# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=\bdigit-| |[\s>]|^)(\d{4})(?=[.?\s<]|-digit\b| |$)"
test_str = ">1234 Lorem ipsum 3400-digit, sit amet 5000 consectetur adipisicing elit. Natus, explicabo 6700? Itaque iure ipsum laboriosam, ex nemo delectus iste quia cupiditate digit-9134? Iste nam digit-2456 at voluptate est 8456-digit? At excepturi quis voluptatibus 7500. 1235<"
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