etl process - XML extract Function
def extract_from_xml(file_to_process):
dataframe = pd.DataFrame(columns=['car_model','year_of_manufacture','price', 'fuel'])
tree = ET.parse(file_to_process)
root = tree.getroot()
for person in root:
car_model = person.find("car_model").text
year_of_manufacture = int(person.find("year_of_manufacture").text)
price = float(person.find("price").text)
fuel = person.find("fuel").text
dataframe = dataframe.append({"car_model":car_model, "year_of_manufacture":year_of_manufacture, "price":price, "fuel":fuel}, ignore_index=True)
return dataframe