# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?mi)
^
(?!
\h*
(?: [A-Z] \h* \. | ANSWER \h* : )
)
\h*
(?<question> \S .*? ) # (1)
\?? \h* \s* ^ \h* A \h* \. \h*
(?<A> .*? ) # (2)
\h*
\s*
(?:
^ \h* B \h* \. \h*
(?<B> .*? ) # (3)
\h*
(?:
\s* ^ \h* C \h* \. \h*
(?<C> .*? ) # (4)
\h*
(?:
\s* ^ \h* D \h* \. \h*
(?<D> .*? ) # (5)
\h*
(?:
\s* ^ \h* E \h* \. \h*
(?<E> .*? ) # (6)
\h*
)?
)?
)?
)?
\s* ^ \h* ANSWER \h* : \h*
(?<answer1> [A-F] ) # (7)
(?:
\h* , \h*
(?<answer2> [A-F] ) # (8)
)?
"""
test_str = ("Linux is\n"
"A. A Graphic Software\n"
"B. A Driver\n"
"C. A Line Controller Software\n"
"D. An Operating System\n"
"ANSWER: D\n"
"Which feature helps in compress and contain the collection of files in to one\n"
"A. Zip\n"
"B. Shortcut\n"
"C. Icon\n"
"D. Extract\n"
"ANSWER: A\n\n"
"What is php?\n\n"
"A. Php is a language.\n\n"
"B. Php creates HTML.\n\n"
"C. Php is fun.\n\n"
"D. none of these.\n\n"
"ANSWER: D\n\n\n\n"
"Which is YII-2?\n\n"
"A. Framework.\n\n"
"B. Tool.\n\n"
"C. None of these\n\n"
"ANSWER: A,B")
matches = re.finditer(regex, test_str, 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