# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
\b
(?=
(?<result>
(?<consume>
(?> \w+ \h+ ){0,3}?
keyword \b
)
(?: \h+ (?! keyword \b ) \w+ ){0,3}
)
) \g{consume}
"""
test_str = ("word1 word2 word3 keyword word4 word5 word6 keyword word7 word8 word9 word10\n"
"word2 keyword word4 word5 word6 keyword word7 word8\n"
"word2 word3 keyword word4 word5 word6 keyword word7 keyword word10")
matches = re.finditer(regex, test_str, re.UNICODE | re.VERBOSE)
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