# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(c\/|calle|carrer)?\W?(\w+\W?[A-z]*\W?[A-z]*\W?[A-z]*\W?[A-z]*\W?[A-z]*\W?[A-z]*(?<!num))\W(nº|num|núm|num\.|núm\.|numero|número|n|n\.|no|no\.)?\W?(\d{1,3}\-?\d{1,3}?)\W?(bis|dup|mod|ant)?\W+(BJ)?\W\w+\W"
test_str = ("calle Monistrol de la vega num 13-15, BJ1 08012 Barcelona \n"
"calle Monistrol 13, BJ1 08012 Barcelona\n"
"carrer Monistrol 13, BJ1 08012 Barcelona\n"
"Monistrol 13, BJ1 08012 Barcelona\n"
"c/ Monistrol, 13, BJ1 08012 Barcelona\n"
"calle Monistrol nº 13, BJ1 08012 Barcelona\n"
"calle Monistrol 13, bajo 1 08012 Barcelona\n"
"c/ Monistrol 13, Bajo 1º, 08012 Barcelona\n")
matches = re.finditer(regex, test_str, 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