# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=^Total revenue for )(?=\d+[-_]?\d+)[\d_-]{6,7}(?!\S)"
test_str = ("Total revenue for 2016-03 is 3000 €\n"
"Total revenue for 2016_03 is 3000 €\n"
"Total revenue for 201603 is 3000 € \n\n"
"Total revenue for 2016-03 is 3000 €\n"
"Total revenue for 2016_03 is 3000 €\n"
"Total revenue for 201603 is 3000 €\n"
"Total revenue for 032016 is 3000 €\n"
"Total revenue for 03_2016 is 3000 €\n"
"Total revenue for 03-2016 is 3000 €\n"
"Total revenue for 3000 is 3000 €\n"
"Total revenue for 30-00100-1010101 is 3000 €\n")
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