Parsing apache log files

Question

I just started learning Python and would like to read an Apache log file and put parts of each line into different lists.

line from the file

1

Answer 1

import re


HOST = r'^(?P.*?)'
SPACE = r'\s'
IDENTITY = r'\S+'
USER = r'\S+'
TIME = r'(?P\[.*?\])'
REQUEST = r'\"(?P.*?)\"'
STATUS = r'(?P\d{3})'
SIZE = r'(?P\S+)'

REGEX = HOST+SPACE+IDENTITY+SPACE+USER+SPACE+TIME+SPACE+REQUEST+SPACE+STATUS+SPACE+SIZE+SPACE

def parser(log_line):
    match = re.search(REGEX,log_line)
    return ( (match.group('host'),
            match.group('time'), 
                      match.group('request') , 
                      match.group('status') ,
                      match.group('size')
                     )
                   )


logLine = """180.76.15.30 - - [24/Mar/2017:19:37:57 +0000] "GET /shop/page/32/?count=15&orderby=title&add_to_wishlist=4846 HTTP/1.1" 404 10202 "-" "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"""
result = parser(logLine)
print(result)