Rename crawler_id to just id. Polish.

Author: Pijukatel

src/crawlee/crawlers/_basic/_basic_crawler.py

@@ -213,6 +213,10 @@ class _BasicCrawlerOptions(TypedDict):
     """Allows overriding the default status message. The default status message is provided in the parameters.
     Returning `None` suppresses the status message."""
 
+    id: NotRequired[int]
+    """Id of the crawler used for state tracking. You can use same explicit id to share state between two crawlers.
+    By default, each crawler will use own state."""
+
 
 class _BasicCrawlerOptionsGeneric(TypedDict, Generic[TCrawlingContext, TStatisticsState]):
     """Generic options the `BasicCrawler` constructor."""
@@ -298,7 +302,7 @@ def __init__(
         status_message_logging_interval: timedelta = timedelta(seconds=10),
         status_message_callback: Callable[[StatisticsState, StatisticsState | None, str], Awaitable[str | None]]
         | None = None,
-        crawler_id: int | None = None,
+        id: int | None = None,
         _context_pipeline: ContextPipeline[TCrawlingContext] | None = None,
         _additional_context_managers: Sequence[AbstractAsyncContextManager] | None = None,
         _logger: logging.Logger | None = None,
@@ -351,21 +355,20 @@ def __init__(
             status_message_logging_interval: Interval for logging the crawler status messages.
             status_message_callback: Allows overriding the default status message. The default status message is
                 provided in the parameters. Returning `None` suppresses the status message.
-            crawler_id: Id of the crawler used for state and statistics tracking. You can use same explicit id to share
-                state and statistics between two crawlers. By default, each crawler will use own state and statistics.
+            id: Id of the crawler used for state tracking. You can use same explicit id to share state and between two
+                crawlers. By default, each crawler will use own state.
             _context_pipeline: Enables extending the request lifecycle and modifying the crawling context.
                 Intended for use by subclasses rather than direct instantiation of `BasicCrawler`.
             _additional_context_managers: Additional context managers used throughout the crawler lifecycle.
                 Intended for use by subclasses rather than direct instantiation of `BasicCrawler`.
             _logger: A logger instance, typically provided by a subclass, for consistent logging labels.
                 Intended for use by subclasses rather than direct instantiation of `BasicCrawler`.
         """
-        if crawler_id is None:
-            # This could look into set of already used ids, but lets not overengineer this.
-            self.id = BasicCrawler.__next_id
+        if id is None:
+            self._id = BasicCrawler.__next_id
             BasicCrawler.__next_id += 1
         else:
-            self.id = crawler_id
+            self._id = id
 
         implicit_event_manager_with_explicit_config = False
         if not configuration:
@@ -842,7 +845,7 @@ async def _use_state(
         default_value: dict[str, JsonSerializable] | None = None,
     ) -> dict[str, JsonSerializable]:
         kvs = await self.get_key_value_store()
-        return await kvs.get_auto_saved_value(f'{self._CRAWLEE_STATE_KEY}_{self.id}', default_value)
+        return await kvs.get_auto_saved_value(f'{self._CRAWLEE_STATE_KEY}_{self._id}', default_value)
 
     async def _save_crawler_state(self) -> None:
         store = await self.get_key_value_store()

tests/unit/crawlers/_basic/test_basic_crawler.py

@@ -821,15 +821,15 @@ async def handler(context: BasicCrawlingContext) -> None:
         assert isinstance(state['urls'], list)
         state['urls'].append(context.request.url)
 
-    crawler_1 = BasicCrawler(crawler_id=0, request_handler=handler)
-    crawler_2 = BasicCrawler(crawler_id=0, request_handler=handler)
+    crawler_1 = BasicCrawler(id=0, request_handler=handler)
+    crawler_2 = BasicCrawler(id=0, request_handler=handler)
 
     await crawler_1.run(['https://a.com'])
     await crawler_2.run(['https://b.com'])
 
     kvs = await KeyValueStore.open()
-    assert crawler_1.id == crawler_2.id == 0
-    assert await kvs.get_value(f'{BasicCrawler._CRAWLEE_STATE_KEY}_{crawler_1.id}') == {
+    assert crawler_1._id == crawler_2._id == 0
+    assert await kvs.get_value(f'{BasicCrawler._CRAWLEE_STATE_KEY}_{crawler_1._id}') == {
         'urls': ['https://a.com', 'https://b.com']
     }
 
@@ -838,8 +838,8 @@ async def test_crawlers_share_stats() -> None:
     async def handler(context: BasicCrawlingContext) -> None:
         await context.use_state({'urls': []})
 
-    crawler_1 = BasicCrawler(crawler_id=0, request_handler=handler)
-    crawler_2 = BasicCrawler(crawler_id=0, request_handler=handler, statistics=crawler_1.statistics)
+    crawler_1 = BasicCrawler(id=0, request_handler=handler)
+    crawler_2 = BasicCrawler(id=0, request_handler=handler, statistics=crawler_1.statistics)
 
     result1 = await crawler_1.run(['https://a.com'])
     result2 = await crawler_2.run(['https://b.com'])
@@ -1722,7 +1722,7 @@ async def test_add_requests_with_rq_param(queue_name: str | None, queue_alias: s
     crawler = BasicCrawler()
     rq = await RequestQueue.open(name=queue_name, alias=queue_alias)
     if by_id:
-        queue_id = rq.id
+        queue_id = rq._id
         queue_name = None
     else:
         queue_id = None