Last active
November 25, 2016 20:14
-
-
Save starenka/650925f51a119e270a986d8e9fc352fc to your computer and use it in GitHub Desktop.
This file contains 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
#!/usr/bin/env python | |
# coding=utf-8 | |
import argparse | |
import re | |
import logging | |
import datetime | |
import itertools | |
import pandas as pd | |
RE_LINE = re.compile( | |
r'^(?P<ip>.*) - - \[(?P<stamp>.*)\] "(?P<request>.*)" (?P<http_code>\d+) (?P<resp_bytes>\d+) "(?P<referer>.*)" "(?P<ua>.*)"$') | |
logging.basicConfig(level=logging.INFO) | |
log = logging.getLogger(__name__) | |
def parse_file(fpath, drop_fields=None): | |
drop_fields = drop_fields or [] | |
log.info('Parsing %s' % fpath) | |
with open(fpath) as f: | |
for line in f: | |
match = re.match(RE_LINE, line[:line.rindex('"')+1]) | |
parsed = match.groupdict() | |
parsed['stamp'] = parsed['stamp'].split(' ')[0] | |
parsed['http_code'] = int(parsed['http_code']) | |
for field in drop_fields: | |
del parsed[field] | |
yield parsed | |
def parse_files(files, drop_fields=None): | |
return pd.DataFrame.from_records(itertools.chain.from_iterable(parse_file(lfile, drop_fields) for lfile in files)) | |
if __name__ == '__main__': | |
parser = argparse.ArgumentParser(description='parses common access log format to pandas df') | |
parser.add_argument('logfiles', metavar='N', nargs='+', help='logfile(s)') | |
parser.add_argument('--ips', metavar='N', nargs='*', help='just this IPs') | |
parser.add_argument('-d', '--days-back', dest='days_back', type=int, default=1, help='lines newer then n days') | |
args = parser.parse_args() | |
df = parse_files(args.logfiles, drop_fields=('request', 'resp_bytes', 'referer')) | |
df['stamp'] = pd.to_datetime(df['stamp'], format='%d/%b/%Y:%H:%M:%S') | |
if args.days_back: | |
log.info('Filtering by date') | |
dfrom = datetime.date.today() - datetime.timedelta(days=args.days_back) | |
df = df.loc[(df['stamp'] > dfrom)] | |
if args.ips: | |
log.info('Filtering IPs') | |
df = df[df['ip'].isin(args.ips)] | |
by_ip_code = df.groupby(['ip', 'http_code']) | |
by_ip_ua = df.groupby(['ip', 'ua']) | |
# by_ip_ua.sizes()['ip.ad.d.r'] | |
import ipdb | |
ipdb.set_trace() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment