start_list.py

#!/usr/bin/env python

import sys
import bs4 as bs
import urllib.request
import pandas as pd
import seaborn as sns

splats = ['buggy', 'wissler', 'cook, jamie', 'gossow']
hamilton_abbr = ['hamilton', 'hwcc']
lifecycle_abbr = ['lifecycle']
uq_abbr = ['university', 'uq']
bne_abbr = ['bne', 'brisbane']
sccc_abbr = ['sunshine']
mbcc_abbr = ['moreton']
def guess_team(row):
    if "splat" in row.club.lower() or any([x in row.rider.lower() for x in splats]):
        return "Splatties"
    if "watt bomb" in row.club.lower():
        return "WattBomb"
    if "wolf" in row.club.lower():
        return "Wolf Racing"
    if "futuro" in row.club.lower():
        return "Futuro Racing"
    if "argenic" in row.club.lower():
        return "Argenic Racing"
    if "taylor" in row.club.lower():
        return "Taylor Cycles Racing"
    if "rats" in row.club.lower():
        return "RATS Racing"
    if "initiative" in row.club.lower():
        return "Women's Cycling Development Initiative"
    if "solaris" in row.club.lower():
        return "Solaris Racing"
    
    if any([x in row.club.lower() for x in mbcc_abbr]):
        return "MBCC"
    if any([x in row.club.lower() for x in hamilton_abbr]):
        return "Hamilton"
    if any([x in row.club.lower() for x in lifecycle_abbr]):
        return "Lifecycle"
    if any([x in row.club.lower() for x in uq_abbr]):
        return "UQCC"
    if any([x in row.club.lower() for x in bne_abbr]):
        return "BNECC"
    if any([x in row.club.lower() for x in sccc_abbr]):
        return "SunnyCoast"
    if any([x in row.club.lower() for x in ["Balmoral"]]):
        return "Balmoral"
    if any([x in row.club.lower() for x in ["Kangaroo"]]):
        return "KPCC"
    return "TheRest"


# url = "https://entryboss.cc/races/18894/startlist"
def get_riders(url):
    source = urllib.request.urlopen(url).read()
    soup = bs.BeautifulSoup(source,'lxml')

    table = soup.find_all('table')
    df = pd.read_html(str(table))[0]
    df.rename(columns={'Club/Team': 'club', 'Participant': 'rider'}, inplace=True)
    df['team'] = df.apply(guess_team, axis=1)

    return df

def plot_category(df, category):
    df_ = df[df.Category == category]
    num_riders = df_.shape[0]
    df_ = df_.groupby(['Category', 'team']).agg({'club': len})
    df_ = df_.groupby(['Category', 'team'], group_keys=False)
    df_ = df_.apply(lambda x: x.sort_values('club', ascending=False))

    sns.set(font_scale=1)
    ax = sns.catplot(df_, kind='bar', 
                x='team', y='club', col='Category', hue='team',
                height=6, aspect=2.0, errorbar=None, legend=False)

    ax.figure.subplots_adjust(top=1.0); 
    ax.figure.suptitle(f"Category {category} - {num_riders} riders")


if __name__ == "__main__":
    df = get_riders(sys.argv[0])
    plot_category(df, 'B')
    plot_category(df, 'C')
    plot_category(df, 'D')