fork(1) download
  1. import re
  2.  
  3. txt = '''293 PACKAGE(S)x000D PRINTED HEAD ITEM: KA02033-E844 A5 :INVOICE: FIT-2401-01 HS CODE: 84732:100 KNITTED FABRIC H.S CODE: 6006.2:2.00 INV#: TSTEX0124-009 (TC-240021:) WOVEN TWILL CAP HS.CODE: 6505.00:.90 KNITTED FABRIC HS 600410 FABRIC: P57101 (T989, 100% POLYESTER, WIDT:H 152CM) HS CODE : 54075200_x000D_ (*)EMA:IL:IMPORT-SHA@ZHL.CN USCI:913101141:32276439L (**)USCI:
  4.  
  5. Container DRYU9124108: 13 PACKAGE(S), AUTOMATIC TOOTH TURNING MACHINESD-CYJ500-1000 HS CODE:84597010; '''
  6. print(re.findall(r'(\S.*?)\s+H\.?S\b\.?(?:\s*CODE)?\s*:?\s*\S+', txt))
Success #stdin #stdout 0.04s 9672KB
stdin
Standard input is empty
stdout
['293 PACKAGE(S)x000D PRINTED HEAD ITEM: KA02033-E844 A5 :INVOICE: FIT-2401-01', 'KNITTED FABRIC', 'INV#: TSTEX0124-009 (TC-240021:) WOVEN TWILL CAP', 'KNITTED FABRIC', 'FABRIC: P57101 (T989, 100% POLYESTER, WIDT:H 152CM)', 'Container DRYU9124108: 13 PACKAGE(S), AUTOMATIC TOOTH TURNING MACHINESD-CYJ500-1000']