chore: initialize lawyers crawler project

utils/rate_limiter.py

@@ -0,0 +1,76 @@
+"""
+全局请求速率限制器
+确保代理每秒不超过5次请求
+"""
+import time
+import threading
+from collections import deque
+
+
+class RateLimiter:
+    """
+    令牌桶算法实现的速率限制器
+    """
+    def __init__(self, max_requests_per_second: int = 5):
+        """
+        初始化速率限制器
+        
+        Args:
+            max_requests_per_second: 每秒最大请求数
+        """
+        self.max_requests = max_requests_per_second
+        self.requests = deque()
+        self.lock = threading.RLock()
+    
+    def acquire(self):
+        """
+        获取请求权限，如果需要则等待
+        """
+        with self.lock:
+            now = time.time()
+            
+            # 清理超过1秒的请求记录
+            while self.requests and now - self.requests[0] >= 1.0:
+                self.requests.popleft()
+            
+            # 如果当前请求数已达上限，等待
+            if len(self.requests) >= self.max_requests:
+                # 计算需要等待的时间
+                wait_time = 1.0 - (now - self.requests[0])
+                if wait_time > 0:
+                    time.sleep(wait_time)
+                    return self.acquire()  # 递归调用以重新检查
+            
+            # 记录这次请求
+            self.requests.append(now)
+    
+    def can_make_request(self) -> bool:
+        """
+        检查是否可以立即发起请求（非阻塞）
+        """
+        with self.lock:
+            now = time.time()
+            
+            # 清理超过1秒的请求记录
+            while self.requests and now - self.requests[0] >= 1.0:
+                self.requests.popleft()
+            
+            return len(self.requests) < self.max_requests
+
+
+# 全局速率限制器实例
+global_rate_limiter = RateLimiter(max_requests_per_second=5)
+
+
+def wait_for_request():
+    """
+    等待直到可以发起请求
+    """
+    global_rate_limiter.acquire()
+
+
+def can_request_now() -> bool:
+    """
+    检查是否可以立即发起请求
+    """
+    return global_rate_limiter.can_make_request()