# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"[-\[,:.\/]?\b(?:1\d{3}|200[0123]|\d0)(?:'?s)?\b[-\],:.\/]?"
test_str = ("I need it to catch a date between 1000 and 2003 in these forms:\n"
"1975\n"
"1970s\n"
"1970's\n"
"1970S\n"
"1970'S\n"
"70s\n"
"70's\n"
"70S\n"
"70'S\n\n"
"I also need it to catch certain characters on either side of the date, including\n"
"dashes\n"
"-1973-\n"
"brackets\n"
"[1973]\n"
"commas\n"
",1973,\n"
"colons\n"
":1973:\n"
"periods\n"
".1973.\n"
"slashes\n"
"/1973/\n\n"
" - some on both sides, some on only one.\n"
"/1973\n"
"or\n"
"1973/\n\n"
"My problem is that the expression is catching other characers on either side of the date as well - +1975 gets through, for instance, as does 1970s& - letters and numbers on either side do not get through, however. I'm confused.\n\n"
"I think I might need some sort of limit on either side before I can state the exceptions, I'm not sure what that would look like - some kind of look back? Any help would be appreciated.")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE)
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