# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:(?:Sun|Mon|Tue|Wed|Thu|Fri|Sat),)?\s*([0-9]{2})(?:\s+|-)([Jj][Aa][Nn]|[Ff][Ee][Bb]|[Mm][Aa][Rr]|[Aa][Pp][Rr]|[Mm][Aa][Yy]|[Jj][Uu][Nn]|[Jj][Uu][Ll]|[Aa][Uu][Gg]|[Ss][Ee][Pp]|[Oo][Cc][Tt]|[Nn][Oo][Vv]|[Dd][Ee][Cc])(?:\s+|-)([0-9][0-9]([0-9][0-9])?)\s+(?:([01][0-9]|[2][0-3])):([0-5][0-9]):([0-5][0-9])\s*(?:GMT)?"
test_str = ("Wed, 23-May-12 01:23:31 GMT \n"
"23-May-12 01:23:31 GMT \n"
"23-May-12 01:23:31 \n"
"23 May 2012 01:23:31 GMT \n"
"23 May 2012 01:23:31 GMT\n"
"Wed, 23 May 2012 01:23:31 GMT\n"
"23 mAy 2012 01:23:31 GMT\n"
"23 maY 12 01:23:31\n"
"23 jan 12 22:23:31\n"
"01 AUG 12 15:23:31 GMT\n\n"
"01 bla 12 15:23:31 GMT\n"
"1 May 2012 15:23:31 GMT\n"
"01 May 2012 15:23:31 BLA\n"
"01 May 2012-15:23:31\n"
"01 May 2012-15/23:31\n"
"01 May 2012-15/23:31")
matches = re.finditer(regex, test_str)
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