import re
regex = re.compile(r"(?P<remote_addr>((?:[0-9]{1,3}\.){3}[0-9]{1,3})) (?P<dash>\S+) (?P<remote_user>\S+) \[(?P<time_local>[\w:\/]+\s[+|-]\d{4})\] \"(?P<request>\S+)\s?(?P<path>\S+)?\s?(?P<protocol>\S+)?\" (?P<status_code>\d{3}|-) (?P<body_bytes_sent>\d+|-)\s?\"?(?P<http_referer>[^\"]*)\"?\s\"?(?P<http_user_agent>[^\"]*)\"\s\"?(?P<http_x_forwarded_for>[^\"]*)", flags=re.MULTILINE)
test_str = "137.184.55.175 - 137.184.55.175 [28/Jul/2022:15:10:09 +0700] \"GET /c/version.js HTTP/1.1\" 404 18868 \"lkk\" \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36\" \"agent\""
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} 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