data_wrangling.py

import re

with open("company (2).txt") as file:
    com = file.read()
com_split = com.split("-------")
com_list = com_split[3].replace('--', '').split("\n")[1:-3]
a = [x.split('(') for x in com_list]
dict_prod = {}
for i in a:
    dict_prod[i[0]] = i[1].replace(')', '')
for i in dict_prod.keys():
    if 'million' in dict_prod[i]:
        dict_prod[i] = float(re.findall(r'\d+\.\d+|\d+', dict_prod[i])[0]) * 1000000
    elif 'thousand' in dict_prod[i]:
        dict_prod[i] = float(re.findall(r'\d+\.\d+|\d+', dict_prod[i])[0]) * 1000

sorted_dict = {k: v for k, v in sorted(dict_prod.items(), key=lambda item: item[1], reverse=True)}
for count, product in enumerate(sorted_dict):
    count += 1
    if count <= 5:
        print(f"{count}. {product}")