# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((?<start_date>\d{4}).*?)?(?<end_date>\d{4}|(?<=-)\d{2})?$"
test_str = ("May 30, 1949, published 1979\n"
"May 30, 1949 and 1951, published 1979\n"
"May 30, 1949, printed 1980\n"
"May 30, 1949, print executed 1988\n"
"May 30, 1949, prints executed 1988\n"
"published 1940\n"
"August or September 1908\n"
"May 30, 1949\n"
"May 30, 1949, printed\n"
"1920\n"
"1920-21")
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