# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(\d*?)(?:, )?([a-zéèàçù -]+?)\n(\d\d ?\d\d\d) ([a-z- ]+?)$"
test_str = ("61, avenue de Gauthier\n"
"81 516 Michel-sur-Paris\n\n"
"6, boulevard de Nguyen\n"
"02 998 Techer\n\n"
"boulevard Lucie Bouvet\n"
"16 345 Morel-sur-Marques\n\n"
"7, impasse Francois\n"
"29172 Deschampsnec\n\n"
"30, place Lucy Guillot\n"
"94 786 Texier-sur-Rolland\n\n"
"rue de Pruvost\n"
"91 147 Brun\n\n"
"boulevard Amélie Martin\n"
"56243 Godard\n")
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