diff --git a/requirements/ci-3.11.txt b/requirements/ci-3.11.txt
index 33143f5cd..f382fe2b9 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 ff071d125..4c14acc41 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 0d2814426..ebb121aa6 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 c9f4dc3dd..d81f2c94c 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 000000000..f12a78444
--- /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 bf68d9e47..3c1150895 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
@@ -195,27 +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"""
-    url = "https://github.com/py-pdf/pypdf/files/13452885/example.pdf"
-    name = "iss2290.pdf"
-    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    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 00a548ab0..e38280244 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))
diff --git a/tests/test_images.py b/tests/test_images.py
index a309549e6..3e9e8a034 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",
@@ -215,9 +214,7 @@ 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()
 
diff --git a/tests/test_page_labels.py b/tests/test_page_labels.py
index 8b2e11b0d..1eb6f6aab 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 b252e48f9..555a3b2fe 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 e01e5c6fd..f864a9df9 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",
         )