def extract_features(filename): # Assuming filename format: "FTVGirls.22.07.19.Lola.Sinn.Hot.Busty.Summer.XX..." components = filename.split('.') features = { "series": components[0], "date": datetime.strptime('.'.join(components[1:3]), '%d.%m.%y').date() if len(components) > 2 else None, "model": ' '.join(components[3:-1]), # Simple join, might need more sophisticated handling "description": ' '.join(components[3:-1]), # This could potentially be improved "tags": [c.lower() for c in ' '.join(components[3:-1]).split() if c.lower() in ["hot", "busty", "summer"]], # Basic tagging } return features
filename = "FTVGirls.22.07.19.Lola.Sinn.Hot.Busty.Summer.XX..." features = extract_features(filename) FTVGirls.22.07.19.Lola.Sinn.Hot.Busty.Summer.XX...
import re from datetime import datetime