Getting stats for more players¶

# Read list of players
players_df = pd.read_excel('./output/player_stats.xlsx').drop(columns=['Unnamed: 0'])
players_df.head()

all_players = []
seasons = [
    ('M2_01 Wolf 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-wolf/1/1/{user}', './output/season_of_the_wolf_2020_extra.xlsx'),
    ('M2_02 Love 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-love/1/1/{user}', './output/season_of_love_2020_extra.xlsx'),
    ('M2_03 Bear 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-bear/1/1/{user}', './output/season_of_the_bear_2020_extra.xlsx'),
    ('M2_04 Elf 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-elf/1/1/{user}', './output/season_of_the_elf_2020_extra.xlsx'),
    ('M2_05 Viper 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-viper/1/1/{user}', './output/season_of_the_viper_2020_extra.xlsx'),
    ('M2_06 Magic 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-magic/1/1/{user}', './output/season_of_magic_2020_extra.xlsx'),
    ('M2_07 Griffin 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-griffin/1/1/{user}', './output/season_of_the_griffin_2020_extra.xlsx'),
    ('M2_08 Draconid 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-draconid/1/1/{user}', './output/season_of_the_draconid_2020_extra.xlsx'),
    ('M2_09 Dryad 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-dryad/1/1/{user}', './output/season_of_the_dryad_2020_extra.xlsx'),
    ('M2_10 Cat 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-cat/1/1/{user}', './output/season_of_the_cat_2020_extra.xlsx'),
    ('M2_11 Mahakam 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-mahakam/1/1/{user}', './output/season_of_the_mahakam_2020_extra.xlsx'),
    ('M2_12 Wild Hunt 2020', 'https://masters.playgwent.com/en/rankings/masters-2/season-of-the-wild-hunt/1/1/{user}', './output/season_of_the_wild_hunt_2020_extra.xlsx'),
    ('M3_01 Wolf 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-wolf/1/1/{user}', './output/season_of_the_wolf_2021_extra.xlsx'),
    ('M3_02 Love 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-love/1/1/{user}', './output/season_of_love_2021_extra.xlsx'),
    ('M3_03 Bear 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-bear/1/1/{user}', './output/season_of_the_bear_2021_extra.xlsx'),
    ('M3_04 Elf 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-elf/1/1/{user}', './output/season_of_the_elf_2021_extra.xlsx'),
    ('M3_05 Viper 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-viper/1/1/{user}', './output/season_of_the_viper_2021_extra.xlsx'),
    ('M3_06 Magic 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-magic/1/1/{user}', './output/season_of_magic_2021_extra.xlsx'),
    ('M3_07 Griffin 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-griffin/1/1/{user}', './output/season_of_griffin_2021_extra.xlsx'),
    ('M3_08 Draconid 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-draconid/1/1/{user}', './output/season_of_the_draconid_2021_extra.xlsx'),
    ('M3_09 Dryad 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-dryad/1/1/{user}', './output/season_of_the_dryad_2021_extra.xlsx'),
    ('M3_10 Cat 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-cat/1/1/{user}', './output/season_of_the_cat_2021_extra.xlsx'),
    ('M3_11 Mahakam 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-mahakam/1/1/{user}', './output/season_of_the_mahakam_2021_extra.xlsx'),
    ('M3_12 Wild Hunt 2021', 'https://masters.playgwent.com/en/rankings/masters-3/season-of-the-wild-hunt/1/1/{user}', './output/season_of_the_wild_hunt_2021_extra.xlsx'),
    ('M4_01 Wolf 2022', 'https://masters.playgwent.com/en/rankings/masters-4/season-of-the-wolf/1/1/{user}', './output/season_of_the_wolf_2022_extra.xlsx'),
    ('M4_02 Love 2022', 'https://masters.playgwent.com/en/rankings/masters-4/season-of-the-love/1/1/{user}', './output/season_of_love_2022_extra.xlsx'),

]

for season, url_template, output_path in seasons:
    if os.path.exists(output_path):
        print(f"{output_path} exists, loading file instead of downloading ...")
        df = pd.read_excel(output_path).drop(['Unnamed: 0'], axis=1)
        all_players = players_df[(players_df.season == season) & (players_df['rank'] <=500)].name.unique()
    else:
        output = []
        known_players = players_df[players_df.season == season].name.values
        unknown_players = [n for n in all_players if n not in known_players]
        
        for player in tqdm(unknown_players):       
            url = url_template.replace('{user}', str(player))
            try:
                r = requests.get(url)
                soup = BeautifulSoup(r.text, 'html.parser')
                rows = soup.find_all("div", {"class": "c-ranking__inner-frame-found"})
                for row in rows[:1]:
                    flag = row.find("i", {"class": "flag-icon"})["class"][1]
                    new_record = {
                        'rank': int(row.find("div", {"class": "td-number"}).text.strip()),
                        'name': row.find("div", {"class": "td-nick"}).text.strip(),
                        'country': flag.replace('flag-icon-', '').upper(),
                        'matches': int(row.find("div", {"class": "td-matches"}).text.strip().replace(' matches', '')),
                        'mmr': int(row.find("div", {"class": "td-mmr"}).text.strip().replace(',', '')),
                        'season': season
                    }
                    if 0 < new_record['matches']:
                        output.append(new_record)
            except:
                pass
            
        df = pd.DataFrame(output).drop_duplicates()
        df.to_excel(output_path)
        all_players = players_df[(players_df.season == season) & (players_df['rank'] <= 500)].name.unique()