import re
regex = re.compile(r"""
^(Prefeitura|Pref\.|P\.)\s(Municipal\s?|Mun.\s?|M.\s?)?(de\s)?(S[aã]o\sPaulo|S.\sP.|S.\sPaulo|S.P.|SP)$
""", flags=re.MULTILINE | re.VERBOSE)
test_str = ("Prefeitura Municipal de São Paulo\n"
"Prefeitura Municipal de Sao Paulo\n"
"Prefeitura de São Paulo\n"
"Prefeitura de Sao Paulo\n"
"Prefeitura Mun. de São Paulo\n"
"Pref. Mun. de São Paulo\n"
"Pref. Mun. de S. P.\n"
"Pref. de São Paulo\n"
"Pref. de S. Paulo\n"
"Pref. M. de São Paulo\n"
"P. M. de Sao Paulo\n"
"Prefeitura São Paulo\n"
"Pref. Mun. São Paulo\n"
"Pref. Mun. S. Paulo\n"
"Prefeitura de S.P.\n"
"Prefeitura de SP")
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