import re
regex = re.compile(r"^([a-zA-Z]{2,}\s[a-zA-Z]{1,}'?-?[a-zA-Z]{2,}\s?([a-zA-Z]{1,})?)", flags=re.MULTILINE)
test_str = ("Al Bundy\n"
"Jean-Claude Van Damme\n"
"Lev Nikolayevich Tolstoy\n"
"Лев Николаевич Толстой\n"
"Bruce Lee\n"
"李小龍\n"
"Döner\n"
"López\n")
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