Data Collection Overview

{year}/
├── events.json                 # Season calendar
├── {race-name}/
│   ├── event_info.json        # Race details
│   ├── results.json           # Race results
│   ├── quali_results.json     # Qualifying results
│   ├── driverPoints.json      # Driver standings after this race
│   ├── teamPoints.json        # Constructor standings after this race
│   ├── laptimes.json          # Lap-by-lap timing (1996+)
│   ├── pitstops.json          # Pit stop data (2011+)
│   └── sprint_results.json    # Sprint race results (select races)

BASE_URL = "https://api.jolpi.ca/ergast/f1"

RATE_LIMIT_BURST = 4  # requests per second
REQUEST_DELAY = 1 / RATE_LIMIT_BURST  # 0.25 seconds between requests

def fetch_with_rate_limit(url):
    time.sleep(REQUEST_DELAY)
    response = requests.get(url)
    
    if response.status_code == 429:
        time.sleep(60)  # Wait and retry
        return fetch_with_rate_limit(url)
    
    return response.json()

class Fetcher:
    def __init__(self):
        self.burst_limit = 4
        self.last_request_time = 0
    
    def make_request(self, url):
        current_time = time.time()
        time_since_last = current_time - self.last_request_time
        
        if time_since_last < (1 / self.burst_limit):
            sleep_time = (1 / self.burst_limit) - time_since_last
            time.sleep(sleep_time)
        
        response = requests.get(url)
        self.last_request_time = time.time()
        return response.json()

def slugify(race_name):
    return race_name.lower().replace(" ", "-")

def get_race_folder_name(race):
    return race["raceName"].lower().replace(" ", "-")

def create_directory(path):
    if not os.path.exists(path):
        os.makedirs(path)

import logging

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
    handlers=[
        logging.FileHandler("script_name.log"),
        logging.StreamHandler()
    ]
)

logger = logging.getLogger(__name__)