import re
regex = re.compile(r"(?:(Type: )(?<type>\w+)) *(?:(Year: )(?<year>\d{4})) *(?:(Title: )(?<title>[^ISBN]*))(?:(ISBN:) *(?<ISBN>\d*))* *(?:(Pages: )(?<pages>\d*))* *(?:(Authors: )(?<author1>(?:(?:(?!Length: )[\w ,])*) *)) *;* *(?<author2>(?:(?:(?!Length: )[\w ,])*) *)(?:(Length: )(?<length>\d*))* *(?:Media Type: )*(?<discType>[\w ,]*)", flags=re.MULTILINE)
test_str = ("Type: eBook Year: 1990 Title: This is ebook 1 ISBN:15465452 Pages: 100 Authors: Cendric, Paul\n"
"Type: Movie Year: 2016 Title: This is movie 1 Authors: Pepe Giron ; Yamasaki Suzuki Length: 4500 Media Type: DVD\n"
"Type: Movie Year: 2016 Title: This is movie 1 Authors: Pepe Giron Length: 4500 Media Type: DVD")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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