Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

adjust regex pattern for better log matching results + small refactoring #18

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

adjust regex pattern for better log matching results + small refactoring #18

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 17 additions & 10 deletions geoip2influx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,11 +39,17 @@
# global variables
monitored_ip_types = ['PUBLIC', 'ALLOCATED APNIC', 'ALLOCATED ARIN', 'ALLOCATED RIPE NCC', 'ALLOCATED LACNIC', 'ALLOCATED AFRINIC']

re_ipv4_pattern = r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})'
re_ipv6_pattern = r'(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))' # NOQA

re_ipv4_log_pattern = r'(?P<ipaddress>\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}) - (?P<remote_user>\S+) \[(?P<dateandtime>\d{2}\/[A-Z]{1}[a-z]{2}\/\d{4}:\d{2}:\d{2}:\d{2} (?:\+|\-)\d{4})\]\s?"(?P<request>(?:(?P<method>[A-Z]+) (?P<referrer>.+?) (?P<http_version>HTTP\/[1-3]\.[0-9])|[^"]*))" (?P<status_code>\d{3}) (?P<bytes_sent>\d{1,99})\s?"(?P<url>(?:\-|.+))"(?P<host>.+?)"(?P<user_agent>.+?)"\s?"(?P<request_time>.+?)" "(?P<connect_time>.+?)"\s?"(?P<city>.+?)" "(?P<country_code>.+?)"' # NOQA
re_ipv6_log_pattern = r'(?P<ipaddress>(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])))'\
r' - (?P<remote_user>\S+) \[(?P<dateandtime>\d{2}\/[A-Z]{1}[a-z]{2}\/\d{4}:\d{2}:\d{2}:\d{2} (?:\+|\-)\d{4})\]\s?"(?P<request>(?:(?P<method>[A-Z]+) (?P<referrer>.+?) (?P<http_version>HTTP\/[1-3]\.[0-9])|[^"]*))" (?P<status_code>\d{3}) (?P<bytes_sent>\d{1,99})\s?"(?P<url>(?:\-|.+))"(?P<host>.+?)"(?P<user_agent>.+?)"\s?"(?P<request_time>.+?)" "(?P<connect_time>.+?)"\s?"(?P<city>.+?)" "(?P<country_code>.+?)"' # NOQA

def regex_tester(log_path, N):
time_out = time() + 60
re_ipv4 = compile(r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})')
re_ipv6 = compile(r'(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))') # NOQA
re_ipv4 = compile(re_ipv4_pattern)
re_ipv6 = compile(re_ipv6_pattern) # NOQA
while True:
assert N >= 0
pos = N + 1
Expand All @@ -61,12 +67,12 @@ def regex_tester(log_path, N):
log_lines = lines[-N:]
for line in log_lines:
if re_ipv4.match(line):
regex = compile(r'(?P<ipaddress>\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}) - (?P<remote_user>.+) \[(?P<dateandtime>\d{2}\/[A-Z]{1}[a-z]{2}\/\d{4}:\d{2}:\d{2}:\d{2} ((\+|\-)\d{4}))\](["](?P<method>.+)) (?P<referrer>.+) ((?P<http_version>HTTP\/[1-3]\.[0-9])["]) (?P<status_code>\d{3}) (?P<bytes_sent>\d{1,99})(["](?P<url>(\-)|(.+))["]) (?P<host>.+) (["](?P<user_agent>.+)["])(["](?P<request_time>.+)["]) (["](?P<connect_time>.+)["])(["](?P<city>.+)["]) (["](?P<country_code>.+)["])', IGNORECASE) # NOQA
regex = compile(re_ipv4_log_pattern, IGNORECASE) # NOQA
if regex.match(line):
logging.debug(f'Regex is matching {log_path} continuing...')
return True
if re_ipv6.match(line):
regex = compile(r'(?P<ipaddress>(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))) - (?P<remote_user>.+) \[(?P<dateandtime>\d{2}\/[A-Z]{1}[a-z]{2}\/\d{4}:\d{2}:\d{2}:\d{2} ((\+|\-)\d{4}))\](["](?P<method>.+)) (?P<referrer>.+) ((?P<http_version>HTTP\/[1-3]\.[0-9])["]) (?P<status_code>\d{3}) (?P<bytes_sent>\d{1,99})(["](?P<url>(\-)|(.+))["]) (?P<host>.+) (["](?P<user_agent>.+)["])(["](?P<request_time>.+)["]) (["](?P<connect_time>.+)["])(["](?P<city>.+)["]) (["](?P<country_code>.+)["])', IGNORECASE) # NOQA
regex = compile(re_ipv6_log_pattern, IGNORECASE) # NOQA
if regex.match(line):
logging.debug(f'Regex is matching {log_path} continuing...')
return True
Expand Down Expand Up @@ -148,23 +154,23 @@ def logparse(
client.create_retention_policy(name=f'{influxdb_database} {influxdb_retention}-{influxdb_shard}', duration=influxdb_retention, replication='1',
database=influxdb_database, default=True, shard_duration=influxdb_shard)

re_ipv4 = compile(r'(?P<ipaddress>\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}) - (?P<remote_user>.+) \[(?P<dateandtime>\d{2}\/[A-Z]{1}[a-z]{2}\/\d{4}:\d{2}:\d{2}:\d{2} ((\+|\-)\d{4}))\](["](?P<method>.+)) (?P<referrer>.+) ((?P<http_version>HTTP\/[1-3]\.[0-9])["]) (?P<status_code>\d{3}) (?P<bytes_sent>\d{1,99})(["](?P<url>(\-)|(.+))["]) (?P<host>.+) (["](?P<user_agent>.+)["])(["](?P<request_time>.+)["]) (["](?P<connect_time>.+)["])(["](?P<city>.+)["]) (["](?P<country_code>.+)["])', IGNORECASE) # NOQA
re_ipv6 = compile(r'(?P<ipaddress>(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))) - (?P<remote_user>.+) \[(?P<dateandtime>\d{2}\/[A-Z]{1}[a-z]{2}\/\d{4}:\d{2}:\d{2}:\d{2} ((\+|\-)\d{4}))\](["](?P<method>.+)) (?P<referrer>.+) ((?P<http_version>HTTP\/[1-3]\.[0-9])["]) (?P<status_code>\d{3}) (?P<bytes_sent>\d{1,99})(["](?P<url>(\-)|(.+))["]) (?P<host>.+) (["](?P<user_agent>.+)["])(["](?P<request_time>.+)["]) (["](?P<connect_time>.+)["])(["](?P<city>.+)["]) (["](?P<country_code>.+)["])', IGNORECASE) # NOQA
re_ipv4 = compile(re_ipv4_log_pattern, IGNORECASE) # NOQA
re_ipv6 = compile(re_ipv6_log_pattern, IGNORECASE) # NOQA

gi = Reader(geoip_db_path)

if send_nginx_logs in ('true', 'True'):
send_logs = True
else:
send_logs = False
re_ipv4 = compile(r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})')
re_ipv6 = compile(r'(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))') # NOQA
re_ipv4 = compile(re_ipv4_pattern)
re_ipv6 = compile(re_ipv6_pattern) # NOQA
logging.info('SEND_NGINX_LOGS set to false')
pass
if not regex_tester(log_path,3):
if send_logs:
re_ipv4 = compile(r'(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})')
re_ipv6 = compile(r'(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))') # NOQA
re_ipv4 = compile(re_ipv4_pattern)
re_ipv6 = compile(re_ipv6_pattern) # NOQA
send_logs = False
logging.warning('NGINX log metrics disabled! Double check your NGINX custom log format..')

Expand Down Expand Up @@ -246,6 +252,7 @@ def logparse(
log_data_tags['ip'] = datadict['ipaddress']
log_data_tags['datetime'] = datetime.strptime(datadict['dateandtime'], '%d/%b/%Y:%H:%M:%S %z')
log_data_tags['remote_user'] = datadict['remote_user']
log_data_tags['request'] = datadict['request']
log_data_tags['method'] = datadict['method']
log_data_tags['referrer'] = datadict['referrer']
log_data_tags['host'] = datadict['host']
Expand Down