# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(Entre\ssemana|El\sfin\sde\ssemana)\s([A-Z][a-z]+?)\s([A-Z][a-z]+?)\s([A-Z][a-z]+?)\s([A-Z][a-z]+?)\sse\sacuesta\sa\slas\s([0-9]{2}\:[0-9]{2}\s)(am|pm)\sy\sse\slevanta\sa\slas\s([0-9]{2}\:[0-9]{2}\s)(am|pm).*$"
test_str = ("Entre semana Juan Miguel Rangel Moncada se acuesta a las 8 pm y se levanta a las 08 am.\n"
"Entre semana Jorge Enrique Canon Pinzon se acuesta a las 9 pm y se levanta a las 3 am.\n"
"El fin de semana Maria Lucia Espitia Lovera se acuesta a las 7 pm y se levanta a las 12 pm.\n"
"El fin de semana Yesid Alexander Munoz Lozano se acuesta a las 10 pm y se levanta a las 5 am.")
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