def test_get_blacklist(self):
roots = HTML5Strip.parse("<p>hello, world<br></p>")
fragment = HTML5Fragment(roots[0])
self.assertEqual(fragment.blacklist, set(roots[0].findall("br")))
def test_parse(self):
roots = HTML5Strip.parse("<p>hello, world</p>")
self.assertEqual(roots[0].text, "hello, world")
def test_has_no_text_on_html(self):
roots = HTML5Strip.parse(u"<p>\u2000</p>")
self.assertFalse(HTML5Fragment.has_text(roots[0].text))
def test_has_text_on_html(self):
roots = HTML5Strip.parse(u"<p>hello, world</p>")
self.assertTrue(HTML5Fragment.has_text(roots[0].text))
def test_strip_tail(self):
fragment = HTML5Fragment(HTML5Strip.parse("<p>hello,<br>world</p>")[0])
res = fragment.strip(set(fragment.root.findall("br")))
self.assertEqual(res, "<p>hello,world</p>")
def test_strip_root(self):
fragment = HTML5Fragment(HTML5Strip.parse("<p>hello, world</p>")[0])
res = fragment.strip(set([fragment.root]))
self.assertEqual(res, "")
def test_parse_fragments(self):
roots = HTML5Strip.parse("<p>hello</p><p>world</p>")
self.assertEqual([r.text for r in roots], ["hello", "world"])
