kevadesu/costmikuSearch
1
0
Fork 0
forked from Icycoide/searxng
Code Pull requests Activity

[fix] searx.utils.HTMLTextExtractor: invalid HTML don't raise an Exception

Browse source 
Close #2188
This commit is contained in:
Alexandre Flament 2020-09-11 10:23:56 +02:00
parent ae07f4a211
commit 6deb85072a
2 changed files with 18 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/unit/test_utils.py
View file

@ -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):