fork download
  1. import re
  2. import pprint
  3.  
  4. pattern = r"^([A-Z0-9](?:[A-Z0-9 ]*[A-Z0-9])?\b)(?: \((a\.k\.a\.[^()]+(?:\sa\.k\.a\.[^()]+)*)\))?"
  5. textData = ("2ND COMPLEX OF NEURAL SCIENCES (a.k.a. ACADEMY OF NEURAL \n"
  6. "SCIENCES; a.k.a. CHE 2 CHAON KAHAK-WON; a.k.a. CHE 2 CHAYON KAHAK-WON;\n"
  7. "a.k.a. KUKPAN KAHAK-WON; a.k.a. NATIONAL DEFENSE ACADEMY; a.k.a.\n"
  8. "SANSRI; a.k.a. SECOND COMPLEX OF NEURAL SCIENCES; a.k.a. SECOND\n"
  9. "COMPLEX OF NEURAL SCIENCES RESEARCH INSTITUTE), Pyongyang, Korea,\n"
  10. "North; Secondary sanctions risk: North Korea Sanctions Regulations,\n"
  11. "sections 510.201 and 510.210; Transactions Prohibited For Persons\n"
  12. "Owned or Controlled By U.S. Financial Institutions: North Korea\n"
  13. "Sanctions Regulations section 510.214.\n\n"
  14. "LOSTIK VE HAVAIK HIZMETLARI LTD., No. 3/182 Antepe\n"
  15. "Bagdat Cad. Istasyon Yolu Sok., Istanbul 34840, Turkey; Additional\n"
  16. "Sanctions Information - Subject to Secondary Sanctions.\n"
  17. "[IFSR] (Linked To: MAHAN AIR).\n\n"
  18. "7 KARNES, Avenida Ciudad de Cali No. 15A-91, Local A06-07, Bogota,\n"
  19. "Colombia; Matricula Mercantil No 1978075 (Colombia).\n\n"
  20. "SWING OF TIR (a.k.a. 7TH OF TIR COMPLEX; a.k.a. 7TH OF TIR INDUSTRIAL\n"
  21. "COMPLEX; a.k.a. 7TH OF TIR INDUSTRIES; a.k.a. 7TH OF TIR INDUSTRIES\n"
  22. "OF ISFAHAN/ESFAHAN; a.k.a. MOJTAMAE SANATE HAFTOME TIR; a.k.a.\n"
  23. "SANAYE HAFTOME TIR; a.k.a. SEVENTH OF TIR), Mobarakeh Road Km 45,\n"
  24. "Isfahan, Iran; P.O. Box 81465-478, Isfahan, Iran; Additional\n"
  25. "Sanctions Information - Subject to Secondary Sanctions.")
  26.  
  27. d = {}
  28.  
  29. for t in re.findall(pattern, textData, re.M):
  30. parts = [p for p in re.split(r"(?:;\s)?a\.k\.a\.\s", t[1]) if p]
  31. parts.insert(0, (t[0]))
  32. d[t[0]] = parts
  33.  
  34. pprint.pprint(d)
  35.  
Success #stdin #stdout 0.02s 9536KB
stdin
Standard input is empty
stdout
{'2ND COMPLEX OF NEURAL SCIENCES': ['2ND COMPLEX OF NEURAL SCIENCES',
                                    'ACADEMY OF NEURAL \nSCIENCES',
                                    'CHE 2 CHAON KAHAK-WON',
                                    'CHE 2 CHAYON KAHAK-WON',
                                    'KUKPAN KAHAK-WON',
                                    'NATIONAL DEFENSE ACADEMY',
                                    'SANSRI',
                                    'SECOND COMPLEX OF NEURAL SCIENCES',
                                    'SECOND\n'
                                    'COMPLEX OF NEURAL SCIENCES RESEARCH '
                                    'INSTITUTE'],
 '7 KARNES': ['7 KARNES'],
 'LOSTIK VE HAVAIK HIZMETLARI LTD': ['LOSTIK VE HAVAIK HIZMETLARI LTD'],
 'SWING OF TIR': ['SWING OF TIR',
                  '7TH OF TIR COMPLEX',
                  '7TH OF TIR INDUSTRIAL\nCOMPLEX',
                  '7TH OF TIR INDUSTRIES',
                  '7TH OF TIR INDUSTRIES\nOF ISFAHAN/ESFAHAN',
                  'MOJTAMAE SANATE HAFTOME TIR',
                  'SANAYE HAFTOME TIR',
                  'SEVENTH OF TIR']}