def test_preserve_refs(): """Test that HTML character/entity references are preserved when we strip tags.""" text = u"la philologie mène au pire" assert strip_tags(text) == u"la philologie mène au pire" text = u"la philologie mène au pire" assert strip_tags(text) == u"la philologie mène au pire" text = u"veer & wander" assert strip_tags(text) == "veer & wander"
def test_preserve_refs(): """Test that HTML character/entity references are preserved when we strip tags.""" text = u'la philologie mène au pire' assert strip_tags(text) == u'la philologie mène au pire' text = u'la philologie mène au pire' assert strip_tags(text) == u'la philologie mène au pire' text = u'veer & wander' assert strip_tags(text) == 'veer & wander'
def test_strip_tags(): text = ( "<div><script> AAH JAVASCRIPT</script><style> AAH CSS AHH</style>" 'check out this <a href="http://example.com">link</a> yo!</div>' ) assert strip_tags(text).strip() == "check out this link yo!" # MS Word conditional marked section text = "<![if word]>content<![endif]>" assert strip_tags(text).strip() == "content" # Unknown marked section text = """<![FOR]>""" with pytest.raises(HTMLParseError): strip_tags(text)
def calculate_html_snippet(self, text): text = text.replace('<br>', ' ').replace('<br/>', ' '). \ replace('<br />', ' ') text = strip_tags(text) return self.calculate_plaintext_snippet(text)
def calculate_html_snippet(self, text): text = strip_tags(text) return self.calculate_plaintext_snippet(text)
def calculate_html_snippet(self, text): text = text.replace('<br>', ' ').replace('<br/>', ' '). \ replace('<br />', ' ') text = strip_tags(text) self.calculate_plaintext_snippet(text)
def calculate_html_snippet(msg, text): text = text.replace("<br>", " ").replace("<br/>", " ").replace("<br />", " ") text = strip_tags(text) calculate_plaintext_snippet(msg, text)
def test_strip_tags(): text = ('<div><script> AAH JAVASCRIPT</script><style> AAH CSS AHH</style>' 'check out this <a href="http://example.com">link</a> yo!</div>') assert strip_tags(text) == 'check out this link yo!'
def calculate_html_snippet(msg, text): text = text.replace('<br>', ' ').replace('<br/>', ' '). \ replace('<br />', ' ') text = strip_tags(text) calculate_plaintext_snippet(msg, text)