mirror of
https://github.com/Tautulli/Tautulli.git
synced 2025-08-20 13:23:24 -07:00
Bump beautifulsoup4 from 4.11.2 to 4.12.2 (#2037)
* Bump beautifulsoup4 from 4.11.2 to 4.12.2 Bumps [beautifulsoup4](https://www.crummy.com/software/BeautifulSoup/bs4/) from 4.11.2 to 4.12.2. --- updated-dependencies: - dependency-name: beautifulsoup4 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Update beautifulsoup4==4.12.2 --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com> [skip ci]
This commit is contained in:
dependabot[bot]
GitHub
parent
1798594569
commit
e70e08c3f5
32 changed files with 1439 additions and 755 deletions
|
|
@ -297,37 +297,11 @@ class TreeBuilderSmokeTest(object):
|
|||
markup, multi_valued_attributes=multi_valued_attributes
|
||||
)
|
||||
assert soup.a['class'] == ['a', 'b', 'c']
|
||||
|
||||
def test_fuzzed_input(self):
|
||||
# This test centralizes in one place the various fuzz tests
|
||||
# for Beautiful Soup created by the oss-fuzz project.
|
||||
|
||||
# These strings superficially resemble markup, but they
|
||||
# generally can't be parsed into anything. The best we can
|
||||
# hope for is that parsing these strings won't crash the
|
||||
# parser.
|
||||
#
|
||||
# n.b. This markup is commented out because these fuzz tests
|
||||
# _do_ crash the parser. However the crashes are due to bugs
|
||||
# in html.parser, not Beautiful Soup -- otherwise I'd fix the
|
||||
# bugs!
|
||||
|
||||
bad_markup = [
|
||||
# https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=28873
|
||||
# https://github.com/guidovranken/python-library-fuzzers/blob/master/corp-html/519e5b4269a01185a0d5e76295251921da2f0700
|
||||
# https://bugs.python.org/issue37747
|
||||
#
|
||||
#b'\n<![\xff\xfe\xfe\xcd\x00',
|
||||
|
||||
#https://github.com/guidovranken/python-library-fuzzers/blob/master/corp-html/de32aa55785be29bbc72a1a8e06b00611fb3d9f8
|
||||
# https://bugs.python.org/issue34480
|
||||
#
|
||||
#b'<![n\x00'
|
||||
]
|
||||
for markup in bad_markup:
|
||||
with warnings.catch_warnings(record=False):
|
||||
soup = self.soup(markup)
|
||||
|
||||
def test_invalid_doctype(self):
|
||||
markup = '<![if word]>content<![endif]>'
|
||||
markup = '<!DOCTYPE html]ff>'
|
||||
soup = self.soup(markup)
|
||||
|
||||
class HTMLTreeBuilderSmokeTest(TreeBuilderSmokeTest):
|
||||
|
||||
|
|
@ -577,8 +551,8 @@ Hello, world!
|
|||
"""Whitespace must be preserved in <pre> and <textarea> tags,
|
||||
even if that would mean not prettifying the markup.
|
||||
"""
|
||||
pre_markup = "<pre> </pre>"
|
||||
textarea_markup = "<textarea> woo\nwoo </textarea>"
|
||||
pre_markup = "<pre>a z</pre>\n"
|
||||
textarea_markup = "<textarea> woo\nwoo </textarea>\n"
|
||||
self.assert_soup(pre_markup)
|
||||
self.assert_soup(textarea_markup)
|
||||
|
||||
|
|
@ -589,7 +563,7 @@ Hello, world!
|
|||
assert soup.textarea.prettify() == textarea_markup
|
||||
|
||||
soup = self.soup("<textarea></textarea>")
|
||||
assert soup.textarea.prettify() == "<textarea></textarea>"
|
||||
assert soup.textarea.prettify() == "<textarea></textarea>\n"
|
||||
|
||||
def test_nested_inline_elements(self):
|
||||
"""Inline elements can be nested indefinitely."""
|
||||
|
|
|
|||
|
|
@ -0,0 +1 @@
|
|||
˙<!DOCTyPEV PUBLIC'''Đ'
|
||||
|
|
@ -0,0 +1 @@
|
|||
)<a><math><TR><a><mI><a><p><a>
|
||||
Binary file not shown.
|
|
@ -0,0 +1,2 @@
|
|||
|
||||
<![
|
||||
|
|
@ -0,0 +1 @@
|
|||
-<math><sElect><mi><sElect><sElect>
|
||||
Binary file not shown.
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1 @@
|
|||
ñ<table><svg><html>
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
487
lib/bs4/tests/test_css.py
Normal file
487
lib/bs4/tests/test_css.py
Normal file
|
|
@ -0,0 +1,487 @@
|
|||
import pytest
|
||||
import types
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
from bs4 import (
|
||||
CSS,
|
||||
BeautifulSoup,
|
||||
ResultSet,
|
||||
)
|
||||
|
||||
from . import (
|
||||
SoupTest,
|
||||
SOUP_SIEVE_PRESENT,
|
||||
)
|
||||
|
||||
if SOUP_SIEVE_PRESENT:
|
||||
from soupsieve import SelectorSyntaxError
|
||||
|
||||
|
||||
@pytest.mark.skipif(not SOUP_SIEVE_PRESENT, reason="Soup Sieve not installed")
|
||||
class TestCSSSelectors(SoupTest):
|
||||
"""Test basic CSS selector functionality.
|
||||
|
||||
This functionality is implemented in soupsieve, which has a much
|
||||
more comprehensive test suite, so this is basically an extra check
|
||||
that soupsieve works as expected.
|
||||
"""
|
||||
|
||||
HTML = """
|
||||
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
|
||||
"http://www.w3.org/TR/html4/strict.dtd">
|
||||
<html>
|
||||
<head>
|
||||
<title>The title</title>
|
||||
<link rel="stylesheet" href="blah.css" type="text/css" id="l1">
|
||||
</head>
|
||||
<body>
|
||||
<custom-dashed-tag class="dashed" id="dash1">Hello there.</custom-dashed-tag>
|
||||
<div id="main" class="fancy">
|
||||
<div id="inner">
|
||||
<h1 id="header1">An H1</h1>
|
||||
<p>Some text</p>
|
||||
<p class="onep" id="p1">Some more text</p>
|
||||
<h2 id="header2">An H2</h2>
|
||||
<p class="class1 class2 class3" id="pmulti">Another</p>
|
||||
<a href="http://bob.example.org/" rel="friend met" id="bob">Bob</a>
|
||||
<h2 id="header3">Another H2</h2>
|
||||
<a id="me" href="http://simonwillison.net/" rel="me">me</a>
|
||||
<span class="s1">
|
||||
<a href="#" id="s1a1">span1a1</a>
|
||||
<a href="#" id="s1a2">span1a2 <span id="s1a2s1">test</span></a>
|
||||
<span class="span2">
|
||||
<a href="#" id="s2a1">span2a1</a>
|
||||
</span>
|
||||
<span class="span3"></span>
|
||||
<custom-dashed-tag class="dashed" id="dash2"/>
|
||||
<div data-tag="dashedvalue" id="data1"/>
|
||||
</span>
|
||||
</div>
|
||||
<x id="xid">
|
||||
<z id="zida"/>
|
||||
<z id="zidab"/>
|
||||
<z id="zidac"/>
|
||||
</x>
|
||||
<y id="yid">
|
||||
<z id="zidb"/>
|
||||
</y>
|
||||
<p lang="en" id="lang-en">English</p>
|
||||
<p lang="en-gb" id="lang-en-gb">English UK</p>
|
||||
<p lang="en-us" id="lang-en-us">English US</p>
|
||||
<p lang="fr" id="lang-fr">French</p>
|
||||
</div>
|
||||
|
||||
<div id="footer">
|
||||
</div>
|
||||
"""
|
||||
|
||||
def setup_method(self):
|
||||
self.soup = BeautifulSoup(self.HTML, 'html.parser')
|
||||
|
||||
def assert_selects(self, selector, expected_ids, **kwargs):
|
||||
results = self.soup.select(selector, **kwargs)
|
||||
assert isinstance(results, ResultSet)
|
||||
el_ids = [el['id'] for el in results]
|
||||
el_ids.sort()
|
||||
expected_ids.sort()
|
||||
assert expected_ids == el_ids, "Selector %s, expected [%s], got [%s]" % (
|
||||
selector, ', '.join(expected_ids), ', '.join(el_ids)
|
||||
)
|
||||
|
||||
assertSelect = assert_selects
|
||||
|
||||
def assert_select_multiple(self, *tests):
|
||||
for selector, expected_ids in tests:
|
||||
self.assert_selects(selector, expected_ids)
|
||||
|
||||
def test_precompiled(self):
|
||||
sel = self.soup.css.compile('div')
|
||||
|
||||
els = self.soup.select(sel)
|
||||
assert len(els) == 4
|
||||
for div in els:
|
||||
assert div.name == 'div'
|
||||
|
||||
el = self.soup.select_one(sel)
|
||||
assert 'main' == el['id']
|
||||
|
||||
def test_one_tag_one(self):
|
||||
els = self.soup.select('title')
|
||||
assert len(els) == 1
|
||||
assert els[0].name == 'title'
|
||||
assert els[0].contents == ['The title']
|
||||
|
||||
def test_one_tag_many(self):
|
||||
els = self.soup.select('div')
|
||||
assert len(els) == 4
|
||||
for div in els:
|
||||
assert div.name == 'div'
|
||||
|
||||
el = self.soup.select_one('div')
|
||||
assert 'main' == el['id']
|
||||
|
||||
def test_select_one_returns_none_if_no_match(self):
|
||||
match = self.soup.select_one('nonexistenttag')
|
||||
assert None == match
|
||||
|
||||
|
||||
def test_tag_in_tag_one(self):
|
||||
els = self.soup.select('div div')
|
||||
self.assert_selects('div div', ['inner', 'data1'])
|
||||
|
||||
def test_tag_in_tag_many(self):
|
||||
for selector in ('html div', 'html body div', 'body div'):
|
||||
self.assert_selects(selector, ['data1', 'main', 'inner', 'footer'])
|
||||
|
||||
|
||||
def test_limit(self):
|
||||
self.assert_selects('html div', ['main'], limit=1)
|
||||
self.assert_selects('html body div', ['inner', 'main'], limit=2)
|
||||
self.assert_selects('body div', ['data1', 'main', 'inner', 'footer'],
|
||||
limit=10)
|
||||
|
||||
def test_tag_no_match(self):
|
||||
assert len(self.soup.select('del')) == 0
|
||||
|
||||
def test_invalid_tag(self):
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select('tag%t')
|
||||
|
||||
def test_select_dashed_tag_ids(self):
|
||||
self.assert_selects('custom-dashed-tag', ['dash1', 'dash2'])
|
||||
|
||||
def test_select_dashed_by_id(self):
|
||||
dashed = self.soup.select('custom-dashed-tag[id=\"dash2\"]')
|
||||
assert dashed[0].name == 'custom-dashed-tag'
|
||||
assert dashed[0]['id'] == 'dash2'
|
||||
|
||||
def test_dashed_tag_text(self):
|
||||
assert self.soup.select('body > custom-dashed-tag')[0].text == 'Hello there.'
|
||||
|
||||
def test_select_dashed_matches_find_all(self):
|
||||
assert self.soup.select('custom-dashed-tag') == self.soup.find_all('custom-dashed-tag')
|
||||
|
||||
def test_header_tags(self):
|
||||
self.assert_select_multiple(
|
||||
('h1', ['header1']),
|
||||
('h2', ['header2', 'header3']),
|
||||
)
|
||||
|
||||
def test_class_one(self):
|
||||
for selector in ('.onep', 'p.onep', 'html p.onep'):
|
||||
els = self.soup.select(selector)
|
||||
assert len(els) == 1
|
||||
assert els[0].name == 'p'
|
||||
assert els[0]['class'] == ['onep']
|
||||
|
||||
def test_class_mismatched_tag(self):
|
||||
els = self.soup.select('div.onep')
|
||||
assert len(els) == 0
|
||||
|
||||
def test_one_id(self):
|
||||
for selector in ('div#inner', '#inner', 'div div#inner'):
|
||||
self.assert_selects(selector, ['inner'])
|
||||
|
||||
def test_bad_id(self):
|
||||
els = self.soup.select('#doesnotexist')
|
||||
assert len(els) == 0
|
||||
|
||||
def test_items_in_id(self):
|
||||
els = self.soup.select('div#inner p')
|
||||
assert len(els) == 3
|
||||
for el in els:
|
||||
assert el.name == 'p'
|
||||
assert els[1]['class'] == ['onep']
|
||||
assert not els[0].has_attr('class')
|
||||
|
||||
def test_a_bunch_of_emptys(self):
|
||||
for selector in ('div#main del', 'div#main div.oops', 'div div#main'):
|
||||
assert len(self.soup.select(selector)) == 0
|
||||
|
||||
def test_multi_class_support(self):
|
||||
for selector in ('.class1', 'p.class1', '.class2', 'p.class2',
|
||||
'.class3', 'p.class3', 'html p.class2', 'div#inner .class2'):
|
||||
self.assert_selects(selector, ['pmulti'])
|
||||
|
||||
def test_multi_class_selection(self):
|
||||
for selector in ('.class1.class3', '.class3.class2',
|
||||
'.class1.class2.class3'):
|
||||
self.assert_selects(selector, ['pmulti'])
|
||||
|
||||
def test_child_selector(self):
|
||||
self.assert_selects('.s1 > a', ['s1a1', 's1a2'])
|
||||
self.assert_selects('.s1 > a span', ['s1a2s1'])
|
||||
|
||||
def test_child_selector_id(self):
|
||||
self.assert_selects('.s1 > a#s1a2 span', ['s1a2s1'])
|
||||
|
||||
def test_attribute_equals(self):
|
||||
self.assert_select_multiple(
|
||||
('p[class="onep"]', ['p1']),
|
||||
('p[id="p1"]', ['p1']),
|
||||
('[class="onep"]', ['p1']),
|
||||
('[id="p1"]', ['p1']),
|
||||
('link[rel="stylesheet"]', ['l1']),
|
||||
('link[type="text/css"]', ['l1']),
|
||||
('link[href="blah.css"]', ['l1']),
|
||||
('link[href="no-blah.css"]', []),
|
||||
('[rel="stylesheet"]', ['l1']),
|
||||
('[type="text/css"]', ['l1']),
|
||||
('[href="blah.css"]', ['l1']),
|
||||
('[href="no-blah.css"]', []),
|
||||
('p[href="no-blah.css"]', []),
|
||||
('[href="no-blah.css"]', []),
|
||||
)
|
||||
|
||||
def test_attribute_tilde(self):
|
||||
self.assert_select_multiple(
|
||||
('p[class~="class1"]', ['pmulti']),
|
||||
('p[class~="class2"]', ['pmulti']),
|
||||
('p[class~="class3"]', ['pmulti']),
|
||||
('[class~="class1"]', ['pmulti']),
|
||||
('[class~="class2"]', ['pmulti']),
|
||||
('[class~="class3"]', ['pmulti']),
|
||||
('a[rel~="friend"]', ['bob']),
|
||||
('a[rel~="met"]', ['bob']),
|
||||
('[rel~="friend"]', ['bob']),
|
||||
('[rel~="met"]', ['bob']),
|
||||
)
|
||||
|
||||
def test_attribute_startswith(self):
|
||||
self.assert_select_multiple(
|
||||
('[rel^="style"]', ['l1']),
|
||||
('link[rel^="style"]', ['l1']),
|
||||
('notlink[rel^="notstyle"]', []),
|
||||
('[rel^="notstyle"]', []),
|
||||
('link[rel^="notstyle"]', []),
|
||||
('link[href^="bla"]', ['l1']),
|
||||
('a[href^="http://"]', ['bob', 'me']),
|
||||
('[href^="http://"]', ['bob', 'me']),
|
||||
('[id^="p"]', ['pmulti', 'p1']),
|
||||
('[id^="m"]', ['me', 'main']),
|
||||
('div[id^="m"]', ['main']),
|
||||
('a[id^="m"]', ['me']),
|
||||
('div[data-tag^="dashed"]', ['data1'])
|
||||
)
|
||||
|
||||
def test_attribute_endswith(self):
|
||||
self.assert_select_multiple(
|
||||
('[href$=".css"]', ['l1']),
|
||||
('link[href$=".css"]', ['l1']),
|
||||
('link[id$="1"]', ['l1']),
|
||||
('[id$="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's2a1', 's1a2s1', 'dash1']),
|
||||
('div[id$="1"]', ['data1']),
|
||||
('[id$="noending"]', []),
|
||||
)
|
||||
|
||||
def test_attribute_contains(self):
|
||||
self.assert_select_multiple(
|
||||
# From test_attribute_startswith
|
||||
('[rel*="style"]', ['l1']),
|
||||
('link[rel*="style"]', ['l1']),
|
||||
('notlink[rel*="notstyle"]', []),
|
||||
('[rel*="notstyle"]', []),
|
||||
('link[rel*="notstyle"]', []),
|
||||
('link[href*="bla"]', ['l1']),
|
||||
('[href*="http://"]', ['bob', 'me']),
|
||||
('[id*="p"]', ['pmulti', 'p1']),
|
||||
('div[id*="m"]', ['main']),
|
||||
('a[id*="m"]', ['me']),
|
||||
# From test_attribute_endswith
|
||||
('[href*=".css"]', ['l1']),
|
||||
('link[href*=".css"]', ['l1']),
|
||||
('link[id*="1"]', ['l1']),
|
||||
('[id*="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's1a2', 's2a1', 's1a2s1', 'dash1']),
|
||||
('div[id*="1"]', ['data1']),
|
||||
('[id*="noending"]', []),
|
||||
# New for this test
|
||||
('[href*="."]', ['bob', 'me', 'l1']),
|
||||
('a[href*="."]', ['bob', 'me']),
|
||||
('link[href*="."]', ['l1']),
|
||||
('div[id*="n"]', ['main', 'inner']),
|
||||
('div[id*="nn"]', ['inner']),
|
||||
('div[data-tag*="edval"]', ['data1'])
|
||||
)
|
||||
|
||||
def test_attribute_exact_or_hypen(self):
|
||||
self.assert_select_multiple(
|
||||
('p[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
|
||||
('[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
|
||||
('p[lang|="fr"]', ['lang-fr']),
|
||||
('p[lang|="gb"]', []),
|
||||
)
|
||||
|
||||
def test_attribute_exists(self):
|
||||
self.assert_select_multiple(
|
||||
('[rel]', ['l1', 'bob', 'me']),
|
||||
('link[rel]', ['l1']),
|
||||
('a[rel]', ['bob', 'me']),
|
||||
('[lang]', ['lang-en', 'lang-en-gb', 'lang-en-us', 'lang-fr']),
|
||||
('p[class]', ['p1', 'pmulti']),
|
||||
('[blah]', []),
|
||||
('p[blah]', []),
|
||||
('div[data-tag]', ['data1'])
|
||||
)
|
||||
|
||||
def test_quoted_space_in_selector_name(self):
|
||||
html = """<div style="display: wrong">nope</div>
|
||||
<div style="display: right">yes</div>
|
||||
"""
|
||||
soup = BeautifulSoup(html, 'html.parser')
|
||||
[chosen] = soup.select('div[style="display: right"]')
|
||||
assert "yes" == chosen.string
|
||||
|
||||
def test_unsupported_pseudoclass(self):
|
||||
with pytest.raises(NotImplementedError):
|
||||
self.soup.select("a:no-such-pseudoclass")
|
||||
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select("a:nth-of-type(a)")
|
||||
|
||||
def test_nth_of_type(self):
|
||||
# Try to select first paragraph
|
||||
els = self.soup.select('div#inner p:nth-of-type(1)')
|
||||
assert len(els) == 1
|
||||
assert els[0].string == 'Some text'
|
||||
|
||||
# Try to select third paragraph
|
||||
els = self.soup.select('div#inner p:nth-of-type(3)')
|
||||
assert len(els) == 1
|
||||
assert els[0].string == 'Another'
|
||||
|
||||
# Try to select (non-existent!) fourth paragraph
|
||||
els = self.soup.select('div#inner p:nth-of-type(4)')
|
||||
assert len(els) == 0
|
||||
|
||||
# Zero will select no tags.
|
||||
els = self.soup.select('div p:nth-of-type(0)')
|
||||
assert len(els) == 0
|
||||
|
||||
def test_nth_of_type_direct_descendant(self):
|
||||
els = self.soup.select('div#inner > p:nth-of-type(1)')
|
||||
assert len(els) == 1
|
||||
assert els[0].string == 'Some text'
|
||||
|
||||
def test_id_child_selector_nth_of_type(self):
|
||||
self.assert_selects('#inner > p:nth-of-type(2)', ['p1'])
|
||||
|
||||
def test_select_on_element(self):
|
||||
# Other tests operate on the tree; this operates on an element
|
||||
# within the tree.
|
||||
inner = self.soup.find("div", id="main")
|
||||
selected = inner.select("div")
|
||||
# The <div id="inner"> tag was selected. The <div id="footer">
|
||||
# tag was not.
|
||||
self.assert_selects_ids(selected, ['inner', 'data1'])
|
||||
|
||||
def test_overspecified_child_id(self):
|
||||
self.assert_selects(".fancy #inner", ['inner'])
|
||||
self.assert_selects(".normal #inner", [])
|
||||
|
||||
def test_adjacent_sibling_selector(self):
|
||||
self.assert_selects('#p1 + h2', ['header2'])
|
||||
self.assert_selects('#p1 + h2 + p', ['pmulti'])
|
||||
self.assert_selects('#p1 + #header2 + .class1', ['pmulti'])
|
||||
assert [] == self.soup.select('#p1 + p')
|
||||
|
||||
def test_general_sibling_selector(self):
|
||||
self.assert_selects('#p1 ~ h2', ['header2', 'header3'])
|
||||
self.assert_selects('#p1 ~ #header2', ['header2'])
|
||||
self.assert_selects('#p1 ~ h2 + a', ['me'])
|
||||
self.assert_selects('#p1 ~ h2 + [rel="me"]', ['me'])
|
||||
assert [] == self.soup.select('#inner ~ h2')
|
||||
|
||||
def test_dangling_combinator(self):
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select('h1 >')
|
||||
|
||||
def test_sibling_combinator_wont_select_same_tag_twice(self):
|
||||
self.assert_selects('p[lang] ~ p', ['lang-en-gb', 'lang-en-us', 'lang-fr'])
|
||||
|
||||
# Test the selector grouping operator (the comma)
|
||||
def test_multiple_select(self):
|
||||
self.assert_selects('x, y', ['xid', 'yid'])
|
||||
|
||||
def test_multiple_select_with_no_space(self):
|
||||
self.assert_selects('x,y', ['xid', 'yid'])
|
||||
|
||||
def test_multiple_select_with_more_space(self):
|
||||
self.assert_selects('x, y', ['xid', 'yid'])
|
||||
|
||||
def test_multiple_select_duplicated(self):
|
||||
self.assert_selects('x, x', ['xid'])
|
||||
|
||||
def test_multiple_select_sibling(self):
|
||||
self.assert_selects('x, y ~ p[lang=fr]', ['xid', 'lang-fr'])
|
||||
|
||||
def test_multiple_select_tag_and_direct_descendant(self):
|
||||
self.assert_selects('x, y > z', ['xid', 'zidb'])
|
||||
|
||||
def test_multiple_select_direct_descendant_and_tags(self):
|
||||
self.assert_selects('div > x, y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
|
||||
|
||||
def test_multiple_select_indirect_descendant(self):
|
||||
self.assert_selects('div x,y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
|
||||
|
||||
def test_invalid_multiple_select(self):
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select(',x, y')
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select('x,,y')
|
||||
|
||||
def test_multiple_select_attrs(self):
|
||||
self.assert_selects('p[lang=en], p[lang=en-gb]', ['lang-en', 'lang-en-gb'])
|
||||
|
||||
def test_multiple_select_ids(self):
|
||||
self.assert_selects('x, y > z[id=zida], z[id=zidab], z[id=zidb]', ['xid', 'zidb', 'zidab'])
|
||||
|
||||
def test_multiple_select_nested(self):
|
||||
self.assert_selects('body > div > x, y > z', ['xid', 'zidb'])
|
||||
|
||||
def test_select_duplicate_elements(self):
|
||||
# When markup contains duplicate elements, a multiple select
|
||||
# will find all of them.
|
||||
markup = '<div class="c1"/><div class="c2"/><div class="c1"/>'
|
||||
soup = BeautifulSoup(markup, 'html.parser')
|
||||
selected = soup.select(".c1, .c2")
|
||||
assert 3 == len(selected)
|
||||
|
||||
# Verify that find_all finds the same elements, though because
|
||||
# of an implementation detail it finds them in a different
|
||||
# order.
|
||||
for element in soup.find_all(class_=['c1', 'c2']):
|
||||
assert element in selected
|
||||
|
||||
def test_closest(self):
|
||||
inner = self.soup.find("div", id="inner")
|
||||
closest = inner.css.closest("div[id=main]")
|
||||
assert closest == self.soup.find("div", id="main")
|
||||
|
||||
def test_match(self):
|
||||
inner = self.soup.find("div", id="inner")
|
||||
main = self.soup.find("div", id="main")
|
||||
assert inner.css.match("div[id=main]") == False
|
||||
assert main.css.match("div[id=main]") == True
|
||||
|
||||
def test_iselect(self):
|
||||
gen = self.soup.css.iselect("h2")
|
||||
assert isinstance(gen, types.GeneratorType)
|
||||
[header2, header3] = gen
|
||||
assert header2['id'] == 'header2'
|
||||
assert header3['id'] == 'header3'
|
||||
|
||||
def test_filter(self):
|
||||
inner = self.soup.find("div", id="inner")
|
||||
results = inner.css.filter("h2")
|
||||
assert len(inner.css.filter("h2")) == 2
|
||||
|
||||
results = inner.css.filter("h2[id=header3]")
|
||||
assert isinstance(results, ResultSet)
|
||||
[result] = results
|
||||
assert result['id'] == 'header3'
|
||||
|
||||
def test_escape(self):
|
||||
m = self.soup.css.escape
|
||||
assert m(".foo#bar") == '\\.foo\\#bar'
|
||||
assert m("()[]{}") == '\\(\\)\\[\\]\\{\\}'
|
||||
assert m(".foo") == self.soup.css.escape(".foo")
|
||||
|
|
@ -80,20 +80,20 @@ class TestFormatter(SoupTest):
|
|||
@pytest.mark.parametrize(
|
||||
"indent,expect",
|
||||
[
|
||||
(None, '<a>\n<b>\ntext\n</b>\n</a>'),
|
||||
(-1, '<a>\n<b>\ntext\n</b>\n</a>'),
|
||||
(0, '<a>\n<b>\ntext\n</b>\n</a>'),
|
||||
("", '<a>\n<b>\ntext\n</b>\n</a>'),
|
||||
(None, '<a>\n<b>\ntext\n</b>\n</a>\n'),
|
||||
(-1, '<a>\n<b>\ntext\n</b>\n</a>\n'),
|
||||
(0, '<a>\n<b>\ntext\n</b>\n</a>\n'),
|
||||
("", '<a>\n<b>\ntext\n</b>\n</a>\n'),
|
||||
|
||||
(1, '<a>\n <b>\n text\n </b>\n</a>'),
|
||||
(2, '<a>\n <b>\n text\n </b>\n</a>'),
|
||||
(1, '<a>\n <b>\n text\n </b>\n</a>\n'),
|
||||
(2, '<a>\n <b>\n text\n </b>\n</a>\n'),
|
||||
|
||||
("\t", '<a>\n\t<b>\n\t\ttext\n\t</b>\n</a>'),
|
||||
('abc', '<a>\nabc<b>\nabcabctext\nabc</b>\n</a>'),
|
||||
("\t", '<a>\n\t<b>\n\t\ttext\n\t</b>\n</a>\n'),
|
||||
('abc', '<a>\nabc<b>\nabcabctext\nabc</b>\n</a>\n'),
|
||||
|
||||
# Some invalid inputs -- the default behavior is used.
|
||||
(object(), '<a>\n <b>\n text\n </b>\n</a>'),
|
||||
(b'bytes', '<a>\n <b>\n text\n </b>\n</a>'),
|
||||
(object(), '<a>\n <b>\n text\n </b>\n</a>\n'),
|
||||
(b'bytes', '<a>\n <b>\n text\n </b>\n</a>\n'),
|
||||
]
|
||||
)
|
||||
def test_indent(self, indent, expect):
|
||||
|
|
|
|||
91
lib/bs4/tests/test_fuzz.py
Normal file
91
lib/bs4/tests/test_fuzz.py
Normal file
|
|
@ -0,0 +1,91 @@
|
|||
"""This file contains test cases reported by third parties using
|
||||
fuzzing tools, primarily from Google's oss-fuzz project. Some of these
|
||||
represent real problems with Beautiful Soup, but many are problems in
|
||||
libraries that Beautiful Soup depends on, and many of the test cases
|
||||
represent different ways of triggering the same problem.
|
||||
|
||||
Grouping these test cases together makes it easy to see which test
|
||||
cases represent the same problem, and puts the test cases in close
|
||||
proximity to code that can trigger the problems.
|
||||
"""
|
||||
import os
|
||||
import pytest
|
||||
from bs4 import (
|
||||
BeautifulSoup,
|
||||
ParserRejectedMarkup,
|
||||
)
|
||||
|
||||
class TestFuzz(object):
|
||||
|
||||
# Test case markup files from fuzzers are given this extension so
|
||||
# they can be included in builds.
|
||||
TESTCASE_SUFFIX = ".testcase"
|
||||
|
||||
# This class of error has been fixed by catching a less helpful
|
||||
# exception from html.parser and raising ParserRejectedMarkup
|
||||
# instead.
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5703933063462912",
|
||||
]
|
||||
)
|
||||
def test_rejected_markup(self, filename):
|
||||
markup = self.__markup(filename)
|
||||
with pytest.raises(ParserRejectedMarkup):
|
||||
BeautifulSoup(markup, 'html.parser')
|
||||
|
||||
# This class of error has to do with very deeply nested documents
|
||||
# which overflow the Python call stack when the tree is converted
|
||||
# to a string. This is an issue with Beautiful Soup which was fixed
|
||||
# as part of [bug=1471755].
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5984173902397440",
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5167584867909632",
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6124268085182464",
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6450958476902400",
|
||||
]
|
||||
)
|
||||
def test_deeply_nested_document(self, filename):
|
||||
# Parsing the document and encoding it back to a string is
|
||||
# sufficient to demonstrate that the overflow problem has
|
||||
# been fixed.
|
||||
markup = self.__markup(filename)
|
||||
BeautifulSoup(markup, 'html.parser').encode()
|
||||
|
||||
# This class of error represents problems with html5lib's parser,
|
||||
# not Beautiful Soup. I use
|
||||
# https://github.com/html5lib/html5lib-python/issues/568 to notify
|
||||
# the html5lib developers of these issues.
|
||||
@pytest.mark.skip("html5lib problems")
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
# b"""ÿ<!DOCTyPEV PUBLIC'''Ð'"""
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-4818336571064320",
|
||||
|
||||
# b')<a><math><TR><a><mI><a><p><a>'
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-4999465949331456",
|
||||
|
||||
# b'-<math><sElect><mi><sElect><sElect>'
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5843991618256896",
|
||||
|
||||
# b'ñ<table><svg><html>'
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6241471367348224",
|
||||
|
||||
# <TABLE>, some ^@ characters, some <math> tags.
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6600557255327744",
|
||||
|
||||
# Nested table
|
||||
"crash-0d306a50c8ed8bcd0785b67000fcd5dea1d33f08"
|
||||
]
|
||||
)
|
||||
def test_html5lib_parse_errors(self, filename):
|
||||
markup = self.__markup(filename)
|
||||
print(BeautifulSoup(markup, 'html5lib').encode())
|
||||
|
||||
def __markup(self, filename):
|
||||
if not filename.endswith(self.TESTCASE_SUFFIX):
|
||||
filename += self.TESTCASE_SUFFIX
|
||||
this_dir = os.path.split(__file__)[0]
|
||||
path = os.path.join(this_dir, 'fuzz', filename)
|
||||
return open(path, 'rb').read()
|
||||
|
|
@ -3,9 +3,11 @@ trees."""
|
|||
|
||||
from pdb import set_trace
|
||||
import pickle
|
||||
import pytest
|
||||
import warnings
|
||||
from bs4.builder import (
|
||||
HTMLParserTreeBuilder,
|
||||
ParserRejectedMarkup,
|
||||
XMLParsedAsHTMLWarning,
|
||||
)
|
||||
from bs4.builder._htmlparser import BeautifulSoupHTMLParser
|
||||
|
|
@ -15,6 +17,28 @@ class TestHTMLParserTreeBuilder(SoupTest, HTMLTreeBuilderSmokeTest):
|
|||
|
||||
default_builder = HTMLParserTreeBuilder
|
||||
|
||||
def test_rejected_input(self):
|
||||
# Python's html.parser will occasionally reject markup,
|
||||
# especially when there is a problem with the initial DOCTYPE
|
||||
# declaration. Different versions of Python sound the alarm in
|
||||
# different ways, but Beautiful Soup consistently raises
|
||||
# errors as ParserRejectedMarkup exceptions.
|
||||
bad_markup = [
|
||||
# https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=28873
|
||||
# https://github.com/guidovranken/python-library-fuzzers/blob/master/corp-html/519e5b4269a01185a0d5e76295251921da2f0700
|
||||
# https://github.com/python/cpython/issues/81928
|
||||
b'\n<![\xff\xfe\xfe\xcd\x00',
|
||||
|
||||
#https://github.com/guidovranken/python-library-fuzzers/blob/master/corp-html/de32aa55785be29bbc72a1a8e06b00611fb3d9f8
|
||||
# https://github.com/python/cpython/issues/78661
|
||||
#
|
||||
b'<![n\x00',
|
||||
b"<![UNKNOWN[]]>",
|
||||
]
|
||||
for markup in bad_markup:
|
||||
with pytest.raises(ParserRejectedMarkup):
|
||||
soup = self.soup(markup)
|
||||
|
||||
def test_namespaced_system_doctype(self):
|
||||
# html.parser can't handle namespaced doctypes, so skip this one.
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -189,13 +189,15 @@ class TestLXMLXMLTreeBuilder(SoupTest, XMLTreeBuilderSmokeTest):
|
|||
assert soup.find('prefix:tag3').name == 'tag3'
|
||||
assert soup.subtag.find('prefix:tag3').name == 'tag3'
|
||||
|
||||
def test_pickle_removes_builder(self):
|
||||
# The lxml TreeBuilder is not picklable, so it won't be
|
||||
# preserved in a pickle/unpickle operation.
|
||||
|
||||
def test_pickle_restores_builder(self):
|
||||
# The lxml TreeBuilder is not picklable, so when unpickling
|
||||
# a document created with it, a new TreeBuilder of the
|
||||
# appropriate class is created.
|
||||
soup = self.soup("<a>some markup</a>")
|
||||
assert isinstance(soup.builder, self.default_builder)
|
||||
pickled = pickle.dumps(soup)
|
||||
unpickled = pickle.loads(pickled)
|
||||
|
||||
assert "some markup" == unpickled.a.string
|
||||
assert unpickled.builder is None
|
||||
assert unpickled.builder != soup.builder
|
||||
assert isinstance(unpickled.builder, self.default_builder)
|
||||
|
|
|
|||
|
|
@ -2,20 +2,18 @@
|
|||
import copy
|
||||
import pickle
|
||||
import pytest
|
||||
import sys
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
from bs4.element import (
|
||||
Comment,
|
||||
ResultSet,
|
||||
SoupStrainer,
|
||||
)
|
||||
from . import (
|
||||
SoupTest,
|
||||
SOUP_SIEVE_PRESENT,
|
||||
)
|
||||
|
||||
if SOUP_SIEVE_PRESENT:
|
||||
from soupsieve import SelectorSyntaxError
|
||||
|
||||
class TestEncoding(SoupTest):
|
||||
"""Test the ability to encode objects into strings."""
|
||||
|
||||
|
|
@ -51,10 +49,21 @@ class TestEncoding(SoupTest):
|
|||
assert "\N{SNOWMAN}".encode("utf8") == soup.b.encode_contents(
|
||||
encoding="utf8"
|
||||
)
|
||||
|
||||
def test_encode_deeply_nested_document(self):
|
||||
# This test verifies that encoding a string doesn't involve
|
||||
# any recursive function calls. If it did, this test would
|
||||
# overflow the Python interpreter stack.
|
||||
limit = sys.getrecursionlimit() + 1
|
||||
markup = "<span>" * limit
|
||||
soup = self.soup(markup)
|
||||
encoded = soup.encode()
|
||||
assert limit == encoded.count(b"<span>")
|
||||
|
||||
def test_deprecated_renderContents(self):
|
||||
html = "<b>\N{SNOWMAN}</b>"
|
||||
soup = self.soup(html)
|
||||
soup.renderContents()
|
||||
assert "\N{SNOWMAN}".encode("utf8") == soup.b.renderContents()
|
||||
|
||||
def test_repr(self):
|
||||
|
|
@ -159,7 +168,31 @@ class TestFormatters(SoupTest):
|
|||
soup = self.soup("<div> foo <pre> \tbar\n \n </pre> baz <textarea> eee\nfff\t</textarea></div>")
|
||||
# Everything outside the <pre> tag is reformatted, but everything
|
||||
# inside is left alone.
|
||||
assert '<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n <textarea> eee\nfff\t</textarea>\n</div>' == soup.div.prettify()
|
||||
assert '<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n <textarea> eee\nfff\t</textarea>\n</div>\n' == soup.div.prettify()
|
||||
|
||||
def test_prettify_handles_nested_string_literal_tags(self):
|
||||
# Most of this markup is inside a <pre> tag, so prettify()
|
||||
# only does three things to it:
|
||||
# 1. Add a newline and a space between the <div> and the <pre>
|
||||
# 2. Add a newline after the </pre>
|
||||
# 3. Add a newline at the end.
|
||||
#
|
||||
# The contents of the <pre> tag are left completely alone. In
|
||||
# particular, we don't start adding whitespace again once we
|
||||
# encounter the first </pre> tag, because we know it's not
|
||||
# the one that put us into string literal mode.
|
||||
markup = """<div><pre><code>some
|
||||
<script><pre>code</pre></script> for you
|
||||
</code></pre></div>"""
|
||||
|
||||
expect = """<div>
|
||||
<pre><code>some
|
||||
<script><pre>code</pre></script> for you
|
||||
</code></pre>
|
||||
</div>
|
||||
"""
|
||||
soup = self.soup(markup)
|
||||
assert expect == soup.div.prettify()
|
||||
|
||||
def test_prettify_accepts_formatter_function(self):
|
||||
soup = BeautifulSoup("<html><body>foo</body></html>", 'html.parser')
|
||||
|
|
@ -216,429 +249,6 @@ class TestFormatters(SoupTest):
|
|||
assert soup.contents[0].name == 'pre'
|
||||
|
||||
|
||||
@pytest.mark.skipif(not SOUP_SIEVE_PRESENT, reason="Soup Sieve not installed")
|
||||
class TestCSSSelectors(SoupTest):
|
||||
"""Test basic CSS selector functionality.
|
||||
|
||||
This functionality is implemented in soupsieve, which has a much
|
||||
more comprehensive test suite, so this is basically an extra check
|
||||
that soupsieve works as expected.
|
||||
"""
|
||||
|
||||
HTML = """
|
||||
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
|
||||
"http://www.w3.org/TR/html4/strict.dtd">
|
||||
<html>
|
||||
<head>
|
||||
<title>The title</title>
|
||||
<link rel="stylesheet" href="blah.css" type="text/css" id="l1">
|
||||
</head>
|
||||
<body>
|
||||
<custom-dashed-tag class="dashed" id="dash1">Hello there.</custom-dashed-tag>
|
||||
<div id="main" class="fancy">
|
||||
<div id="inner">
|
||||
<h1 id="header1">An H1</h1>
|
||||
<p>Some text</p>
|
||||
<p class="onep" id="p1">Some more text</p>
|
||||
<h2 id="header2">An H2</h2>
|
||||
<p class="class1 class2 class3" id="pmulti">Another</p>
|
||||
<a href="http://bob.example.org/" rel="friend met" id="bob">Bob</a>
|
||||
<h2 id="header3">Another H2</h2>
|
||||
<a id="me" href="http://simonwillison.net/" rel="me">me</a>
|
||||
<span class="s1">
|
||||
<a href="#" id="s1a1">span1a1</a>
|
||||
<a href="#" id="s1a2">span1a2 <span id="s1a2s1">test</span></a>
|
||||
<span class="span2">
|
||||
<a href="#" id="s2a1">span2a1</a>
|
||||
</span>
|
||||
<span class="span3"></span>
|
||||
<custom-dashed-tag class="dashed" id="dash2"/>
|
||||
<div data-tag="dashedvalue" id="data1"/>
|
||||
</span>
|
||||
</div>
|
||||
<x id="xid">
|
||||
<z id="zida"/>
|
||||
<z id="zidab"/>
|
||||
<z id="zidac"/>
|
||||
</x>
|
||||
<y id="yid">
|
||||
<z id="zidb"/>
|
||||
</y>
|
||||
<p lang="en" id="lang-en">English</p>
|
||||
<p lang="en-gb" id="lang-en-gb">English UK</p>
|
||||
<p lang="en-us" id="lang-en-us">English US</p>
|
||||
<p lang="fr" id="lang-fr">French</p>
|
||||
</div>
|
||||
|
||||
<div id="footer">
|
||||
</div>
|
||||
"""
|
||||
|
||||
def setup_method(self):
|
||||
self.soup = BeautifulSoup(self.HTML, 'html.parser')
|
||||
|
||||
def assert_selects(self, selector, expected_ids, **kwargs):
|
||||
el_ids = [el['id'] for el in self.soup.select(selector, **kwargs)]
|
||||
el_ids.sort()
|
||||
expected_ids.sort()
|
||||
assert expected_ids == el_ids, "Selector %s, expected [%s], got [%s]" % (
|
||||
selector, ', '.join(expected_ids), ', '.join(el_ids)
|
||||
)
|
||||
|
||||
assertSelect = assert_selects
|
||||
|
||||
def assert_select_multiple(self, *tests):
|
||||
for selector, expected_ids in tests:
|
||||
self.assert_selects(selector, expected_ids)
|
||||
|
||||
def test_one_tag_one(self):
|
||||
els = self.soup.select('title')
|
||||
assert len(els) == 1
|
||||
assert els[0].name == 'title'
|
||||
assert els[0].contents == ['The title']
|
||||
|
||||
def test_one_tag_many(self):
|
||||
els = self.soup.select('div')
|
||||
assert len(els) == 4
|
||||
for div in els:
|
||||
assert div.name == 'div'
|
||||
|
||||
el = self.soup.select_one('div')
|
||||
assert 'main' == el['id']
|
||||
|
||||
def test_select_one_returns_none_if_no_match(self):
|
||||
match = self.soup.select_one('nonexistenttag')
|
||||
assert None == match
|
||||
|
||||
|
||||
def test_tag_in_tag_one(self):
|
||||
els = self.soup.select('div div')
|
||||
self.assert_selects('div div', ['inner', 'data1'])
|
||||
|
||||
def test_tag_in_tag_many(self):
|
||||
for selector in ('html div', 'html body div', 'body div'):
|
||||
self.assert_selects(selector, ['data1', 'main', 'inner', 'footer'])
|
||||
|
||||
|
||||
def test_limit(self):
|
||||
self.assert_selects('html div', ['main'], limit=1)
|
||||
self.assert_selects('html body div', ['inner', 'main'], limit=2)
|
||||
self.assert_selects('body div', ['data1', 'main', 'inner', 'footer'],
|
||||
limit=10)
|
||||
|
||||
def test_tag_no_match(self):
|
||||
assert len(self.soup.select('del')) == 0
|
||||
|
||||
def test_invalid_tag(self):
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select('tag%t')
|
||||
|
||||
def test_select_dashed_tag_ids(self):
|
||||
self.assert_selects('custom-dashed-tag', ['dash1', 'dash2'])
|
||||
|
||||
def test_select_dashed_by_id(self):
|
||||
dashed = self.soup.select('custom-dashed-tag[id=\"dash2\"]')
|
||||
assert dashed[0].name == 'custom-dashed-tag'
|
||||
assert dashed[0]['id'] == 'dash2'
|
||||
|
||||
def test_dashed_tag_text(self):
|
||||
assert self.soup.select('body > custom-dashed-tag')[0].text == 'Hello there.'
|
||||
|
||||
def test_select_dashed_matches_find_all(self):
|
||||
assert self.soup.select('custom-dashed-tag') == self.soup.find_all('custom-dashed-tag')
|
||||
|
||||
def test_header_tags(self):
|
||||
self.assert_select_multiple(
|
||||
('h1', ['header1']),
|
||||
('h2', ['header2', 'header3']),
|
||||
)
|
||||
|
||||
def test_class_one(self):
|
||||
for selector in ('.onep', 'p.onep', 'html p.onep'):
|
||||
els = self.soup.select(selector)
|
||||
assert len(els) == 1
|
||||
assert els[0].name == 'p'
|
||||
assert els[0]['class'] == ['onep']
|
||||
|
||||
def test_class_mismatched_tag(self):
|
||||
els = self.soup.select('div.onep')
|
||||
assert len(els) == 0
|
||||
|
||||
def test_one_id(self):
|
||||
for selector in ('div#inner', '#inner', 'div div#inner'):
|
||||
self.assert_selects(selector, ['inner'])
|
||||
|
||||
def test_bad_id(self):
|
||||
els = self.soup.select('#doesnotexist')
|
||||
assert len(els) == 0
|
||||
|
||||
def test_items_in_id(self):
|
||||
els = self.soup.select('div#inner p')
|
||||
assert len(els) == 3
|
||||
for el in els:
|
||||
assert el.name == 'p'
|
||||
assert els[1]['class'] == ['onep']
|
||||
assert not els[0].has_attr('class')
|
||||
|
||||
def test_a_bunch_of_emptys(self):
|
||||
for selector in ('div#main del', 'div#main div.oops', 'div div#main'):
|
||||
assert len(self.soup.select(selector)) == 0
|
||||
|
||||
def test_multi_class_support(self):
|
||||
for selector in ('.class1', 'p.class1', '.class2', 'p.class2',
|
||||
'.class3', 'p.class3', 'html p.class2', 'div#inner .class2'):
|
||||
self.assert_selects(selector, ['pmulti'])
|
||||
|
||||
def test_multi_class_selection(self):
|
||||
for selector in ('.class1.class3', '.class3.class2',
|
||||
'.class1.class2.class3'):
|
||||
self.assert_selects(selector, ['pmulti'])
|
||||
|
||||
def test_child_selector(self):
|
||||
self.assert_selects('.s1 > a', ['s1a1', 's1a2'])
|
||||
self.assert_selects('.s1 > a span', ['s1a2s1'])
|
||||
|
||||
def test_child_selector_id(self):
|
||||
self.assert_selects('.s1 > a#s1a2 span', ['s1a2s1'])
|
||||
|
||||
def test_attribute_equals(self):
|
||||
self.assert_select_multiple(
|
||||
('p[class="onep"]', ['p1']),
|
||||
('p[id="p1"]', ['p1']),
|
||||
('[class="onep"]', ['p1']),
|
||||
('[id="p1"]', ['p1']),
|
||||
('link[rel="stylesheet"]', ['l1']),
|
||||
('link[type="text/css"]', ['l1']),
|
||||
('link[href="blah.css"]', ['l1']),
|
||||
('link[href="no-blah.css"]', []),
|
||||
('[rel="stylesheet"]', ['l1']),
|
||||
('[type="text/css"]', ['l1']),
|
||||
('[href="blah.css"]', ['l1']),
|
||||
('[href="no-blah.css"]', []),
|
||||
('p[href="no-blah.css"]', []),
|
||||
('[href="no-blah.css"]', []),
|
||||
)
|
||||
|
||||
def test_attribute_tilde(self):
|
||||
self.assert_select_multiple(
|
||||
('p[class~="class1"]', ['pmulti']),
|
||||
('p[class~="class2"]', ['pmulti']),
|
||||
('p[class~="class3"]', ['pmulti']),
|
||||
('[class~="class1"]', ['pmulti']),
|
||||
('[class~="class2"]', ['pmulti']),
|
||||
('[class~="class3"]', ['pmulti']),
|
||||
('a[rel~="friend"]', ['bob']),
|
||||
('a[rel~="met"]', ['bob']),
|
||||
('[rel~="friend"]', ['bob']),
|
||||
('[rel~="met"]', ['bob']),
|
||||
)
|
||||
|
||||
def test_attribute_startswith(self):
|
||||
self.assert_select_multiple(
|
||||
('[rel^="style"]', ['l1']),
|
||||
('link[rel^="style"]', ['l1']),
|
||||
('notlink[rel^="notstyle"]', []),
|
||||
('[rel^="notstyle"]', []),
|
||||
('link[rel^="notstyle"]', []),
|
||||
('link[href^="bla"]', ['l1']),
|
||||
('a[href^="http://"]', ['bob', 'me']),
|
||||
('[href^="http://"]', ['bob', 'me']),
|
||||
('[id^="p"]', ['pmulti', 'p1']),
|
||||
('[id^="m"]', ['me', 'main']),
|
||||
('div[id^="m"]', ['main']),
|
||||
('a[id^="m"]', ['me']),
|
||||
('div[data-tag^="dashed"]', ['data1'])
|
||||
)
|
||||
|
||||
def test_attribute_endswith(self):
|
||||
self.assert_select_multiple(
|
||||
('[href$=".css"]', ['l1']),
|
||||
('link[href$=".css"]', ['l1']),
|
||||
('link[id$="1"]', ['l1']),
|
||||
('[id$="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's2a1', 's1a2s1', 'dash1']),
|
||||
('div[id$="1"]', ['data1']),
|
||||
('[id$="noending"]', []),
|
||||
)
|
||||
|
||||
def test_attribute_contains(self):
|
||||
self.assert_select_multiple(
|
||||
# From test_attribute_startswith
|
||||
('[rel*="style"]', ['l1']),
|
||||
('link[rel*="style"]', ['l1']),
|
||||
('notlink[rel*="notstyle"]', []),
|
||||
('[rel*="notstyle"]', []),
|
||||
('link[rel*="notstyle"]', []),
|
||||
('link[href*="bla"]', ['l1']),
|
||||
('[href*="http://"]', ['bob', 'me']),
|
||||
('[id*="p"]', ['pmulti', 'p1']),
|
||||
('div[id*="m"]', ['main']),
|
||||
('a[id*="m"]', ['me']),
|
||||
# From test_attribute_endswith
|
||||
('[href*=".css"]', ['l1']),
|
||||
('link[href*=".css"]', ['l1']),
|
||||
('link[id*="1"]', ['l1']),
|
||||
('[id*="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's1a2', 's2a1', 's1a2s1', 'dash1']),
|
||||
('div[id*="1"]', ['data1']),
|
||||
('[id*="noending"]', []),
|
||||
# New for this test
|
||||
('[href*="."]', ['bob', 'me', 'l1']),
|
||||
('a[href*="."]', ['bob', 'me']),
|
||||
('link[href*="."]', ['l1']),
|
||||
('div[id*="n"]', ['main', 'inner']),
|
||||
('div[id*="nn"]', ['inner']),
|
||||
('div[data-tag*="edval"]', ['data1'])
|
||||
)
|
||||
|
||||
def test_attribute_exact_or_hypen(self):
|
||||
self.assert_select_multiple(
|
||||
('p[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
|
||||
('[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
|
||||
('p[lang|="fr"]', ['lang-fr']),
|
||||
('p[lang|="gb"]', []),
|
||||
)
|
||||
|
||||
def test_attribute_exists(self):
|
||||
self.assert_select_multiple(
|
||||
('[rel]', ['l1', 'bob', 'me']),
|
||||
('link[rel]', ['l1']),
|
||||
('a[rel]', ['bob', 'me']),
|
||||
('[lang]', ['lang-en', 'lang-en-gb', 'lang-en-us', 'lang-fr']),
|
||||
('p[class]', ['p1', 'pmulti']),
|
||||
('[blah]', []),
|
||||
('p[blah]', []),
|
||||
('div[data-tag]', ['data1'])
|
||||
)
|
||||
|
||||
def test_quoted_space_in_selector_name(self):
|
||||
html = """<div style="display: wrong">nope</div>
|
||||
<div style="display: right">yes</div>
|
||||
"""
|
||||
soup = BeautifulSoup(html, 'html.parser')
|
||||
[chosen] = soup.select('div[style="display: right"]')
|
||||
assert "yes" == chosen.string
|
||||
|
||||
def test_unsupported_pseudoclass(self):
|
||||
with pytest.raises(NotImplementedError):
|
||||
self.soup.select("a:no-such-pseudoclass")
|
||||
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select("a:nth-of-type(a)")
|
||||
|
||||
def test_nth_of_type(self):
|
||||
# Try to select first paragraph
|
||||
els = self.soup.select('div#inner p:nth-of-type(1)')
|
||||
assert len(els) == 1
|
||||
assert els[0].string == 'Some text'
|
||||
|
||||
# Try to select third paragraph
|
||||
els = self.soup.select('div#inner p:nth-of-type(3)')
|
||||
assert len(els) == 1
|
||||
assert els[0].string == 'Another'
|
||||
|
||||
# Try to select (non-existent!) fourth paragraph
|
||||
els = self.soup.select('div#inner p:nth-of-type(4)')
|
||||
assert len(els) == 0
|
||||
|
||||
# Zero will select no tags.
|
||||
els = self.soup.select('div p:nth-of-type(0)')
|
||||
assert len(els) == 0
|
||||
|
||||
def test_nth_of_type_direct_descendant(self):
|
||||
els = self.soup.select('div#inner > p:nth-of-type(1)')
|
||||
assert len(els) == 1
|
||||
assert els[0].string == 'Some text'
|
||||
|
||||
def test_id_child_selector_nth_of_type(self):
|
||||
self.assert_selects('#inner > p:nth-of-type(2)', ['p1'])
|
||||
|
||||
def test_select_on_element(self):
|
||||
# Other tests operate on the tree; this operates on an element
|
||||
# within the tree.
|
||||
inner = self.soup.find("div", id="main")
|
||||
selected = inner.select("div")
|
||||
# The <div id="inner"> tag was selected. The <div id="footer">
|
||||
# tag was not.
|
||||
self.assert_selects_ids(selected, ['inner', 'data1'])
|
||||
|
||||
def test_overspecified_child_id(self):
|
||||
self.assert_selects(".fancy #inner", ['inner'])
|
||||
self.assert_selects(".normal #inner", [])
|
||||
|
||||
def test_adjacent_sibling_selector(self):
|
||||
self.assert_selects('#p1 + h2', ['header2'])
|
||||
self.assert_selects('#p1 + h2 + p', ['pmulti'])
|
||||
self.assert_selects('#p1 + #header2 + .class1', ['pmulti'])
|
||||
assert [] == self.soup.select('#p1 + p')
|
||||
|
||||
def test_general_sibling_selector(self):
|
||||
self.assert_selects('#p1 ~ h2', ['header2', 'header3'])
|
||||
self.assert_selects('#p1 ~ #header2', ['header2'])
|
||||
self.assert_selects('#p1 ~ h2 + a', ['me'])
|
||||
self.assert_selects('#p1 ~ h2 + [rel="me"]', ['me'])
|
||||
assert [] == self.soup.select('#inner ~ h2')
|
||||
|
||||
def test_dangling_combinator(self):
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select('h1 >')
|
||||
|
||||
def test_sibling_combinator_wont_select_same_tag_twice(self):
|
||||
self.assert_selects('p[lang] ~ p', ['lang-en-gb', 'lang-en-us', 'lang-fr'])
|
||||
|
||||
# Test the selector grouping operator (the comma)
|
||||
def test_multiple_select(self):
|
||||
self.assert_selects('x, y', ['xid', 'yid'])
|
||||
|
||||
def test_multiple_select_with_no_space(self):
|
||||
self.assert_selects('x,y', ['xid', 'yid'])
|
||||
|
||||
def test_multiple_select_with_more_space(self):
|
||||
self.assert_selects('x, y', ['xid', 'yid'])
|
||||
|
||||
def test_multiple_select_duplicated(self):
|
||||
self.assert_selects('x, x', ['xid'])
|
||||
|
||||
def test_multiple_select_sibling(self):
|
||||
self.assert_selects('x, y ~ p[lang=fr]', ['xid', 'lang-fr'])
|
||||
|
||||
def test_multiple_select_tag_and_direct_descendant(self):
|
||||
self.assert_selects('x, y > z', ['xid', 'zidb'])
|
||||
|
||||
def test_multiple_select_direct_descendant_and_tags(self):
|
||||
self.assert_selects('div > x, y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
|
||||
|
||||
def test_multiple_select_indirect_descendant(self):
|
||||
self.assert_selects('div x,y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
|
||||
|
||||
def test_invalid_multiple_select(self):
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select(',x, y')
|
||||
with pytest.raises(SelectorSyntaxError):
|
||||
self.soup.select('x,,y')
|
||||
|
||||
def test_multiple_select_attrs(self):
|
||||
self.assert_selects('p[lang=en], p[lang=en-gb]', ['lang-en', 'lang-en-gb'])
|
||||
|
||||
def test_multiple_select_ids(self):
|
||||
self.assert_selects('x, y > z[id=zida], z[id=zidab], z[id=zidb]', ['xid', 'zidb', 'zidab'])
|
||||
|
||||
def test_multiple_select_nested(self):
|
||||
self.assert_selects('body > div > x, y > z', ['xid', 'zidb'])
|
||||
|
||||
def test_select_duplicate_elements(self):
|
||||
# When markup contains duplicate elements, a multiple select
|
||||
# will find all of them.
|
||||
markup = '<div class="c1"/><div class="c2"/><div class="c1"/>'
|
||||
soup = BeautifulSoup(markup, 'html.parser')
|
||||
selected = soup.select(".c1, .c2")
|
||||
assert 3 == len(selected)
|
||||
|
||||
# Verify that find_all finds the same elements, though because
|
||||
# of an implementation detail it finds them in a different
|
||||
# order.
|
||||
for element in soup.find_all(class_=['c1', 'c2']):
|
||||
assert element in selected
|
||||
|
||||
|
||||
class TestPersistence(SoupTest):
|
||||
"Testing features like pickle and deepcopy."
|
||||
|
||||
|
|
@ -668,12 +278,24 @@ class TestPersistence(SoupTest):
|
|||
loaded = pickle.loads(dumped)
|
||||
assert loaded.__class__ == BeautifulSoup
|
||||
assert loaded.decode() == self.tree.decode()
|
||||
|
||||
|
||||
def test_deepcopy_identity(self):
|
||||
# Making a deepcopy of a tree yields an identical tree.
|
||||
copied = copy.deepcopy(self.tree)
|
||||
assert copied.decode() == self.tree.decode()
|
||||
|
||||
def test_copy_deeply_nested_document(self):
|
||||
# This test verifies that copy and deepcopy don't involve any
|
||||
# recursive function calls. If they did, this test would
|
||||
# overflow the Python interpreter stack.
|
||||
limit = sys.getrecursionlimit() + 1
|
||||
markup = "<span>" * limit
|
||||
|
||||
soup = self.soup(markup)
|
||||
|
||||
copied = copy.copy(soup)
|
||||
copied = copy.deepcopy(soup)
|
||||
|
||||
def test_copy_preserves_encoding(self):
|
||||
soup = BeautifulSoup(b'<p> </p>', 'html.parser')
|
||||
encoding = soup.original_encoding
|
||||
|
|
|
|||
|
|
@ -24,6 +24,7 @@ from bs4.builder import (
|
|||
from bs4.element import (
|
||||
Comment,
|
||||
SoupStrainer,
|
||||
PYTHON_SPECIFIC_ENCODINGS,
|
||||
Tag,
|
||||
NavigableString,
|
||||
)
|
||||
|
|
@ -210,6 +211,47 @@ class TestConstructor(SoupTest):
|
|||
assert [] == soup.string_container_stack
|
||||
|
||||
|
||||
class TestOutput(SoupTest):
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"eventual_encoding,actual_encoding", [
|
||||
("utf-8", "utf-8"),
|
||||
("utf-16", "utf-16"),
|
||||
]
|
||||
)
|
||||
def test_decode_xml_declaration(self, eventual_encoding, actual_encoding):
|
||||
# Most of the time, calling decode() on an XML document will
|
||||
# give you a document declaration that mentions the encoding
|
||||
# you intend to use when encoding the document as a
|
||||
# bytestring.
|
||||
soup = self.soup("<tag></tag>")
|
||||
soup.is_xml = True
|
||||
assert (f'<?xml version="1.0" encoding="{actual_encoding}"?>\n<tag></tag>'
|
||||
== soup.decode(eventual_encoding=eventual_encoding))
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"eventual_encoding", [x for x in PYTHON_SPECIFIC_ENCODINGS] + [None]
|
||||
)
|
||||
def test_decode_xml_declaration_with_missing_or_python_internal_eventual_encoding(self, eventual_encoding):
|
||||
# But if you pass a Python internal encoding into decode(), or
|
||||
# omit the eventual_encoding altogether, the document
|
||||
# declaration won't mention any particular encoding.
|
||||
soup = BeautifulSoup("<tag></tag>", "html.parser")
|
||||
soup.is_xml = True
|
||||
assert (f'<?xml version="1.0"?>\n<tag></tag>'
|
||||
== soup.decode(eventual_encoding=eventual_encoding))
|
||||
|
||||
def test(self):
|
||||
# BeautifulSoup subclasses Tag and extends the decode() method.
|
||||
# Make sure the other Tag methods which call decode() call
|
||||
# it correctly.
|
||||
soup = self.soup("<tag></tag>")
|
||||
assert b"<tag></tag>" == soup.encode(encoding="utf-8")
|
||||
assert b"<tag></tag>" == soup.encode_contents(encoding="utf-8")
|
||||
assert "<tag></tag>" == soup.decode_contents()
|
||||
assert "<tag>\n</tag>\n" == soup.prettify()
|
||||
|
||||
|
||||
class TestWarnings(SoupTest):
|
||||
# Note that some of the tests in this class create BeautifulSoup
|
||||
# objects directly rather than using self.soup(). That's
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue