File: parser.py

package info (click to toggle)
dnsrecon 1.3.1-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 1,672 kB
  • sloc: python: 5,154; makefile: 5
file content (344 lines) | stat: -rwxr-xr-x 13,003 bytes parent folder | download | duplicates (2)
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
#!/usr/bin/env python3

#    DNSRecon Data Parser
#
#    Copyright (C) 2012  Carlos Perez
#
#    This program is free software; you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation; Applies version 2 of the License.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    You should have received a copy of the GNU General Public License
#    along with this program; if not, write to the Free Software
#    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA

__version__ = '0.0.7'
__author__ = 'Carlos Perez, Carlos_Perez@darkoperator.com'

import csv
import getopt
import os
import re
import sys
import xml.etree.ElementTree as cElementTree

from netaddr import *

# Function Definitions
# ------------------------------------------------------------------------------


def print_status(message=''):
    print(f'\033[1;34m[*]\033[1;m {message}')


def print_good(message=''):
    print(f'\033[1;32m[*]\033[1;m {message}')


def print_error(message=''):
    print(f'\033[1;31m[-]\033[1;m {message}')


def print_debug(message=''):
    print(f'\033[1;31m[!]\033[1;m {message}')


def print_line(message=''):
    print(f'{message}')


def process_range(arg):
    """
    This function will take a string representation of a range for IPv4 or IPv6 in
    CIDR or Range format and return a list of IPs.
    """
    try:
        ip_list = None
        range_vals = []
        if re.match(r'\S*/\S*', arg):
            ip_list = IPNetwork(arg)

        range_vals.extend(arg.split('-'))
        if len(range_vals) == 2:
            ip_list = IPNetwork(IPRange(range_vals[0], range_vals[1])).cidrs()[-1]
    except Exception:
        print_error(f'Range provided is not valid: {arg()}')
        return []
    return ip_list


def xml_parse(xm_file, ifilter, tfilter, nfilter, list):
    """
    Function for parsing XML files created by DNSRecon and apply filters.
    """
    iplist = []
    for event, elem in cElementTree.iterparse(xm_file):
        # Check if it is a record
        if elem.tag == 'record':
            # Check that it is a RR Type that has an IP Address
            if 'address' in elem.attrib:
                # Check if the IP is in the filter list of IPs to ignore
                if (len(ifilter) == 0 or IPAddress(elem.attrib['address']) in ifilter) and (elem.attrib['address'] != 'no_ip'):
                    # Check if the RR Type against the types
                    if re.match(tfilter, elem.attrib['type'], re.I):
                        # Process A, AAAA and PTR Records
                        if re.search(r'PTR|^[A]$|AAAA', elem.attrib['type']) and re.search(nfilter, elem.attrib['name'], re.I):
                            if list:
                                if elem.attrib['address'] not in iplist:
                                    print(elem.attrib['address'])
                            else:
                                print_good(f"{elem.attrib['type']} {elem.attrib['name']} {elem.attrib['address']}")

                        # Process NS Records
                        elif re.search(r'NS', elem.attrib['type']) and re.search(nfilter, elem.attrib['target'], re.I):
                            if list:
                                if elem.attrib['address'] not in iplist:
                                    iplist.append(elem.attrib['address'])
                            else:
                                print_good(f"{elem.attrib['type']} {elem.attrib['target']} {elem.attrib['address']}")

                        # Process SOA Records
                        elif re.search(r'SOA', elem.attrib['type']) and re.search(nfilter, elem.attrib['mname'], re.I):
                            if list:
                                if elem.attrib['address'] not in iplist:
                                    iplist.append(elem.attrib['address'])
                            else:
                                print_good(f"{elem.attrib['type']} {elem.attrib['mname']} {elem.attrib['address']}")

                        # Process MS Records
                        elif re.search(r'MX', elem.attrib['type']) and re.search(nfilter, elem.attrib['exchange'], re.I):
                            if list:
                                if elem.attrib['address'] not in iplist:
                                    iplist.append(elem.attrib['address'])
                            else:
                                print_good(f"{elem.attrib['type']} {elem.attrib['exchange']} {elem.attrib['address']}")

                        # Process SRV Records
                        elif re.search(r'SRV', elem.attrib['type']) and re.search(nfilter, elem.attrib['target'], re.I):
                            if list:
                                if elem.attrib['address'] not in iplist:
                                    iplist.append(elem.attrib['address'])
                            else:
                                print_good(
                                    '{0} {1} {2} {3} {4}'.format(
                                        elem.attrib['type'],
                                        elem.attrib['name'],
                                        elem.attrib['address'],
                                        elem.attrib['target'],
                                        elem.attrib['port'],
                                    )
                                )
            else:
                if re.match(tfilter, elem.attrib['type'], re.I):
                    # Process TXT and SPF Records
                    if re.search(r'TXT|SPF', elem.attrib['type']):
                        if not list:
                            print_good('{0} {1}'.format(elem.attrib['type'], elem.attrib['strings']))
    # Process IPs in a list
    if len(iplist) > 0:
        try:
            for ip in filter(None, iplist):
                print_line(ip)
        except OSError:
            sys.exit(0)


def csv_parse(csv_file, ifilter, tfilter, nfilter, list):
    """
    Function for parsing CSV files created by DNSRecon and apply filters.
    """
    iplist = []
    reader = csv.reader(open(csv_file), delimiter=',')
    next(reader)
    for row in reader:
        # Check if IP is in the filter list of addresses to ignore
        if ((len(ifilter) == 0) or (IPAddress(row[2]) in ifilter)) and (row[2] != 'no_ip'):
            # Check Host Name regex and type list
            if re.search(tfilter, row[0], re.I) and re.search(nfilter, row[1], re.I):
                if list:
                    if row[2] not in iplist:
                        print(row[2])
                else:
                    print_good(' '.join(row))
    # Process IPs for target list if available
    # if len(iplist) > 0:
    #    for ip in filter(None, iplist):
    #        print_line(ip)


def extract_hostnames(file):
    host_names = []
    hostname_pattern = re.compile('(^[^.]*)')
    file_type = detect_type(file)
    if file_type == 'xml':
        for event, elem in cElementTree.iterparse(file):
            # Check if it is a record
            if elem.tag == 'record':
                # Check that it is a RR Type that has an IP Address
                if 'address' in elem.attrib:
                    # Process A, AAAA and PTR Records
                    if re.search(r'PTR|^[A]$|AAAA', elem.attrib['type']):
                        host_names.append(re.search(hostname_pattern, elem.attrib['name']).group(1))

                    # Process NS Records
                    elif re.search(r'NS', elem.attrib['type']):
                        host_names.append(re.search(hostname_pattern, elem.attrib['target']).group(1))

                    # Process SOA Records
                    elif re.search(r'SOA', elem.attrib['type']):
                        host_names.append(re.search(hostname_pattern, elem.attrib['mname']).group(1))

                    # Process MX Records
                    elif re.search(r'MX', elem.attrib['type']):
                        host_names.append(re.search(hostname_pattern, elem.attrib['exchange']).group(1))

                    # Process SRV Records
                    elif re.search(r'SRV', elem.attrib['type']):
                        host_names.append(re.search(hostname_pattern, elem.attrib['target']).group(1))

    elif file_type == 'csv':
        reader = csv.reader(open(file), delimiter=',')
        reader.next()
        for row in reader:
            host_names.append(re.search(hostname_pattern, row[1]).group(1))

    host_names = list(set(host_names))
    # Return list with no empty values
    return filter(None, host_names)


def detect_type(file):
    """
    Function for detecting the file type by checking the first line of the file.
    Returns xml, csv or None.
    """
    ftype = None

    # Get the fist lile of the file for checking
    with open(file) as file:
        firs_line = file.readline()

    # Determine file type based on the fist line content
    if re.search('(xml version)', firs_line):
        ftype = 'xml'
    elif re.search(r'\w*,[^,]*,[^,]*', firs_line):
        ftype = 'csv'
    else:
        raise Exception('Unsupported File Type')
    return ftype


def usage():
    print(f'Version: {__version__}')
    print('DNSRecon output file parser')
    print('Usage: parser.py <options>\n')
    print('Options:')
    print('   -h, --help               Show this help message and exit')
    print('   -f, --file    <file>     DNSRecon XML or CSV output file to parse.')
    print('   -l, --list               Output an unique IP List that can be used with other tools.')
    print('   -i, --ips     <ranges>   IP Ranges in a comma separated list each in formats (first-last)')
    print('                            or in (range/bitmask) for ranges to be included from output.')
    print('                            For A, AAAA, NS, MX, SOA, SRV and PTR Records.')
    print('   -t, --type    <type>     Resource Record Types as a regular expression to filter output.')
    print('                            For A, AAAA, NS, MX, SOA, TXT, SPF, SRV and PTR Records.')
    print('   -s, --str     <regex>    Regular expression between quotes for filtering host names on.')
    print('                            For A, AAAA, NS, MX, SOA, SRV and PTR Records.')
    print('   -n, --name               Return list of unique host names.')
    print('                            For A, AAAA, NS, MX, SOA, SRV and PTR Records.')
    sys.exit(0)


def main():
    #
    # Option Variables
    #
    ip_filter = []
    name_filter = '(.*)'
    type_filter = '(.*)'
    target_list = False
    file = None
    names = False

    #
    # Define options
    #
    try:
        options, args = getopt.getopt(
            sys.argv[1:],
            'hi:t:s:lf:n',
            ['help', 'ips=', 'type=', 'str=', 'list', 'file=', 'name'],
        )

    except getopt.GetoptError as error:
        print_error('Wrong Option Provided!')
        print_error(error)
        return

    #
    # Parse options
    #
    for opt, arg in options:
        if opt in ('-t', '--type'):
            type_filter = arg

        elif opt in ('-i', '--ips'):
            ipranges = arg.split(',')
            for r in ipranges:
                ip_filter.extend(process_range(r))

        elif opt in ('-s', '--str'):
            name_filter = f'({arg})'

        elif opt in ('-l', '--list'):
            target_list = True

        elif opt in ('-f', '--file'):
            # Check if the dictionary file exists
            if os.path.isfile(arg):
                file = arg
            else:
                print_error(f'File {arg} does not exist!')
                exit(1)

        elif opt in ('-r', '--range'):
            ip_list = []
            ip_range = process_range(arg)
            if len(ip_range) > 0:
                ip_list.extend(ip_range)
            else:
                sys.exit(1)
        elif opt in ('-n', '--name'):
            names = True

        elif opt in '-h':
            usage()

    # start execution based on options
    if file:
        if names:
            try:
                found_names = extract_hostnames(file)
                found_names.sort()
                for n in found_names:
                    print_line(n)
            except OSError:
                sys.exit(0)
        else:
            file_type = detect_type(file)
            if file_type == 'xml':
                xml_parse(file, ip_filter, type_filter, name_filter, target_list)
            elif file_type == 'csv':
                csv_parse(file, ip_filter, type_filter, name_filter, target_list)
    else:
        print_error('A DNSRecon XML or CSV output file must be provided to be parsed')
        usage()


if __name__ == '__main__':
    main()