"""Tests to ensure that the html.parser tree builder generates good trees.""" from pdb import set_trace import pickle from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest from bs4.builder import HTMLParserTreeBuilder from bs4.builder._htmlparser import BeautifulSoupHTMLParser class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest): @property def default_builder(self): return HTMLParserTreeBuilder() def test_namespaced_system_doctype(self): # html.parser can't handle namespaced doctypes, so skip this one. pass def test_namespaced_public_doctype(self): # html.parser can't handle namespaced doctypes, so skip this one. pass def test_builder_is_pickled(self): """Unlike most tree builders, HTMLParserTreeBuilder and will be restored after pickling. """ tree = self.soup("foo") dumped = pickle.dumps(tree, 2) loaded = pickle.loads(dumped) self.assertTrue(isinstance(loaded.builder, type(tree.builder))) def test_redundant_empty_element_closing_tags(self): self.assertSoupEquals('





', "


") self.assertSoupEquals('


', "") def test_empty_element(self): # This verifies that any buffered data present when the parser # finishes working is handled. self.assertSoupEquals("foo &# bar", "foo &# bar") class TestHTMLParserSubclass(SoupTest): def test_error(self): """Verify that our HTMLParser subclass implements error() in a way that doesn't cause a crash. """ parser = BeautifulSoupHTMLParser() parser.error("don't crash")