# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(([A-Za-z]{3}\s[0-9]{1,2})\s?([0-9]{2}:[0-9]{2})?\s?-?\s?([0-9]{2}:[0-9]{2})?\s?([A-Z0-9]{3,4})?\s?)"
test_str = ("Sun 16\n"
"08:00 -\n"
"16:00\n"
"RTW\n"
"Mon 17\n"
"08:00 - 16:00\n"
"RTW\n"
"Tue 18\n"
"08:00 -\n"
"16:00\n"
"RTW\n"
"Wed 19\n"
"08:00 -\n"
"16:00\n"
"RTW\n"
"Thu 20\n"
"08:00 - 16:00\n"
"RTW\n"
"Fri 21\n"
"08:00 - 16:00\n"
"RTW\n"
"Sat 22\n"
"OFF\n"
"Sun 23\n"
"OFF\n"
"Mon 24\n"
"OFF\n"
"Tue 25\n"
"04:40 -\n"
"13:07\n"
"5180\n"
"KM+\n"
"Wed\n"
"26\n"
"04:11\n"
"-\n"
"12:22\n"
"5178\n"
"Thu 27\n"
"10:00 - 18:00\n"
"Work.Group\n"
"Scheduling &\n"
"Rostering 1300-\n"
"1500 @Burwood...\n"
"Fri 28\n"
"OFF\n"
"Sat 29\n"
"NTA")
matches = re.finditer(regex, test_str, re.MULTILINE)
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