import re def identify_document_id(data_list): keywords = ["Document ID", "Document Number", "Passport Number", "ID Number"] # Add other possible keywords for item in data_list: for keyword in keywords: if keyword in item: # Extract document ID based on format and length document_id = re.findall(r'\b[A-Za-z0-9]+\b', item) # Additional checks for format and length can be added here return document_id[0] if document_id else None return None # Test the function with the given data list data_list = ["Govermment of the People's Republic of Bangladesh", 'NationalIDCard', '12May 1975', 'HETH', 'Caaaat', 'Name', 'ROMANARAHMAN', 'Date of tn 12 May 1975', '8673674936'] document_id = identify_document_id(data_list) print(document_id)