Fix _get_tag_name() crash for non-string elem.tag (#7686) (#7687)

* Fix _get_tag_name() crash for non-string elem.tag (#7686)

* test: improve non-string tag test accuracy and add direct unit test

* test: use minimal payload for non-string tag test

* test: address Adrian+syncrain PR feedback

- remove first docstring line (Adrian: unnecessary)
- replace weak isinstance assert with no-op call
- keep Cython function mention (Adrian: wording is great)

* test: replace silent call with assert results == [] per Adrian

* chore: drop accidental pyproject.toml and uv.lock changes

scrapy/utils/sitemap.py

@@ -97,10 +97,11 @@ class Sitemap:
 
     @staticmethod
     def _get_tag_name(elem: lxml.etree._Element) -> str:
-        if TYPE_CHECKING:
+        tag = elem.tag
-            assert isinstance(elem.tag, str)
+        if not isinstance(tag, str):
-        _, _, localname = elem.tag.partition("}")
+            return ""
-        return localname or elem.tag
+        _, _, localname = tag.partition("}")
+        return localname or tag
 
 
 def sitemap_urls_from_robots(

tests/test_utils_sitemap.py

@@ -311,3 +311,14 @@ def test_xml_entity_expansion():
     """
     )
     assert list(s) == [{"loc": "http://127.0.0.1:8000/"}]
+
+
+def test_sitemap_non_string_tag():
+    """With recover=True and resolve_entities=False, libxml2 >= 2.14.6 (used
+    by lxml >= 6.1.1) preserves undeclared entity reference nodes whose
+    .tag is a non-string ``Cython function`` object instead of a ``str``.
+    _get_tag_name must handle this gracefully instead of raising
+    AttributeError.
+    """
+    results = list(Sitemap(b"<url>&k;"))
+    assert results == []