# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\d+?[\+x])?\d+ ?(litros?|u(ni)?ds?|kg|g|cl)(.?, \w+ \d+ ?(litros?|u(ni)?ds|kg|g))?"
test_str = ("Aceite de oliva virgen extra CARBONELL, garrafa 3 litros\n"
"Aceite de oliva virgen CARBONELL, botella 1 litro\n"
"First Bike, bici sin pedales roja,edad rec:2-5 años CHICCO, peso máximo 25 Kg\n"
"Bombón de almendras MAGNUM, 3+1 uds., caja 423 g\n"
"Bote PLAY-DOH,pasta de moldear, sutidos sorpresa, edad rec:+2 años, pack 4uds\n"
"Magdalena 0% azúcar LA BELLA EASO, 8 unid., paquete 232 g\n"
"Magdalena 0% azúcar LA BELLA EASO, 8 unid., paquete 232 g\n"
"Cerveza MAHOU 5 Estrellas, pack botellín 12x25 cl\n"
"Bote PLAY-DOH,pasta de moldear, sutidos sorpresa, edad rec:+2 años, pack 4uds")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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