import re
regex = re.compile(r"[^.]+_([^.]+\.[^.]+)", flags=re.MULTILINE)
test_str = ("\"1234_4534_41247612_2462184_2131_ABCDEF.GHI.xlsx\"\n"
"\"1234_4534__sfhaksj_DHJKhd_hJD_41247612_2462184_2131_PQRST.GHI.xlsx\"\n"
"\"12JSAF34_45aAF34__sfhaksj_DHJKhd_hJD_41247612_2f462184_2131_JKLMN.OPQ.xlsx\"\n"
"\"1234_4534__sfhaksj_DHJKhd_hJD_41FA247612_2462184_2131_WXY.TUV.xlsx\"")
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