Test Windows related issue

Author: Pijukatel

src/crawlee/crawlers/_basic/_basic_crawler.py

@@ -690,7 +690,6 @@ def sigint_handler() -> None:
         except CancelledError:
             pass
         finally:
-            await self._crawler_state_rec_task.stop()
             if threading.current_thread() is threading.main_thread():
                 with suppress(NotImplementedError):
                     asyncio.get_running_loop().remove_signal_handler(signal.SIGINT)
@@ -742,7 +741,10 @@ async def _run_crawler(self) -> None:
                 await exit_stack.enter_async_context(context)  # type: ignore[arg-type]
 
             self._crawler_state_rec_task.start()
-            await self._autoscaled_pool.run()
+            try:
+                await self._autoscaled_pool.run()
+            finally:
+                await self._crawler_state_rec_task.stop()
 
             # Emit PERSIST_STATE event when crawler is finishing to allow listeners to persist their state if needed
             if not self.statistics.state.crawler_last_started_at:

tests/unit/crawlers/_basic/test_basic_crawler.py

@@ -5,6 +5,7 @@
 import concurrent
 import json
 import logging
+import multiprocessing
 import os
 import sys
 import time
@@ -1678,7 +1679,7 @@ async def test_crawler_statistics_persistence(tmp_path: Path) -> None:
 
     This test simulates starting the crawler process twice, and checks that the statistics include first run."""
 
-    with concurrent.futures.ProcessPoolExecutor() as executor:
+    with concurrent.futures.ProcessPoolExecutor(mp_context=multiprocessing.get_context('fork')) as executor:
         # Crawl 2 requests in the first run and automatically persist the state.
         first_run_state = executor.submit(
             _process_run_crawler,