BUG: PageObject.scale() scales media box incorrectly (#3487)

pypdf/_page.py

@@ -1503,7 +1503,7 @@ def scale(self, sx: float, sy: float) -> None:
         Scale a page by the given factors by applying a transformation matrix
         to its content and updating the page size.
 
-        This updates the various page boundaries (mediabox, cropbox, etc.)
+        This updates the various page boundaries (artbox, cropbox, etc.)
         and the contents of the page.
 
         Args:
@@ -1512,11 +1512,11 @@ def scale(self, sx: float, sy: float) -> None:
 
         """
         self.add_transformation((sx, 0, 0, sy, 0, 0))
-        self.mediabox = self.mediabox.scale(sx, sy)
-        self.cropbox = self.cropbox.scale(sx, sy)
         self.bleedbox = self.bleedbox.scale(sx, sy)
         self.trimbox = self.trimbox.scale(sx, sy)
         self.artbox = self.artbox.scale(sx, sy)
+        self.cropbox = self.cropbox.scale(sx, sy)
+        self.mediabox = self.mediabox.scale(sx, sy)
 
         if PG.ANNOTS in self:
             annotations = self[PG.ANNOTS]

tests/test_page.py

@@ -1504,3 +1504,27 @@ def __getitem__(self, item) -> Any:
     page[NameObject("/Resources")] = resources
     with mock.patch.object(none_reference, "get_object", return_value=None):
         assert page.extract_text() == ""
+
+
+@pytest.mark.enable_socket
+def test_scale_by():
+    """Tests for #3487"""
+    url = "https://github.com/user-attachments/files/22685841/input.pdf"
+    name = "issue3487.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+
+    original_box = RectangleObject((0, 0, 595.275604, 841.88974))
+    expected_box = RectangleObject((0.0, 0.0, 297.637802, 420.94487))
+    for page in reader.pages:
+        assert page.artbox == original_box
+        assert page.bleedbox == original_box
+        assert page.cropbox == original_box
+        assert page.mediabox == original_box
+        assert page.trimbox == original_box
+
+        page.scale_by(0.5)
+        assert page.artbox == expected_box
+        assert page.bleedbox == expected_box
+        assert page.cropbox == expected_box
+        assert page.mediabox == expected_box
+        assert page.trimbox == expected_box