Building a Starting XI With All Players With the Same Name

import requests
from bs4 import BeautifulSoup
import time
from tqdm import tqdm
import pandas as pd

r = requests.get("https://fbref.com/en/players/")
soup = BeautifulSoup(r.content, "lxml")
letter_links = soup.select("ul.page_index a")

players_data = []
for link in tqdm(letter_links, desc="Getting letter pages..."):
    time.sleep(2.5) ##make sure we are being polite and following the rate limit
    r = requests.get("https://fbref.com"+link['href'])
    soup = BeautifulSoup(r.content, 'lxml')

    ptags = soup.select("div[id^='div_'].section_content p")
    for ptag in tqdm(ptags, desc="Collecting player information..."):
        try:
            player_dict = {}
            player_dict['link'] = ptag.select_one("a")['href']
            player_dict['player_name'] = ptag.select_one("a").text
            player_dict["other_details"] = ptag.getText().split("·")[1:]
            players_data.append(player_dict)
        except error as e:
            print(e)

df = pd.DataFrame(players_data)
df = pd.to_csv("players_data.csv" index=False)

import pandas as pd; pd.set_option('display.max_columns', None)
import numpy as np

df = pd.read_csv("players_data.csv")
df.head()

"""
|    | link                                 | player_name     | other_details                                                     |
|---:|:-------------------------------------|:----------------|:------------------------------------------------------------------|
|  0 | /en/players/9c60f681/Ahmad-Aadi      | Ahmad A'adi     | ['2014-2022', 'GK', 'Kuwait']                                     |
|  1 | /en/players/ad713dff/Jamal-Aabbou    | Jamal Aabbou    | ['2018-2022', 'FW', 'R.E. Virton, Lommel SK, Lierse Kempenzonen'] |
|  2 | /en/players/c2e5d028/Zakariya-Aabbou | Zakariya Aabbou | ['2021-2022', 'FW', 'RC Vichy']                                   |
|  3 | /en/players/c48b5529/Kim-Aabech      | Kim Aabech      | ['2007-2017', 'MF', 'Lyngby, Aarhus, Horsens, Nordsjælland']      |
|  4 | /en/players/d7ed844d/Kamilla-Aabel   | Kamilla Aabel   | ['2018-2021', 'DF', 'Røa, Arna-Bjørnar']                          |
"""

df.shape 

"""
(169623, 3)
"""

def clean_data(data):
    """
    """
    if data.strip()[0] == "[" and data.strip()[-1] == "]":
        data = eval(data) 
        data = [value.strip() for value in data]
        
        if len(data) == 4:
            a,b,c,d = data
            return [a,b,c+d]

        elif len(data) == 3: ## all three values in list
            return data

        elif len(data) == 2: ##when two values in list
            a,b = data
            if a.startswith("20") or a.startswith("19"):
                if b in ["MF", "DF", "GK", "FW"]:
                    return [a, b, np.nan]
                else:
                    return [a, np.nan, b]
            elif a in ["MF", "DF", "GK", "FW"]:
                return [np.nan, a, b]
            else:
                return [np.nan, np.nan, np.nan]

        elif len(data) == 1: ##case where only 1 value in list
            a, = data
            if a.startswith("20") or a.startswith("19"):
                return [a, np.nan, np.nan]
            elif a in ["MF", "DF", "GK", "FW"]:
                return [np.nan, a, np.nan] 
            else:
                return [np.nan, np.nan, a]
            
        elif len(data) == 0:
            return [np.nan, np.nan, np.nan]

    else:
        return [np.nan, np.nan, np.nan]
        
        
def get_first_name(x):
    try:
        return x.split(" ", 1)[0]
    except:
        return np.nan
    
def get_last_name(x):
    try:
        return x.split(" ", 1)[1]
    except:
        return np.nan   
    
def get_years(years):
    if years is not np.nan:
        if "-" in years:
            return [int(years.split("-")[0]), int(years.split("-")[1])]
        else:
            return [np.nan, np.nan]
    else:
        return [np.nan, np.nan]

df['other_details'] = df["other_details"].apply(clean_data)
df[['years', 'position', 'squad_nation']] = pd.DataFrame(df['other_details'].tolist(), index=df.index)
df[['start_year', 'end_year']] = pd.DataFrame(df['years'].apply(get_years).tolist(), index=df.index)
df['playing_time'] = df['end_year'] - df['start_year'] 
df['first_name'] = df.player_name.apply(get_first_name)
df['last_name'] = df.player_name.apply(get_last_name)
df.head()

"""
|    | link                                 | player_name     | other_details                                                     | years     | position   | squad_nation                               |   start_year |   end_year |   playing_time | first_name   | last_name   |
|---:|:-------------------------------------|:----------------|:------------------------------------------------------------------|:----------|:-----------|:-------------------------------------------|-------------:|-----------:|---------------:|:-------------|:------------|
|  0 | /en/players/9c60f681/Ahmad-Aadi      | Ahmad A'adi     | ['2014-2022', 'GK', 'Kuwait']                                     | 2014-2022 | GK         | Kuwait                                     |         2014 |       2022 |              8 | Ahmad        | A'adi       |
|  1 | /en/players/ad713dff/Jamal-Aabbou    | Jamal Aabbou    | ['2018-2022', 'FW', 'R.E. Virton, Lommel SK, Lierse Kempenzonen'] | 2018-2022 | FW         | R.E. Virton, Lommel SK, Lierse Kempenzonen |         2018 |       2022 |              4 | Jamal        | Aabbou      |
|  2 | /en/players/c2e5d028/Zakariya-Aabbou | Zakariya Aabbou | ['2021-2022', 'FW', 'RC Vichy']                                   | 2021-2022 | FW         | RC Vichy                                   |         2021 |       2022 |              1 | Zakariya     | Aabbou      |
|  3 | /en/players/c48b5529/Kim-Aabech      | Kim Aabech      | ['2007-2017', 'MF', 'Lyngby, Aarhus, Horsens, Nordsjælland']      | 2007-2017 | MF         | Lyngby, Aarhus, Horsens, Nordsjælland      |         2007 |       2017 |             10 | Kim          | Aabech      |
|  4 | /en/players/d7ed844d/Kamilla-Aabel   | Kamilla Aabel   | ['2018-2021', 'DF', 'Røa, Arna-Bjørnar']                          | 2018-2021 | DF         | Røa, Arna-Bjørnar                          |         2018 |       2021 |              3 | Kamilla      | Aabel       |
"""

merged = df.first_name.value_counts().\
            reset_index().\
            rename(columns={"index":"name"}).\
            merge(df.last_name.\
                  value_counts().\
                  reset_index().\
                  rename(columns={"index":"name"}), 
                  on='name', how='outer').\
            fillna(0)
merged['total'] = merged['first_name'] + merged['last_name']
merged = merged.sort_values("total", ascending=False).reset_index(drop=True)
merged.head(35)

from mplsoccer.pitch import VerticalPitch
import matplotlib.pyplot as plt
from matplotlib.markers import MarkerStyle

plt.rcParams['font.family'] = ['sans-serif']
plt.rcParams['font.sans-serif'] = ['Calibri']

p = VerticalPitch('opta',pitch_color='grass', line_color='white', stripe=True)

fig, ax = p.draw(figsize=(8,12))
fig.set_facecolor('green')
ax.set_title(label=f"{player_name} XI",
            fontsize=35, x=0.04,
             y=0.98,
            ha='left',
            fontweight='bold')

xs = [15, 
     40, 30, 30, 40, 
     60, 45, 60, 
     70, 80, 70]
ys = [50, 
     90, 65, 35, 10, 
     65, 50, 35, 
     85, 50, 15]
names = [
    "David de Gea",
"David Raum", "David Alaba", "David Luiz", "Luke David Ayling",
"David Silva", "David Lopez", "David Beckham",
"David Neres", "Jonathan David", "David Brooks",]

ax.scatter(ys,xs, s=1000, color='xkcd:salmon', ec='k',lw=2, marker = MarkerStyle("o", fillstyle="top"))
ax.scatter(ys,xs, s=1000, color='dodgerblue', ec='k',lw=2, marker = MarkerStyle("o", fillstyle="bottom"))

[ax.text(y,x-4, name, va='center', ha='center', fontsize=18, fontweight='demibold') for x,y,name in zip(xs, ys, names)];