fork download
  1. import re
  2.  
  3. regex = r"\b([A-Z]+(?:[^\S\r\n]+[A-Z]+)*):[^\S\r\n]+([A-Z0-9].*?(?= [A-Z]|$))"
  4. test_str = "COMPANY NAME: Ruff name of company TYPE OF EVENT: Party NOTIFIED DATE: 1/27/20 COMPANY NAME: Company2/CPT TYPE OF EVENT: Fire NOTIFIED DATE: 1/31/20"
  5. matches = re.finditer(regex, test_str)
  6. items = [];
  7.  
  8. for matchNum, match in enumerate(matches, start=1):
  9. items.append(match.group(1))
  10. items.append(match.group(2))
  11.  
  12. print(items)
Success #stdin #stdout 0.02s 9508KB
stdin
Standard input is empty
stdout
['COMPANY NAME', 'Ruff name of company', 'TYPE OF EVENT', 'Party', 'NOTIFIED DATE', '1/27/20  ', 'COMPANY NAME', 'Company2/CPT', 'TYPE OF EVENT', 'Fire', 'NOTIFIED DATE', '1/31/20']