[Python] I wanted to get the number of playoff games of a list of 200 players from Basketball...

I want to get the number of playoff games played by a list of players. To do that I used Selenium and Beautiful Soup. The result is being saved in a csv file but the values for each of the player is coming as 0.

Code I tried:

# Load Excel
df = pd.read_excel("nba.xlsx", sheet_name="Sheet9")
players = df['Player'].str.replace("*", "", regex=False).str.strip()

# Selenium setup
chrome_options = Options()
chrome_options.add_argument("--headless")
chrome_options.add_argument("--disable-gpu")
driver = webdriver.Chrome(options=chrome_options)

def get_player_code(name):
name = name.lower().replace(".", "")
parts = name.split()
last = parts[-1].replace("’", "").replace("'", "")
first = parts[0].replace("’", "").replace("'", "")
code = (last[:5] if len(last) >= 5 else last).ljust(5, 'x')
code += (first[:2] if len(first) >= 2 else first).ljust(2, 'x')
return code + "01"

def get_playoff_games(player_name):
player_code = get_player_code(player_name)
url = f"https://www.basketball-reference.com/players/{player_code[0]}/{player_code}.html"
print(f"Fetching playoff games for {player_name} -> {url}")

try:
driver.get(url)
time.sleep(2)

# Use BeautifulSoup to parse the *commented* tables
soup = BeautifulSoup(driver.page_source, "html.parser")
comments = soup.find_all(string=lambda text: isinstance(text, Comment))

for comment in comments:
if "id=\"totals\"" in comment:
table_soup = BeautifulSoup(comment, "html.parser")
foot = table_soup.find("tfoot")
if foot:
tds = foot.find_all("td")
if len(tds) > 0:
return int(tds[0].text) # First TD is Games (G)
return 0
except Exception as e:
print(f"Error for {player_name}: {e}")
return 0

results = []
for player in players:
games = get_playoff_games(player)
results.append({"Player": player, "Playoff Games": games})

driver.quit()
final_df = pd.DataFrame(results)
final_df.to_csv("nba_playoff_games.csv", index=False)
print("Saved as nba_playoff_games.csv")

Continue reading...