import re
regex = re.compile(r"^(.*?)\/(?<mnemonic>.{2,8}?)_(?<isbn>\d{13})_(?<primaryId>bnd\d{0,3}?)_(?<secondaryId>all|0[1-9]|[1-9][1-9])(?:_r(?<revisionNumber>\d+))?\.(?<extension>indd|qxp|qxd)$", flags=re.MULTILINE)
test_str = ("Obam_9781524763138_bnd_all_r3 Folder/Links/Obam_9781524763138_bnd_all_r1.indd\n"
"Obam_9781524763138_bnd_all_r3 Folder/Links/Obam_9781524763138_bnd_01_r1.indd\n"
"Obam_9781524763138_bnd_all_r3 Folder/Links/Obam_9781524763138_bnd_11_r1.indd\n"
"Obam_9781524763138_bnd_all_r3 Folder/Links/Obam_9781524763138_bnd_111_r1.indd\n"
"Obam_9781524763138_bnd_all_r3 Folder/Links/Obam_9781524763138_bnd_00_r1.indd")
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