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

def get_structured_access_logs_list(access_logs):
	# Initialize required variables
	log_data = []
    # Get components from each line of the log file into a structured dict
	for line in access_logs:
		try:
			log_data.append(pattern.match(line).groupdict())
		except:
			pass
	return log_data
	
lines = ['83.198.250.175 - - [22/Mar/2009:07:40:06 +0100] "GET /images/ht1.gif HTTP/1.1" 200 61 "http://w...content-available-to-author-only...s.fr/" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Wanadoo 6.7; Orange 8.0)" "-"',
'65.33.94.190 - - [05/Apr/2003:17:26:27 -0500] "POST /samples/dem/tt.php?x=e2323 HTTP/1.0" 404 276',
'151.227.152.48 - - [02/Jul/2014:14:35:55 +0100] "GET /css/main.css HTTP/1.1" 200 4658 "http://s...content-available-to-author-only...o.uk/" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36"',
'10.143.2.119 64.103.161.112 - [06/Jan/1970:00:48:01 +0000] "GET /right_arrow.jpg HTTP/1.1" 304 0 "http://64.103.161.112/index_eth_diag.html" "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36"']
for res in get_structured_access_logs_list(lines):
	print(res)