Codebase list sublist3r / 58607b24-5707-4ecc-bd7b-8ba69f14ce1d/upstream sublist3r.py
58607b24-5707-4ecc-bd7b-8ba69f14ce1d/upstream

Tree @58607b24-5707-4ecc-bd7b-8ba69f14ce1d/upstream (Download .tar.gz)

sublist3r.py @58607b24-5707-4ecc-bd7b-8ba69f14ce1d/upstreamraw · history · blame

   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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
#!/usr/bin/env python
# coding: utf-8
# Sublist3r v1.0
# By Ahmed Aboul-Ela - twitter.com/aboul3la

# modules in standard library
import re
import sys
import os
import argparse
import time
import hashlib
import random
import multiprocessing
import threading
import socket
import json
from collections import Counter

# external modules
from subbrute import subbrute
import dns.resolver
import requests

# Python 2.x and 3.x compatiablity
if sys.version > '3':
    import urllib.parse as urlparse
    import urllib.parse as urllib
else:
    import urlparse
    import urllib

# In case you cannot install some of the required development packages
# there's also an option to disable the SSL warning:
try:
    import requests.packages.urllib3
    requests.packages.urllib3.disable_warnings()
except:
    pass

# Check if we are running this on windows platform
is_windows = sys.platform.startswith('win')

# Console Colors
if is_windows:
    # Windows deserves coloring too :D
    G = '\033[92m'  # green
    Y = '\033[93m'  # yellow
    B = '\033[94m'  # blue
    R = '\033[91m'  # red
    W = '\033[0m'   # white
    try:
        import win_unicode_console , colorama
        win_unicode_console.enable()
        colorama.init()
        #Now the unicode will work ^_^
    except:
        print("[!] Error: Coloring libraries not installed, no coloring will be used [Check the readme]")
        G = Y = B = R = W = G = Y = B = R = W = ''


else:
    G = '\033[92m'  # green
    Y = '\033[93m'  # yellow
    B = '\033[94m'  # blue
    R = '\033[91m'  # red
    W = '\033[0m'   # white

def no_color():
    global G, Y, B, R, W
    G = Y = B = R = W = ''


def banner():
    print("""%s
                 ____        _     _ _     _   _____
                / ___| _   _| |__ | (_)___| |_|___ / _ __
                \___ \| | | | '_ \| | / __| __| |_ \| '__|
                 ___) | |_| | |_) | | \__ \ |_ ___) | |
                |____/ \__,_|_.__/|_|_|___/\__|____/|_|%s%s

                # Coded By Ahmed Aboul-Ela - @aboul3la
    """ % (R, W, Y))


def parser_error(errmsg):
    banner()
    print("Usage: python " + sys.argv[0] + " [Options] use -h for help")
    print(R + "Error: " + errmsg + W)
    sys.exit()


def parse_args():
    # parse the arguments
    parser = argparse.ArgumentParser(epilog='\tExample: \r\npython ' + sys.argv[0] + " -d google.com")
    parser.error = parser_error
    parser._optionals.title = "OPTIONS"
    parser.add_argument('-d', '--domain', help="Domain name to enumerate it's subdomains", required=True)
    parser.add_argument('-b', '--bruteforce', help='Enable the subbrute bruteforce module', nargs='?', default=False)
    parser.add_argument('-p', '--ports', help='Scan the found subdomains against specified tcp ports')
    parser.add_argument('-v', '--verbose', help='Enable Verbosity and display results in realtime', nargs='?', default=False)
    parser.add_argument('-t', '--threads', help='Number of threads to use for subbrute bruteforce', type=int, default=30)
    parser.add_argument('-e', '--engines', help='Specify a comma-separated list of search engines')
    parser.add_argument('-o', '--output', help='Save the results to text file')
    parser.add_argument('-n', '--no-color', help='Output without color', default=False, action='store_true')
    return parser.parse_args()


def write_file(filename, subdomains):
    # saving subdomains results to output file
    print("%s[-] Saving results to file: %s%s%s%s" % (Y, W, R, filename, W))
    with open(str(filename), 'wt') as f:
        for subdomain in subdomains:
            f.write(subdomain + os.linesep)


def subdomain_sorting_key(hostname):
    """Sorting key for subdomains

    This sorting key orders subdomains from the top-level domain at the right
    reading left, then moving '^' and 'www' to the top of their group. For
    example, the following list is sorted correctly:

    [
        'example.com',
        'www.example.com',
        'a.example.com',
        'www.a.example.com',
        'b.a.example.com',
        'b.example.com',
        'example.net',
        'www.example.net',
        'a.example.net',
    ]

    """
    parts = hostname.split('.')[::-1]
    if parts[-1] == 'www':
        return parts[:-1], 1
    return parts, 0


class enumratorBase(object):
    def __init__(self, base_url, engine_name, domain, subdomains=None, silent=False, verbose=True):
        subdomains = subdomains or []
        self.domain = urlparse.urlparse(domain).netloc
        self.session = requests.Session()
        self.subdomains = []
        self.timeout = 25
        self.base_url = base_url
        self.engine_name = engine_name
        self.silent = silent
        self.verbose = verbose
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'Accept-Language': 'en-US,en;q=0.8',
            'Accept-Encoding': 'gzip',
        }
        self.print_banner()

    def print_(self, text):
        if not self.silent:
            print(text)
        return

    def print_banner(self):
        """ subclass can override this if they want a fancy banner :)"""
        self.print_(G + "[-] Searching now in %s.." % (self.engine_name) + W)
        return

    def send_req(self, query, page_no=1):

        url = self.base_url.format(query=query, page_no=page_no)
        try:
            resp = self.session.get(url, headers=self.headers, timeout=self.timeout)
        except Exception:
            resp = None
        return self.get_response(resp)

    def get_response(self, response):
        if response is None:
            return 0
        return response.text if hasattr(response, "text") else response.content

    def check_max_subdomains(self, count):
        if self.MAX_DOMAINS == 0:
            return False
        return count >= self.MAX_DOMAINS

    def check_max_pages(self, num):
        if self.MAX_PAGES == 0:
            return False
        return num >= self.MAX_PAGES

    # override
    def extract_domains(self, resp):
        """ chlid class should override this function """
        return

    # override
    def check_response_errors(self, resp):
        """ chlid class should override this function
        The function should return True if there are no errors and False otherwise
        """
        return True

    def should_sleep(self):
        """Some enumrators require sleeping to avoid bot detections like Google enumerator"""
        return

    def generate_query(self):
        """ chlid class should override this function """
        return

    def get_page(self, num):
        """ chlid class that user different pagnation counter should override this function """
        return num + 10

    def enumerate(self, altquery=False):
        flag = True
        page_no = 0
        prev_links = []
        retries = 0

        while flag:
            query = self.generate_query()
            count = query.count(self.domain)  # finding the number of subdomains found so far

            # if they we reached the maximum number of subdomains in search query
            # then we should go over the pages
            if self.check_max_subdomains(count):
                page_no = self.get_page(page_no)

            if self.check_max_pages(page_no):  # maximum pages for Google to avoid getting blocked
                return self.subdomains
            resp = self.send_req(query, page_no)

            # check if there is any error occured
            if not self.check_response_errors(resp):
                return self.subdomains
            links = self.extract_domains(resp)

            # if the previous page hyperlinks was the similar to the current one, then maybe we have reached the last page
            if links == prev_links:
                retries += 1
                page_no = self.get_page(page_no)

        # make another retry maybe it isn't the last page
                if retries >= 3:
                    return self.subdomains

            prev_links = links
            self.should_sleep()

        return self.subdomains


class enumratorBaseThreaded(multiprocessing.Process, enumratorBase):
    def __init__(self, base_url, engine_name, domain, subdomains=None, q=None, lock=threading.Lock(), silent=False, verbose=True):
        subdomains = subdomains or []
        enumratorBase.__init__(self, base_url, engine_name, domain, subdomains, silent=silent, verbose=verbose)
        multiprocessing.Process.__init__(self)
        self.lock = lock
        self.q = q
        return

    def run(self):
        domain_list = self.enumerate()
        for domain in domain_list:
            self.q.append(domain)


class GoogleEnum(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = "https://google.com/search?q={query}&btnG=Search&hl=en-US&biw=&bih=&gbv=1&start={page_no}&filter=0"
        self.engine_name = "Google"
        self.MAX_DOMAINS = 11
        self.MAX_PAGES = 200
        super(GoogleEnum, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        self.q = q
        return

    def extract_domains(self, resp):
        links_list = list()
        link_regx = re.compile('<cite.*?>(.*?)<\/cite>')
        try:
            links_list = link_regx.findall(resp)
            for link in links_list:
                link = re.sub('<span.*>', '', link)
                if not link.startswith('http'):
                    link = "http://" + link
                subdomain = urlparse.urlparse(link).netloc
                if subdomain and subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception:
            pass
        return links_list

    def check_response_errors(self, resp):
        if (type(resp) is str or type(resp) is unicode) and 'Our systems have detected unusual traffic' in resp:
            self.print_(R + "[!] Error: Google probably now is blocking our requests" + W)
            self.print_(R + "[~] Finished now the Google Enumeration ..." + W)
            return False
        return True

    def should_sleep(self):
        time.sleep(5)
        return

    def generate_query(self):
        if self.subdomains:
            fmt = 'site:{domain} -www.{domain} -{found}'
            found = ' -'.join(self.subdomains[:self.MAX_DOMAINS - 2])
            query = fmt.format(domain=self.domain, found=found)
        else:
            query = "site:{domain} -www.{domain}".format(domain=self.domain)
        return query


class YahooEnum(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = "https://search.yahoo.com/search?p={query}&b={page_no}"
        self.engine_name = "Yahoo"
        self.MAX_DOMAINS = 10
        self.MAX_PAGES = 0
        super(YahooEnum, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        self.q = q
        return

    def extract_domains(self, resp):
        link_regx2 = re.compile('<span class=" fz-.*? fw-m fc-12th wr-bw.*?">(.*?)</span>')
        link_regx = re.compile('<span class="txt"><span class=" cite fw-xl fz-15px">(.*?)</span>')
        links_list = []
        try:
            links = link_regx.findall(resp)
            links2 = link_regx2.findall(resp)
            links_list = links + links2
            for link in links_list:
                link = re.sub("<(\/)?b>", "", link)
                if not link.startswith('http'):
                    link = "http://" + link
                subdomain = urlparse.urlparse(link).netloc
                if not subdomain.endswith(self.domain):
                    continue
                if subdomain and subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception:
            pass

        return links_list

    def should_sleep(self):
        return

    def get_page(self, num):
        return num + 10

    def generate_query(self):
        if self.subdomains:
            fmt = 'site:{domain} -domain:www.{domain} -domain:{found}'
            found = ' -domain:'.join(self.subdomains[:77])
            query = fmt.format(domain=self.domain, found=found)
        else:
            query = "site:{domain}".format(domain=self.domain)
        return query


class AskEnum(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'http://www.ask.com/web?q={query}&page={page_no}&qid=8D6EE6BF52E0C04527E51F64F22C4534&o=0&l=dir&qsrc=998&qo=pagination'
        self.engine_name = "Ask"
        self.MAX_DOMAINS = 11
        self.MAX_PAGES = 0
        enumratorBaseThreaded.__init__(self, base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        self.q = q
        return

    def extract_domains(self, resp):
        links_list = list()
        link_regx = re.compile('<p class="web-result-url">(.*?)</p>')
        try:
            links_list = link_regx.findall(resp)
            for link in links_list:
                if not link.startswith('http'):
                    link = "http://" + link
                subdomain = urlparse.urlparse(link).netloc
                if subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception:
            pass

        return links_list

    def get_page(self, num):
        return num + 1

    def generate_query(self):
        if self.subdomains:
            fmt = 'site:{domain} -www.{domain} -{found}'
            found = ' -'.join(self.subdomains[:self.MAX_DOMAINS])
            query = fmt.format(domain=self.domain, found=found)
        else:
            query = "site:{domain} -www.{domain}".format(domain=self.domain)

        return query


class BingEnum(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://www.bing.com/search?q={query}&go=Submit&first={page_no}'
        self.engine_name = "Bing"
        self.MAX_DOMAINS = 30
        self.MAX_PAGES = 0
        enumratorBaseThreaded.__init__(self, base_url, self.engine_name, domain, subdomains, q=q, silent=silent)
        self.q = q
        self.verbose = verbose
        return

    def extract_domains(self, resp):
        links_list = list()
        link_regx = re.compile('<li class="b_algo"><h2><a href="(.*?)"')
        link_regx2 = re.compile('<div class="b_title"><h2><a href="(.*?)"')
        try:
            links = link_regx.findall(resp)
            links2 = link_regx2.findall(resp)
            links_list = links + links2

            for link in links_list:
                link = re.sub('<(\/)?strong>|<span.*?>|<|>', '', link)
                if not link.startswith('http'):
                    link = "http://" + link
                subdomain = urlparse.urlparse(link).netloc
                if subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception:
            pass

        return links_list

    def generate_query(self):
        if self.subdomains:
            fmt = 'domain:{domain} -www.{domain} -{found}'
            found = ' -'.join(self.subdomains[:self.MAX_DOMAINS])
            query = fmt.format(domain=self.domain, found=found)
        else:
            query = "domain:{domain} -www.{domain}".format(domain=self.domain)
        return query


class BaiduEnum(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://www.baidu.com/s?pn={page_no}&wd={query}&oq={query}'
        self.engine_name = "Baidu"
        self.MAX_DOMAINS = 2
        self.MAX_PAGES = 760
        enumratorBaseThreaded.__init__(self, base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        self.querydomain = self.domain
        self.q = q
        return

    def extract_domains(self, resp):
        links = list()
        found_newdomain = False
        subdomain_list = []
        link_regx = re.compile('<a.*?class="c-showurl".*?>(.*?)</a>')
        try:
            links = link_regx.findall(resp)
            for link in links:
                link = re.sub('<.*?>|>|<|&nbsp;', '', link)
                if not link.startswith('http'):
                    link = "http://" + link
                subdomain = urlparse.urlparse(link).netloc
                if subdomain.endswith(self.domain):
                    subdomain_list.append(subdomain)
                    if subdomain not in self.subdomains and subdomain != self.domain:
                        found_newdomain = True
                        if self.verbose:
                            self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                        self.subdomains.append(subdomain.strip())
        except Exception:
            pass
        if not found_newdomain and subdomain_list:
            self.querydomain = self.findsubs(subdomain_list)
        return links

    def findsubs(self, subdomains):
        count = Counter(subdomains)
        subdomain1 = max(count, key=count.get)
        count.pop(subdomain1, "None")
        subdomain2 = max(count, key=count.get) if count else ''
        return (subdomain1, subdomain2)

    def check_response_errors(self, resp):
        return True

    def should_sleep(self):
        time.sleep(random.randint(2, 5))
        return

    def generate_query(self):
        if self.subdomains and self.querydomain != self.domain:
            found = ' -site:'.join(self.querydomain)
            query = "site:{domain} -site:www.{domain} -site:{found} ".format(domain=self.domain, found=found)
        else:
            query = "site:{domain} -site:www.{domain}".format(domain=self.domain)
        return query


class NetcraftEnum(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        self.base_url = 'https://searchdns.netcraft.com/?restriction=site+ends+with&host={domain}'
        self.engine_name = "Netcraft"
        self.lock = threading.Lock()
        super(NetcraftEnum, self).__init__(self.base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        self.q = q
        return

    def req(self, url, cookies=None):
        cookies = cookies or {}
        try:
            resp = self.session.get(url, headers=self.headers, timeout=self.timeout, cookies=cookies)
        except Exception as e:
            self.print_(e)
            resp = None
        return resp
    
    def should_sleep(self):
        time.sleep(random.randint(1, 2))
        return    

    def get_next(self, resp):
        link_regx = re.compile('<a.*?href="(.*?)">Next Page')
        link = link_regx.findall(resp)
        url = 'http://searchdns.netcraft.com' + link[0]
        return url

    def create_cookies(self, cookie):
        cookies = dict()
        cookies_list = cookie[0:cookie.find(';')].split("=")
        cookies[cookies_list[0]] = cookies_list[1]
        # hashlib.sha1 requires utf-8 encoded str
        cookies['netcraft_js_verification_response'] = hashlib.sha1(urllib.unquote(cookies_list[1]).encode('utf-8')).hexdigest()
        return cookies

    def get_cookies(self, headers):
        if 'set-cookie' in headers:
            cookies = self.create_cookies(headers['set-cookie'])
        else:
            cookies = {}
        return cookies

    def enumerate(self):
        start_url = self.base_url.format(domain='example.com')
        resp = self.req(start_url)
        cookies = self.get_cookies(resp.headers)
        url = self.base_url.format(domain=self.domain)
        while True:
            resp = self.get_response(self.req(url, cookies))
            self.extract_domains(resp)
            if 'Next Page' not in resp:
                return self.subdomains
                break
            url = self.get_next(resp)
            self.should_sleep()

    def extract_domains(self, resp):
        links_list = list()
        link_regx = re.compile('<a class="results-table__host" href="(.*?)"')
        try:
            links_list = link_regx.findall(resp)
            for link in links_list:
                subdomain = urlparse.urlparse(link).netloc
                if not subdomain.endswith(self.domain):
                    continue
                if subdomain and subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception:
            pass
        return links_list


class DNSdumpster(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://dnsdumpster.com/'
        self.live_subdomains = []
        self.engine_name = "DNSdumpster"
        self.threads = 70
        self.lock = threading.BoundedSemaphore(value=self.threads)
        self.q = q
        super(DNSdumpster, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        return

    def check_host(self, host):
        is_valid = False
        Resolver = dns.resolver.Resolver()
        Resolver.nameservers = ['8.8.8.8', '8.8.4.4']
        self.lock.acquire()
        try:
            ip = Resolver.query(host, 'A')[0].to_text()
            if ip:
                if self.verbose:
                    self.print_("%s%s: %s%s" % (R, self.engine_name, W, host))
                is_valid = True
                self.live_subdomains.append(host)
        except:
            pass
        self.lock.release()
        return is_valid

    def req(self, req_method, url, params=None):
        params = params or {}
        headers = dict(self.headers)
        headers['Referer'] = 'https://dnsdumpster.com'
        try:
            if req_method == 'GET':
                resp = self.session.get(url, headers=headers, timeout=self.timeout)
            else:
                resp = self.session.post(url, data=params, headers=headers, timeout=self.timeout)
        except Exception as e:
            self.print_(e)
            resp = None
        return self.get_response(resp)

    def get_csrftoken(self, resp):
        csrf_regex = re.compile('<input type="hidden" name="csrfmiddlewaretoken" value="(.*?)">', re.S)
        token = csrf_regex.findall(resp)[0]
        return token.strip()

    def enumerate(self):
        resp = self.req('GET', self.base_url)
        token = self.get_csrftoken(resp)
        params = {'csrfmiddlewaretoken': token, 'targetip': self.domain}
        post_resp = self.req('POST', self.base_url, params)
        self.extract_domains(post_resp)
        for subdomain in self.subdomains:
            t = threading.Thread(target=self.check_host, args=(subdomain,))
            t.start()
            t.join()
        return self.live_subdomains

    def extract_domains(self, resp):
        tbl_regex = re.compile('<a name="hostanchor"><\/a>Host Records.*?<table.*?>(.*?)</table>', re.S)
        link_regex = re.compile('<td class="col-md-4">(.*?)<br>', re.S)
        links = []
        try:
            results_tbl = tbl_regex.findall(resp)[0]
        except IndexError:
            results_tbl = ''
        links_list = link_regex.findall(results_tbl)
        links = list(set(links_list))
        for link in links:
            subdomain = link.strip()
            if not subdomain.endswith(self.domain):
                continue
            if subdomain and subdomain not in self.subdomains and subdomain != self.domain:
                self.subdomains.append(subdomain.strip())
        return links


class Virustotal(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://www.virustotal.com/ui/domains/{domain}/subdomains'
        self.engine_name = "Virustotal"
        self.lock = threading.Lock()
        self.q = q
        super(Virustotal, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        self.url = self.base_url.format(domain=self.domain)
        return

    # the main send_req need to be rewritten
    def send_req(self, url):
        try:
            resp = self.session.get(url, headers=self.headers, timeout=self.timeout)
        except Exception as e:
            self.print_(e)
            resp = None

        return self.get_response(resp)

    # once the send_req is rewritten we don't need to call this function, the stock one should be ok
    def enumerate(self):
        while self.url != '':
            resp = self.send_req(self.url)
            resp = json.loads(resp)
            if 'error' in resp:
                self.print_(R + "[!] Error: Virustotal probably now is blocking our requests" + W)
                break
            if 'links' in resp and 'next' in resp['links']:
                self.url = resp['links']['next']
            else:
                self.url = ''
            self.extract_domains(resp)
        return self.subdomains

    def extract_domains(self, resp):
        #resp is already parsed as json
        try:
            for i in resp['data']:
                if i['type'] == 'domain':
                    subdomain = i['id']
                    if not subdomain.endswith(self.domain):
                        continue
                    if subdomain not in self.subdomains and subdomain != self.domain:
                        if self.verbose:
                            self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                        self.subdomains.append(subdomain.strip())
        except Exception:
            pass


class ThreatCrowd(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://www.threatcrowd.org/searchApi/v2/domain/report/?domain={domain}'
        self.engine_name = "ThreatCrowd"
        self.lock = threading.Lock()
        self.q = q
        super(ThreatCrowd, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        return

    def req(self, url):
        try:
            resp = self.session.get(url, headers=self.headers, timeout=self.timeout)
        except Exception:
            resp = None

        return self.get_response(resp)

    def enumerate(self):
        url = self.base_url.format(domain=self.domain)
        resp = self.req(url)
        self.extract_domains(resp)
        return self.subdomains

    def extract_domains(self, resp):
        try:
            links = json.loads(resp)['subdomains']
            for link in links:
                subdomain = link.strip()
                if not subdomain.endswith(self.domain):
                    continue
                if subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception as e:
            pass


class CrtSearch(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://crt.sh/?q=%25.{domain}'
        self.engine_name = "SSL Certificates"
        self.lock = threading.Lock()
        self.q = q
        super(CrtSearch, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        return

    def req(self, url):
        try:
            resp = self.session.get(url, headers=self.headers, timeout=self.timeout)
        except Exception:
            resp = None

        return self.get_response(resp)

    def enumerate(self):
        url = self.base_url.format(domain=self.domain)
        resp = self.req(url)
        if resp:
            self.extract_domains(resp)
        return self.subdomains

    def extract_domains(self, resp):
        link_regx = re.compile('<TD>(.*?)</TD>')
        try:
            links = link_regx.findall(resp)
            for link in links:
                link = link.strip()
                subdomains = []
                if '<BR>' in link:
                    subdomains = link.split('<BR>')
                else:
                    subdomains.append(link)

                for subdomain in subdomains:
                    if not subdomain.endswith(self.domain) or '*' in subdomain:
                        continue

                    if '@' in subdomain:
                        subdomain = subdomain[subdomain.find('@')+1:]

                    if subdomain not in self.subdomains and subdomain != self.domain:
                        if self.verbose:
                            self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                        self.subdomains.append(subdomain.strip())
        except Exception as e:
            print(e)
            pass


class PassiveDNS(enumratorBaseThreaded):
    def __init__(self, domain, subdomains=None, q=None, silent=False, verbose=True):
        subdomains = subdomains or []
        base_url = 'https://api.sublist3r.com/search.php?domain={domain}'
        self.engine_name = "PassiveDNS"
        self.lock = threading.Lock()
        self.q = q
        super(PassiveDNS, self).__init__(base_url, self.engine_name, domain, subdomains, q=q, silent=silent, verbose=verbose)
        return

    def req(self, url):
        try:
            resp = self.session.get(url, headers=self.headers, timeout=self.timeout)
        except Exception as e:
            resp = None

        return self.get_response(resp)

    def enumerate(self):
        url = self.base_url.format(domain=self.domain)
        resp = self.req(url)
        if not resp:
            return self.subdomains

        self.extract_domains(resp)
        return self.subdomains

    def extract_domains(self, resp):
        try:
            subdomains = json.loads(resp)
            for subdomain in subdomains:
                if subdomain not in self.subdomains and subdomain != self.domain:
                    if self.verbose:
                        self.print_("%s%s: %s%s" % (R, self.engine_name, W, subdomain))
                    self.subdomains.append(subdomain.strip())
        except Exception as e:
            pass


class portscan():
    def __init__(self, subdomains, ports):
        self.subdomains = subdomains
        self.ports = ports
        self.threads = 20
        self.lock = threading.BoundedSemaphore(value=self.threads)

    def port_scan(self, host, ports):
        openports = []
        self.lock.acquire()
        for port in ports:
            try:
                s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
                s.settimeout(2)
                result = s.connect_ex((host, int(port)))
                if result == 0:
                    openports.append(port)
                s.close()
            except Exception:
                pass
        self.lock.release()
        if len(openports) > 0:
            print("%s%s%s - %sFound open ports:%s %s%s%s" % (G, host, W, R, W, Y, ', '.join(openports), W))

    def run(self):
        for subdomain in self.subdomains:
            t = threading.Thread(target=self.port_scan, args=(subdomain, self.ports))
            t.start()


def main(domain, threads, savefile, ports, silent, verbose, enable_bruteforce, engines):
    bruteforce_list = set()
    search_list = set()

    if is_windows:
        subdomains_queue = list()
    else:
        subdomains_queue = multiprocessing.Manager().list()

    # Check Bruteforce Status
    if enable_bruteforce or enable_bruteforce is None:
        enable_bruteforce = True

    # Validate domain
    domain_check = re.compile("^(http|https)?[a-zA-Z0-9]+([\-\.]{1}[a-zA-Z0-9]+)*\.[a-zA-Z]{2,}$")
    if not domain_check.match(domain):
        if not silent:
            print(R + "Error: Please enter a valid domain" + W)
        return []

    if not domain.startswith('http://') or not domain.startswith('https://'):
        domain = 'http://' + domain

    parsed_domain = urlparse.urlparse(domain)

    if not silent:
        print(B + "[-] Enumerating subdomains now for %s" % parsed_domain.netloc + W)

    if verbose and not silent:
        print(Y + "[-] verbosity is enabled, will show the subdomains results in realtime" + W)

    supported_engines = {'baidu': BaiduEnum,
                         'yahoo': YahooEnum,
                         'google': GoogleEnum,
                         'bing': BingEnum,
                         'ask': AskEnum,
                         'netcraft': NetcraftEnum,
                         'dnsdumpster': DNSdumpster,
                         'virustotal': Virustotal,
                         'threatcrowd': ThreatCrowd,
                         'ssl': CrtSearch,
                         'passivedns': PassiveDNS
                         }

    chosenEnums = []

    if engines is None:
        chosenEnums = [
            BaiduEnum, YahooEnum, GoogleEnum, BingEnum, AskEnum,
            NetcraftEnum, DNSdumpster, Virustotal, ThreatCrowd,
            CrtSearch, PassiveDNS
        ]
    else:
        engines = engines.split(',')
        for engine in engines:
            if engine.lower() in supported_engines:
                chosenEnums.append(supported_engines[engine.lower()])

    # Start the engines enumeration
    enums = [enum(domain, [], q=subdomains_queue, silent=silent, verbose=verbose) for enum in chosenEnums]
    for enum in enums:
        enum.start()
    for enum in enums:
        enum.join()

    subdomains = set(subdomains_queue)
    for subdomain in subdomains:
        search_list.add(subdomain)

    if enable_bruteforce:
        if not silent:
            print(G + "[-] Starting bruteforce module now using subbrute.." + W)
        record_type = False
        path_to_file = os.path.dirname(os.path.realpath(__file__))
        subs = os.path.join(path_to_file, 'subbrute', 'names.txt')
        resolvers = os.path.join(path_to_file, 'subbrute', 'resolvers.txt')
        process_count = threads
        output = False
        json_output = False
        bruteforce_list = subbrute.print_target(parsed_domain.netloc, record_type, subs, resolvers, process_count, output, json_output, search_list, verbose)

    subdomains = search_list.union(bruteforce_list)

    if subdomains:
        subdomains = sorted(subdomains, key=subdomain_sorting_key)

        if savefile:
            write_file(savefile, subdomains)

        if not silent:
            print(Y + "[-] Total Unique Subdomains Found: %s" % len(subdomains) + W)

        if ports:
            if not silent:
                print(G + "[-] Start port scan now for the following ports: %s%s" % (Y, ports) + W)
            ports = ports.split(',')
            pscan = portscan(subdomains, ports)
            pscan.run()

        elif not silent:
            for subdomain in subdomains:
                print(G + subdomain + W)
    return subdomains


def interactive():
    args = parse_args()
    domain = args.domain
    threads = args.threads
    savefile = args.output
    ports = args.ports
    enable_bruteforce = args.bruteforce
    verbose = args.verbose
    engines = args.engines
    if verbose or verbose is None:
        verbose = True
    if args.no_color:
        no_color()
    banner()
    res = main(domain, threads, savefile, ports, silent=False, verbose=verbose, enable_bruteforce=enable_bruteforce, engines=engines)

if __name__ == "__main__":
    interactive()