import glob
import requests
import re


def download_files():
    #This function creates two .dat files necessary for further calculations

    weather_source = requests.get('http://codekata.com/data/04/weather.dat')
    football_source = requests.get('http://codekata.com/data/04/football.dat')

    with open('weather.dat', 'wb') as f:
        f.write(weather_source.content)

    with open('football.dat', 'wb') as f:
        f.write(football_source.content)

def read_file(data):
    filenames = glob.glob('*.dat')

    for file in filenames:
        data = open(file)

        data_list = []
        for line in data:
            data_list += [line.split()]
    return data_list



def smallest_difference(column1, column2):
    data_list = read_file(data)

    cleaned_up_data = [[re.sub(r'[^\w]', '', elem) for elem in lst if elem] for lst in
                   data_list[1:]]
    separate_rows_data = [x for x in cleaned_up_data[1:] if x!=['']]
    values = [[int(x) for x in sublist if x.isdigit()] for sublist in separate_rows_data]
    column1_list = [x[column1] for x in values]
    column2_list = [x[column2] for x in values]
    subtraction_results = [x - y for x, y in zip(column1_list, column2_list)]
    #smallest_spread = subtraction_results.index(abs(min(subtraction_results)))
    print(subtraction_results)

    if data.startswith('weather'):
        day_with_smallest_temp_spread = subtraction_results.index(min(subtraction_results)) + 1
        print('Day with smallest temperature spread is day number', day_with_smallest_temp_spread)

    elif data.startswith('football'):

        team_names = [x[1] for x in separate_rows_data]
        teams_goals = {k:v for (k, v) in zip(team_names, subtraction_results)}
        lowest_goal_difference_team = min(teams_goals, key=lambda v: abs(teams_goals[v]))

        print('Team with smallest difference in "for" and "against" goals is', lowest_goal_difference_team)
        print(team_names)
data='weather.dat'
read_file(data)
smallest_difference(1, 2)