chrismattmann
diff --git a/‎docs/source/_static/test-files/remote.html‎
Lines changed: 5 additions & 0 deletions b/‎docs/source/_static/test-files/remote.html‎
Lines changed: 5 additions & 0 deletions
diff --git a/‎docs/source/_static/test-files/remote.jpg‎
518 Bytes b/‎docs/source/_static/test-files/remote.jpg‎
518 Bytes
diff --git a/‎docs/source/_static/test-files/remote.mp3‎
44 Bytes b/‎docs/source/_static/test-files/remote.mp3‎
44 Bytes
diff --git a/‎docs/source/_static/test-files/remote.pdf‎
34.4 KB b/‎docs/source/_static/test-files/remote.pdf‎
34.4 KB
diff --git a/‎tests/conftest.py‎
Lines changed: 29 additions & 0 deletions b/‎tests/conftest.py‎
Lines changed: 29 additions & 0 deletions
diff --git a/‎tests/test_parser.py‎
Lines changed: 8 additions & 11 deletions b/‎tests/test_parser.py‎
Lines changed: 8 additions & 11 deletions
diff --git a/‎tika/__init__.py‎
Lines changed: 1 addition & 1 deletion b/‎tika/__init__.py‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎tika/tika.py‎
Lines changed: 1 addition & 1 deletion b/‎tika/tika.py‎
Lines changed: 1 addition & 1 deletion
@@ -0,0 +1,5 @@
+<!doctype html>
+<html lang="en">
+<head><meta charset="utf-8"><title>Tika Python Remote HTML Fixture</title></head>
+<body><main><h1>Tika Python Remote HTML Fixture</h1><p>This deterministic file is hosted by the tika-python documentation site for parser remote URL tests.</p></main></body>
+</html>
@@ -1,10 +1,39 @@
 # SPDX-License-Identifier: Apache-2.0
 
+from functools import partial
+from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
+import os
 from pathlib import Path
+import threading
 
 import pytest
 
+GITHUB_PAGES_REMOTE_FIXTURE_BASE_URL = (
+    "https://chrismattmann.github.io/tika-python/_static/test-files"
+)
+
 
 @pytest.fixture
 def test_file_path():
     return Path(__file__).parent / "files" / "rwservlet.pdf"
+
+
+@pytest.fixture(scope="session")
+def remote_fixture_base_url():
+    configured_url = os.getenv("TIKA_REMOTE_TEST_BASE_URL")
+    if configured_url:
+        yield configured_url.rstrip("/")
+        return
+
+    if not os.getenv("CI"):
+        yield GITHUB_PAGES_REMOTE_FIXTURE_BASE_URL
+        return
+
+    static_dir = Path(__file__).parents[1] / "docs" / "source" / "_static" / "test-files"
+    handler = partial(SimpleHTTPRequestHandler, directory=static_dir)
+
+    with ThreadingHTTPServer(("127.0.0.1", 0), handler) as httpd:
+        thread = threading.Thread(target=httpd.serve_forever, daemon=True)
+        thread.start()
+        yield f"http://127.0.0.1:{httpd.server_port}"
+        httpd.shutdown()
@@ -5,27 +5,24 @@
 from tika import parser
 
 
-def test_remote_pdf():
+def test_remote_pdf(remote_fixture_base_url):
     """parse remote PDF"""
-    assert parser.from_file(
-        "https://upload.wikimedia.org/wikipedia/commons/4/42/Article_feedback_flow_B_-_Thank_editors.pdf")
+    assert parser.from_file(f"{remote_fixture_base_url}/remote.pdf")
 
 
-def test_remote_html():
+def test_remote_html(remote_fixture_base_url):
     """parse remote HTML"""
-    assert parser.from_file("http://nossl.sh")
+    assert parser.from_file(f"{remote_fixture_base_url}/remote.html")
 
 
-def test_remote_mp3():
+def test_remote_mp3(remote_fixture_base_url):
     """parse remote mp3"""
-    assert parser.from_file(
-        "https://archive.org/download/Ainst-Spaceshipdemo.mp3/Ainst-Spaceshipdemo.mp3")
+    assert parser.from_file(f"{remote_fixture_base_url}/remote.mp3")
 
 
-def test_remote_jpg():
+def test_remote_jpg(remote_fixture_base_url):
     """parse remote jpg"""
-    assert parser.from_file(
-        "https://upload.wikimedia.org/wikipedia/commons/b/b7/X_logo.jpg")
+    assert parser.from_file(f"{remote_fixture_base_url}/remote.jpg")
 
 
 def test_local_binary(test_file_path):
 
@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "3.1.0"
+__version__ = "3.3.2"
 
 from pkgutil import extend_path
 
 
@@ -152,7 +152,7 @@ def make_content_disposition_header(fn):
 log.setLevel(logging.INFO)
 
 Windows = True if platform.system() == "Windows" else False
-TikaVersion = os.getenv('TIKA_VERSION', '3.1.0')
+TikaVersion = os.getenv('TIKA_VERSION', '3.3.2')
 TikaJarPath = os.getenv('TIKA_PATH', tempfile.gettempdir())
 TikaFilesPath = tempfile.gettempdir()
 TikaServerLogFilePath = log_path