Parse an apache log into a pipe-delimited file

apache-log-to-delim.py

from __future__ import print_function
import sys
import re

parts = [
    r'(?P<host>\S+)',                   # host %h
    r'\S+',                             # indent %l (unused)
    r'(?P<user>\S+)',                   # user %u
    r'\[(?P<time>.+)\]',                # time %t
    r'"(?P<request>.+)"',               # request "%r"
    r'(?P<status>[0-9]+)',              # status %>s
    r'(?P<size>\S+)',                   # size %b (careful, can be '-')
    r'"(?P<referer>.*)"',               # referer "%{Referer}i"
    r'"(?P<agent>.*)"',                 # user agent "%{User-agent}i"
]
pattern = re.compile(r'\s+'.join(parts)+r'\s*\Z')

with open(sys.argv[1]) as f:
    for line in f:
        try:
            m = pattern.match(line)
            res = m.groupdict()
            print("|".join([res['status'],res['request'],res['agent']]))
        except:
            print("Unable to parse line %s" % line, file=sys.stderr)

f.close()

This may have been borrowed from someone else