# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?:\s|^) # Start of string or word boundary
( # Capture Group
(?: # Non-Capture Group for X.
(?: # Nested NCG for 0..255
(?:\d){1,2}| # Allow any single digit or any pair of digits or
(?:1\d{2})| # 3 Digits starting with 1 or
(?:2[0-4]\d)| # 3 Digists starting with 20..24 or
(?:25[0-5]) # 250..255
) # this should allow X=0..255 in the NCG
\. # Must be followed by a literal .
){3} # X. Must repeat exactly 3 times
(?: # NCG for final 0..255
(?:\d{1,2})| # Allow any single digit or any pair of digits or
(?:1\d{2})| # 3 Digits starting with 1 or
(?:2[0-4]\d)| # 3 digits starting 20..24 or
(?:25[0-5]) # 250.255
) # End of final 0.255
) # End of capture group
(?:\s|$) # Must be followed by EOS or wspace
"""
test_str = "123.123.123.145 is an IP4 so is 1.2.3.4 and 1.22.33.44 but 256.1.2.3 isn't 254.1.2.3 is but 260.1.1.1 isn't nor 2.5.256.1 and 1.2.3.4:222 IP6 1.2.3.4.5.6"
matches = re.finditer(regex, test_str, re.VERBOSE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
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