forked from smicallef/spiderfoot
-
Notifications
You must be signed in to change notification settings - Fork 0
/
sflib.py
692 lines (573 loc) · 25.7 KB
/
sflib.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
#-------------------------------------------------------------------------------
# Name: sflib
# Purpose: Common functions used by SpiderFoot modules.
# Also defines the SpiderFootPlugin abstract class for modules.
#
# Author: Steve Micallef <steve@binarypool.com>
#
# Created: 26/03/2012
# Copyright: (c) Steve Micallef 2012
# Licence: GPL
#-------------------------------------------------------------------------------
import inspect
import hashlib
import re
import os
import random
import socket
import sys
import time
import urllib2
class SpiderFoot:
dbh = None
scanGUID = None
# 'options' is a dictionary of options which changes the behaviour
# of how certain things are done in this module
# 'handle' will be supplied if the module is being used within the
# SpiderFoot GUI, in which case all feedback should be fed back
def __init__(self, options, handle=None):
self.handle = handle
self.opts = options
# Supplied an option value, return the data based on what the
# value is. If val is a URL, you'll get back the fetched content,
# if val is a file path it will be loaded and get back the contents,
# and if a string it will simply be returned back.
def optValueToData(self, val, fatal=True, splitLines=True):
if val.startswith('@'):
fname = val.split('@')[1]
try:
self.info("Loading configuration data from: " + fname)
f = open(fname, "r")
if splitLines:
arr = f.readlines()
ret = list()
for x in arr:
ret.append(x.rstrip('\n'))
else:
ret = f.read()
return ret
except BaseException as b:
if fatal:
self.error("Unable to open option file, " + fname + ".")
else:
return None
if val.lower().startswith('http://') or val.lower().startswith('https://'):
try:
self.info("Downloading configuration data from: " + val)
res = urllib2.urlopen(val)
data = res.read()
if splitLines:
return data.splitlines()
else:
return data
except BaseException as e:
if fatal:
self.error("Unable to open option URL, " + val + ".")
else:
return None
return val
# Called usually some time after instantiation
# to set up a database handle and scan GUID, used
# for logging events to the database about a scan.
def setDbh(self, handle):
self.dbh = handle
def setScanId(self, id):
self.scanGUID = id
def _dblog(self, level, message, component=None):
return self.dbh.scanLogEvent(self.scanGUID, level, message, component)
def error(self, error, exception=True):
if self.dbh == None:
print '[Error] ' + error
else:
self._dblog("ERROR", error)
if exception:
raise BaseException("Internal Error Encountered: " + error)
def fatal(self, error):
if self.dbh == None:
print '[Fatal] ' + error
else:
self._dblog("FATAL", error)
exit(-1)
def status(self, message):
if self.dbh == None:
print "[Status] " + message
else:
self._dblog("STATUS", message)
def info(self, message):
frm = inspect.stack()[1]
mod = inspect.getmodule(frm[0])
if mod == None:
modName = "Unknown"
else:
modName = mod.__name__
if self.dbh == None:
print '[' + modName + '] ' + message
else:
self._dblog("INFO", message, modName)
return
def debug(self, message):
if self.opts['_debug'] == False:
return
frm = inspect.stack()[1]
mod = inspect.getmodule(frm[0])
if mod == None:
modName = "Unknown"
else:
modName = mod.__name__
if self.dbh == None:
print '[' + modName + '] ' + message
else:
self._dblog("DEBUG", message, modName)
return
def myPath(self):
# This will get us the program's directory, even if we are frozen using py2exe.
# Determine whether we've been compiled by py2exe
if hasattr(sys, "frozen"):
return os.path.dirname(unicode(sys.executable, sys.getfilesystemencoding()))
return os.path.dirname(unicode(__file__, sys.getfilesystemencoding()))
#
# Configuration process
#
# Convert a Python dictionary to something storable
# in the database.
def configSerialize(self, opts, filterSystem=True):
storeopts = dict()
for opt in opts.keys():
# Filter out system temporary variables like GUID and others
if opt.startswith('__') and filterSystem:
continue
if type(opts[opt]) is int or type(opts[opt]) is str:
storeopts[opt] = opts[opt]
if type(opts[opt]) is bool:
if opts[opt]:
storeopts[opt] = 1
else:
storeopts[opt] = 0
if type(opts[opt]) is list:
storeopts[opt] = ','.join(opts[opt])
if not opts.has_key('__modules__'):
return storeopts
for mod in opts['__modules__']:
for opt in opts['__modules__'][mod]['opts']:
if opt.startswith('_') and filterSystem:
continue
if type(opts['__modules__'][mod]['opts'][opt]) is int or \
type(opts['__modules__'][mod]['opts'][opt]) is str:
storeopts[mod + ":" + opt] = opts['__modules__'][mod]['opts'][opt]
if type(opts['__modules__'][mod]['opts'][opt]) is bool:
if opts['__modules__'][mod]['opts'][opt]:
storeopts[mod + ":" + opt] = 1
else:
storeopts[mod + ":" + opt] = 0
if type(opts['__modules__'][mod]['opts'][opt]) is list:
storeopts[mod + ":" + opt] = ','.join(str(x) \
for x in opts['__modules__'][mod]['opts'][opt])
return storeopts
# Take strings, etc. from the database or UI and convert them
# to a dictionary for Python to process.
# referencePoint is needed to know the actual types the options
# are supposed to be.
def configUnserialize(self, opts, referencePoint, filterSystem=True):
returnOpts = referencePoint
# Global options
for opt in referencePoint.keys():
if opt.startswith('__') and filterSystem:
# Leave out system variables
continue
if opts.has_key(opt):
if type(referencePoint[opt]) is bool:
if opts[opt] == "1":
returnOpts[opt] = True
else:
returnOpts[opt] = False
if type(referencePoint[opt]) is str:
returnOpts[opt] = str(opts[opt])
if type(referencePoint[opt]) is int:
returnOpts[opt] = int(opts[opt])
if type(referencePoint[opt]) is list:
if type(referencePoint[opt][0]) is int:
returnOpts[opt] = list()
for x in str(opts[opt]).split(","):
returnOpts[opt].append(int(x))
else:
returnOpts[opt] = str(opts[opt]).split(",")
if not referencePoint.has_key('__modules__'):
return returnOpts
# Module options
# A lot of mess to handle typing..
for modName in referencePoint['__modules__']:
for opt in referencePoint['__modules__'][modName]['opts']:
if opt.startswith('_') and filterSystem:
continue
if opts.has_key(modName + ":" + opt):
if type(referencePoint['__modules__'][modName]['opts'][opt]) is bool:
if opts[modName + ":" + opt] == "1":
returnOpts['__modules__'][modName]['opts'][opt] = True
else:
returnOpts['__modules__'][modName]['opts'][opt] = False
if type(referencePoint['__modules__'][modName]['opts'][opt]) is str:
returnOpts['__modules__'][modName]['opts'][opt] = \
str(opts[modName + ":" + opt])
if type(referencePoint['__modules__'][modName]['opts'][opt]) is int:
returnOpts['__modules__'][modName]['opts'][opt] = \
int(opts[modName + ":" + opt])
if type(referencePoint['__modules__'][modName]['opts'][opt]) is list:
if type(referencePoint['__modules__'][modName]['opts'][opt][0]) is int:
returnOpts['__modules__'][modName]['opts'][opt] = list()
for x in str(opts[modName + ":" + opt]).split(","):
returnOpts['__modules__'][modName]['opts'][opt].append(int(x))
else:
returnOpts['__modules__'][modName]['opts'][opt] = \
str(opts[modName + ":" + opt]).split(",")
return returnOpts
#
# URL parsing functions
#
# Turn a relative path into an absolute path
def urlRelativeToAbsolute(self, url):
finalBits = list()
if '..' not in url:
return url
bits = url.split('/')
for chunk in bits:
if chunk == '..':
# Don't pop the last item off if we're at the top
if len(finalBits) <= 1:
continue
# Don't pop the last item off if the first bits are not the path
if '://' in url and len(finalBits) <= 3:
continue
finalBits.pop()
continue
finalBits.append(chunk)
self.debug('xfrmed rel to abs path: ' + url + ' to ' + '/'.join(finalBits))
return '/'.join(finalBits)
# Extract the top level directory from a URL
def urlBaseDir(self, url):
bits = url.split('/')
# For cases like 'www.somesite.com'
if len(bits) == 0:
self.debug('base dir of ' + url + ' not identified, using URL as base.')
return url + '/'
# For cases like 'http://www.blah.com'
if '://' in url and url.count('/') < 3:
self.debug('base dir of ' + url + ' is: ' + url + '/')
return url + '/'
base = '/'.join(bits[:-1])
self.debug('base dir of ' + url + ' is: ' + base + '/')
return base + '/'
# Extract the scheme and domain from a URL
# Does not return the trailing slash! So you can do .endswith()
# checks.
def urlBaseUrl(self, url):
if '://' in url:
bits = re.match('(\w+://.[^/:]*)[:/].*', url)
else:
bits = re.match('(.[^/:]*)[:/]', url)
if bits == None:
return url.lower()
self.debug('base url of ' + url + ' is: ' + bits.group(1))
return bits.group(1).lower()
# Extract the FQDN from a URL
def urlFQDN(self, url):
baseurl = self.urlBaseUrl(url)
# http://abc.com will split to ['http:', '', 'abc.com']
return baseurl.split('/')[2].lower()
# Extract the keyword (the domain without the TLD or any subdomains)
# from a domain. Crude for now.. just gets the first word.
def domainKeyword(self, domain):
return domain.split('.', 2)[0].lower()
#
# General helper functions to automate many common tasks between modules
#
# Parse the contents of robots.txt, returns a list of patterns
# which should not be followed
def parseRobotsTxt(self, robotsTxtData):
returnArr = list()
# We don't check the User-Agent rule yet.. probably should at some stage
for line in robotsTxtData.splitlines():
if line.lower().startswith('disallow:'):
m = re.match('disallow:\s*(.[^ #]*)', line, re.IGNORECASE)
self.debug('robots.txt parsing found disallow: ' + m.group(1))
returnArr.append(m.group(1))
continue
return returnArr
# Find all URLs within the supplied content. This does not fetch any URLs!
# A dictionary will be returned, where each link will have the keys
# 'source': The URL where the link was obtained from
# 'original': What the link looked like in the content it was obtained from
# The key will be the *absolute* URL of the link obtained, so for example if
# the link '/abc' was obtained from 'http://xyz.com', the key in the dict will
# be 'http://xyz.com/abc' with the 'original' attribute set to '/abc'
def parseLinks(self, url, data, domain):
returnLinks = dict()
if data == None or len(data) == 0:
self.debug('parseLinks() called with no data to parse')
return None
# Find actual links
try:
regRel = re.compile('(href|src|action|url)[:=][ \'\"]*(.[^\'\"<> ]*)',
re.IGNORECASE)
urlsRel = regRel.findall(data)
except Exception as e:
self.error("Error applying regex to: " + data)
return None
# Find potential links that aren't links (text possibly in comments, etc.)
try:
# Because we're working with a big blob of text now, don't worry
# about clobbering proper links by url decoding them.
data = urllib2.unquote(data)
regRel = re.compile('(.)([a-zA-Z0-9\-\.]+\.'+domain+')',
re.IGNORECASE)
urlsRel = urlsRel + regRel.findall(data)
except Exception as e:
self.error("Error applying regex2 to: " + data)
# Loop through all the URLs/links found by the regex
for linkTuple in urlsRel:
# Remember the regex will return two vars (two groups captured)
meta = linkTuple[0]
link = linkTuple[1]
absLink = None
# Don't include stuff likely part of some dynamically built incomplete
# URL found in Javascript code (character is part of some logic)
if link[len(link)-1] == '.' or link[0] == '+' or \
'javascript:' in link.lower() or '();' in link:
self.debug('unlikely link: ' + link)
continue
# Filter in-page links
if re.match('.*#.[^/]+', link):
self.debug('in-page link: ' + link)
continue
# Ignore mail links
if 'mailto:' in link.lower():
self.debug("Ignoring mail link: " + link)
continue
# URL decode links
if '%2f' in link.lower():
link = urllib2.unquote(link)
# Capture the absolute link:
# If the link contains ://, it is already an absolute link
if '://' in link:
absLink = link
# If the link starts with a /, the absolute link is off the base URL
if link.startswith('/'):
absLink = self.urlBaseUrl(url) + link
# Maybe the domain was just mentioned and not a link, so we make it one
if absLink == None and domain.lower() in link.lower():
absLink = 'http://' + link
# Otherwise, it's a flat link within the current directory
if absLink == None:
absLink = self.urlBaseDir(url) + link
# Translate any relative pathing (../)
absLink = self.urlRelativeToAbsolute(absLink)
returnLinks[absLink] = {'source': url, 'original': link}
return returnLinks
# Fetch a URL, return the response object
def fetchUrl(self, url, fatal=False, cookies=None, timeout=30,
useragent="SpiderFoot"):
result = {
'code': None,
'status': None,
'content': None,
'headers': None,
'realurl': None
}
if url == None:
self.error('Blank URL supplied to be fetched')
return result
try:
header = dict()
if type(useragent) is list:
header['User-Agent'] = random.choice(useragent)
else:
header['User-Agent'] = useragent
req = urllib2.Request(url, None, header)
if cookies != None:
req.add_header('cookie', cookies)
self.info("Fetching (incl. cookies): " + url + \
" [user-agent: " + header['User-Agent'] + "] [timeout: " + \
str(timeout) + "]")
else:
self.info("Fetching: " + url + " [user-agent: " + \
header['User-Agent'] + "] [timeout: " + str(timeout) + "]")
opener = urllib2.build_opener(SmartRedirectHandler())
fullPage = opener.open(req, timeout=timeout)
# Prepare result to return
result['content'] = unicode(fullPage.read(), 'utf-8', errors='replace')
result['headers'] = fullPage.info()
#print "FOR: " + url
#print "HEADERS: " + str(result['headers'])
result['realurl'] = fullPage.geturl()
result['code'] = fullPage.getcode()
result['status'] = 'OK'
except urllib2.HTTPError as h:
self.info("HTTP code " + str(h.code) + " encountered for " + url)
# Capture the HTTP error code
result['code'] = h.code
result['headers'] = h.info()
if fatal:
self.fatal('URL could not be fetched (' + h.code + ')')
except urllib2.URLError as e:
self.info("Error fetching " + url + "(" + str(e) + ")")
result['status'] = str(e)
if fatal:
self.fatal('URL could not be fetched (' + str(e) + ')')
except Exception as x:
self.info("Unexpected exception occurred fetching: " + url + "(" + str(x) + ")")
result['content'] = None
result['status'] = str(x)
if fatal:
self.fatal('URL could not be fetched (' + str(x) + ')')
return result
# Check if wildcard DNS is enabled by looking up two random hostnames
def checkDnsWildcard(self, target):
randpool = 'bcdfghjklmnpqrstvwxyz3456789'
randhost1 = ''.join([random.choice(randpool) for x in range(6)])
randhost2 = ''.join([random.choice(randpool) for x in range(10)])
# An exception will be raised if either of the resolutions fail
try:
addrs = socket.gethostbyname_ex(randhost1 + "." + target)
addrs = socket.gethostbyname_ex(randhost2 + "." + target)
self.debug(target + " has wildcard DNS.")
return True
except BaseException as e:
self.debug(target + " does not have wildcard DNS.")
return False
#
# SpiderFoot plug-in module base class
#
class SpiderFootPlugin(object):
# Will be set to True by the controller if the user aborts scanning
_stopScanning = False
# Modules that will be notified when this module produces events
_listenerModules = list()
# Current event being processed
_currentEvent = None
# Name of this module, set at startup time
__name__ = "module_name_not_set!"
# Not really needed in most cases.
def __init__(self):
pass
# Used to clear any listener relationships, etc. This is needed because
# Python seems to cache local variables even between threads.
def clearListeners(self):
self._listenerModules = list()
self._stopScanning = False
# Will always be overriden by the implementer.
def setup(self, sf, url, userOpts=dict()):
pass
# Listener modules which will get notified once we have data for them to
# work with.
def registerListener(self, listener):
self._listenerModules.append(listener)
# Call the handleEvent() method of every other plug-in listening for
# events from this plug-in. Remember that those plug-ins will be called
# within the same execution context of this thread, not on their own.
def notifyListeners(self, sfEvent):
eventName = sfEvent.eventType
eventData = sfEvent.data
# Check if we've been asked to stop in the meantime, so that
# notifications stop triggering module activity.
if self.checkForStop():
return None
if eventData == None or (type(eventData) is unicode and len(eventData) == 0):
#print "No data to send for " + eventName + " to " + listener.__module__
return None
for listener in self._listenerModules:
#print listener.__module__ + ": " + listener.watchedEvents().__str__()
if eventName not in listener.watchedEvents() and '*' not in listener.watchedEvents():
#print listener.__module__ + " not listening for " + eventName
continue
#print "Notifying " + eventName + " to " + listener.__module__
listener._currentEvent = sfEvent
listener.handleEvent(sfEvent)
# Called to stop scanning
def stopScanning(self):
self._stopScanning = True
# For modules to use to check for when they should give back control
def checkForStop(self):
return self._stopScanning
# Return a list of the default configuration options for the module.
def defaultOpts(self):
return self.opts
# What events is this module interested in for input. The format is a list
# of event types that are applied to event types that this module wants to
# be notified of, or * if it wants everything.
# Will usually be overriden by the implementer, unless it is interested
# in all events (default behavior).
def watchedEvents(self):
return [ '*' ]
# Handle events to this module
# Will usually be overriden by the implementer, unless it doesn't handle
# any events.
def handleEvent(self, sfEvent):
return None
# Kick off the work (for some modules nothing will happen here, but instead
# the work will start from the handleEvent() method.
# Will usually be overriden by the implementer.
def start(self):
return None
# Class for SpiderFoot Events
class SpiderFootEvent(object):
generated = None
eventType = None
confidence = None
visibility = None
risk = None
module = None
data = None
sourceEvent = None
sourceEventHash = None
__id = None
def __init__(self, eventType, data, module, sourceEvent=None,
confidence=100, visibility=100, risk=0):
self.eventType = eventType
self.generated = time.time()
self.confidence = confidence
self.visibility = visibility
self.risk = risk
self.module = module
self.data = data
self.sourceEvent = sourceEvent
# "ROOT" is a special "hash" reserved for elements with no
# actual parent (e.g. the first page spidered.)
if sourceEvent != None:
self.sourceEventHash = sourceEvent.getHash()
else:
self.sourceEventHash = "ROOT"
# Handle lists, dicts
#if type(self.data) not in [str, unicode]:
# self.__id = unicode(self.eventType + str(self.data) + str(self.generated) + self.module, 'utf-8', errors='replace')
#else:
# self.__id = self.eventType + self.data + str(self.generated) + self.module
self.__id = self.eventType + str(self.generated) + self.module + \
str(random.randint(0, 99999999))
# Unique hash of this event
def getHash(self):
if self.eventType == "INITIAL_TARGET":
return "ROOT"
digestStr = self.__id.encode('raw_unicode_escape')
return hashlib.sha256(digestStr).hexdigest()
# Update variables as new information becomes available
def setConfidence(self, confidence):
self.confidence = confidence
def setVisibility(self, visibility):
self.visibility = visibility
def setRisk(self, risk):
self.risk = risk
def setSourceEventHash(self, srcHash):
self.sourceEventHash = srcHash
# Override the default redirectors to re-use cookies
class SmartRedirectHandler(urllib2.HTTPRedirectHandler):
def http_error_301(self, req, fp, code, msg, headers):
if headers.has_key("Set-Cookie"):
req.add_header('cookie', headers['Set-Cookie'])
result = urllib2.HTTPRedirectHandler.http_error_301(
self, req, fp, code, msg, headers)
return result
def http_error_302(self, req, fp, code, msg, headers):
if headers.has_key("Set-Cookie"):
req.add_header('cookie', headers['Set-Cookie'])
result = urllib2.HTTPRedirectHandler.http_error_302(
self, req, fp, code, msg, headers)
return result