import re
regex = re.compile(r"^.*?([A-Z]{2,}(?: [A-Z-]+){1,5})", flags=re.MULTILINE)
test_str = ("성 벼 | 5 번YAO LIAO거 CHINA P R체류자격 결혼이민F-1)말급일자', # 'YAO LIAO'\n"
"성 별 F 등록번호명 JAO HALJUNGCHINA P R격 결혼이민(F-6)밥급인자', # 'JAO HALJUNG'\n"
"성 별 F명 CHENG HAIJING국 가 CHINA P R 역체 가차격 결혼이민(C-4) 박급인자', # 'CHENG HAIJING'\n"
"KOa MDOVUD TAREEQ SAID HAFIZULLAH TURKIYE움첫;자격 거주(F-2)발급일자', # 'DOVUD TAREEQ SAID HAFIZULLAH'\n"
"KOn 별 MDOVUD TAREEQ SAID- IIAFIZULLAH 감 TURKIYE동체나자격 거주F-2) 발급일자', # 'DOVUD TAREEQ SAID- IIAFIZULLAH' \n"
"등록번호IN\" 성 별 M명 TAREEQ SAD IIAFIZULLAH 값 TURKIYE8체주자격 거주-2)발급일자' # 'TAREEQ SAD IIAFIZULLAH'\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