import re
regex = re.compile(r"(?<src_host>\w+\.\w+:\d{2})\s(?<src_ip>\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})\D{1,6}(?<date_time>[^ ]+)\s(?<GMT_offset>[^ ]+)\]\s\"(?<action>(GET|POST|HEAD|TRACE|PUT|DELETE|CONNECT))\s(?<hash_url>[^ ]+)\s(?<protocol>[^\"]+)\"\s(?<code>\d{1,3})\s(?<size>[^ ]+)\s\"(?<referrer>[^ ]+)\"\s\"(?<user_agent>[^ ]+.+)\"")
test_str = "google.com:80 212.111.203.171 - - [02/Mar/2015:10:27:04 +0000] \"GET /css/style.css HTTP/1.1\" 304 138 \"http://google.com\" \"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.115 Safari/537.36\""
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