# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^[^\W\d_]+\.?(?:[- ][^\W\d_]+\.?)*$"
test_str = ("Valid street names are:\n"
"Mainstreet.\n"
"Mainstreet\n"
"Main Street\n"
"Big New mainstreet\n"
"Mainstreet-New\n"
"Mains Str.\n"
"St. Alexander Street\n"
"abcÜüßäÄöÖàâäèéêëîï ôœùûüÿçÀÂ-ÄÈÉÊËÎÏÔŒÙÛÜŸÇ.\n"
"John Kennedy Street\n\n"
"Not valid street names are:\n"
"Mainstreet #+;:_*´`?=)(/&%$§!\n"
"Mainstreet#+;:_*´`?=)(/&%$§!\n"
"Mainstreet 2\n"
"Mainstreet..\n"
"Mainstreet§\n\n"
"Valid cities are:\n"
"Edinôœùûüÿ\n"
"Berlin.\n"
"St. Petersburg\n"
"New-Berlin\n"
"Aue-Bad Schlema\n"
"Frankfurt am Main\n"
"Nürnberg\n"
"Ab\n"
"New York CityßäÄöÖàâäèéêëîïôœùûüÿçÀÂ-ÄÈÉÊËÎÏÔŒÙÛÜŸ\n"
"Not valid cities are:\n\n"
"Edingburgh 123\n"
"Edingburg123\n"
"St. Andrews 12\n"
"Berlin,#+;:_*´`?=)(/&%$§!\n"
"Berlin__\n"
"The solutions that I have at the moment matches very close but not perfectly:\n\n"
"For city and street name:\n"
"Unfortunately no match for these examples (the rest works fine):\n\n"
"St. Alexander Street\n"
"St. Petersburg\n")
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