goaccess.py

import re
import pandas as pd

from sys import stdin

regex = 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>.+)["])"""
p = re.compile(regex, re.IGNORECASE)
df = pd.DataFrame([p.match(l).groupdict() for l in stdin.readlines() if p.match(l)])

print(df.head())