Return self from __call__

sources/scraping/runner.py

@@ -1,9 +1,10 @@
 import threading
 import typing as t
-
 import dlt
+
 from dlt.common import logger
 from pydispatch import dispatcher  # type: ignore
+from typing_extensions import Self
 
 from scrapy import signals, Item, Spider  # type: ignore
 from scrapy.crawler import CrawlerProcess  # type: ignore
@@ -20,9 +21,6 @@ def __init__(self, pipeline_name: str, queue: ScrapingQueue[T]) -> None:
         self.queue = queue
         self.pipeline_name = pipeline_name
 
-    def __call__(self, crawler: CrawlerProcess) -> None:
-        self.crawler = crawler
-
     def on_item_scraped(self, item: Item) -> None:
         if not self.queue.is_closed:
             self.queue.put(item)
@@ -40,6 +38,10 @@ def on_engine_stopped(self) -> None:
         self.queue.join()
         self.queue.close()
 
+    def __call__(self, crawler: CrawlerProcess) -> Self:
+        self.crawler = crawler
+        return self
+
     def __enter__(self) -> None:
         # We want to receive on_item_scraped callback from
         # outside so we don't have to know about any queue instance.