Strip only a whole www. prefix from parsed domains

src/mvt/common/url.py

@@ -349,7 +349,9 @@ class URL:
             return tld_obj
         if tld_obj is None:
             return ""
-        return tld_obj.parsed_url.netloc.lower().lstrip("www.")
+        # removeprefix, not lstrip: lstrip takes a set of characters, so it ate the
+        # leading "w"s and dots of any domain ("web.evil.com" -> "eb.evil.com").
+        return tld_obj.parsed_url.netloc.lower().removeprefix("www.")
 
     def get_top_level(self) -> str:
         """Get only the top-level domain from a URL.

tests/common/test_url.py

@@ -22,3 +22,18 @@ def test_google_maps_url_is_not_shortened(url):
 
 def test_other_google_short_url_is_shortened():
     assert URL("https://goo.gl/example").check_if_shortened() is True
+
+
+@pytest.mark.parametrize(
+    "url, domain",
+    [
+        ("https://www.example.com/path", "example.com"),
+        # Only the whole "www." prefix comes off, not any leading "w" or "." character.
+        ("https://web.example.com", "web.example.com"),
+        ("https://wow.com", "wow.com"),
+        ("https://wired.com", "wired.com"),
+        ("https://www.wow.com", "wow.com"),
+    ],
+)
+def test_get_domain_strips_only_a_whole_www_prefix(url, domain):
+    assert URL(url).domain == domain