import re
regex = re.compile(r"\b(?:((?:0?[1-9]|[12]\d|3[01])(?:\s*(?:st|[rn]d|th))?)\s*)?(Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|June?|July?|Aug(?:ust)?|Sep(?:t(?:ember)?)?|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?)\s*(\d{2}(?:\d{2})?)\s*[-—–]\s*(?:((?:0?[1-9]|[12]\d|3[01])(?:\s*(?:st|[rn]d|th))?)\s*)?(Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|June?|July?|Aug(?:ust)?|Sep(?:t(?:ember)?)?|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?)\s*(\d{2}(?:\d{2})?)(?!\d)", flags=re.MULTILINE | re.IGNORECASE)
test_str = ("July 2014 - 28th August 2014\n"
"Jan 2012 - 3rd sep 2014\n"
"Jan 2008 - May 2012\n"
"Jan 2008 and May 2012")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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