# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:start:(?=\w+(?:-\w+){2,9}:end)|(?<=-)\G)(\w+)(?:-|:end)"
test_str = ("-Should-not-match\n"
"Some text here and start:test-test-lorem-ipsum-sir-doloret-etc-something:end another something start:SIR-doloret-something:endand this is a non-match: start:SOMmething-blabla:end because hasn't got enough groups.\n"
" \n"
"This also start:REST-doloret-etc-something:end but not this: start:XXYY-lorem-ipsum-sir-doloret-etc-something-8-nine-ten-eleven:end because i\n"
"t's too long. start:XXYY-lorem-ipsum-sir-doloret-etc-something-8-nine-ten:end just there, and also start:XXYY-lorem-ipsum:end-garbage\n\n"
"This shouldn-t match also start:nothing:end! start:nothing-next:end\n\n"
"Test start:Something-nine-ten-eleven:end-bla-blastart:REST-doloret-etc-something:end---")
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