diff --git a/.github/ISSUE_TEMPLATE/bug-report.md b/.github/ISSUE_TEMPLATE/bug-report.md
index 4878a3c1e7..05284f39be 100644
--- a/.github/ISSUE_TEMPLATE/bug-report.md
+++ b/.github/ISSUE_TEMPLATE/bug-report.md
@@ -34,8 +34,8 @@ better. Let us know if we may add them to our tests!
 
 ## Traceback
 
-This is the complete Traceback I see:
+This is the complete traceback I see:
 
 ```
-# TODO: Your Traceback goes here (if applicable)
+# TODO: Your traceback goes here (if applicable)
 ```
diff --git a/.github/workflows/benchmark.yaml b/.github/workflows/benchmark.yaml
index 96389177b7..98dc86ed92 100644
--- a/.github/workflows/benchmark.yaml
+++ b/.github/workflows/benchmark.yaml
@@ -21,7 +21,7 @@ jobs:
       with:
         submodules: 'recursive'
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install requirements (Python 3)
diff --git a/.github/workflows/github-ci.yaml b/.github/workflows/github-ci.yaml
index 8b52544e1e..a6157a484a 100644
--- a/.github/workflows/github-ci.yaml
+++ b/.github/workflows/github-ci.yaml
@@ -26,7 +26,7 @@ jobs:
       with:
         submodules: 'recursive'
     - name: Setup Python (3.11+)
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.12  # latest stable python
         allow-prereleases: true
@@ -80,14 +80,14 @@ jobs:
         path: '**/tests/pdf_cache/*'
         key: cache-downloaded-files
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       if: matrix.python-version == '3.6' || matrix.python-version == '3.7' || matrix.python-version == '3.8' || matrix.python-version == '3.9' || matrix.python-version == '3.10'
       with:
         python-version: ${{ matrix.python-version }}
         cache: 'pip'
         cache-dependency-path: '**/requirements/ci.txt'
     - name: Setup Python (3.11+)
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       if: matrix.python-version == '3.11' || matrix.python-version == '3.12'
       with:
         python-version: ${{ matrix.python-version }}
@@ -143,7 +143,7 @@ jobs:
       with:
         submodules: 'recursive'
     - name: Setup Python 3.11
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: "3.11"
         cache: 'pip'
@@ -171,7 +171,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{env.PYTHON_LATEST}}
 
@@ -194,7 +194,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           # Use latest Python, so it understands all syntax.
           python-version: ${{env.PYTHON_LATEST}}
diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml
index 9fb135d8a8..3ca2426d63 100644
--- a/.github/workflows/release.yaml
+++ b/.github/workflows/release.yaml
@@ -20,7 +20,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.x
 
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6102d43b09..0f52bf2707 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,18 @@
 # CHANGELOG
 
+## Version 3.17.2, 2023-12-10
+
+### Bug Fixes (BUG)
+-  Cope with deflated images with CMYK Black Only (#2322)
+-  Handle indirect objects as parameters for CCITTFaxDecode (#2307)
+-  check words length in _cmap type1_alternative function (#2310)
+
+### Robustness (ROB)
+-  Relax flate decoding for too many lookup values (#2331)
+-  Let _build_destination skip in case of missing /D key (#2018)
+
+[Full Changelog](https://github.com/py-pdf/pypdf/compare/3.17.1...3.17.2)
+
 ## Version 3.17.1, 2023-11-14
 
 ### Bug Fixes (BUG)
diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md
index 18fd750463..7fffed4d65 100644
--- a/CONTRIBUTORS.md
+++ b/CONTRIBUTORS.md
@@ -15,6 +15,7 @@ history and [GitHubs 'Contributors' feature](https://github.com/py-pdf/pypdf/gra
 * [ArkieCoder](https://github.com/ArkieCoder)
 * [Clauss, Christian](https://github.com/cclauss)
 * [DL6ER](https://github.com/DL6ER)
+* [Duy, Phan Thanh](https://github.com/zuypt)
 * [ediamondscience](https://github.com/ediamondscience)
 * [Ermeson, Felipe](https://github.com/FelipeErmeson)
 * [Freitag, François](https://github.com/francoisfreitag)
diff --git a/docs/dev/intro.md b/docs/dev/intro.md
index 7d10901ab6..6765b4a44a 100644
--- a/docs/dev/intro.md
+++ b/docs/dev/intro.md
@@ -59,10 +59,13 @@ BODY
 
 The `PREFIX` can be:
 
+* `SEC`: Security improvements. Typically an infinite loop that was possible.
 * `BUG`: A bug was fixed. Likely there is one or multiple issues. Then write in
    the `BODY`: `Closes #123` where 123 is the issue number on GitHub.
    It would be absolutely amazing if you could write a regression test in those
    cases. That is a test that would fail without the fix.
+   A bug is always an issue for pypdf users - test code or CI that was fixed is
+   not considered a bug here.
 * `ENH`: A new feature! Describe in the body what it can be used for.
 * `DEP`: A deprecation - either marking something as "this is going to be removed"
    or actually removing it.
@@ -75,7 +78,21 @@ The `PREFIX` can be:
 * `MAINT`: Quite a lot of different stuff. Performance improvements are for sure
            the most interesting changes in here. Refactorings as well.
 * `STY`: A style change. Something that makes pypdf code more consistent.
-         Typically a small change.
+         Typically a small change. It could also be better error messages for
+         end users.
+
+The prefix is used to generate the CHANGELOG. Every PR must have exactly one -
+if you feel like several match, take the top one from this list that matches for
+your PR.
+
+## Pull Request Size
+
+Smaller Pull Requests (PRs) are preferred as it's typically easier to merge
+them. For example, if you have some typos, a few code-style changes, a new
+feature, and a bug-fix, that could be 3 or 4 PRs.
+
+A PR must be complete. That means if you introduce a new feature it must be
+finished within the PR and have a test for that feature.
 
 ## Benchmarks
 
diff --git a/docs/user/forms.md b/docs/user/forms.md
index ff729d0596..3cc29ee00a 100644
--- a/docs/user/forms.md
+++ b/docs/user/forms.md
@@ -8,6 +8,9 @@ from pypdf import PdfReader
 reader = PdfReader("form.pdf")
 fields = reader.get_form_text_fields()
 fields == {"key": "value", "key2": "value2"}
+
+# You can also get all fields:
+fields = reader.get_fields()
 ```
 
 ## Filling out forms
diff --git a/pypdf/_cmap.py b/pypdf/_cmap.py
index 2706007c27..f221d2d23d 100644
--- a/pypdf/_cmap.py
+++ b/pypdf/_cmap.py
@@ -6,13 +6,19 @@
 from ._codecs import adobe_glyphs, charset_encoding
 from ._utils import b_, logger_warning
 from .errors import PdfReadWarning
-from .generic import DecodedStreamObject, DictionaryObject, IndirectObject, NullObject, StreamObject
+from .generic import (
+    DecodedStreamObject,
+    DictionaryObject,
+    IndirectObject,
+    NullObject,
+    StreamObject,
+)
 
 
 # code freely inspired from @twiggy ; see #711
 def build_char_map(
     font_name: str, space_width: float, obj: DictionaryObject
-) -> Tuple[str, float, Union[str, Dict[int, str]], Dict, DictionaryObject]:
+) -> Tuple[str, float, Union[str, Dict[int, str]], Dict[Any, Any], DictionaryObject]:
     """
     Determine information about a font.
 
@@ -34,7 +40,7 @@ def build_char_map(
 
 def build_char_map_from_dict(
     space_width: float, ft: DictionaryObject
-) -> Tuple[str, float, Union[str, Dict[int, str]], Dict]:
+) -> Tuple[str, float, Union[str, Dict[int, str]], Dict[Any, Any]]:
     """
     Determine information about a font.
 
@@ -489,7 +495,7 @@ def type1_alternative(
     for li in lines:
         if li.startswith(b"dup"):
             words = [_w for _w in li.split(b" ") if _w != b""]
-            if words[3] != b"put":
+            if len(words) > 3 and words[3] != b"put":
                 continue
             try:
                 i = int(words[1])
diff --git a/pypdf/_encryption.py b/pypdf/_encryption.py
index 2cc857f167..c000a2a2a7 100644
--- a/pypdf/_encryption.py
+++ b/pypdf/_encryption.py
@@ -759,7 +759,7 @@ class PasswordType(IntEnum):
     OWNER_PASSWORD = 2
 
 
-class EncryptAlgorithm(tuple, Enum):  # noqa: SLOT001
+class EncryptAlgorithm(tuple, Enum):  # type: ignore # noqa: SLOT001
     # V, R, Length
     RC4_40 = (1, 2, 40)
     RC4_128 = (2, 3, 128)
@@ -1144,7 +1144,7 @@ def read(encryption_entry: DictionaryObject, first_id_entry: bytes) -> "Encrypti
     def make(
         alg: EncryptAlgorithm, permissions: int, first_id_entry: bytes
     ) -> "Encryption":
-        alg_ver, alg_rev, key_bits = cast(tuple, alg)
+        alg_ver, alg_rev, key_bits = alg
 
         stm_filter, str_filter, ef_filter = "/V2", "/V2", "/V2"
 
diff --git a/pypdf/_page.py b/pypdf/_page.py
index e8216e9d04..120e15a193 100644
--- a/pypdf/_page.py
+++ b/pypdf/_page.py
@@ -296,6 +296,16 @@ def rotate(self, rotation: float) -> "Transformation":
     def __repr__(self) -> str:
         return f"Transformation(ctm={self.ctm})"
 
+    @overload
+    def apply_on(self, pt: List[float], as_object: bool = False) -> List[float]:
+        ...
+
+    @overload
+    def apply_on(
+        self, pt: Tuple[float, float], as_object: bool = False
+    ) -> Tuple[float, float]:
+        ...
+
     def apply_on(
         self,
         pt: Union[Tuple[float, float], List[float]],
@@ -1232,10 +1242,10 @@ def _merge_page_writer(
                 if "/QuadPoints" in a:
                     q = cast(ArrayObject, a["/QuadPoints"])
                     aa[NameObject("/QuadPoints")] = ArrayObject(
-                        cast(tuple, trsf.apply_on((q[0], q[1]), True))
-                        + cast(tuple, trsf.apply_on((q[2], q[3]), True))
-                        + cast(tuple, trsf.apply_on((q[4], q[5]), True))
-                        + cast(tuple, trsf.apply_on((q[6], q[7]), True))
+                        trsf.apply_on((q[0], q[1]), True)
+                        + trsf.apply_on((q[2], q[3]), True)
+                        + trsf.apply_on((q[4], q[5]), True)
+                        + trsf.apply_on((q[6], q[7]), True)
                     )
                 try:
                     aa["/Popup"][NameObject("/Parent")] = aa.indirect_reference
@@ -1936,7 +1946,7 @@ def _extract_text(
         def current_spacewidth() -> float:
             return _space_width / 1000.0
 
-        def process_operation(operator: bytes, operands: List) -> None:
+        def process_operation(operator: bytes, operands: List[Any]) -> None:
             nonlocal cm_matrix, cm_stack, tm_matrix, cm_prev, tm_prev, memo_cm, memo_tm
             nonlocal char_scale, space_scale, _space_width, TL, font_size, cmap
             nonlocal orientations, rtl_dir, visitor_text, output, text
@@ -2479,7 +2489,7 @@ def annotations(self, value: Optional[ArrayObject]) -> None:
             self[NameObject("/Annots")] = value
 
 
-class _VirtualList(Sequence):
+class _VirtualList(Sequence[PageObject]):
     def __init__(
         self,
         length_function: Callable[[], int],
@@ -2664,7 +2674,7 @@ def process_font(f: DictionaryObject) -> None:
     return fnt, emb  # return the sets for each page
 
 
-class _VirtualListImages(Sequence):
+class _VirtualListImages(Sequence[ImageFile]):
     def __init__(
         self,
         ids_function: Callable[[], List[Union[str, List[str]]]],
diff --git a/pypdf/_protocols.py b/pypdf/_protocols.py
index de0fa78ce4..fdb8a01b58 100644
--- a/pypdf/_protocols.py
+++ b/pypdf/_protocols.py
@@ -70,7 +70,7 @@ class PdfWriterProtocol(Protocol):  # deprecated
     def get_object(self, indirect_reference: Any) -> Optional[PdfObjectProtocol]:
         ...
 
-    def write(self, stream: Union[Path, StrByteType]) -> Tuple[bool, IO]:
+    def write(self, stream: Union[Path, StrByteType]) -> Tuple[bool, IO[Any]]:
         ...
 
     def _add_object(self, obj: Any) -> Any:
diff --git a/pypdf/_reader.py b/pypdf/_reader.py
index 7357fd1a76..365cb0bae9 100644
--- a/pypdf/_reader.py
+++ b/pypdf/_reader.py
@@ -721,7 +721,7 @@ def get_form_text_fields(self, full_qualified_name: bool = False) -> Dict[str, A
             second and following will get the suffix .2, .3, ...
         """
 
-        def indexed_key(k: str, fields: dict) -> str:
+        def indexed_key(k: str, fields: Dict[Any, Any]) -> str:
             if k not in fields:
                 return k
             else:
@@ -804,8 +804,11 @@ def _get_named_destinations(
                 except IndexError:
                     break
                 i += 1
-                if isinstance(value, DictionaryObject) and "/D" in value:
-                    value = value["/D"]
+                if isinstance(value, DictionaryObject):
+                    if "/D" in value:
+                        value = value["/D"]
+                    else:
+                        continue
                 dest = self._build_destination(key, value)  # type: ignore
                 if dest is not None:
                     retval[key] = dest
@@ -813,7 +816,10 @@ def _get_named_destinations(
             for k__, v__ in tree.items():
                 val = v__.get_object()
                 if isinstance(val, DictionaryObject):
-                    val = val["/D"].get_object()
+                    if "/D" in val:
+                        val = val["/D"].get_object()
+                    else:
+                        continue
                 dest = self._build_destination(k__, val)
                 if dest is not None:
                     retval[k__] = dest
@@ -2292,7 +2298,7 @@ def _get_attachments(
         return attachments
 
 
-class LazyDict(Mapping):
+class LazyDict(Mapping[Any, Any]):
     def __init__(self, *args: Any, **kw: Any) -> None:
         self._raw_dict = dict(*args, **kw)
 
diff --git a/pypdf/_utils.py b/pypdf/_utils.py
index 9613cd1b02..0e3e7ebabb 100644
--- a/pypdf/_utils.py
+++ b/pypdf/_utils.py
@@ -453,7 +453,7 @@ def logger_warning(msg: str, src: str) -> None:
     logging.getLogger(src).warning(msg)
 
 
-def deprecation_bookmark(**aliases: str) -> Callable:
+def deprecation_bookmark(**aliases: str) -> Callable[..., Any]:
     """
     Decorator for deprecated term "bookmark".
 
@@ -462,7 +462,7 @@ def deprecation_bookmark(**aliases: str) -> Callable:
         outline = a collection of outline items.
     """
 
-    def decoration(func: Callable) -> Any:
+    def decoration(func: Callable[..., Any]) -> Any:
         @functools.wraps(func)
         def wrapper(*args: Any, **kwargs: Any) -> Any:
             rename_kwargs(func.__name__, kwargs, aliases, fail=True)
diff --git a/pypdf/_version.py b/pypdf/_version.py
index 7e84c71b24..4874dc2b76 100644
--- a/pypdf/_version.py
+++ b/pypdf/_version.py
@@ -1 +1 @@
-__version__ = "3.17.1"
+__version__ = "3.17.2"
diff --git a/pypdf/_writer.py b/pypdf/_writer.py
index 10cc9342a9..e4db6e32e7 100644
--- a/pypdf/_writer.py
+++ b/pypdf/_writer.py
@@ -885,7 +885,7 @@ def _update_text_field(self, field: DictionaryObject) -> None:
         if font_name not in dr:
             # ...or AcroForm dictionary
             dr = cast(
-                dict,
+                Dict[Any, Any],
                 cast(DictionaryObject, self._root_object["/AcroForm"]).get("/DR", {}),
             )
             if isinstance(dr, IndirectObject):  # pragma: no cover
@@ -1353,7 +1353,7 @@ def write_stream(self, stream: StreamType) -> None:
         xref_location = self._write_xref_table(stream, object_positions)
         self._write_trailer(stream, xref_location)
 
-    def write(self, stream: Union[Path, StrByteType]) -> Tuple[bool, IO]:
+    def write(self, stream: Union[Path, StrByteType]) -> Tuple[bool, IO[Any]]:
         """
         Write the collection of pages added to this object out as a PDF file.
 
@@ -2240,7 +2240,10 @@ def clean_forms(
                 # to prevent infinite looping
                 return [], []  # pragma: no cover
             try:
-                d = cast(dict, cast(DictionaryObject, elt["/Resources"])["/XObject"])
+                d = cast(
+                    Dict[Any, Any],
+                    cast(DictionaryObject, elt["/Resources"])["/XObject"],
+                )
             except KeyError:
                 d = {}
             images = []
@@ -2793,7 +2796,7 @@ def add_annotation(
         # Internal link annotations need the correct object type for the
         # destination
         if to_add.get("/Subtype") == "/Link" and "/Dest" in to_add:
-            tmp = cast(dict, to_add[NameObject("/Dest")])
+            tmp = cast(Dict[Any, Any], to_add[NameObject("/Dest")])
             dest = Destination(
                 NameObject("/LinkName"),
                 tmp["target_page_index"],
@@ -3029,7 +3032,7 @@ def merge(
         for dest in reader._namedDests.values():
             arr = dest.dest_array
             if "/Names" in self._root_object and dest["/Title"] in cast(
-                list,
+                List[Any],
                 cast(
                     DictionaryObject,
                     cast(DictionaryObject, self._root_object["/Names"])["/Dests"],
@@ -3188,7 +3191,9 @@ def _add_articles_thread(
 
     def add_filtered_articles(
         self,
-        fltr: Union[Pattern, str],  # thread entry from the reader's array of threads
+        fltr: Union[
+            Pattern[Any], str
+        ],  # thread entry from the reader's array of threads
         pages: Dict[int, PageObject],
         reader: PdfReader,
     ) -> None:
@@ -3245,7 +3250,7 @@ def _insert_filtered_annotations(
     ) -> List[Destination]:
         outlist = ArrayObject()
         if isinstance(annots, IndirectObject):
-            annots = cast("List", annots.get_object())
+            annots = cast("List[Any]", annots.get_object())
         for an in annots:
             ano = cast("DictionaryObject", an.get_object())
             if (
diff --git a/pypdf/_xobj_image_helpers.py b/pypdf/_xobj_image_helpers.py
index 87bff19b96..a390357dd5 100644
--- a/pypdf/_xobj_image_helpers.py
+++ b/pypdf/_xobj_image_helpers.py
@@ -4,7 +4,7 @@
 from io import BytesIO
 from typing import Any, List, Tuple, Union, cast
 
-from ._utils import logger_warning
+from ._utils import WHITESPACES, logger_warning
 from .constants import ColorSpaces
 from .errors import PdfReadError
 from .generic import (
@@ -91,10 +91,18 @@ def _get_imagemode(
         )
         return mode2, True
     elif color_space[0] == "/DeviceN":
+        original_color_space = color_space
         color_components = len(color_space[1])
         color_space = color_space[2]
         if isinstance(color_space, IndirectObject):  # pragma: no cover
             color_space = color_space.get_object()
+        if color_space == "/DeviceCMYK" and color_components == 1:
+            if original_color_space[1][0] != "/Black":
+                logger_warning(
+                    f"Color {original_color_space[1][0]} converted to Gray. Please share PDF with pypdf dev team",
+                    __name__,
+                )
+            return "L", True
         mode2, invert_color = _get_imagemode(
             color_space, color_components, prev_mode, depth + 1
         )
@@ -187,7 +195,13 @@ def bits2byte(data: bytes, size: Tuple[int, int], bits: int) -> bytes:
         else:
             if img.mode == "1":
                 # Two values ("high" and "low").
-                assert len(lookup) == 2 * nb, len(lookup)
+                expected_count = 2 * nb
+                if len(lookup) != expected_count:
+                    if len(lookup) < expected_count:
+                        raise PdfReadError(f"Not enough lookup values: Expected {expected_count}, got {len(lookup)}.")
+                    lookup = lookup[:expected_count]
+                    if not all(_value in WHITESPACES for _value in lookup[expected_count:]):
+                        raise PdfReadError(f"Too many lookup values: Expected {expected_count}, got {len(lookup)}.")
                 colors_arr = [lookup[:nb], lookup[nb:]]
                 arr = b"".join(
                     [
diff --git a/pypdf/filters.py b/pypdf/filters.py
index b6d198f55b..d1c06a3418 100644
--- a/pypdf/filters.py
+++ b/pypdf/filters.py
@@ -322,7 +322,7 @@ def decode(
         **kwargs: Any,
     ) -> bytes:
         """
-        Decode an ASCII-Hex encoded data stream.
+        Decode a run length encoded data stream.
 
         Args:
           data: a bytes sequence of length/data
@@ -558,23 +558,27 @@ class CCITTFaxDecode:
 
     @staticmethod
     def _get_parameters(
-        parameters: Union[None, ArrayObject, DictionaryObject], rows: int
+        parameters: Union[None, ArrayObject, DictionaryObject, IndirectObject],
+        rows: int,
     ) -> CCITParameters:
         # TABLE 3.9 Optional parameters for the CCITTFaxDecode filter
         k = 0
         columns = 1728
         if parameters:
-            if isinstance(parameters, ArrayObject):
-                for decode_parm in parameters:
+            parameters_unwrapped = cast(
+                Union[ArrayObject, DictionaryObject], parameters.get_object()
+            )
+            if isinstance(parameters_unwrapped, ArrayObject):
+                for decode_parm in parameters_unwrapped:
                     if CCITT.COLUMNS in decode_parm:
                         columns = decode_parm[CCITT.COLUMNS]
                     if CCITT.K in decode_parm:
                         k = decode_parm[CCITT.K]
             else:
-                if CCITT.COLUMNS in parameters:
-                    columns = parameters[CCITT.COLUMNS]  # type: ignore
-                if CCITT.K in parameters:
-                    k = parameters[CCITT.K]  # type: ignore
+                if CCITT.COLUMNS in parameters_unwrapped:
+                    columns = parameters_unwrapped[CCITT.COLUMNS]  # type: ignore
+                if CCITT.K in parameters_unwrapped:
+                    k = parameters_unwrapped[CCITT.K]  # type: ignore
 
         return CCITParameters(k, columns, rows)
 
@@ -777,8 +781,8 @@ def _xobj_to_image(x_object_obj: Dict[str, Any]) -> Tuple[Optional[str], bytes,
     alpha = None
     filters = x_object_obj.get(SA.FILTER, [None])
     lfilters = filters[-1] if isinstance(filters, list) else filters
-    if lfilters == FT.FLATE_DECODE:
-        img, image_format, extension, invert_color = _handle_flate(
+    if lfilters in (FT.FLATE_DECODE, FT.RUN_LENGTH_DECODE):
+        img, image_format, extension, _ = _handle_flate(
             size,
             data,
             mode,
@@ -820,15 +824,14 @@ def _xobj_to_image(x_object_obj: Dict[str, Any]) -> Tuple[Optional[str], bytes,
             ".png",
             False,
         )
-
     # CMYK image and other colorspaces without decode
     # requires reverting scale (cf p243,2§ last sentence)
     decode = x_object_obj.get(
         IA.DECODE,
         ([1.0, 0.0] * len(img.getbands()))
         if (
-            (img.mode == "CMYK" or (invert_color and img.mode == "L"))
-            and lfilters in (FT.DCT_DECODE, FT.JPX_DECODE)
+            (img.mode == "CMYK" and lfilters in (FT.DCT_DECODE, FT.JPX_DECODE))
+            or (invert_color and img.mode == "L")
         )
         else None,
     )
diff --git a/pypdf/generic/_base.py b/pypdf/generic/_base.py
index a50bb5faff..667d675266 100644
--- a/pypdf/generic/_base.py
+++ b/pypdf/generic/_base.py
@@ -727,7 +727,7 @@ def readFromStream(
 
 
 def encode_pdfdocencoding(unicode_string: str) -> bytes:
-    retval = b""
+    retval = bytearray()
     for c in unicode_string:
         try:
             retval += b_(chr(_pdfdoc_encoding_rev[c]))
diff --git a/pypdf/generic/_data_structures.py b/pypdf/generic/_data_structures.py
index 4ee13a13b0..d9853a2d1e 100644
--- a/pypdf/generic/_data_structures.py
+++ b/pypdf/generic/_data_structures.py
@@ -87,7 +87,7 @@
 IndirectPattern = re.compile(rb"[+-]?(\d+)\s+(\d+)\s+R[^a-zA-Z]")
 
 
-class ArrayObject(list, PdfObject):
+class ArrayObject(List[Any], PdfObject):
     def clone(
         self,
         pdf_dest: PdfWriterProtocol,
@@ -174,7 +174,7 @@ def readFromStream(
         return ArrayObject.read_from_stream(stream, pdf)
 
 
-class DictionaryObject(dict, PdfObject):
+class DictionaryObject(Dict[Any, Any], PdfObject):
     def clone(
         self,
         pdf_dest: PdfWriterProtocol,
@@ -420,7 +420,7 @@ def get_next_obj_pos(
             else:
                 return get_next_obj_pos(p, p1, rem_gens[1:], pdf)
 
-        def read_unsized_from_steam(
+        def read_unsized_from_stream(
             stream: StreamType, pdf: PdfReaderProtocol
         ) -> bytes:
             # we are just pointing at beginning of the stream
@@ -535,7 +535,7 @@ def read_unsized_from_steam(
                     data["__streamdata__"] = data["__streamdata__"][:-1]
                 elif pdf is not None and not pdf.strict:
                     stream.seek(pstart, 0)
-                    data["__streamdata__"] = read_unsized_from_steam(stream, pdf)
+                    data["__streamdata__"] = read_unsized_from_stream(stream, pdf)
                     pos = stream.tell()
                 else:
                     stream.seek(pos, 0)
@@ -631,7 +631,7 @@ def insert_child(
         child: Any,
         before: Any,
         pdf: PdfWriterProtocol,
-        inc_parent_counter: Optional[Callable] = None,
+        inc_parent_counter: Optional[Callable[..., Any]] = None,
     ) -> IndirectObject:
         if inc_parent_counter is None:
             inc_parent_counter = self.inc_parent_counter_default
diff --git a/pyproject.toml b/pyproject.toml
index 6d3021745e..7ab3c384d8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -225,6 +225,7 @@ wrap-descriptions = 0
 show_error_codes = true
 ignore_missing_imports = true
 check_untyped_defs = true
+disallow_any_generics = true
 disallow_untyped_defs = true
 disallow_incomplete_defs = true
 warn_redundant_casts = true
diff --git a/requirements/ci-3.11.txt b/requirements/ci-3.11.txt
index 33143f5cd3..f382fe2b94 100644
--- a/requirements/ci-3.11.txt
+++ b/requirements/ci-3.11.txt
@@ -69,6 +69,8 @@ pytest-timeout==2.1.0
     # via -r requirements/ci.in
 pytest-xdist==3.3.1
     # via -r requirements/ci.in
+pyyaml==6.0.1
+    # via -r requirements/ci.in
 ruff==0.0.290
     # via -r requirements/ci.in
 typeguard==4.1.2
diff --git a/requirements/ci.in b/requirements/ci.in
index ff071d125c..4c14acc41e 100644
--- a/requirements/ci.in
+++ b/requirements/ci.in
@@ -17,3 +17,4 @@ pytest-cov
 typeguard
 types-dataclasses
 types-Pillow
+pyyaml
diff --git a/requirements/ci.txt b/requirements/ci.txt
index 0d28144261..ebb121aa68 100644
--- a/requirements/ci.txt
+++ b/requirements/ci.txt
@@ -83,6 +83,8 @@ pytest-timeout==2.1.0
     # via -r requirements/ci.in
 pytest-xdist==3.0.2
     # via -r requirements/ci.in
+pyyaml==6.0.1
+    # via -r requirements/ci.in
 six==1.16.0
     # via flake8-print
 tomli==1.2.3
diff --git a/tests/__init__.py b/tests/__init__.py
index c9f4dc3ddd..d81f2c94cc 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -1,13 +1,16 @@
+import concurrent.futures
 import ssl
 import urllib.request
 from pathlib import Path
-from typing import List
+from typing import Dict, List, Optional
 from urllib.error import HTTPError
 
+import yaml
+
 from pypdf.generic import DictionaryObject, IndirectObject
 
 
-def get_data_from_url(url: str, name: str) -> bytes:
+def get_data_from_url(url: Optional[str] = None, name: Optional[str] = None) -> bytes:
     """
     Download a File from a URL and return its contents.
 
@@ -22,28 +25,33 @@ def get_data_from_url(url: str, name: str) -> bytes:
     Returns:
         Read File as bytes
     """
-    if url.startswith("file://"):
-        with open(url[7:].replace("\\", "/"), "rb") as fp:
-            return fp.read()
+    if name is None:
+        raise ValueError("A name must always be specified")
+
     cache_dir = Path(__file__).parent / "pdf_cache"
     if not cache_dir.exists():
         cache_dir.mkdir()
     cache_path = cache_dir / name
-    if not cache_path.exists():
-        ssl._create_default_https_context = ssl._create_unverified_context
-        cpt = 3
-        while cpt > 0:
-            try:
-                with urllib.request.urlopen(  # noqa: S310
-                    url
-                ) as response, cache_path.open("wb") as out_file:
-                    out_file.write(response.read())
-                cpt = 0
-            except HTTPError as e:
-                if cpt > 0:
-                    cpt -= 1
-                else:
-                    raise e
+
+    if url is not None:
+        if url.startswith("file://"):
+            with open(url[7:].replace("\\", "/"), "rb") as fp:
+                return fp.read()
+        if not cache_path.exists():
+            ssl._create_default_https_context = ssl._create_unverified_context
+            cpt = 3
+            while cpt > 0:
+                try:
+                    with urllib.request.urlopen(  # noqa: S310
+                        url
+                    ) as response, cache_path.open("wb") as out_file:
+                        out_file.write(response.read())
+                    cpt = 0
+                except HTTPError as e:
+                    if cpt > 0:
+                        cpt -= 1
+                    else:
+                        raise e
     with open(cache_path, "rb") as fp:
         data = fp.read()
     return data
@@ -106,12 +114,32 @@ def is_sublist(child_list, parent_list):
     return is_sublist(child_list, parent_list[1:])
 
 
+def read_yaml_to_list_of_dicts(yaml_file: Path) -> List[Dict[str, str]]:
+    with open(yaml_file) as yaml_input:
+        data = yaml.safe_load(yaml_input)
+    return data
+
+
 def download_test_pdfs():
     """
     Run this before the tests are executed to ensure you have everything locally.
 
     This is especially important to avoid pytest timeouts.
     """
-    pdfs = [("https://arxiv.org/pdf/2201.00214.pdf", "2201.00214.pdf")]
-    for url, name in pdfs:
-        get_data_from_url(url, name=name)
+    pdfs = read_yaml_to_list_of_dicts(Path(__file__).parent / "example_files.yaml")
+
+    with concurrent.futures.ThreadPoolExecutor(max_workers=20) as executor:
+        futures = [
+            executor.submit(get_data_from_url, pdf["url"], name=pdf["local_filename"])
+            for pdf in pdfs
+        ]
+        concurrent.futures.wait(futures)
+
+
+def test_csv_consistency():
+    pdfs = read_yaml_to_list_of_dicts(Path(__file__).parent / "example_files.csv")
+    # Ensure the names are unique
+    assert len(pdfs) == len({pdf["name"] for pdf in pdfs})
+
+    # Ensure the urls are unique
+    assert len(pdfs) == len({pdf["url"] for pdf in pdfs})
diff --git a/tests/example_files.yaml b/tests/example_files.yaml
new file mode 100644
index 0000000000..f12a784449
--- /dev/null
+++ b/tests/example_files.yaml
@@ -0,0 +1,112 @@
+- local_filename: 2201.00214.pdf
+  url: https://arxiv.org/pdf/2201.00214.pdf
+- local_filename: ASurveyofImageClassificationBasedTechniques.pdf
+  url: https://raw.githubusercontent.com/xyegithub/myBlog/12127c712ac2008782616c743224b187a4069477/posts/c94b2364/paper_pdfs/ImageClassification/2007%2CASurveyofImageClassificationBasedTechniques.pdf
+- local_filename: Giacalone.pdf
+  url: https://github.com/yxj-HGNwmb5kdp8ewr/yxj-HGNwmb5kdp8ewr.github.io/raw/master/files/Giacalone%20Llobell%20Jaeger%20(2022)%20Food%20Qual%20Prefer.pdf
+- local_filename: iss1718.pdf
+  url: https://github.com/py-pdf/pypdf/files/10983477/Ballinasloe_WS.pdf
+- local_filename: iss2077.pdf
+  url: https://github.com/py-pdf/pypdf/files/12309492/example_134.pdf
+- local_filename: pdf_font_garbled.pdf
+  url: https://github.com/py-pdf/pypdf/files/11219022/pdf_font_garbled.pdf
+- local_filename: The%20lean%20times%20in%20the%20Peruvian%20economy.pdf
+  url: https://github.com/alexanderquispe/1REI05/raw/main/reports/report_1/The%20lean%20times%20in%20the%20Peruvian%20economy.pdf
+- local_filename: tika-908104.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf
+- local_filename: tika-923406.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/923/923406.pdf
+- local_filename: tika-955562.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/955/955562.pdf
+- local_filename: tika-959173.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf
+- local_filename: waarom-meisjes-het-beter-doen-op-HAVO-en-VWO-ROA.pdf
+  url: https://github.com/py-pdf/pypdf/files/10773829/waarom-meisjes-het-beter-doen-op-HAVO-en-VWO-ROA.pdf
+- local_filename: tika-957144.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/957/957144.pdf
+- local_filename: ascii charset.pdf
+  url: https://github.com/py-pdf/pypdf/files/9472500/main.pdf
+- local_filename: cmap1370.pdf
+  url: https://github.com/py-pdf/pypdf/files/9667138/cmap1370.pdf
+- local_filename: 02voc.pdf
+  url: https://github.com/py-pdf/pypdf/files/9712729/02voc.pdf
+- local_filename: iss1533.pdf
+  url: https://github.com/py-pdf/pypdf/files/10376149/iss1533.pdf
+- local_filename: tstUCS2.pdf
+  url: https://github.com/py-pdf/pypdf/files/11190189/pdf_font_garbled.pdf
+- local_filename: tst-GBK_EUC.pdf
+  url: https://github.com/py-pdf/pypdf/files/11315397/3.pdf
+- local_filename: math_latex.pdf
+  url: https://github.com/py-pdf/pypdf/files/12163370/math-in-text-created-via-latex.pdf
+- local_filename: unixxx_glyphs.pdf
+  url: https://arxiv.org/pdf/2201.00021.pdf
+- local_filename: TextAttack_paper.pdf
+  url: https://arxiv.org/pdf/2005.05909.pdf
+- local_filename: iss2173.pdf
+  url: https://github.com/py-pdf/pypdf/files/12552700/tt.pdf
+- local_filename: iss2290.pdf
+  url: https://github.com/py-pdf/pypdf/files/13452885/example.pdf
+- local_filename: NewJersey.pdf
+  url: https://github.com/py-pdf/pypdf/files/12090692/New.Jersey.Coinbase.staking.securities.charges.2023-0606_Coinbase-Penalty-and-C-D.pdf
+- local_filename: tika-952445.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/952/952445.pdf
+- local_filename: tika-921632.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/921/921632.pdf
+- local_filename: tika-976970.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/976/976970.pdf
+- local_filename: tika-914102.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/914/914102.pdf
+- local_filename: iss1737.pdf
+  url: https://github.com/py-pdf/pypdf/files/11068604/tt1.pdf
+- local_filename: issue-1801.pdf
+  url: https://github.com/py-pdf/pypdf/files/11250359/test_img.pdf
+- local_filename: tika-924546.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf
+- local_filename: tika-924546.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf
+- local_filename: issue-1801.png
+  url: https://user-images.githubusercontent.com/1658117/232842886-9d1b0726-3a5b-430d-8464-595d919c266c.png
+- local_filename: grimm10
+  url: https://github.com/py-pdf/pypdf/files/11336817/grimm10.pdf
+- local_filename: labeled-edges-center-image.png
+  url: https://user-images.githubusercontent.com/4083478/236685544-a1940b06-fb42-4bb1-b589-1e4ad429d68e.png
+- local_filename: pdf_font_garbled.pdf
+  url: https://github.com/py-pdf/pypdf/files/11219022/pdf_font_garbled.pdf
+- local_filename: watermark1.png
+  url: https://user-images.githubusercontent.com/4083478/236793172-09340aef-3440-4c8a-af85-a91cdad27d46.png
+- local_filename: tika-977609.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/977/977609.pdf
+- local_filename: tifimage.png
+  url: https://user-images.githubusercontent.com/4083478/236793166-288b4b59-dee3-49fd-a04e-410aab06199a.png
+- local_filename: tika-972174.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/972/972174.pdf
+- local_filename: tika-972174_p0-im0.png
+  url: https://user-images.githubusercontent.com/4083478/238288207-b77dd38c-34b4-4f4f-810a-bf9db7ca0414.png
+- local_filename: Vitocal.pdf
+  url: https://github.com/py-pdf/pypdf/files/11962229/DB-5368770_Vitocal_200-G.pdf
+- local_filename: VitocalImage.png
+  url: https://user-images.githubusercontent.com/4083478/251283945-38c5b92c-cf94-473c-bb57-a51b74fc39be.jpg
+- local_filename: cmyk_deflate.pdf
+  url: https://github.com/py-pdf/pypdf/files/12078533/cmyk2.pdf
+- local_filename: cmyk_deflate.tif
+  url: https://github.com/py-pdf/pypdf/files/12078556/cmyk.tif.txt
+- local_filename: o1whh9b3.pdf
+  url: https://github.com/py-pdf/pypdf/files/11578953/USC.EMBA.-.Pre-Season.and.Theme.I.pdf
+- local_filename: selbst.72916.pdf
+  url: https://www.selbst.de/paidcontent/dl/64733/72916
+- local_filename: iss1912.pdf
+  url: https://github.com/py-pdf/pypdf/files/11845099/GeoTopo-komprimiert.pdf
+- local_filename: calRGB.pdf
+  url: https://github.com/py-pdf/pypdf/files/12061061/tt.pdf
+- local_filename: 2023USDC.pdf
+  url: https://github.com/py-pdf/pypdf/files/12090523/2023.USDC_Circle.Examination.Report.May.2023.pdf
+- local_filename: iss1982_im1.png
+  url: https://github.com/py-pdf/pypdf/files/12144094/im1.png.txt
+- local_filename: iss1982_im2.png
+  url: https://github.com/py-pdf/pypdf/files/12144093/im2.png.txt
+- local_filename: tika-972174.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/972/972174.pdf
+- local_filename: usa.png
+  url: https://github.com/py-pdf/pypdf/assets/4083478/56c93021-33cd-4387-ae13-5cbe7e673f42
+- local_filename: paid.pdf
+  url: https://github.com/py-pdf/pypdf/files/12050253/tt.pdf
diff --git a/tests/test_cmap.py b/tests/test_cmap.py
index 09cac1bb59..3c11508950 100644
--- a/tests/test_cmap.py
+++ b/tests/test_cmap.py
@@ -17,24 +17,24 @@
     [
         # compute_space_width:
         (
-            "https://corpora.tika.apache.org/base/docs/govdocs1/923/923406.pdf",
+            None,
             "tika-923406.pdf",
             False,
         ),
         # _parse_to_unicode_process_rg:
         (
-            "https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf",
+            None,
             "tika-959173.pdf",
             False,
         ),
         (
-            "https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf",
+            None,
             "tika-959173.pdf",
             True,
         ),
         # issue #1718:
         (
-            "https://github.com/py-pdf/pypdf/files/10983477/Ballinasloe_WS.pdf",
+            None,
             "iss1718.pdf",
             False,
         ),
@@ -53,27 +53,24 @@ def test_text_extraction_slow(caplog, url: str, name: str, strict: bool):
     [
         # bfchar_on_2_chars: issue #1293
         (
-            "https://raw.githubusercontent.com/xyegithub/myBlog/12127c712ac2008782616c743224b187a4069477/posts/"
-            "c94b2364/paper_pdfs/ImageClassification/2007%2CASurveyofImageClassificationBasedTechniques.pdf",
+            None,
             "ASurveyofImageClassificationBasedTechniques.pdf",
             False,
         ),
         # L40, get_font_width_from_default
         (
-            "https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf",
+            None,
             "tika-908104.pdf",
             False,
         ),
         # multiline_bfrange / regression test for issue #1285:
         (
-            "https://github.com/alexanderquispe/1REI05/raw/main/reports/report_1/"
-            "The%20lean%20times%20in%20the%20Peruvian%20economy.pdf",
+            None,
             "The%20lean%20times%20in%20the%20Peruvian%20economy.pdf",
             False,
         ),
         (
-            "https://github.com/yxj-HGNwmb5kdp8ewr/yxj-HGNwmb5kdp8ewr.github.io/raw/master/files/"
-            "Giacalone%20Llobell%20Jaeger%20(2022)%20Food%20Qual%20Prefer.pdf",
+            None,
             "Giacalone.pdf",
             False,
         ),
@@ -89,10 +86,7 @@ def test_text_extraction_fast(caplog, url: str, name: str, strict: bool):
 
 @pytest.mark.enable_socket()
 def test_parse_encoding_advanced_encoding_not_implemented():
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/957/957144.pdf"
-    name = "tika-957144.pdf"
-
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-957144.pdf")))
     with pytest.warns(PdfReadWarning, match="Advanced encoding .* not implemented yet"):
         for page in reader.pages:
             page.extract_text()
@@ -100,10 +94,8 @@ def test_parse_encoding_advanced_encoding_not_implemented():
 
 @pytest.mark.enable_socket()
 def test_ascii_charset():
-    # iss #1312
-    url = "https://github.com/py-pdf/pypdf/files/9472500/main.pdf"
-    name = "ascii charset.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    # Issue #1312
+    reader = PdfReader(BytesIO(get_data_from_url(name="ascii charset.pdf")))
     assert "/a" not in reader.pages[0].extract_text()
 
 
@@ -112,13 +104,13 @@ def test_ascii_charset():
     ("url", "name", "page_nb", "within_text"),
     [
         (
-            "https://github.com/py-pdf/pypdf/files/9667138/cmap1370.pdf",
+            None,
             "cmap1370.pdf",
             0,
             "",
         ),
         (
-            "https://github.com/py-pdf/pypdf/files/9712729/02voc.pdf",
+            None,
             "02voc.pdf",
             2,
             "Document delineation and character sequence decoding",
@@ -135,9 +127,7 @@ def test_text_extraction_of_specific_pages(
 
 @pytest.mark.enable_socket()
 def test_iss1533():
-    url = "https://github.com/py-pdf/pypdf/files/10376149/iss1533.pdf"
-    name = "iss1533.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss1533.pdf")))
     reader.pages[0].extract_text()  # no error
     assert build_char_map("/F", 200, reader.pages[0])[3]["\x01"] == "Ü"
 
@@ -147,14 +137,14 @@ def test_iss1533():
     ("url", "name", "page_index", "within_text", "caplog_text"),
     [
         (
-            "https://github.com/py-pdf/pypdf/files/11190189/pdf_font_garbled.pdf",
+            None,
             "tstUCS2.pdf",
             1,
             ["2 / 12", "S0490520090001", "于博"],
             "",
         ),
         (
-            "https://github.com/py-pdf/pypdf/files/11315397/3.pdf",
+            None,
             "tst-GBK_EUC.pdf",
             0,
             ["NJA", "中华男科学杂志"],
@@ -172,9 +162,7 @@ def test_cmap_encodings(caplog, url, name, page_index, within_text, caplog_text)
 
 @pytest.mark.enable_socket()
 def test_latex():
-    url = "https://github.com/py-pdf/pypdf/files/12163370/math-in-text-created-via-latex.pdf"
-    name = "math_latex.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="math_latex.pdf")))
     txt = reader.pages[0].extract_text()  # no error
     for pat in ("α", "β", "γ", "ϕ", "φ", "ℏ", "∫", "∂", "·", "×"):
         assert pat in txt
@@ -183,9 +171,7 @@ def test_latex():
 
 @pytest.mark.enable_socket()
 def test_unixxx_glyphs():
-    url = "https://arxiv.org/pdf/2201.00021.pdf"
-    name = "unixxx_glyphs.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="unixxx_glyphs.pdf")))
     txt = reader.pages[0].extract_text()  # no error
     for pat in ("闫耀庭", "龚龑", "张江水", "1′′.2"):
         assert pat in txt
@@ -195,18 +181,22 @@ def test_unixxx_glyphs():
 def test_cmap_compute_space_width():
     # issue 2137
     # original file URL:
-    url = "https://arxiv.org/pdf/2005.05909.pdf"
+    # url = "https://arxiv.org/pdf/2005.05909.pdf"
     # URL from github issue is too long to pass code stype check, use original arxiv URL instead
     # url = "https://github.com/py-pdf/pypdf/files/12489914/Morris.et.al.-.2020.-.TextAttack.A.Framework.for.Adversarial.Attacks.Data.Augmentation.and.Adversarial.Training.in.NLP.pdf"
-    name = "TextAttack_paper.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="TextAttack_paper.pdf")))
     reader.pages[0].extract_text()  # no error
 
 
 @pytest.mark.enable_socket()
 def test_tabs_in_cmap():
     """Issue #2173"""
-    url = "https://github.com/py-pdf/pypdf/files/12552700/tt.pdf"
-    name = "iss2173.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss2173.pdf")))
+    reader.pages[0].extract_text()
+
+
+@pytest.mark.enable_socket()
+def test_ignoring_non_put_entries():
+    """Issue #2290"""
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss2290.pdf")))
     reader.pages[0].extract_text()
diff --git a/tests/test_filters.py b/tests/test_filters.py
index 00a548ab00..873e7a957d 100644
--- a/tests/test_filters.py
+++ b/tests/test_filters.py
@@ -142,9 +142,7 @@ def test_decode_ahx():
     See #1979
     Gray Image in CMYK : requiring reverse
     """
-    url = "https://github.com/py-pdf/pypdf/files/12090692/New.Jersey.Coinbase.staking.securities.charges.2023-0606_Coinbase-Penalty-and-C-D.pdf"
-    name = "NewJersey.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="NewJersey.pdf")))
     for p in reader.pages:
         _ = list(p.images.keys())
 
@@ -231,9 +229,7 @@ def test_ccitt_fax_decode():
 @pytest.mark.enable_socket()
 @patch("pypdf._reader.logger_warning")
 def test_decompress_zlib_error(mock_logger_warning):
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/952/952445.pdf"
-    name = "tika-952445.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-952445.pdf")))
     for page in reader.pages:
         page.extract_text()
     mock_logger_warning.assert_called_with(
@@ -243,9 +239,7 @@ def test_decompress_zlib_error(mock_logger_warning):
 
 @pytest.mark.enable_socket()
 def test_lzw_decode_neg1():
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/921/921632.pdf"
-    name = "tika-921632.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-921632.pdf")))
     page = reader.pages[47]
     with pytest.raises(PdfReadError) as exc:
         page.extract_text()
@@ -254,17 +248,13 @@ def test_lzw_decode_neg1():
 
 @pytest.mark.enable_socket()
 def test_issue_399():
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/976/976970.pdf"
-    name = "tika-976970.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-976970.pdf")))
     reader.pages[1].extract_text()
 
 
 @pytest.mark.enable_socket()
 def test_image_without_pillow(tmp_path):
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/914/914102.pdf"
     name = "tika-914102.pdf"
-    _ = get_data_from_url(url, name=name)
     pdf_path = Path(__file__).parent / "pdf_cache" / name
     pdf_path_str = str(pdf_path.resolve()).replace("\\", "/")
 
@@ -304,9 +294,7 @@ def test_image_without_pillow(tmp_path):
 
 @pytest.mark.enable_socket()
 def test_issue_1737():
-    url = "https://github.com/py-pdf/pypdf/files/11068604/tt1.pdf"
-    name = "iss1737.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss1737.pdf")))
     reader.pages[0]["/Resources"]["/XObject"]["/Im0"].get_data()
     reader.pages[0]["/Resources"]["/XObject"]["/Im1"].get_data()
     reader.pages[0]["/Resources"]["/XObject"]["/Im2"].get_data()
@@ -319,9 +307,7 @@ def test_pa_image_extraction():
 
     This is a regression test for issue #1801
     """
-    url = "https://github.com/py-pdf/pypdf/files/11250359/test_img.pdf"
-    name = "issue-1801.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="issue-1801.pdf")))
 
     page0 = reader.pages[0]
     images = page0.images
@@ -329,20 +315,14 @@ def test_pa_image_extraction():
     assert images[0].name == "Im1.png"
 
     # Ensure visual appearence
-    data = get_data_from_url(
-        "https://user-images.githubusercontent.com/"
-        "1658117/232842886-9d1b0726-3a5b-430d-8464-595d919c266c.png",
-        "issue-1801.png",
-    )
+    data = get_data_from_url(name="issue-1801.png")
     assert data == images[0].data
 
 
 @pytest.mark.enable_socket()
 def test_1bit_image_extraction():
     """Cf issue #1814"""
-    url = "https://github.com/py-pdf/pypdf/files/11336817/grimm10.pdf"
-    name = "grimm10"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="grimm10")))
     for p in reader.pages:
         p.images
 
@@ -352,9 +332,9 @@ def test_png_transparency_reverse():
     """Cf issue #1599"""
     pdf_path = RESOURCE_ROOT / "labeled-edges-center-image.pdf"
     reader = PdfReader(pdf_path)
-    url_png = "https://user-images.githubusercontent.com/4083478/236685544-a1940b06-fb42-4bb1-b589-1e4ad429d68e.png"
-    name_png = "labeled-edges-center-image.png"
-    _refimg = Image.open(BytesIO(get_data_from_url(url_png, name=name_png)))
+    _refimg = Image.open(
+        BytesIO(get_data_from_url(name="labeled-edges-center-image.png"))
+    )
     data = reader.pages[0].images[0]
     _img = Image.open(BytesIO(data.data))
     assert ".jp2" in data.name
@@ -364,12 +344,8 @@ def test_png_transparency_reverse():
 @pytest.mark.enable_socket()
 def test_iss1787():
     """Cf issue #1787"""
-    url = "https://github.com/py-pdf/pypdf/files/11219022/pdf_font_garbled.pdf"
-    name = "pdf_font_garbled.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
-    url_png = "https://user-images.githubusercontent.com/4083478/236793172-09340aef-3440-4c8a-af85-a91cdad27d46.png"
-    name_png = "watermark1.png"
-    refimg = Image.open(BytesIO(get_data_from_url(url_png, name=name_png)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="pdf_font_garbled.pdf")))
+    refimg = Image.open(BytesIO(get_data_from_url(name="watermark1.png")))
     data = reader.pages[0].images[0]
     img = Image.open(BytesIO(data.data))
     assert ".png" in data.name
@@ -385,12 +361,8 @@ def test_iss1787():
 @pytest.mark.enable_socket()
 def test_tiff_predictor():
     """Decode Tiff Predictor 2 Images"""
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/977/977609.pdf"
-    name = "tika-977609.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
-    url_png = "https://user-images.githubusercontent.com/4083478/236793166-288b4b59-dee3-49fd-a04e-410aab06199a.png"
-    name_png = "tifimage.png"
-    refimg = Image.open(BytesIO(get_data_from_url(url_png, name=name_png)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-977609.pdf")))
+    refimg = Image.open(BytesIO(get_data_from_url(name="tifimage.png")))
     data = reader.pages[0].images[0]
     img = Image.open(BytesIO(data.data))
     assert ".png" in data.name
@@ -400,15 +372,11 @@ def test_tiff_predictor():
 @pytest.mark.enable_socket()
 def test_rgba():
     """Decode rgb with transparency"""
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/972/972174.pdf"
-    name = "tika-972174.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
-    url_png = "https://user-images.githubusercontent.com/4083478/238288207-b77dd38c-34b4-4f4f-810a-bf9db7ca0414.png"
-    name_png = "tika-972174_p0-im0.png"
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-972174.pdf")))
     data = reader.pages[0].images[0]
     assert ".jp2" in data.name
     similarity = image_similarity(
-        data.image, BytesIO(get_data_from_url(url_png, name=name_png))
+        data.image, BytesIO(get_data_from_url(name="tika-972174_p0-im0.png"))
     )
     assert similarity > 0.99
 
@@ -421,23 +389,15 @@ def test_cmyk():
         from Crypto.Cipher import AES  # noqa: F401
     except ImportError:
         return  # the file is encrypted
-    url = "https://github.com/py-pdf/pypdf/files/11962229/DB-5368770_Vitocal_200-G.pdf"
-    name = "Vitocal.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
-    url_png = "https://user-images.githubusercontent.com/4083478/251283945-38c5b92c-cf94-473c-bb57-a51b74fc39be.jpg"
-    name_png = "VitocalImage.png"
-    refimg = BytesIO(get_data_from_url(url_png, name=name_png))
+    reader = PdfReader(BytesIO(get_data_from_url(name="Vitocal.pdf")))
+    refimg = BytesIO(get_data_from_url(name="VitocalImage.png"))
     data = reader.pages[1].images[0]
     assert data.image.mode == "CMYK"
     assert ".jpg" in data.name
     assert image_similarity(data.image, refimg) > 0.99
     # deflate
-    url = "https://github.com/py-pdf/pypdf/files/12078533/cmyk2.pdf"
-    name = "cmyk_deflate.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
-    url_png = "https://github.com/py-pdf/pypdf/files/12078556/cmyk.tif.txt"
-    name_png = "cmyk_deflate.tif"
-    refimg = BytesIO(get_data_from_url(url_png, name=name_png))
+    reader = PdfReader(BytesIO(get_data_from_url(name="cmyk_deflate.pdf")))
+    refimg = BytesIO(get_data_from_url(name="cmyk_deflate.tif"))
     data = reader.pages[0].images[0]
     assert data.image.mode == "CMYK"
     assert ".tif" in data.name
@@ -447,9 +407,7 @@ def test_cmyk():
 @pytest.mark.enable_socket()
 def test_iss1863():
     """Test doc from iss1863"""
-    url = "https://github.com/py-pdf/pypdf/files/11578953/USC.EMBA.-.Pre-Season.and.Theme.I.pdf"
-    name = "o1whh9b3.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="o1whh9b3.pdf")))
     for p in reader.pages:
         for i in p.images:
             i.name
@@ -457,9 +415,7 @@ def test_iss1863():
 
 @pytest.mark.enable_socket()
 def test_read_images():
-    url = "https://www.selbst.de/paidcontent/dl/64733/72916"
-    name = "selbst.72916.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="selbst.72916.pdf")))
     page = reader.pages[0]
     for _ in page.images:
         pass
@@ -467,9 +423,7 @@ def test_read_images():
 
 @pytest.mark.enable_socket()
 def test_cascaded_filters_images():
-    url = "https://github.com/py-pdf/pypdf/files/11845099/GeoTopo-komprimiert.pdf"
-    name = "iss1912.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss1912.pdf")))
     # for focus, analyse the page 23
     for p in reader.pages:
         for i in p.images:
@@ -478,40 +432,28 @@ def test_cascaded_filters_images():
 
 @pytest.mark.enable_socket()
 def test_calrgb():
-    url = "https://github.com/py-pdf/pypdf/files/12061061/tt.pdf"
-    name = "calRGB.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="calRGB.pdf")))
     reader.pages[0].images[0]
 
 
 @pytest.mark.enable_socket()
 def test_index_lookup():
     """The lookup is provided as an str and bytes"""
-    url = "https://github.com/py-pdf/pypdf/files/12090523/2023.USDC_Circle.Examination.Report.May.2023.pdf"
-    name = "2023USDC.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="2023USDC.pdf")))
     # TextStringObject Lookup
-    url_png = "https://github.com/py-pdf/pypdf/files/12144094/im1.png.txt"
-    name_png = "iss1982_im1.png"
-    refimg = BytesIO(get_data_from_url(url_png, name=name_png))
+    refimg = BytesIO(get_data_from_url(name="iss1982_im1.png"))
     data = reader.pages[0].images[-1]
     assert data.image.mode == "RGB"
     assert image_similarity(data.image, refimg) > 0.999
     # ByteStringObject Lookup
-    url_png = "https://github.com/py-pdf/pypdf/files/12144093/im2.png.txt"
-    name_png = "iss1982_im2.png"
-    refimg = BytesIO(get_data_from_url(url_png, name=name_png))
+    refimg = BytesIO(get_data_from_url(name="iss1982_im2.png"))
     data = reader.pages[-1].images[-1]
     assert data.image.mode == "RGB"
     assert image_similarity(data.image, refimg) > 0.999
     # indexed CMYK images
     # currently with a  TODO as we convert to RBG the palette
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/972/972174.pdf"
-    name = "tika-972174.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
-    url_png = "https://github.com/py-pdf/pypdf/assets/4083478/56c93021-33cd-4387-ae13-5cbe7e673f42"
-    name_png = "usa.png"
-    refimg = Image.open(BytesIO(get_data_from_url(url_png, name=name_png)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-972174.pdf")))
+    refimg = Image.open(BytesIO(get_data_from_url(name="usa.png")))
     data = reader.pages[0].images["/Im3"]
     # assert data.image.mode == "PA" but currently "RGBA"
     assert image_similarity(data.image, refimg) > 0.999
@@ -520,9 +462,7 @@ def test_index_lookup():
 @pytest.mark.enable_socket()
 def test_2bits_image():
     """From #1954, test with 2bits image. TODO: 4bits also"""
-    url = "https://github.com/py-pdf/pypdf/files/12050253/tt.pdf"
-    name = "paid.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="paid.pdf")))
     url_png = "https://user-images.githubusercontent.com/4083478/253568117-ca95cc85-9dea-4145-a5e0-032f1c1aa322.png"
     name_png = "Paid.png"
     refimg = BytesIO(get_data_from_url(url_png, name=name_png))
@@ -649,3 +589,12 @@ def test_flate_decode_with_image_mode_1():
     reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
     for image in reader.pages[7].images:
         _ = image
+
+
+@pytest.mark.enable_socket()
+def test_flate_decode_with_image_mode_1__whitespace_at_end_of_lookup():
+    """From #2331"""
+    url = "https://github.com/py-pdf/pypdf/files/13611048/out1.pdf"
+    name = "issue2331.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader.pages[0].images[0]
diff --git a/tests/test_images.py b/tests/test_images.py
index 9e03c9f352..3e9e8a034e 100644
--- a/tests/test_images.py
+++ b/tests/test_images.py
@@ -105,9 +105,8 @@ def test_image_similarity_mid():
 
 @pytest.mark.enable_socket()
 def test_image_new_property():
-    url = "https://github.com/py-pdf/pypdf/files/11219022/pdf_font_garbled.pdf"
     name = "pdf_font_garbled.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name=name)))
     assert reader.pages[0].images.keys() == [
         "/I0",
         "/I1",
@@ -215,8 +214,22 @@ def test_image_extraction(src, page_index, image_key, expected):
 @pytest.mark.timeout(30)
 def test_loop_in_image_keys():
     """Cf #2077"""
-    url = "https://github.com/py-pdf/pypdf/files/12309492/example_134.pdf"
-    name = "iss2077.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss2077.pdf")))
     reader.pages[0]["/Resources"]["/XObject"][NameObject("/toto")] = NullObject()
     reader.pages[0].images.keys()
+
+
+@pytest.mark.enable_socket()
+def test_devicen_cmyk_black_only():
+    """Cf #2321"""
+    url = "https://github.com/py-pdf/pypdf/files/13501846/Addressing_Adversarial_Attacks.pdf"
+    name = "iss2321.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    url = "https://github.com/py-pdf/pypdf/assets/4083478/cc2dabc1-86e6-4179-a8a4-2b0efea124be"
+    name = "iss2321_img0.pdf"
+    img = Image.open(BytesIO(get_data_from_url(url, name=name)))
+    assert image_similarity(reader.pages[5].images[0].image, img) >= 0.99
+    url = "https://github.com/py-pdf/pypdf/assets/4083478/6b64a949-42be-40d5-9eea-95707f350d89"
+    name = "iss2321_img1.pdf"
+    img = Image.open(BytesIO(get_data_from_url(url, name=name)))
+    assert image_similarity(reader.pages[10].images[0].image, img) >= 0.99
diff --git a/tests/test_page.py b/tests/test_page.py
index 8df25ad465..1c388c426a 100644
--- a/tests/test_page.py
+++ b/tests/test_page.py
@@ -129,9 +129,11 @@ def test_page_operations(pdf_path, password):
         (175, 680, 844),
         (45, 994, 994),
         (-80, 888, 742),
-    ]
+    ],
 )
-def test_mediabox_expansion_after_rotation(angle: float, expected_width: int, expected_height: int):
+def test_mediabox_expansion_after_rotation(
+    angle: float, expected_width: int, expected_height: int
+):
     """
     Mediabox dimensions after rotation at a non-right angle with expension are correct.
 
diff --git a/tests/test_page_labels.py b/tests/test_page_labels.py
index 8b2e11b0da..1eb6f6aab4 100644
--- a/tests/test_page_labels.py
+++ b/tests/test_page_labels.py
@@ -70,9 +70,8 @@ def test_number2uppercase_letter():
 
 @pytest.mark.enable_socket()
 def test_index2label(caplog):
-    url = "https://github.com/py-pdf/pypdf/files/10773829/waarom-meisjes-het-beter-doen-op-HAVO-en-VWO-ROA.pdf"
     name = "waarom-meisjes-het-beter-doen-op-HAVO-en-VWO-ROA.pdf"
-    r = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    r = PdfReader(BytesIO(get_data_from_url(name=name)))
     assert index2label(r, 1) == "ii"
     assert index2label(r, 9) == "6"
     # very silly data to get test cover
diff --git a/tests/test_reader.py b/tests/test_reader.py
index b252e48f90..555a3b2fe7 100644
--- a/tests/test_reader.py
+++ b/tests/test_reader.py
@@ -1027,17 +1027,13 @@ def test_header(src, pdf_header):
 
 @pytest.mark.enable_socket()
 def test_outline_color():
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf"
-    name = "tika-924546.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-924546.pdf")))
     assert reader.outline[0].color == [0, 0, 1]
 
 
 @pytest.mark.enable_socket()
 def test_outline_font_format():
-    url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf"
-    name = "tika-924546.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader = PdfReader(BytesIO(get_data_from_url(name="tika-924546.pdf")))
     assert reader.outline[0].font_format == 2
 
 
diff --git a/tests/test_xmp.py b/tests/test_xmp.py
index e01e5c6fde..f864a9df9d 100644
--- a/tests/test_xmp.py
+++ b/tests/test_xmp.py
@@ -118,7 +118,7 @@ def test_identity_function(x):
     ("url", "name", "xmpmm_instance_id"),
     [
         (
-            "https://corpora.tika.apache.org/base/docs/govdocs1/955/955562.pdf",
+            None,
             "tika-955562.pdf",
             "uuid:ca96e032-c2af-49bd-a71c-95889bafbf1d",
         )