# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=: ),?.*?(?=[A-Z]*?:\W|$)"
test_str = ("FREEZE: (1 of a liquid 3:4) be turned into ice or another solid as a result of extreme cold.\n"
"\"in the winter the milk froze\"\n"
"PULL: a force drawing someone or something, in a particular: direction or course of action; \n"
"WAY OF PATH: a road, track, path, or street for traveling along. \n"
"RADIO: communicate or send a message by radio!.\n"
"COUNTER TOP: (1:3) a flat surface for working on, especially in a kitchen:\n"
"and possible outdoor kitchen\n"
"PATIO: a paved outdoor area adjoining a house\n"
"SEA SPRAY: Sea spray are aerosol particles formed from the ocean, mostly by ejection into Earth's atmosphere by bursting bubbles at the air-sea interface: Sea spray contains both organic matter and inorganic salts that form sea salt aerosol\n\n")
matches = re.finditer(regex, test_str, re.DOTALL)
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