import re
regex = r"\b ([A-Z]+(?:[^\S \r \n ]+[A-Z]+)*):[^\S \r \n ]+([A-Z0-9].*?(?= [A-Z]|$))"
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"
matches = re .finditer ( regex, test_str)
items = [ ] ;
for matchNum, match in enumerate ( matches, start= 1 ) :
items.append ( match.group ( 1 ) )
items.append ( match.group ( 2 ) )
print ( items)
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
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']