API节流是如何实现的？

import time
from threading import Lock

class TokenBucket:
    def __init__(self, capacity, refill_rate):
        self.capacity = capacity
        self.tokens = capacity
        self.refill_rate = refill_rate
        self.last_refill_time = time.time()
        self.lock = Lock()

    def refill(self):
        now = time.time()
        tokens_to_add = (now - self.last_refill_time) * self.refill_rate
        self.tokens = min(self.capacity, self.tokens + tokens_to_add)
        self.last_refill_time = now

    def consume(self, tokens=1):
        with self.lock:
            self.refill()
            if self.tokens >= tokens:
                self.tokens -= tokens
                return True
            return False

# 示例使用
bucket = TokenBucket(capacity=10, refill_rate=1)

def handle_request():
    if bucket.consume():
        print("Request processed")
    else:
        print("Rate limit exceeded")

# 模拟请求
for _ in range(15):
    handle_request()
    time.sleep(0.5)