def test_parseOnlyThese_renamed_to_parse_only(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", parseOnlyThese=SoupStrainer("b"))
msg = str(w[0].message)
self.assertTrue("parseOnlyThese" in msg)
self.assertTrue("parse_only" in msg)
self.assertEqual(b"<b></b>", soup.encode())
def test_soupstrainer(self):
# The html5lib tree builder does not support SoupStrainers.
strainer = SoupStrainer("b")
markup = "<p>A <b>bold</b> statement.</p>"
with warnings.catch_warnings(record=True) as w:
soup = self.soup(markup, parse_only=strainer)
self.assertEqual(soup.decode(), self.document_for(markup))
self.assertTrue("the html5lib tree builder doesn't support parse_only"
in str(w[0].message))
def test_soupstrainer(self):
"""Parsers should be able to work with SoupStrainers."""
strainer = SoupStrainer("b")
soup = self.soup("A <b>bold</b> <meta/> <i>statement</i>",
parse_only=strainer)
self.assertEqual(soup.decode(), "<b>bold</b>")
def test_parse_with_soupstrainer(self):
markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
strainer = SoupStrainer("b")
soup = self.soup(markup, parse_only=strainer)
self.assertEqual(soup.encode(), b"<b>Yes</b><b>Yes <c>Yes</c></b>")