diff --git a/MANIFEST.in b/MANIFEST.in
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -3,4 +3,4 @@
 include version.txt
 include README.md
 recursive-include swh py.typed
-recursive-include swh/scanner/tests/data/ *
+recursive-include swh/scanner/tests/data/ *.tgz
diff --git a/swh/scanner/tests/conftest.py b/swh/scanner/tests/conftest.py
--- a/swh/scanner/tests/conftest.py
+++ b/swh/scanner/tests/conftest.py
@@ -7,6 +7,8 @@
 import asyncio
 import aiohttp
 import os
+import shutil
+
 from pathlib import PosixPath
 from aioresponses import aioresponses  # type: ignore
 
@@ -121,12 +123,14 @@
 
 
 @pytest.fixture
-def test_folder():
+def test_sample_folder(datadir, tmp_path):
     """Location of the "data" folder """
-    tests_path = PosixPath(os.path.abspath(__file__)).parent
-    tests_data_folder = tests_path.joinpath("data")
-    assert tests_data_folder.exists()
-    return tests_data_folder
+    archive_path = PosixPath(os.path.join(datadir, "sample-folder.tgz"))
+    assert archive_path.exists()
+    shutil.unpack_archive(archive_path, extract_dir=tmp_path)
+    test_sample_folder = PosixPath(os.path.join(tmp_path, "sample-folder"))
+    assert test_sample_folder.exists()
+    return test_sample_folder
 
 
 @pytest.fixture(scope="session")
diff --git a/swh/scanner/tests/data/sample-folder.tgz b/swh/scanner/tests/data/sample-folder.tgz
new file mode 100644
index 0000000000000000000000000000000000000000..0000000000000000000000000000000000000000
GIT binary patch
literal 0
Hc$@<O00001

literal 0
Hc$@<O00001

diff --git a/swh/scanner/tests/data/sample-folder/bar/barfoo/another-quote.org b/swh/scanner/tests/data/sample-folder/bar/barfoo/another-quote.org
deleted file mode 100644
--- a/swh/scanner/tests/data/sample-folder/bar/barfoo/another-quote.org
+++ /dev/null
@@ -1,2 +0,0 @@
-A Victory without danger is a triumph without glory.
--- Pierre Corneille
\ No newline at end of file
diff --git a/swh/scanner/tests/data/sample-folder/bar/barfoo2/some-file.txt b/swh/scanner/tests/data/sample-folder/bar/barfoo2/some-file.txt
deleted file mode 100644
--- a/swh/scanner/tests/data/sample-folder/bar/barfoo2/some-file.txt
+++ /dev/null
@@ -1 +0,0 @@
-this is a file.
diff --git a/swh/scanner/tests/data/sample-folder/foo/barfoo b/swh/scanner/tests/data/sample-folder/foo/barfoo
deleted file mode 120000
--- a/swh/scanner/tests/data/sample-folder/foo/barfoo
+++ /dev/null
@@ -1 +0,0 @@
-bar/barfoo
\ No newline at end of file
diff --git a/swh/scanner/tests/data/sample-folder/foo/quotes.md b/swh/scanner/tests/data/sample-folder/foo/quotes.md
deleted file mode 100644
--- a/swh/scanner/tests/data/sample-folder/foo/quotes.md
+++ /dev/null
@@ -1 +0,0 @@
-Shoot for the moon. Even if you miss, you'll land among the stars.
\ No newline at end of file
diff --git a/swh/scanner/tests/data/sample-folder/foo/rel-link-to-barfoo b/swh/scanner/tests/data/sample-folder/foo/rel-link-to-barfoo
deleted file mode 120000
--- a/swh/scanner/tests/data/sample-folder/foo/rel-link-to-barfoo
+++ /dev/null
@@ -1 +0,0 @@
-../bar/barfoo
\ No newline at end of file
diff --git a/swh/scanner/tests/data/sample-folder/link-to-another-quote b/swh/scanner/tests/data/sample-folder/link-to-another-quote
deleted file mode 120000
--- a/swh/scanner/tests/data/sample-folder/link-to-another-quote
+++ /dev/null
@@ -1 +0,0 @@
-bar/barfoo/another-quote.org
\ No newline at end of file
diff --git a/swh/scanner/tests/data/sample-folder/link-to-foo b/swh/scanner/tests/data/sample-folder/link-to-foo
deleted file mode 120000
--- a/swh/scanner/tests/data/sample-folder/link-to-foo
+++ /dev/null
@@ -1 +0,0 @@
-foo
\ No newline at end of file
diff --git a/swh/scanner/tests/data/sample-folder/some-binary b/swh/scanner/tests/data/sample-folder/some-binary
deleted file mode 100755
--- a/swh/scanner/tests/data/sample-folder/some-binary
+++ /dev/null
@@ -1 +0,0 @@
-exec
diff --git a/swh/scanner/tests/data/sample-folder/toexclude/example.txt b/swh/scanner/tests/data/sample-folder/toexclude/example.txt
deleted file mode 100644
--- a/swh/scanner/tests/data/sample-folder/toexclude/example.txt
+++ /dev/null
@@ -1 +0,0 @@
-example file
diff --git a/swh/scanner/tests/test_scanner.py b/swh/scanner/tests/test_scanner.py
--- a/swh/scanner/tests/test_scanner.py
+++ b/swh/scanner/tests/test_scanner.py
@@ -5,7 +5,6 @@
 
 import pytest
 import json
-from pathlib import PosixPath
 
 from .data import correct_api_response, present_swhids, to_exclude_swhid
 
@@ -70,13 +69,11 @@
     assert not app.debug
 
 
-def test_scanner_result(live_server, event_loop, test_folder):
+def test_scanner_result(live_server, event_loop, test_sample_folder):
     api_url = live_server.url() + "/"
 
-    sample_folder = test_folder.joinpath(PosixPath("sample-folder"))
-
-    source_tree = Tree(sample_folder)
-    event_loop.run_until_complete(run(sample_folder, api_url, source_tree, set()))
+    source_tree = Tree(test_sample_folder)
+    event_loop.run_until_complete(run(test_sample_folder, api_url, source_tree, set()))
 
     for child_node in source_tree.iterate():
         node_info = list(child_node.attributes.values())[0]
@@ -86,19 +83,19 @@
             assert node_info["known"] is False
 
 
-def test_scanner_result_with_exclude_patterns(live_server, event_loop, test_folder):
+def test_scanner_result_with_exclude_patterns(
+    live_server, event_loop, test_sample_folder
+):
     api_url = live_server.url() + "/"
 
-    sample_folder = test_folder.joinpath(PosixPath("sample-folder"))
-
-    patterns = (str(sample_folder) + "/toexclude",)
+    patterns = (str(test_sample_folder) + "/toexclude",)
     exclude_pattern = {
-        reg_obj for reg_obj in extract_regex_objs(sample_folder, patterns)
+        reg_obj for reg_obj in extract_regex_objs(test_sample_folder, patterns)
     }
 
-    source_tree = Tree(sample_folder)
+    source_tree = Tree(test_sample_folder)
     event_loop.run_until_complete(
-        run(sample_folder, api_url, source_tree, exclude_pattern)
+        run(test_sample_folder, api_url, source_tree, exclude_pattern)
     )
 
     for child_node in source_tree.iterate():