summaryrefslogtreecommitdiff
path: root/monitor/josef_experimental.py
blob: 49c9e092083b953ee684490d93e13952495df361 (plain)
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
#!/usr/bin/python
# -*- coding: utf-8 -*-     

import sys
import os
from josef_lib import *
# from josef_lib2 import *
# import leveldb
# import argparse
import json
import time
# from josef_leveldb import *
from datetime import datetime as dt
# from josef_monitor import verify_inclusion_by_hash
from monitor_conf import *

def is_new_timestamp(ts):
    MAX_TIMEDIFF = 300 # 5 min, allows for some clock skew
    ts_time = datetime.datetime.fromtimestamp(ts / 1000, UTC()).strftime('%Y-%m-%d %H:%M:%S')
    start_time = datetime.datetime.utcnow().strftime('2015-10-19 00:00:00')
    # delta_time = datetime.datetime.strptime(start_time, '%Y-%m-%d %H:%M:%S') - datetime.datetime.strptime(ts_time, '%Y-%m-%d %H:%M:%S')
    # print delta_time.seconds
    if ts_time < start_time:
        return False
    else:
        return True

def check_inclusion_by_submission(first, last, source, dests):
    # print entries
    for s_log in source:
        try:
            entries = []
            while len(entries) <= last - first:

                print "Getting " + str(first + len(entries)) + " to " + str(last)
                entries += get_entries(s_log["url"], first + len(entries), last)["entries"]
                # print "Fetched entries up to " + str(len(first + len(entries)))
        except:
            print "Failed to get entries from " + s_log["name"]

        for i in range(len(entries)):
            item = entries[i]
            inclusions = []
            for d_log in dests:
                try:
                    entry = extract_original_entry(item)
                    if entry[2]:
                        precert = True
                    else:
                        precert = False
                    submission = []

                    for e in entry[0]:
                        submission.append(base64.b64encode(e))

                    if entry[2]:
                        res = add_prechain(d_log["url"], {"chain" : submission})
                    else:
                        res = add_chain(d_log["url"], {"chain" : submission})
                    # print_reply(res, entry)
                    print res

                    if not is_new_timestamp(res["timestamp"]):
                        inclusions.append(d_log["name"])

                except KeyboardInterrupt:
                    sys.exit()
                except Exception ,e:
                    print Exception, e
                    pass
            s = s_log["name"] + "[" + str(first + i) + "] found in " + str(len(inclusions)) + " logs: " + str(inclusions)
            print s
            # log(logfile, s)
            time.sleep(1)


def update_roots(log):
    roots_hash = None

    roots = get_all_roots(log["url"])
    new_roots_hash = str(hash(str(roots)))

    if new_roots_hash != roots_hash:
        cert_dir = OUTPUT_DIR + log["name"] + "-roots"
        if not os.path.exists(cert_dir):
            os.makedirs(cert_dir)

        hash_list = []
        for cert in roots:
            h = str(hash(str(cert)))
            hash_list.append(h)

        loaded_list = os.listdir(cert_dir)

        added, removed = compare_lists(hash_list[:-1], loaded_list)

        # TODO log changes
        if len(added) != 0:
            print str(len(added)) + " new roots found!"
        if len(removed) != 0:
            print str(len(removed)) + " roots removed!"

        for item in removed:
            data = open(cert_dir + "/" + item).read()

            root_cert = base64.decodestring(data)
            subject = get_cert_info(root_cert)["subject"]
            issuer = get_cert_info(root_cert)["issuer"]
            if subject == issuer:
                print "Removed Root: " + item + ", " + subject
            else: 
                print "WTF? Not a root..."


        for item in added:
            root_cert = base64.decodestring(roots[hash_list.index(item)])
            subject = get_cert_info(root_cert)["subject"]
            issuer = get_cert_info(root_cert)["issuer"]
            if subject == issuer:
                print "New Root: " + item + ", " + subject
            else: 
                print "WTF? Not a root..."

            fn = cert_dir + "/" + item
            tempname = fn + ".new"
            data = roots[hash_list.index(item)]
            open(tempname, 'w').write(data)
            mv_file(tempname, fn)

def parse_entry(e, idx, log):
    # print the following fields, separated by sep
    sep = ";;;"

    s = log["name"]
    s += sep + str(idx) # index
    s += sep + str(e["timestamp"])
    s += sep + e["serial"] # cert serial number
    s += sep + e["subject"] # Subject
    if "SAN" in e:
        s += sep + e["SAN"] # SAN
    else:
        s += sep
    s += sep + e["issuer"] # issuer
    s += sep + e["chain_length"] # path length
    s += sep + e["sig_algorithm"] # Signature algothithm
    s += sep + e["pubkey_algorithm"] # pubkey algorithm

    try:
        s += sep + e["keylength"]
    except:
        s += sep 
        print "\nERROR: COUND NOT FIND KEYLENGTH!"
        print str(e)

    s += sep + e["not_before"] # valid from
    s += sep + e["not_after"] # valid to
    s += sep + e["validation"] # EV?
    s += sep + e["in_mozilla"] # chains to mozilla root?
    s += sep + e["ca"]

    return s

# def check_api2(url):
#     print "\nTesting " + url
#     try:
#         print get_sth_v2(url)
#     except:
#         print "GET STH Failed..."



if __name__ == '__main__':

    # prompt_confirm("you are about to remove file")

    # Find let's encrypt certs
    if False:
        CHUNK = 1000
        log = CTLOGS[1]
        sth = get_sth(log["url"])
        size = int(sth["tree_size"])
        for i in range(0,100):
            start = size - (i + 1) * CHUNK
            end = size - i * CHUNK
            print "Getting " + str(start) + " to " + str(end)
            entries = get_entries(log["url"],start ,end - 1)["entries"]

            for entry in entries:
                res = check_domain(entry)
                issuer = res["issuer"]
                if "Encrypt" in issuer:
                    print res


    # Experimental
    if False:
        log = CTLOGS[2]
        entries = get_entries(log["url"],187851 ,187851)["entries"]
        entry = entries[0]
        # print extract_original_entry(entry)[1]
        # print check_domain_all(entry)
        res = check_domain_extended(entry)
        # print res
        print parse_entry(res,0,log)

    # Data gathering for Niklas
    if True:
        logs = [CTLOGS[9]] #,CTLOGS[4],CTLOGS[7],CTLOGS[8],CTLOGS[9]]
        for log in logs:
            filename = log["name"] + "_content.txt"
            if os.path.exists(filename):
                if prompt_confirm("You are about to overwrite " + filename):
                    os.remove(filename)
                else:
                    continue

            sth = get_sth(log["url"])
            start = 0
            idx = 0
            end = int(sth["tree_size"]) - 1

            while start + idx < end:
                entries = get_entries(log["url"],start + idx ,end)["entries"]
                print time_str() + " " + log["name"] + ": Got " + str(start + idx) + " to " + str(start + idx + len(entries) - 1)
                
                with open(filename, 'a') as f:
                    for i in range(len(entries)):
                        entry = entries[i]
                        res = check_domain_extended(entry)
                        string = parse_entry(res, i + start + idx, log)
                        f.write(string + "\n")            

                idx += len(entries)