import sys # '19xx' literally would be accepted as well but we won't tell anyone def solve(lines): def detect_date(s): date_f = "19XX r." date_l = len(date_f) j = 0 for i in range(len(s)): c = s[i] if j == date_l: return True elif c == date_f[j] \ or (j in (2, 3) and c.isdigit()): j += 1 continue j = 0 return False return filter(detect_date, lines) if __name__ == "__main__": lines = [] fp = sys.argv[1] with open(fp, encoding="utf-8") as f: # following symlinks might not work on Windows lines = f.readlines() sol = solve(lines) with open("./polish_wiki_excerpt.out", 'w', encoding="utf-8") as f: f.writelines(sol)