# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?=\b(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec|\d{4}|\d{1,2}))\w*[\t\ \\\/\.\,\;\:\-\+\_]+(\d{1,2}|jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\w*[\t\ \\\/\.\,\;\:\-\+\_]+(\d{4}|\d{1,2})\w*\b"
test_str = (" january 23rd 2011\n"
"2004 / 03 / 12\n"
" 1/12/2014 16-12-04\n"
" feb 18 1970\n"
" 2014.2.24\n"
"12-12-12\n"
"2nd 12 2004\n\n"
"1st Feb 2008\n\n"
"2001-09-11\n"
"2001 Sep 11\n\n"
"sep-jan 2000\n\n\n\n"
"mar\n\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