Add support to extract gray scale images (#1460)

PyPDF2/filters.py

@@ -602,10 +602,12 @@ def _xobj_to_image(x_object_obj: Dict[str, Any]) -> Tuple[Optional[str], bytes]:
                 from .generic import ByteStringObject
 
                 if isinstance(lookup, ByteStringObject):
+                    if base == ColorSpaces.DEVICE_GRAY and len(lookup) == hival + 1:
+                        lookup = b"".join([lookup[i:i + 1] * 3 for i in range(len(lookup))])
                     img.putpalette(lookup)
                 else:
                     img.putpalette(lookup.get_data())
-                img = img.convert("RGB")
+                img = img.convert("L" if base == ColorSpaces.DEVICE_GRAY else "RGB")
             if G.S_MASK in x_object_obj:  # add alpha channel
                 alpha = Image.frombytes("L", size, x_object_obj[G.S_MASK].get_data())
                 img.putalpha(alpha)

tests/test_reader.py

@@ -192,6 +192,7 @@ def test_get_outline(src, outline_elements):
             marks=pytest.mark.xfail(reason="broken image extraction"),
         ),
         ("imagemagick-CCITTFaxDecode.pdf", ["Im0.tiff"]),
+        (SAMPLE_ROOT / "019-grayscale-image/grayscale-image.pdf", ["X0.png"]),
     ],
 )
 def test_get_images(src, expected_images):
@@ -211,7 +212,7 @@ def test_get_images(src, expected_images):
     for image, expected_image in zip(images_extracted, expected_images):
         assert image.name == expected_image
         try:
-            fn = f"test-out-{src}-{image.name}"
+            fn = f"{src}-test-out-{image.name}"
             with open(fn, "wb") as fp:
                 fp.write(image.data)
                 assert (