import re
regex = re.compile(r"""
^ # Assert begin of line
(?= # First zero-with lookahead
( # Capturing group 1
a # Match a
(?1)? # Recurse group 1 optionally
b # Match b
) # End of group 1
c+ # Match c one or more times
) # End of the first lookahead
(?= # Second zero-with lookahead
a+ # Match a one or more times
( # Capturing group 2
b # Match b
(?2)? # Recurse group 2 optionally
c # Match c
) # End of group 2
) # End of the second lookahead
a+b+c+ # Match each of a,b and c one or more times
$ # Assert end of line
""", flags=re.MULTILINE | re.VERBOSE)
test_str = ("abc\n"
"aabbcc\n"
"aaabbbccc\n\n"
"abbc\n"
"aabbc\n"
"aabbbccc\n\n"
"ab\n"
"aabb\n"
"aaabbb")
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