import re
regex = re.compile(r"^.*\shostname=(?:[^\s.]+\.)*?(?P<myfield>[^\s.]+\.(?:(?:ac|co)\.uk|govt?\.uk|judiciary\.uk|l(?:ea|td)\.uk|m(?:e|il|od)\.uk|n(?:et|hs|ic)\.uk|orgn?\.uk|p(?:arliament|lc|olice)\.uk|(?:royal|sch)\.uk|[^\s.]+)(?!\S))", flags=re.MULTILINE)
test_str = ("hostname=www.aaa.bbb.someurl.net\n\n"
"hostname=www.amazon.co.uk\n\n"
"2021-07-20 18:19:14 reason=Not allowed to browse this category event_id=12345 protocol=HTTP action=Blocked transactionsize=16051 responsesize=789 requestsize=456 urlcategory=Blocked serverip=1.2.4.5 clienttranstime=0 requestmethod=GET refererURL=None useragent=Microsoft-Delivery location=Internal ClientIP=5.6.7.8 status=403 user=John url=dl.delivery.mp.microsoft.com/filestreamingservice/files/abcd-efgh-ijkl/pieceshash vendor=Zscaler hostname=dl.delivery.mp.microsoft.com")
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