 address.
:param ioc: String URL, domain, or IPv4 address.
:rtype: str
"""
# If it's a url, defang just the scheme and netloc.
try:
parsed = urlparse(ioc)
if parsed.netloc:
parsed = parsed._replace(netloc=parsed.netloc.replace('.', '[.]'),
scheme=parsed.scheme.replace('t', 'x'))
return parsed.geturl()
except ValueError:
pass
# If it's a domain or IP, defang up to the first slash.
split_list = ioc.split('/')
defanged = split_list[0].replace('.', '[.]')
# Include everything after the first slash without modification.
if len(split_list) > 1:
defanged = '/'.join([defanged] + split_list[1:])
return defanged
def main():
"""Run as a commandline utility."""
parser = argparse.ArgumentParser(
description="""Advanced Indicator of Compromise (IOC) extractor.
If no arguments are specified, the default behavior is
to extract all IOCs.""")
parser.add_argument('--input', type=lambda x: io.open(x, 'r', encoding='utf-8', errors='ignore'),
default=io.open(0, 'r', encoding='utf-8', errors='ignore'), help="default: stdin")
parser.add_argument('--output', type=lambda x: io.open(x, 'w', encoding='utf-8', errors='ignore'),
default=io.open(1, 'w', encoding='utf-8', errors='ignore'), help="default: stdout")
parser.add_argument('--extract-emails', action='store_true')
parser.add_argument('--extract-ips', action='store_true')
parser.add_argument('--extract-ipv4s', action='store_true')
parser.add_argument('--extract-ipv6s', action='store_true')
parser.add_argument('--extract-urls', action='store_true')
parser.add_argument('--extract-yara-rules', action='store_true')
parser.add_argument('--extract-hashes', action='store_true')
parser.add_argument('--custom-regex', type=lambda x: io.open(x, 'r', encoding='utf-8', errors='ignore'),
metavar='REGEX_FILE',
help="file with custom regex strings, one per line, with one capture group each")
parser.add_argument('--refang', action='store_true', help="default: no")
parser.add_argument('--strip-urls', action='store_true',
help="remove possible garbage from the end of urls. default: no")
parser.add_argument('--wide', action='store_true',
help="preprocess input to allow wide-encoded character matches. default: no")
args = parser.parse_args()
# Read input.
data = args.input.read()
if args.wide:
data = data.replace('\x00', '')
# By default, extract all.
if not (args.extract_ips or args.extract_urls or args.extract_yara_rules or args.extract_hashes or
args.extract_ipv4s or args.extract_ipv6s or args.extract_emails or args.custom_regex):
for ioc in extract_iocs(data, refang=args.refang, strip=args.strip_urls):
args.output.write(u"{ioc}\n".format(ioc=ioc))
else:
if args.extract_emails:
for ioc in extract_emails(data, refang=args.refang):
args.output.write(u"{ioc}\n".format(ioc=ioc))
if args.extract_ips:
for ioc in extract_ips(data, refang=args.refang):
args.output.write(u"{ioc}\n".format(ioc=ioc))
if args.extract_ipv4s:
for ioc in extract_ipv4s(data, refang=args.refang):
args.output.write(u"{ioc}\n".format(ioc=ioc))
if args.extract_ipv6s:
for ioc in extract_ipv6s(data):
args.output.write(u"{ioc}\n".format(ioc=ioc))
if args.extract_urls:
for ioc in extract_urls(data, refang=args.refang, strip=args.strip_urls):
args.output.write(u"{ioc}\n".format(ioc=ioc))
if args.extract_yara_rules:
for ioc in extract_yara_rules(data):
args.output.write(u"{ioc}\n".format(ioc=ioc))
if args.extract_hashes:
for ioc in extract_hashes(data):
args.output.write(u"{ioc}\n".format(ioc=ioc))
# Custom regex file, one per line.
if args.custom_regex:
regex_list = [l.strip() for l in args.custom_regex.readlines()]
try:
for ioc in extract_custom_iocs(data, regex_list):
args.output.write(u"{ioc}\n".format(ioc=ioc))
except (IndexError, re.error) as e:
sys.stderr.write('Error in custom regex: {e}\n'.format(e=e))
if __name__ == "__main__":
main()