mirror of
https://github.com/clinton-hall/nzbToMedia.git
synced 2025-07-15 01:32:53 -07:00
f3fcb47427
Also updates: - appdirs-1.4.3 - babelfish-0.5.5 - beautifulsoup4-4.6.3 - certifi-2018.11.29 - chardet-3.0.4 - click-7.0 - decorator-4.3.0 - dogpile.cache-0.7.1 - enzyme-0.4.1 - guessit-3.0.3 - idna-2.8 - pbr-5.1.1 - pysrt-1.1.1 - python-dateutil-2.7.5 - pytz-2018.7 - rarfile-3.0 - rebulk-1.0.0 - requests-2.21.0 - six-1.12.0 - stevedore-1.30.0 - urllib3-1.24.1
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
"""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("<a><b>foo</a>")
|
|
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('<br></br><br></br><br></br>', "<br/><br/><br/>")
|
|
self.assertSoupEquals('</br></br></br>', "")
|
|
|
|
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")
|