diff options
| author | Alexandre Flament <alex@al-f.net> | 2020-09-11 10:23:56 +0200 |
|---|---|---|
| committer | Alexandre Flament <alex@al-f.net> | 2020-09-13 10:28:11 +0200 |
| commit | 6deb85072ad00b85d2b3c1981c37aeb75ef68cc7 (patch) | |
| tree | a167d983a0006b1dddea5b7e6025d18b772dfc10 /tests/unit/test_utils.py | |
| parent | ae07f4a211ecba0331bcab5903e3263c646f8bdb (diff) | |
| download | searxng-6deb85072ad00b85d2b3c1981c37aeb75ef68cc7.tar.gz searxng-6deb85072ad00b85d2b3c1981c37aeb75ef68cc7.zip | |
[fix] searx.utils.HTMLTextExtractor: invalid HTML don't raise an Exception
Close #2188
Diffstat (limited to 'tests/unit/test_utils.py')
| -rw-r--r-- | tests/unit/test_utils.py | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index 5f98511c3..08b759542 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -52,6 +52,10 @@ class TestUtils(SearxTestCase): self.assertIsNotNone(utils.html_to_text(html)) self.assertEqual(utils.html_to_text(html), "Test text") + def test_html_to_text_invalid(self): + html = '<p><b>Lorem ipsum</i>dolor sit amet</p>' + self.assertEqual(utils.html_to_text(html), "Lorem ipsum") + def test_prettify_url(self): data = (('https://searx.me/', 'https://searx.me/'), ('https://searx.me/ű', 'https://searx.me/ű'), @@ -116,6 +120,11 @@ class TestHTMLTextExtractor(SearxTestCase): self.html_text_extractor.handle_entityref(entity) self.assertIn(entity, self.html_text_extractor.result) + def test_invalid_html(self): + text = '<p><b>Lorem ipsum</i>dolor sit amet</p>' + with self.assertRaises(utils.HTMLTextExtractorException): + self.html_text_extractor.feed(text) + class TestUnicodeWriter(SearxTestCase): |