From 6e319a74343b9efb69517ab178dbea921f438ee1 Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Sat, 28 Jul 2018 16:58:23 -0400 Subject: Correctly handle invalid HTML numeric character entities like “ which reference code points that are not Unicode code points. Note that this is only fixed when Beautiful Soup is used with the html.parser parser -- html5lib already worked and I couldn't fix it with lxml. [bug=1782933] --- bs4/tests/test_tree.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'bs4/tests/test_tree.py') diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index e5cc47e..e5dcfa7 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -1206,7 +1206,7 @@ class TestElementObjects(SoupTest): tag = soup.bTag self.assertEqual(soup.b, tag) self.assertEqual( - '.bTag is deprecated, use .find("b") instead.', + '.bTag is deprecated, use .find("b") instead. If you really were looking for a tag called bTag, use .find("bTag")', str(w[0].message)) def test_has_attr(self): -- cgit v1.2.3