# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|Jun(?:e)?|Jul(?:y)?|Aug(?:ust)?|Sep(?:tember)?|Oct(?:ober)?|(Nov|Dec)(?:ember)?)(\s)([1,2][\d]|[1-9]|30|31)(\s))?(\b[\d]|10|11|12):[0-5][0-9]\s(AM|PM)"
test_str = ("March 9 12:31 AM and March 10 7:30 AM\n"
"March 11 7:30 AM and March 12 10:30 AM\n"
"Mar 31 9:00 PM and Apr 1 12:39 AM\n"
"March 31 10:11 PM and April 1 5:23 AM\n"
"7:45 PM and 10:30 PM\n"
"May 3 4:41 PM PDT and May 4 12:19 AM PDT\n"
"March 31 10:71 PM and April 1 5:23 AM\n"
"27:45 PM and 10:80 PM\n"
"May 3 4:41 PM PDT and May 41 12:19 AM PDT")
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