# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b[^.]+\([^()]+\b(\d{2}|\d{4})\s*\)[^.]*\."
test_str = ("Abc def ghi (foo 2015).\n\n"
"Trondheim is a small city with a university and 140000 inhabitants. Its central bus systems has 42 bus lines, serving 590 stations, with 1900 (departures per) day in average. T h a t gives approximately 60000 scheduled bus station passings per day, which is somehow represented in the route data base. The starting point is to automate the function (Garry Weber, 2005) of a route information agent.\n\n"
"Abc def ghi (foo 2015).\n\n"
"Abc def ghi (foo 201).")
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