Log Analysis

log_analysis.py

#!/usr/bin/python2.7

import re
from collections import Counter
import sys

def do_analysis(data):
    date_map = dict()

    for l in data:
        date_patt = re.compile("\[(.*)\]")
        date_str = date_patt.findall(l)[0][:20]
        (day, month, hour, minute) = (date_str[:2], date_str[3:6], date_str[12:14], date_str[15:17])

        if (day + month) in date_map:
            date_map[day + month].append(hour + minute)
        else:
            date_map[day + month] = [hour + minute]

    for date in date_map:
        c = Counter(date_map[date])
        for t in c:
            print "%s, %d" % (t, c[t])

if __name__ == "__main__":
    data = sys.stdin.readlines()
    do_analysis(data)

Get file URL by clicking on the Raw link

$ wget file_url
$ chmod +x log_analysis.py
$ grep "29/Jun" site-access.log | ./log_analysis.py | sort -nk1 > 29_output.txt