nprasad2077/nbaStats
1
0 Fork 0
mirror of https://github.com/nprasad2077/nbaStats.git synced 2026-11-09 03:20:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

scraped until 2016

Browse Source
This commit is contained in:
nprasad2077 committed 2023-05-10 01:23:50 -05:00
1 parent cad7e179c3
commit 1c54ed2627
1 file changed
+63 -52
Download Patch File Download Diff File Expand all files Collapse all files
nba_data/nba_scraper_shot_chart.py
+63 -52
View File
@@ -13,15 +13,17 @@ django.setup()
from nba_data.models import PlayerShotChartData from nba_data.models import PlayerShotChartData
player_name = 'LeBron James' player_name = 'LeBron James'
season = 2022 season = 2016
# team = 'LAL' # You might want to find a way to get this from the webpage # team = 'LAL' # You might want to find a way to get this from the webpage
url = 'https://www.basketball-reference.com/players/j/jamesle01/shooting/' + str(season) url = 'https://www.basketball-reference.com/players/j/jamesle01/shooting/' + \
str(season)
response = requests.get(url) response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser") soup = BeautifulSoup(response.text, "html.parser")
# Find the comment containing the shot chart # Find the comment containing the shot chart
comment = soup.find(string=lambda text: isinstance(text, Comment) and "div_shot-chart" in text) comment = soup.find(string=lambda text: isinstance(
text, Comment) and "div_shot-chart" in text)
shot_chart_soup = BeautifulSoup(comment, "html.parser") shot_chart_soup = BeautifulSoup(comment, "html.parser")
# Now you can find the shot chart in the parsed comment # Now you can find the shot chart in the parsed comment
@@ -33,70 +35,79 @@ shots = shot_chart.find_all("div", {"class": ["tooltip make", "tooltip miss"]})
shot_chart_data = [] shot_chart_data = []
for shot_div in shots: for shot_div in shots:
# Parse shot data try:
style_values = shot_div['style'].split(';') # Parse shot data
top_value = int(style_values[0].split(':')[1].replace('px', '').strip()) style_values = shot_div['style'].split(';')
left_value = int(style_values[1].split(':')[1].replace('px', '').strip()) top_value = int(style_values[0].split(
':')[1].replace('px', '').strip())
left_value = int(style_values[1].split(
':')[1].replace('px', '').strip())
# Parse tip attribute # Parse tip attribute
tip_parts = shot_div['tip'].split('<br>') tip_parts = shot_div['tip'].split('<br>')
# Within your loop: # Within your loop:
date_and_opponent = re.split(' at | vs ', tip_parts[0]) date_and_opponent = re.split(' at | vs ', tip_parts[0])
date = date_and_opponent[0].strip().split(',')[0] + ',' + date_and_opponent[0].strip().split(',')[1] date = date_and_opponent[0].strip().split(
team = date_and_opponent[0].strip().split(',')[2].strip() ',')[0] + ',' + date_and_opponent[0].strip().split(',')[1]
opponent = date_and_opponent[1].strip() team = date_and_opponent[0].strip().split(',')[2].strip()
opponent = date_and_opponent[1].strip()
quarter_and_time = tip_parts[1].split(',') quarter_and_time = tip_parts[1].split(',')
quarter = quarter_and_time[0].strip() quarter = quarter_and_time[0].strip()
time_remaining = quarter_and_time[1].strip().split(' ')[0] time_remaining = quarter_and_time[1].strip().split(' ')[0]
result_and_type_and_distance = tip_parts[2].split(' ') result_and_type_and_distance = tip_parts[2].split(' ')
result = result_and_type_and_distance[0].strip() == 'Made' result = result_and_type_and_distance[0].strip() == 'Made'
shot_type = int(result_and_type_and_distance[1][0]) shot_type = int(result_and_type_and_distance[1][0])
distance_ft = int(result_and_type_and_distance[-2].strip()) distance_ft = int(result_and_type_and_distance[-2].strip())
team_score_and_opponent_score = tip_parts[3].split(' ')[-1].split('-') team_score_and_opponent_score = tip_parts[3].split(' ')[-1].split('-')
team_score = int(team_score_and_opponent_score[0].strip()) team_score = int(team_score_and_opponent_score[0].strip())
opponent_score = int(team_score_and_opponent_score[1].strip()) opponent_score = int(team_score_and_opponent_score[1].strip())
lead = team_score > opponent_score lead = team_score > opponent_score
shot_chart_row = { shot_chart_row = {
'player_name': player_name, 'player_name': player_name,
'top': top_value, 'top': top_value,
'left': left_value, 'left': left_value,
'date': date, 'date': date,
'qtr': quarter, 'qtr': quarter,
'time_remaining': time_remaining, 'time_remaining': time_remaining,
'result': result, 'result': result,
'shot_type': shot_type, 'shot_type': shot_type,
'distance_ft': distance_ft, 'distance_ft': distance_ft,
'lead': lead, 'lead': lead,
'lebron_team_score': team_score, 'lebron_team_score': team_score,
'opponent_team_score': opponent_score, 'opponent_team_score': opponent_score,
'opponent': opponent, 'opponent': opponent,
'team': team, 'team': team,
'season': season 'season': season
} }
shot_chart_data.append(shot_chart_row) shot_chart_data.append(shot_chart_row)
except Exception as e:
print(f"Error processing shot_div: {shot_div}")
print(f"Exception: {e}")
# shot_chart_entry = PlayerShotChartData(**shot_chart_row)
# shot_chart_entry.save()
# save as CSV file # save as CSV file
script_dir = os.path.dirname(os.path.abspath(__file__)) script_dir = os.path.dirname(os.path.abspath(__file__))
csv_output_path = os.path.join(script_dir, '..', 'data', f'{player_name}_{season}_shot_chart_output.csv') csv_output_path = os.path.join(
script_dir, '..', 'data', f'{player_name}_{season}_shot_chart_output.csv')
with open(csv_output_path, "w", newline="") as csvfile: with open(csv_output_path, "w", newline="") as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=shot_chart_data[0].keys()) writer = csv.DictWriter(csvfile, fieldnames=shot_chart_data[0].keys())
writer.writeheader() writer.writeheader()
for row in shot_chart_data: for row in shot_chart_data:
writer.writerow(row) writer.writerow(row)
# Save the records in the database # Save the records in the database
PlayerShotChartData.objects.bulk_create( try:
PlayerShotChartData(**row) for row in shot_chart_data PlayerShotChartData.objects.bulk_create(
) PlayerShotChartData(**row) for row in shot_chart_data
)
except Exception as e:
print(f"Error inserting data into database: {e}")
print('success')
print('success')