# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?i)^\S+\s+(\d{2})?(\d{2})\s*(?:[-_]|to)\s*(present|\S+)\s*(\d{2})?(\d{2})?$"
test_str = ("February 2016 - March 2019\n"
"September 2015 to August 2019\n"
"April 2015 to present\n"
"September 2018 - present\n"
"Feb. 2016 - March 2019\n"
"Sept 2015 to Aug. 2019\n"
"April 2015 to present\n"
"Nov. 2018 - present\n\n"
"Invalid string:\n"
"George Mason University august 2019\n\n"
"Stratusburg university February 2018\n\n"
"Some text and month followed by year")
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