# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?P<brand>\S+(?:.*Bio)?\s(?!\d|x))?(?:(?P<name>.+)(?=\s\S*\d+\S*|\spièce)\s(?P<quantity>\S*\d+.*|pièce)|(?P<name2>\D.+)?(?P<quantity2>\d.+)?)"
test_str = ("Nature Moi Bio Shampooing Extra Doux Amande Douce Bio 250ml\n"
"Auchan Bio Thé Noir d'Inde Earl Grey x20\n"
"Carotte 1kg\n"
"Auchan Bio Thé Noir d'Inde Earl Grey Bio 20x20\n"
"Auchan Bio Thé Noir d'Inde Earl Grey\n"
"Auchan Bio Thé Noir d'Inde Earl Grey Bio x20\n"
"Coca-Cola 6x1l\n"
"Auchan Bio Avocat Baby pièce\n"
"Nestle Avocat Baby pièce\n"
"Carrefour Carottes 1 kg")
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