# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(0?[1-9]|[12]\d|3[01])[\/\-.](0?[1-9]|[12]\d|3[01])[\/\-.](\d{2}|\d{4})\b"
test_str = ("Bắt các chuỗi ngày tháng này\n"
"12/01/2017\n"
"15/2/2017\n"
"3/03/2018\n"
"12/24/2018\n"
"1.1.2018\n"
"7-9-18\n"
"1.31.2018\n\n\n"
"Không bắt các chuỗi như thế này, vì không đúng ngày tháng\n"
"123/2/1234 13/ab/3346 12/223/12 60/60/2018 32/12/2018\n")
matches = re.finditer(regex, test_str)
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