import re
regex = re.compile(r"(?P<client_ip>[\d.]+) - - \[(?P<timestamp>.*?)\] \"(?P<request_method>\w+) (?P<request_uri>.*?) (?P<protocol>.*?) (?P<protocol_version>.*?)\" (?P<status>\d+) (?P<response_size>\d+|-) \"(?P<referrer>.*?)\" \"(?P<user_agent>.*?)\"", flags=re.MULTILINE)
test_str = ("209.160.24.63 - - [28/Mar/2023:18:22:16] \"GET /product.screen?productId=WC-SH-A02&JSESSIONID=SD0SL6FF7ADFF4953 HTTP 1.1\" 200 3878 \"http://www.google.com\" \"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.46 Safari/536.5\" 349\n"
"209.160.24.63 - - [28/Mar/2023:18:22:16] \"POST /oldlink?itemId=EST-6&JSESSIONID=SD0SL6FF7ADFF4953 HTTP 1.1\" 200 1748 \"http://www.buttercupgames.com/oldlink?itemId=EST-6\" \"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.46 Safari/536.5\" 731\n")
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