import re
regex = re.compile(r"(?<=gene=).+?(?=\])", flags=re.MULTILINE)
test_str = (">lcl|NC_001802.1_cds_NP_057851.1_3 [gene=vif] [locus_tag=HIV1gp3] [db_xref=GeneID:155459] [protein=Vif] [protein_id=NP_057851.1] [location=4587..5165] [gbkey=CDS]\n")
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