# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((?:|\s)\w+(?:\.|))(?:|,|\.)\s(\d+)"
test_str = ("Av. Moinho Fabrini, 600 - Independencia, Sao Bernardo do Campo - SP, 09862-160\n"
"SAO BERNARDO DO CAMPO STATE OF SAO PAULO BRAZIL RUA VICENTE DE CARVALHO 197 09726 600\n"
"RUA JOAO PESSOA, 420, CENTRO, SAO BERNARDO DO CAMPO - SAO PAULO, 09715-000, BRASIL\n"
"AV. ROBERT KENNEDY. 3095 - ASSUNCAO SAO BERNARDO DO CAMPO - SP. 09860-215")
matches = re.finditer(regex, test_str, re.MULTILINE)
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