Created
January 8, 2020 14:12
-
-
Save etigui/aca04ea02684f6c4d4a85b19c505f4a9 to your computer and use it in GitHub Desktop.
Parse Nginx "access.log" file to python object or json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def main(): | |
ng = nginx.Nginx() | |
logs_parsed = ng.get_obj_parsed_logs('input.log') | |
for log in logs_parsed: | |
print(f'{log.date} {log.ip} {log.url} {log.bytes_sent} {log.referrer} {log.user_agent} {log.status} {log.method}') | |
ng.save_json_parsed_logs('input.log', 'output.josn') | |
if __name__ == "__main__": | |
main() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Ref: https://gist.github.com/hreeder/f1ffe1408d296ce0591d | |
import re | |
from datetime import datetime | |
class Nginx: | |
def __init__(self): | |
self.__log_format = re.compile(r"""(?P<ipaddress>\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}) - - \[(?P<dateandtime>\d{2}\/[a-z]{3}\/\d{4}:\d{2}:\d{2}:\d{2} (\+|\-)\d{4})\] ((\"(GET|POST) )(?P<url>.+)(http\/1\.1")) (?P<statuscode>\d{3}) (?P<bytessent>\d+) (["](?P<refferer>(\-)|(.+))["]) (["](?P<useragent>.+)["])""",re.IGNORECASE) | |
self.__input_file_name = '' | |
self.__output_file_name = '' | |
self.parsed_logs = list() | |
def __parser(self): | |
self.parsed_logs.clear() | |
try: | |
with open(self.__input_file_name, 'r') as f: | |
for log in f.readlines(): | |
data = re.search(self.__log_format, log) | |
if data: | |
data_dict = data.groupdict() | |
date = datetime.strptime(data_dict["dateandtime"], "%d/%b/%Y:%H:%M:%S %z").strftime("%Y-%m-%d %H:%M:%S") | |
self.parsed_logs.append(NginxLogs(data_dict["ipaddress"], date, data_dict["url"], data_dict["bytessent"], data_dict["refferer"], data_dict["useragent"], data_dict["statuscode"], data.group(6))) | |
except: | |
raise Exception(f'Cannot open Nginx log file: {self.__input_file_name}') | |
def __write_file(self): | |
try: | |
with open(self.__output_file_name, 'a+') as f: | |
for log in self.parsed_logs: | |
f.write(f'{vars(log)}\n') | |
except: | |
raise Exception(f'Cannot create Nginx output log file: {self.__output_file_name}') | |
def get_obj_parsed_logs(self, input_file_name): | |
self.__input_file_name = input_file_name | |
self.__parser() | |
return self.parsed_logs | |
def save_json_parsed_logs(self, input_file_name, output_file_name): | |
self.__input_file_name = input_file_name | |
self.__output_file_name = output_file_name | |
self.__parser() | |
self.__write_file() | |
class NginxLogs: | |
def __init__(self, ip, date, url, bytes_sent, referrer, user_agent, status, method): | |
self.ip = ip | |
self.date = date | |
self.url = url | |
self.bytes_sent = bytes_sent | |
self.referrer = referrer | |
self.user_agent = user_agent | |
self.status = status | |
self.method = method |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment