import re
regex = re.compile((r"(?:^|\s)(([0-9a-fA-F]{1,4}:){7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]+|::(ffff(:0{1,4})?:)?((25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d)\.){3}(25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d)|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d)\.){3}(25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d))(?=\s|$)\n"), flags=re.IGNORECASE | re.MULTILINE)
test_str = ("{1: Initial address, regex should say valid/match}\n"
"2001:0db8:0000:0000:0000:ff00:0042:8329\n\n"
"{2: After removing all leading zeroes, regex should say valid/match}\n"
"2001:db8:0:0:0:ff00:42:8329\n\n"
"{3: After omitting consecutive sections of zeroes, regex should say valid/match}\n"
"2001:db8::ff00:42:8329\n\n"
"{4: The loopback address, regex should say valid/match}\n"
"0000:0000:0000:0000:0000:0000:0000:0001\n\n"
"{5: The loopback address be abbreviated to ::1 by using both rules, regex should say valid/match}\n"
"::1\n\n"
"{6: This should be valid, regex should say valid/match}\n"
"ABCD:ABCD:ABCD:ABCD:ABCD:ABCD:192.168.158.190\n\n"
"{7: This should NOT be valid/match}\n"
"::\n\n"
"{These two formats allows IPv6 applications to communicate directly with IPv4 applications, regex should say valid/match}\n"
"{8}\n"
"0:0:0:0:0:ffff:192.1.56.10\n"
"{9}\n"
"::ffff:192.1.56.10/96\n\n"
"{These next two formats are used for tunneling. It allows IPv6 nodes to communicate across an IPv4 infrastructure, regex should say valid/match}\n"
"{10}\n"
"0:0:0:0:0:0:192.1.56.10\n"
"{11}\n"
"::192.1.56.10/96\n\n"
"{These 4 should be valid/match}\n"
"{12}\n"
"::FFFF:129.144.52.38\n"
"{13}\n"
"::129.144.52.38\n"
"{14}\n"
"::FFFF:d\n"
"{15}\n"
"1080:0:0:0:8:800:200C:417A\n\n"
"{These 4 should NOT be valid/match}\n"
"{16}\n"
"::FFFF:d.d.d\n"
"{17}\n"
"::FFFF:d.d\n"
"{18}\n"
"::d.d.d\n"
"{19}\n"
"::d.d")
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