# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(([(|\[](?P<series>[^)\]]*)[)|\]]))?((?P<author>.*[^\s][^\-])[\s]+-[\s]*)?(?P<title>[^(]*)([(|\[](?:[\s]*(?P<published>(([12][\d]{3,3})(?:(?!([^.\)\-a-zA-Z_]*(-+[^.\)a-zA-Z_]+)+)))))?)?[\s]*([,]?[\s]*(?P<publisher>[\s\w\s]*)[\s]*)?([,]?[\s]*(isbn:|isbn[-]?13:)?(?P<isbn>[0-9-]+))?[)|\]])?"
test_str = ("(1958, Open Road d34234234, 978-1-4532-1730-6).epub\n"
"(1958, Open Ro234ad , 9781-4532-o1730-6).epub\n"
"(1958, Open Rosd234ad ).epub\n"
"( 1958 ).epub\n"
"(1958).epub\n"
"( Open Road ).epub\n"
"(Open road , 9234-1-4532-17300-9-6).epub\n"
"(1234, 9234-1-4532-17300-9-6).epub\n"
"(91886).epub\n"
"(9186).epub\n"
"(1186).epub\n\n"
"title (1958, Open Road34234234, 978-1-4532-1730-6).epub\n"
"(asdf) author, a2 - title ioiuoi-uyoiu (1958, Open Ro234ad , 9781-4532-1730-6).epub\n"
"author, adf - title ioiuoi-uyoiu (1958, Open Rosd234ad ).epub\n"
"author, adf - title ioiuoi-uyoiu ( 1958 ).epub\n"
"author, adf - title ioiuoi-uyoiu (1958).epub\n"
"author, adf - title ioiuoi-uyoiu ( Open Road ).epub\n"
"(dddfasdfasdf) author666, a66df - title ioiuoi-uyoiu (Open road , 9234-1-4532-17300-9-6).epub\n"
"author, adf - title ioiuoi-uyoiu (1234, 9234-1-4532-17300-9-6).epub\n"
"author, adf - title ioiuoi-uyoiu (1234, 923416).epub\n"
"author, adf - title ioiuoi-uyoiu ( 91886-8).epub\n"
"author, adf - title ioiuoi-uyoiu ( 9186 ).epub\n"
"author, adf - title ioiuoi-uyoiu ( 1186 ).epub\n"
"(dddfasdfasdf) author666, a66df - title ioiuoi-uyoiu ( Open road , isbn:9234-1-4532-17300-9-6).epub\n"
"(dddfasdfasdf) author666, a66df - title ioiuoi-uyoiu ( Open road , isbn13:9234-1-4532-17300-9-6).epub\n"
"(dddfasdfasdf) author666, a66df - title ioiuoi-uyoiu ( Open road , isbn-13:9234-1-4532-17300-9-6).epub\n"
"(dddfasdfasdf) author666, a66df - title ioiuoi-uyoiu ( Open road , 9234-1-4532-17300-9-6).epub")
matches = re.finditer(regex, test_str, re.IGNORECASE | 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