Basic Apache Error Log Parser

roblog.py

import re
import os
import sys
import getopt
import datetime
import csv


class RobLog(object):
    input_file = None
    output_file = None
    regex = '\[(.*?)\] \[(.*?)\] (.*)'
    line_map = ('date', 'type', 'message')
    json_output = []

    def prepare_output(self):
        print 'RobLog: ... preparing CSV output...'
        f = open(self.output_file, 'wb')
        writer = csv.writer(f, delimiter=',', quotechar='"')
        writer.writerow(self.line_map)
        for line in self.json_output:
            writer.writerow([
                line['date'].isoformat(),
                line['type'],
                line['message']
            ])
        f.close()
        print 'RobLog: ... CSV completed!'

    def parse_line(self, line):
        g = re.match(self.regex, line).groups()
        formatted_line = dict(zip(self.line_map, g))
        # get the date and turn it into a datetime
        formatted_line['date'] = datetime.datetime.strptime(formatted_line['date'],
                                                            '%a %b %d %H:%M:%S %Y')
        return formatted_line

    def parse_file(self):
        print 'RobLog: Parsing log file...'
        f = open(self.input_file, 'rb')
        for line in f:
            f_line = self.parse_line(line)
            self.json_output.append(f_line)
        f.close()
        print 'RobLog: ... parsed {0} lines...'.format(len(self.json_output))
        self.prepare_output()

    def __init__(self, argv):
        try:
          opts, args = getopt.getopt(argv,"hi:o:",["ifile=","ofile="])
        except getopt.GetoptError:
          print 'test.py -i <inputfile> -o <outputfile>'
          sys.exit(2)
        for opt, arg in opts:
          if opt == '-h':
             print 'test.py -i <inputfile> -o <outputfile>'
             sys.exit()
          elif opt in ("-i", "--ifile"):
             self.input_file = arg
          elif opt in ("-o", "--ofile"):
             self.output_file = arg


        self.parse_file()

if __name__ == "__main__":
   RobLog(sys.argv[1:])