import re
regex = re.compile(r"(?<req_ip>[\d\.]+)\s(?<req_unk1>[\w\-]+)\s(?<req_unk2>[\w\-]+)\s\[(?<req_ts>\d+\/\w+\/\d+\:\d+\:\d+\:\d+\s\+\d+)\]\s\"(?<req_full>.+?)\"\s(?<req_status>[\d\-]+)\s(?<req_bytes_in>[\d\-]+)\s\"(?<req_referrer>.+?)\"\s\"(?<req_ua>.+?)\"\s\"(?<req_cookie>.+?)\"\s\"(?<req_waf_info>.+?)\"\s\"(?<req_customfield>.+?)\"")
test_str = "1.1.1.1 - - [05/May/2015:13:23:13 +0000] \"HEAD /www.arl.com/path/to/file.php HTTP/1.1\" 200 265 \"-\" \"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\" \"-\" \"-\" \"UNKNOWN\""
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