Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Deprecate defining XMLFeedSpider.parse_item(). (#8147)

Andrey Rakhmatullinbb22ac044b0c
diff --git a/scrapy/spiders/feed.py b/scrapy/spiders/feed.py
index 1e7ac9c34..ad5015227 100644
--- a/scrapy/spiders/feed.py
+++ b/scrapy/spiders/feed.py
@@ -7,9 +7,10 @@ See documentation in docs/topics/spiders.rst
from __future__ import annotations
+import warnings
from typing import TYPE_CHECKING, Any
-from scrapy.exceptions import NotSupported
+from scrapy.exceptions import NotSupported, ScrapyDeprecationWarning
from scrapy.http import Response, TextResponse
from scrapy.selector import Selector
from scrapy.spiders import Spider
@@ -62,7 +63,13 @@ class XMLFeedSpider(Spider):
This method must be overridden with your custom spider functionality.
"""
- if hasattr(self, "parse_item"): # backward compatibility
+ if hasattr(self, "parse_item"):
+ warnings.warn(
+ "Defining parse_item() on XMLFeedSpider subclasses is deprecated,"
+ " define parse_node() instead.",
+ ScrapyDeprecationWarning,
+ stacklevel=2,
+ )
return self.parse_item(response, selector)
raise NotImplementedError
diff --git a/tests/test_spider.py b/tests/test_spider.py
index 6f7f171a3..e06201ad3 100644
--- a/tests/test_spider.py
+++ b/tests/test_spider.py
@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING
import pytest
+from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.http import Request, Response, TextResponse, XmlResponse
from scrapy.spiders import CSVFeedSpider, Spider, XMLFeedSpider
from tests import get_testdata
@@ -87,7 +88,11 @@ class TestXMLFeedSpider(TestSpiderBase):
def parse_item(self, response, selector):
return {"id": selector.xpath("id/text()").get()}
- items, _ = await crawl_items(_Spider, mockserver)
+ with pytest.warns(
+ ScrapyDeprecationWarning,
+ match=r"Defining parse_item\(\) on XMLFeedSpider subclasses",
+ ):
+ items, _ = await crawl_items(_Spider, mockserver)
assert items == [{"id": "1"}]
@coroutine_test