Data Collection Architecture

source/
├── 2014/
│   ├── defense/
│   ├── player_shooting/
│   ├── tracking/
│   └── playoffs/
├── 2015/
...
├── 2025/
│   ├── defense/
│   ├── player_shooting/
│   └── tracking/

#!/bin/bash
# Convert Jupyter notebooks to Python scripts
jupyter nbconvert --to script *.ipynb

# Execute collection scripts in sequence
python player_shooting.py
python scrape_shooting.py
python misc.py
python player_level.py

python team_shooting.py
python update_lebron.py
python dribble.py
python underground.py
python hustle.py
python new_tracking.py
python dates.py
python make_index2.py
python salary2.py
python price.py

# Commit and push updates
git add --all
git commit -m 'Daily Update'
git push origin master

# Distribution script (copy.sh)
WEB_APP_DIR="../web_app/data"
DISCORD_DIR="../discord/data"

# Copy master files to both destinations
cp nba_salaries.csv $WEB_APP_DIR/
cp index_master.csv $WEB_APP_DIR/
cp hustle.csv $WEB_APP_DIR/
cp player_shooting.csv $WEB_APP_DIR/
# ... (50+ additional files)

# Regular season data collection
for year in range(2024, 2026):  # Collects 2024-25 season
    season = f"{year}-{str(year+1)[-2:]}"
    # Fetch and process data...

ps = False  # Regular season
ps = True   # Playoffs

try:
    response = requests.get(url, headers=headers)
    response.raise_for_status()
except requests.exceptions.RequestException as e:
    print(f"Error fetching {url}: {e}")
    continue  # Skip to next iteration