When host_whitelist is empty, don't bother parsing the URLs in allow_embedded_url

CHANGES.rst

@@ -6,6 +6,14 @@ lxml_html_clean changelog
 Unreleased
 ==========
 
+0.3.1 (2024-10-09)
+==================
+
+Features added
+--------------
+
+* Do not parse URL addresses when it is not necessary.
+
 0.3.0 (2024-10-09)
 ==================
 

lxml_html_clean/clean.py

@@ -524,6 +524,8 @@ def allow_embedded_url(self, el, url):
         """
         if self.whitelist_tags is not None and el.tag not in self.whitelist_tags:
             return False
+        if not self.host_whitelist:
+            return False
         parts = urlsplit(url)
         if parts.scheme not in ('http', 'https'):
             return False

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = lxml_html_clean
-version = 0.3.0
+version = 0.3.1
 description = HTML cleaner from lxml project
 long_description = file:README.md
 long_description_content_type = text/markdown

tests/test_clean.py

@@ -348,7 +348,7 @@ def test_memory_usage_many_elements_with_long_tails(self):
 
         self.assertTrue(mem < 10, f"Used {mem} MiB memory, expected at most 10 MiB")
 
-    def test_possibly_invalid_url(self):
+    def test_possibly_invalid_url_with_whitelist(self):
         cleaner = Cleaner(host_whitelist=['google.com'])
         with warnings.catch_warnings(record=True) as w:
             warnings.simplefilter("always")
@@ -359,3 +359,12 @@ def test_possibly_invalid_url(self):
             self.assertIn("impossible to parse the hostname", str(w[-1].message))
         self.assertNotIn("google.com", result)
         self.assertNotIn("example.com", result)
+
+    def test_possibly_invalid_url_without_whitelist(self):
+        cleaner = Cleaner()
+        with warnings.catch_warnings(record=True) as w:
+            warnings.simplefilter("always")
+            result = cleaner.clean_html(r"<p><iframe src='http://example.com:\@google.com'>  </iframe></p>")
+            self.assertEqual(len(w), 0)
+        self.assertNotIn("google.com", result)
+        self.assertNotIn("example.com", result)