# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:(?P<Day1>\d{1,2})(?:\W*(?P<Month1>[A-Z][a-z]*\b))|(?:(?P<Month2>[A-Z][a-z]*\b)\W*)(?:(?P<Day2>\d{1,2})(?:\b|th|st|nd))?|(?P<Month3>\d{1,2})\W+(?P<Day3>\d{1,2})|(?P<Month4>\d{1,2}))?\W+?(?P<Year>\d{2,4}(?=$|;))"
test_str = ("04/20/2009\n"
"04/20/09\n"
"4/20/09\n"
"4/3/09\n"
"Mar-20-2009\n"
"Mar 20, 2009\n"
"March 20, 2009\n"
"Mar. 20, 2009\n"
"Mar 20 2009;\n"
"20 Mar 2009\n"
"20 March 2009\n"
"20 Mar. 2009\n"
"20 March, 2009\n"
"Mar 20th, 2009\n"
"Mar 21st, 2009\n"
"Mar 22nd, 2009\n"
"Feb 2009\n"
"Sep 2009\n"
"Oct 2010\n"
"6/2008\n"
"12/2009\n"
"2009\n"
"2010")
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