# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?=(?:^(?:\d\d\d\d-(?:0[1-9]|10|11|12)-(?:0[1-9]|1[0-9]|2[0-8])|\d\d\d\d-(?:0[13-9]|10|11|12)-(?:29|30)|\d\d\d\d-(?:0[13578]|10|12)-31|(?:\d\d[2468][048]|\d\d0[48]|\d\d[13579][26])-02-29|(?:[02468][048]00|[13579][26]00)-02-29)T(?:(?:0[0-9]|1[0-9]|2[0-3]):(?:[0-5][0-9]):(?:[0-5][0-9]))(?:\.\d\d\d)?(?:Z|[\+\-](?:0[0-9]|1[012]):00|\+0[34569]:30|\+10:30|-0[39]:30|\+1[34]:00|\+0[58]:45|\+12:45)$)|^(?:1972|198[1235]|199[2347]|2012|2015)-06-30T23:59:60Z$|^(?:197[2-9]|1987|1989|199[058]|2005|2008|2016)-12-31T23:59:60Z$)(?!.*-00:00$)^(\d\d\d\d)-(\d\d)-(\d\d)T(\d\d):(\d\d):(\d\d)(?:\.(\d\d\d))?((Z)|([\+\-])(\d\d):(\d\d))$"
test_str = ("Strong Matcher for ISO 8601 / RFC 3339 Date Times; rejects bad TZ offsets, illegal times (Museum of Bad Data)\n"
"See below for expanded matcher\n\n"
"```\n"
"// accept: Exemplars\n"
"2008-02-03T04:05:06.007Z\n"
"2008-02-03T04:05:06Z\n"
"0000-01-01T00:00:00.000Z\n"
"0000-02-29T04:05:06.007Z\n"
"9999-12-31T23:59:59.999Z\n"
"9999-12-31T23:59:59Z\n"
"2008-02-03T04:05:06.007+12:45\n"
"2008-02-03T04:05:06+03:30\n"
"0000-01-01T00:00:00.007-09:30\n"
"0000-02-29T04:05:06.007+14:00\n"
"9999-12-31T23:59:59.999+12:00\n"
"9999-12-31T23:59:59-12:00\n"
"// accept: Leap day, year is multiple of four\n"
"0004-02-29T04:05:06.007Z\n"
"0008-02-29T04:05:06.007Z\n"
"0012-02-29T04:05:06.007Z\n"
"0016-02-29T04:05:06.007Z\n"
"0020-02-29T04:05:06.007Z\n"
"0024-02-29T04:05:06.007Z\n"
"0028-02-29T04:05:06.007Z\n"
"0032-02-29T04:05:06.007Z\n"
"0036-02-29T04:05:06.007Z\n"
"0040-02-29T04:05:06.007Z\n"
"0044-02-29T04:05:06.007Z\n"
"0048-02-29T04:05:06.007Z\n"
"0052-02-29T04:05:06.007Z\n"
"0056-02-29T04:05:06.007Z\n"
"0060-02-29T04:05:06.007Z\n"
"0064-02-29T04:05:06.007Z\n"
"0068-02-29T04:05:06.007Z\n"
"0072-02-29T04:05:06.007Z\n"
"0076-02-29T04:05:06.007Z\n"
"0080-02-29T04:05:06.007Z\n"
"0084-02-29T04:05:06.007Z\n"
"0088-02-29T04:05:06.007Z\n"
"0092-02-29T04:05:06.007Z\n"
"0096-02-29T04:05:06.007Z\n"
"1560-02-29T04:05:06.007Z\n"
"2004-02-29T04:05:06.007Z\n"
"2008-02-29T04:05:06.007Z\n"
"2012-02-29T04:05:06.007Z\n"
"2016-02-29T04:05:06.007Z\n"
"2020-02-29T04:05:06.007Z\n"
"2024-02-29T04:05:06.007Z\n"
"2028-02-29T04:05:06.007Z\n"
"2032-02-29T04:05:06.007Z\n"
"2036-02-29T04:05:06.007Z\n"
"2040-02-29T04:05:06.007Z\n"
"2044-02-29T04:05:06.007Z\n"
"9996-02-29T04:05:06.007Z\n"
"// accept: Leap day, year is Multiple of 400\n"
"0000-02-29T04:05:06.007Z\n"
"0400-02-29T04:05:06.007Z\n"
"0800-02-29T04:05:06.007Z\n"
"1200-02-29T04:05:06.007Z\n"
"1600-02-29T04:05:06.007Z\n"
"2000-02-29T04:05:06.007Z\n"
"2400-02-29T04:05:06.007Z\n"
"2800-02-29T04:05:06.007Z\n"
"3200-02-29T04:05:06.007Z\n"
"3600-02-29T04:05:06.007Z\n"
"4000-02-29T04:05:06.007Z\n"
"4400-02-29T04:05:06.007Z\n"
"4800-02-29T04:05:06.007Z\n"
"5200-02-29T04:05:06.007Z\n"
"5600-02-29T04:05:06.007Z\n"
"6000-02-29T04:05:06.007Z\n"
"6400-02-29T04:05:06.007Z\n"
"6800-02-29T04:05:06.007Z\n"
"7200-02-29T04:05:06.007Z\n"
"7600-02-29T04:05:06.007Z\n"
"8000-02-29T04:05:06.007Z\n"
"8400-02-29T04:05:06.007Z\n"
"8800-02-29T04:05:06.007Z\n"
"9200-02-29T04:05:06.007Z\n"
"9600-02-29T04:05:06.007Z\n"
"// accept: Day in range for month\n"
"2008-01-30T04:05:06.007Z\n"
"2008-03-30T04:05:06.007Z\n"
"2008-04-30T04:05:06.007Z\n"
"2008-05-30T04:05:06.007Z\n"
"2008-06-30T04:05:06.007Z\n"
"2008-07-30T04:05:06.007Z\n"
"2008-08-30T04:05:06.007Z\n"
"2008-09-30T04:05:06.007Z\n"
"2008-10-30T04:05:06.007Z\n"
"2008-11-30T04:05:06.007Z\n"
"2008-12-30T04:05:06.007Z\n"
"2008-01-31T04:05:06.007Z\n"
"2008-03-31T04:05:06.007Z\n"
"2008-05-31T04:05:06.007Z\n"
"2008-07-31T04:05:06.007Z\n"
"2008-08-31T04:05:06.007Z\n"
"2008-10-31T04:05:06.007Z\n"
"2008-12-31T04:05:06.007Z\n"
"// accept: had leap second\n"
"1972-06-30T23:59:60Z\n"
"1981-06-30T23:59:60Z\n"
"1982-06-30T23:59:60Z\n"
"1983-06-30T23:59:60Z\n"
"1985-06-30T23:59:60Z\n"
"1992-06-30T23:59:60Z\n"
"1993-06-30T23:59:60Z\n"
"1994-06-30T23:59:60Z\n"
"1997-06-30T23:59:60Z\n"
"2012-06-30T23:59:60Z\n"
"2015-06-30T23:59:60Z\n"
"1972-12-31T23:59:60Z\n"
"1973-12-31T23:59:60Z\n"
"1974-12-31T23:59:60Z\n"
"1975-12-31T23:59:60Z\n"
"1976-12-31T23:59:60Z\n"
"1977-12-31T23:59:60Z\n"
"1978-12-31T23:59:60Z\n"
"1979-12-31T23:59:60Z\n"
"1987-12-31T23:59:60Z\n"
"1989-12-31T23:59:60Z\n"
"1990-12-31T23:59:60Z\n"
"1995-12-31T23:59:60Z\n"
"1998-12-31T23:59:60Z\n"
"2005-12-31T23:59:60Z\n"
"2008-12-31T23:59:60Z\n"
"2016-12-31T23:59:60Z\n"
"// REJECT: Year out of range\n"
"10000-02-29T04:05:06.007Z\n"
"// REJECT: Month out of range\n"
"2008-00-30T04:05:06.007Z\n"
"2008-13-30T04:05:06.007Z\n"
"2008-14-30T04:05:06.007Z\n"
"2008-20-30T04:05:06.007Z\n"
"// REJECT: Day out of range for month\n"
"2008-02-30T04:05:06.007Z\n"
"2008-04-31T04:05:06.007Z\n"
"2008-06-31T04:05:06.007Z\n"
"2008-09-31T04:05:06.007Z\n"
"2008-11-31T04:05:06.007Z\n"
"2008-02-31T04:05:06.007Z\n"
"// REJECT: Day out of range\n"
"2008-12-32T04:05:06.007Z\n"
"2008-12-99T04:05:06.007Z\n"
"2008-12-00T04:05:06.007Z\n"
"// REJECT: Hour out of range\n"
"2008-12-08T60:05:06.007Z\n"
"2008-12-08T99:05:06.007Z\n"
"// REJECT: Minute out of range\n"
"2008-12-08T04:60:06.007Z\n"
"2008-12-08T04:99:06.007Z\n"
"// REJECT: Seconds out of range\n"
"9999-12-31T59:59:61.999Z\n"
"2008-02-03T04:05:61.999Z\n"
"2008-02-03T04:05:61Z\n"
"// REJECT: Negative dates not accepted\n"
"-2000-02-29T04:05:06.007Z\n"
"-0400-02-29T04:05:06.007Z\n"
"-0100-02-29T04:05:06.007Z\n"
"-0004-02-29T04:05:06.007Z\n"
"// REJECT: stray characters\n"
" 2008-12-31T04:05:06.007Z\n"
"2008-12-31T04:05:06.007Z \n"
"2008-12-31T04:05:06.007 Z\n"
"// REJECT: Malformed\n"
"2008-02-0304:05:06.007Z\n"
"20080203T040506.007Z\n"
"2008-02-03T04:05:06007Z\n"
"2008-02-03T04:05:06.7Z\n"
"2008-02-03T04:05:06.07Z\n"
"2008-02-03T04:05:06.0007Z\n"
"2008-02-03T04:05:06\n"
"2008-02-03T04:05:06.Z\n"
"// REJECT: no leap second\n"
"1973-06-30T23:59:60Z\n"
"1974-06-30T23:59:60Z\n"
"1975-06-30T23:59:60Z\n"
"1976-06-30T23:59:60Z\n"
"1977-06-30T23:59:60Z\n"
"1978-06-30T23:59:60Z\n"
"1979-06-30T23:59:60Z\n"
"1980-06-30T23:59:60Z\n"
"1984-06-30T23:59:60Z\n"
"1986-06-30T23:59:60Z\n"
"1987-06-30T23:59:60Z\n"
"1988-06-30T23:59:60Z\n"
"1989-06-30T23:59:60Z\n"
"1990-06-30T23:59:60Z\n"
"1991-06-30T23:59:60Z\n"
"1995-06-30T23:59:60Z\n"
"1996-06-30T23:59:60Z\n"
"1998-06-30T23:59:60Z\n"
"1999-06-30T23:59:60Z\n"
"2000-06-30T23:59:60Z\n"
"2001-06-30T23:59:60Z\n"
"2002-06-30T23:59:60Z\n"
"2003-06-30T23:59:60Z\n"
"2004-06-30T23:59:60Z\n"
"2005-06-30T23:59:60Z\n"
"2006-06-30T23:59:60Z\n"
"2007-06-30T23:59:60Z\n"
"2008-06-30T23:59:60Z\n"
"2009-06-30T23:59:60Z\n"
"2010-06-30T23:59:60Z\n"
"2011-06-30T23:59:60Z\n"
"2013-06-30T23:59:60Z\n"
"2014-06-30T23:59:60Z\n"
"2016-06-30T23:59:60Z\n"
"2017-06-30T23:59:60Z\n"
"2018-06-30T23:59:60Z\n"
"2019-06-30T23:59:60Z\n"
"2020-06-30T23:59:60Z\n"
"2021-06-30T23:59:60Z\n"
"2022-06-30T23:59:60Z\n"
"2023-06-30T23:59:60Z\n"
"1980-12-31T23:59:60Z\n"
"1981-12-31T23:59:60Z\n"
"1982-12-31T23:59:60Z\n"
"1983-12-31T23:59:60Z\n"
"1984-12-31T23:59:60Z\n"
"1985-12-31T23:59:60Z\n"
"1986-12-31T23:59:60Z\n"
"1988-12-31T23:59:60Z\n"
"1991-12-31T23:59:60Z\n"
"1992-12-31T23:59:60Z\n"
"1993-12-31T23:59:60Z\n"
"1994-12-31T23:59:60Z\n"
"1996-12-31T23:59:60Z\n"
"1997-12-31T23:59:60Z\n"
"1999-12-31T23:59:60Z\n"
"2000-12-31T23:59:60Z\n"
"2001-12-31T23:59:60Z\n"
"2002-12-31T23:59:60Z\n"
"2003-12-31T23:59:60Z\n"
"2004-12-31T23:59:60Z\n"
"2006-12-31T23:59:60Z\n"
"2007-12-31T23:59:60Z\n"
"2009-12-31T23:59:60Z\n"
"2010-12-31T23:59:60Z\n"
"2011-12-31T23:59:60Z\n"
"2012-12-31T23:59:60Z\n"
"2013-12-31T23:59:60Z\n"
"2014-12-31T23:59:60Z\n"
"2015-12-31T23:59:60Z\n"
"2017-12-31T23:59:60Z\n"
"2018-12-31T23:59:60Z\n"
"2019-12-31T23:59:60Z\n"
"2020-12-31T23:59:60Z\n"
"2021-12-31T23:59:60Z\n"
"2022-12-31T23:59:60Z\n"
"2023-12-31T23:59:60Z\n"
"// REJECT: assumes no future leap seconds\n"
"2024-12-31T23:59:60Z\n"
"2099-12-31T23:59:60Z\n"
"9999-12-31T23:59:60Z\n"
"// REJECT: leap seconds only in UTC format\n"
"2005-12-31T23:59:60+00:00\n"
"2008-12-31T23:59:60+00:00\n"
"// REJECT: Not a leap day, year is not a multiple of four\n"
"0101-02-29T04:05:06.007Z\n"
"0102-02-29T04:05:06.007Z\n"
"0103-02-29T04:05:06.007Z\n"
"1537-02-29T04:05:06.007Z\n"
"1538-02-29T04:05:06.007Z\n"
"2001-02-29T04:05:06.007Z\n"
"2002-02-29T04:05:06.007Z\n"
"2003-02-29T04:05:06.007Z\n"
"2021-02-29T04:05:06.007Z\n"
"2022-02-29T04:05:06.007Z\n"
"2023-02-29T04:05:06.007Z\n"
"2025-02-29T04:05:06.007Z\n"
"2026-02-29T04:05:06.007Z\n"
"2027-02-29T04:05:06.007Z\n"
"2029-02-29T04:05:06.007Z\n"
"2030-02-29T04:05:06.007Z\n"
"2031-02-29T04:05:06.007Z\n"
"2033-02-29T04:05:06.007Z\n"
"2034-02-29T04:05:06.007Z\n"
"2035-02-29T04:05:06.007Z\n"
"2037-02-29T04:05:06.007Z\n"
"2038-02-29T04:05:06.007Z\n"
"2039-02-29T04:05:06.007Z\n"
"2041-02-29T04:05:06.007Z\n"
"2042-02-29T04:05:06.007Z\n"
"2043-02-29T04:05:06.007Z\n"
"9997-02-29T04:05:06.007Z\n"
"9998-02-29T04:05:06.007Z\n"
"9999-02-29T04:05:06.007Z\n"
"// REJECT: Not a leap day, year is a multiple of 100 but not 400\n"
"0100-02-29T04:05:06.007Z\n"
"0200-02-29T04:05:06.007Z\n"
"0300-02-29T04:05:06.007Z\n"
"0500-02-29T04:05:06.007Z\n"
"0600-02-29T04:05:06.007Z\n"
"0700-02-29T04:05:06.007Z\n"
"0900-02-29T04:05:06.007Z\n"
"1000-02-29T04:05:06.007Z\n"
"1100-02-29T04:05:06.007Z\n"
"1500-02-29T04:05:06.007Z\n"
"2100-02-29T04:05:06.007Z\n"
"2200-02-29T04:05:06.007Z\n"
"2300-02-29T04:05:06.007Z\n"
"2500-02-29T04:05:06.007Z\n"
"2600-02-29T04:05:06.007Z\n"
"2700-02-29T04:05:06.007Z\n"
"2900-02-29T04:05:06.007Z\n"
"3000-02-29T04:05:06.007Z\n"
"3100-02-29T04:05:06.007Z\n"
"3300-02-29T04:05:06.007Z\n"
"3400-02-29T04:05:06.007Z\n"
"3500-02-29T04:05:06.007Z\n"
"3700-02-29T04:05:06.007Z\n"
"```\n\n"
"```\n"
"(?=\n"
" (?:^\n"
" (?: # All non-leap-second YYYY-MM-DD parts:\n"
" (?:\\d\\d\\d\\d-(?:0[1-9] |10|11|12)-(?:0[1-9]|1[0-9]|2[0-8])) # Days 01-28\n"
" | (?:\\d\\d\\d\\d-(?:0[13-9] |10|11|12)-(29|30)) # Days 29+30\n"
" | (?:\\d\\d\\d\\d-(?:0[13578]|10 |12)-31) # Day 31\n"
" | (?:\\d\\d[2468][048]|\\d\\d0[48]|\\d\\d[13579][26])-02-29 # leap years not divisible by 100\n"
" | (?:[02468][048]00|[13579][26]00)-02-29 # leap years divisible by 400\n"
" )\n"
" T\n"
" (?:(?:0[0-9]|1[0-9]|2[0-3]):(?:[0-5][0-9]):(?:[0-5][0-9])) # time part\n"
" (?:\\.\\d\\d\\d)? # ms part (optional)\n"
" (?:Z|[\\+\\-](?:0[0-9]|1[012]):00|\\+0[34569]:30|\\+10:30|-0[39]:30|\\+1[34]:00|\\+0[58]:45|\\+12:45)\n"
" $)\n"
" |^(?:1972 |198[1235]|199[2347]|2012|2015 )-06-30T23:59:60Z$ # all june leapsecs\n"
" |^(?:197[2-9]|1987|1989|199[058] |2005|2008|2016)-12-31T23:59:60Z$ # all december leapsecs\n"
")\n"
"(?!.*-00:00$) # if given a -00:00 offset reject unconditionally, psychhhh\n"
"# OK! Since only valid times are now possible, we can use a loose pattern match to parse.\n"
"^(\\d\\d\\d\\d)-(\\d\\d)-(\\d\\d)T(\\d\\d):(\\d\\d):(\\d\\d)(?:\\.(\\d\\d\\d))?((Z)|([\\+\\-])(\\d\\d):(\\d\\d))$\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