import re subject = """10001-31021 Nagy Árpád 2015.12.30. 524432 10001-31121 Zagyva László Pál 2016.03.21. 765432 10012-34321 Acél Tibor 2016.02.20. 231231 10201-11021 Lakatos Pál 2016.01.10. 2310456 10210-41011 Nagy Árpád 2016.02.03. 323532""" lines = subject.split("\n") results_list = [] for line in lines: p = re.search(r"^([\d-]+)\s+([A-zÀ-ÿ\s]+)\s+([\d.]+)\s+([\d]+)", line) if p: results_list.append([p.group(1), p.group(2), p.group(3), p.group(4)]) print results_list
Standard input is empty
[['10001-31021', 'Nagy \xc3\x81rp\xc3\xa1d', '2015.12.30.', '524432'], ['10001-31121', 'Zagyva L\xc3\xa1szl\xc3\xb3 P\xc3\xa1l', '2016.03.21.', '765432'], ['10012-34321', 'Ac\xc3\xa9l Tibor', '2016.02.20.', '231231'], ['10201-11021', 'Lakatos P\xc3\xa1l', '2016.01.10.', '2310456'], ['10210-41011', 'Nagy \xc3\x81rp\xc3\xa1d', '2016.02.03.', '323532']]