import re
regex = re.compile(r"\S+\s+\S+\s+\S+\s+\S+\s+\S+\s+(?P<host>[\w\-\.]*)(?::\d+)?\s+(?P<ip>\S+)\s+\S+\s+\S+\s+\[(?P<date>.*?)\s+(?P<timezone>.*?)\]\s+\"\S+\s+(?P<path>.*?)\s+\S+\"\s+(?P<status>\S+)\s+(?P<length>\S+)\s+\"(?P<referrer>.*?)\"\s+\"(?P<user_agent>.*?)\"\s+(?P<generation_time_secs>[.\d]+)")
test_str = "Feb 6 09:33:42 ngx-01 acother: 115.231.222.14 - - [06/Feb/2016:09:33:42 +0100] \"GET http://zc.qq.com/cgi-bin/common/attr?id=260714&r=0.6027916056127199 HTTP/1.1\" 401 590 \"-\" \"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0; 360SE)\" 0.001"
match = regex.search(test_str)
if match:
print(f"Match was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html