# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^([aA]v\/|[aA]venida)\s?([A-Za-z ]{0,})\,?\s?(\d{0,}|s\/n)\,?\s?\d{0,}[ºª]?\s?[a-zA-Z]?$"
test_str = ("calle prueba, 2\n"
"calle de la prueba, 5\n"
"Avenida de la prueba, 5\n"
"Plaza de la prueba, 5\n"
"Avenida Higuereta, 4, 7º B\n"
"Avenida Escritor Conde Zamora s/n\n"
"Avenida Ciudad de Aranjuez 18\n"
"Avenida Pintor Sorolla 125 4ºG\n"
"Polígono Industrial Aranguren 6\n"
"Avenida Gremi Passamaners 24 2º\n"
"Avenida Manuel Rodriguez Ayuso, 170\n"
"Avenida Illa de Buda 55\n"
"C/ Walia, 21 \n"
"C/Alfonso Pesquera, 6")
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