From 1f0f15f9b3620f75b30b700c4764a4f09eca8376 Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Fri, 3 Feb 2023 21:19:24 -0500 Subject: Move the Soup Sieve proxy and its tests into separate files. --- bs4/__init__.py | 1 + bs4/css.py | 251 ++++++++++++++++++++++ bs4/element.py | 233 +-------------------- bs4/tests/test_css.py | 468 ++++++++++++++++++++++++++++++++++++++++++ bs4/tests/test_pageelement.py | 458 ----------------------------------------- 5 files changed, 723 insertions(+), 688 deletions(-) create mode 100644 bs4/css.py create mode 100644 bs4/tests/test_css.py diff --git a/bs4/__init__.py b/bs4/__init__.py index db71cc7..a5128d2 100644 --- a/bs4/__init__.py +++ b/bs4/__init__.py @@ -43,6 +43,7 @@ from .dammit import UnicodeDammit from .element import ( CData, Comment, + CSS, DEFAULT_OUTPUT_ENCODING, Declaration, Doctype, diff --git a/bs4/css.py b/bs4/css.py new file mode 100644 index 0000000..5d60267 --- /dev/null +++ b/bs4/css.py @@ -0,0 +1,251 @@ +"""Integration code for CSS selectors using Soup Sieve (pypi: soupsieve).""" + +try: + import soupsieve +except ImportError as e: + soupsieve = None + warnings.warn( + 'The soupsieve package is not installed. CSS selectors cannot be used.' + ) + + +class CSS(object): + """A proxy object against the soupsieve library, to simplify its + CSS selector API. + + Acquire this object through the .css attribute on the + BeautifulSoup object, or on the Tag you want to use as the + starting point for a CSS selector. + + Specifically, the element to be selected against doesn't need to + be explicitly specified in the function call, since you access + this object through a specific tag. + + """ + + def __init__(self, tag): + """Constructor. + + You don't need to instantiate this class yourself; instead, + access the .css attribute on the BeautifulSoup object, or on + the Tag you want to use as the starting point for your CSS + selector. + + :param tag: All CSS selectors will use this as their starting + point. + + """ + if soupsieve is None: + raise NotImplementedError( + "Cannot execute CSS selectors because the soupsieve package is not installed." + ) + self.tag = tag + + @classmethod + def escape(cls, ident): + """Escape a CSS selector. + + This is a simple wrapper around soupselect.escape(). + """ + if soupsieve is None: + raise NotImplementedError( + "Cannot escape CSS selectors because the soupsieve package is not installed." + ) + return soupsieve.escape(ident) + + def _ns(self, ns): + """Normalize a dictionary of namespaces.""" + if ns is None: + ns = self.tag._namespaces + return ns + + def _rs(self, results): + """Normalize a list of results to a Resultset. + + A ResultSet is more consistent with the rest of Beautiful + Soup, and ResultSet.__getattr__ has a helpful error message if + you try to treat a list of results as a single result (a + common mistake). + """ + # Import here to avoid circular import + from bs4.element import ResultSet + return ResultSet(None, results) + + def select_one(self, select, namespaces=None, flags=0, **kwargs): + """Perform a CSS selection operation on the current Tag and return the + first result. + + This uses the Soup Sieve library. For more information, see + that library's documentation for the soupsieve.select_one() + method. + + :param selector: A CSS selector. + + :param namespaces: A dictionary mapping namespace prefixes + used in the CSS selector to namespace URIs. By default, + Beautiful Soup will use the prefixes it encountered while + parsing the document. + + :param flags: Flags to be passed into Soup Sieve's + soupsieve.select_one() method. + + :param kwargs: Keyword arguments to be passed into SoupSieve's + soupsieve.select_one() method. + + :return: A Tag, or None if the selector has no match. + :rtype: bs4.element.Tag + + """ + return soupsieve.select_one( + select, self.tag, self._ns(namespaces), flags, **kwargs + ) + + def select(self, select, namespaces=None, limit=0, flags=0, **kwargs): + """Perform a CSS selection operation on the current Tag. + + This uses the Soup Sieve library. For more information, see + that library's documentation for the soupsieve.select() + method. + + :param selector: A string containing a CSS selector. + + :param namespaces: A dictionary mapping namespace prefixes + used in the CSS selector to namespace URIs. By default, + Beautiful Soup will pass in the prefixes it encountered while + parsing the document. + + :param limit: After finding this number of results, stop looking. + + :param flags: Flags to be passed into Soup Sieve's + soupsieve.select() method. + + :param kwargs: Keyword arguments to be passed into SoupSieve's + soupsieve.select() method. + + :return: A ResultSet of Tag objects. + :rtype: bs4.element.ResultSet + + """ + if limit is None: + limit = 0 + + return self._rs( + soupsieve.select( + select, self.tag, self._ns(namespaces), limit, flags, + **kwargs + ) + ) + + def iselect(self, select, namespaces=None, limit=0, flags=0, **kwargs): + """Perform a CSS selection operation on the current Tag. + + This uses the Soup Sieve library. For more information, see + that library's documentation for the soupsieve.iselect() + method. It is the same as select(), but it returns a generator + instead of a list. + + :param selector: A string containing a CSS selector. + + :param namespaces: A dictionary mapping namespace prefixes + used in the CSS selector to namespace URIs. By default, + Beautiful Soup will pass in the prefixes it encountered while + parsing the document. + + :param limit: After finding this number of results, stop looking. + + :param flags: Flags to be passed into Soup Sieve's + soupsieve.iselect() method. + + :param kwargs: Keyword arguments to be passed into SoupSieve's + soupsieve.iselect() method. + + :return: A generator + :rtype: types.GeneratorType + """ + return soupsieve.iselect( + select, self.tag, self._ns(namespaces), limit, flags, **kwargs + ) + + def closest(self, select, namespaces=None, flags=0, **kwargs): + """Find the Tag closest to this one that matches the given selector. + + This uses the Soup Sieve library. For more information, see + that library's documentation for the soupsieve.closest() + method. + + :param selector: A string containing a CSS selector. + + :param namespaces: A dictionary mapping namespace prefixes + used in the CSS selector to namespace URIs. By default, + Beautiful Soup will pass in the prefixes it encountered while + parsing the document. + + :param flags: Flags to be passed into Soup Sieve's + soupsieve.closest() method. + + :param kwargs: Keyword arguments to be passed into SoupSieve's + soupsieve.closest() method. + + :return: A Tag, or None if there is no match. + :rtype: bs4.Tag + + """ + return soupsieve.closest( + select, self.tag, self._ns(namespaces), flags, **kwargs + ) + + def match(self, select, namespaces=None, flags=0, **kwargs): + """Check whether this Tag matches the given CSS selector. + + This uses the Soup Sieve library. For more information, see + that library's documentation for the soupsieve.match() + method. + + :param: a CSS selector. + + :param namespaces: A dictionary mapping namespace prefixes + used in the CSS selector to namespace URIs. By default, + Beautiful Soup will pass in the prefixes it encountered while + parsing the document. + + :param flags: Flags to be passed into Soup Sieve's + soupsieve.match() method. + + :param kwargs: Keyword arguments to be passed into SoupSieve's + soupsieve.match() method. + + :return: True if this Tag matches the selector; False otherwise. + :rtype: bool + """ + return soupsieve.match( + select, self.tag, self._ns(namespaces), flags, **kwargs + ) + + def filter(self, select, namespaces=None, flags=0, **kwargs): + """Filter this Tag's direct children based on the given CSS selector. + + This uses the Soup Sieve library. It works the same way as + passing this Tag into that library's soupsieve.filter() + method. More information, for more information see the + documentation for soupsieve.filter(). + + :param namespaces: A dictionary mapping namespace prefixes + used in the CSS selector to namespace URIs. By default, + Beautiful Soup will pass in the prefixes it encountered while + parsing the document. + + :param flags: Flags to be passed into Soup Sieve's + soupsieve.filter() method. + + :param kwargs: Keyword arguments to be passed into SoupSieve's + soupsieve.filter() method. + + :return: A ResultSet of Tag objects. + :rtype: bs4.element.ResultSet + + """ + return self._rs( + soupsieve.filter( + select, self.tag, self._ns(namespaces), flags, **kwargs + ) + ) diff --git a/bs4/element.py b/bs4/element.py index a96593c..619fb73 100644 --- a/bs4/element.py +++ b/bs4/element.py @@ -8,14 +8,8 @@ except ImportError as e: import re import sys import warnings -try: - import soupsieve -except ImportError as e: - soupsieve = None - warnings.warn( - 'The soupsieve package is not installed. CSS selectors cannot be used.' - ) +from bs4.css import CSS from bs4.formatter import ( Formatter, HTMLFormatter, @@ -1948,7 +1942,7 @@ class Tag(PageElement): Beautiful Soup will use the prefixes it encountered while parsing the document. - :param kwargs: Keyword arguments to be passed into SoupSieve's + :param kwargs: Keyword arguments to be passed into Soup Sieve's soupsieve.select() method. :return: A Tag. @@ -1981,7 +1975,7 @@ class Tag(PageElement): @property def css(self): """Return an interface to the CSS selector API.""" - return SoupSieveProxy(self) + return CSS(self) # Old names for backwards compatibility def childGenerator(self): @@ -2296,224 +2290,3 @@ class ResultSet(list): raise AttributeError( "ResultSet object has no attribute '%s'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?" % key ) - -class SoupSieveProxy(object): - """A proxy object against the soupsieve library, to simplify its - CSS selector API. - - Specifically, the element to be selected against doesn't need to - be explicitly specified in the function call, since you access - this object through a specific tag. - """ - - def __init__(self, tag): - """Constructor. - - You don't need to instantiate this class yourself; instead, - access the .css attribute on the Tag you want to use as the - starting point for your CSS selector, or on the BeautifulSoup - object itself. - - :param tag: All CSS selectors will use this as their starting - point. - """ - if soupsieve is None: - raise NotImplementedError( - "Cannot execute CSS selectors because the soupsieve package is not installed." - ) - self.tag = tag - - def _ns(self, ns): - """Normalize a dictionary of namespaces.""" - if ns is None: - ns = self.tag._namespaces - return ns - - def _rs(self, results): - """Normalize a list of results to a Resultset. - - A ResultSet is more consistent with the rest of Beautiful - Soup, and ResultSet.__getattr__ has a helpful error message if - you try to treat a list of results as a single result (a - common mistake). - """ - return ResultSet(None, results) - - def select_one(self, select, namespaces=None, flags=0, **kwargs): - """Perform a CSS selection operation on the current Tag and return the - first result. - - This uses the Soup Sieve library. For more information, see - that library's documentation for the soupsieve.select_one() - method. - - :param selector: A CSS selector. - - :param namespaces: A dictionary mapping namespace prefixes - used in the CSS selector to namespace URIs. By default, - Beautiful Soup will use the prefixes it encountered while - parsing the document. - - :param flags: Flags to be passed into Soup Sieve's - soupsieve.select_one() method. - - :param kwargs: Keyword arguments to be passed into SoupSieve's - soupsieve.select_one() method. - - :return: A Tag, or None if the selector has no match. - :rtype: bs4.element.Tag - - """ - return soupsieve.select_one( - select, self.tag, self._ns(namespaces), flags, **kwargs - ) - - def select(self, select, namespaces=None, limit=0, flags=0, **kwargs): - """Perform a CSS selection operation on the current Tag. - - This uses the Soup Sieve library. For more information, see - that library's documentation for the soupsieve.select() - method. - - :param selector: A string containing a CSS selector. - - :param namespaces: A dictionary mapping namespace prefixes - used in the CSS selector to namespace URIs. By default, - Beautiful Soup will pass in the prefixes it encountered while - parsing the document. - - :param limit: After finding this number of results, stop looking. - - :param flags: Flags to be passed into Soup Sieve's - soupsieve.select() method. - - :param kwargs: Keyword arguments to be passed into SoupSieve's - soupsieve.select() method. - - :return: A ResultSet of Tag objects. - :rtype: bs4.element.ResultSet - - """ - if limit is None: - limit = 0 - - return self._rs( - soupsieve.select( - select, self.tag, self._ns(namespaces), limit, flags, - **kwargs - ) - ) - - def iselect(self, select, namespaces=None, limit=0, flags=0, **kwargs): - """Perform a CSS selection operation on the current Tag. - - This uses the Soup Sieve library. For more information, see - that library's documentation for the soupsieve.iselect() - method. It is the same as select(), but it returns a generator - instead of a list. - - :param selector: A string containing a CSS selector. - - :param namespaces: A dictionary mapping namespace prefixes - used in the CSS selector to namespace URIs. By default, - Beautiful Soup will pass in the prefixes it encountered while - parsing the document. - - :param limit: After finding this number of results, stop looking. - - :param flags: Flags to be passed into Soup Sieve's - soupsieve.iselect() method. - - :param kwargs: Keyword arguments to be passed into SoupSieve's - soupsieve.iselect() method. - - :return: A generator - :rtype: types.GeneratorType - """ - return soupsieve.iselect( - select, self.tag, self._ns(namespaces), limit, flags, **kwargs - ) - - def closest(self, select, namespaces=None, flags=0, **kwargs): - """Find the Tag closest to this one that matches the given selector. - - This uses the Soup Sieve library. For more information, see - that library's documentation for the soupsieve.closest() - method. - - :param selector: A string containing a CSS selector. - - :param namespaces: A dictionary mapping namespace prefixes - used in the CSS selector to namespace URIs. By default, - Beautiful Soup will pass in the prefixes it encountered while - parsing the document. - - :param flags: Flags to be passed into Soup Sieve's - soupsieve.closest() method. - - :param kwargs: Keyword arguments to be passed into SoupSieve's - soupsieve.closest() method. - - :return: A Tag, or None if there is no match. - :rtype: bs4.Tag - - """ - return soupsieve.closest( - select, self.tag, self._ns(namespaces), flags, **kwargs - ) - - def match(self, select, namespaces=None, flags=0, **kwargs): - """Check whether this Tag matches the given CSS selector. - - This uses the Soup Sieve library. For more information, see - that library's documentation for the soupsieve.match() - method. - - :param: a CSS selector. - - :param namespaces: A dictionary mapping namespace prefixes - used in the CSS selector to namespace URIs. By default, - Beautiful Soup will pass in the prefixes it encountered while - parsing the document. - - :param flags: Flags to be passed into Soup Sieve's - soupsieve.match() method. - - :param kwargs: Keyword arguments to be passed into SoupSieve's - soupsieve.match() method. - - :return: True if this Tag matches the selector; False otherwise. - :rtype: bool - """ - return soupsieve.match( - select, self.tag, self._ns(namespaces), flags, **kwargs - ) - - def filter(self, select, namespaces=None, flags=0, **kwargs): - """Filter this Tag's direct children based on the given CSS selector. - - This uses the Soup Sieve library. It works the same way as - passing this Tag into that library's soupsieve.filter() - method. More information, for more information see the - documentation for soupsieve.filter(). - - :param namespaces: A dictionary mapping namespace prefixes - used in the CSS selector to namespace URIs. By default, - Beautiful Soup will pass in the prefixes it encountered while - parsing the document. - - :param flags: Flags to be passed into Soup Sieve's - soupsieve.filter() method. - - :param kwargs: Keyword arguments to be passed into SoupSieve's - soupsieve.filter() method. - - :return: A ResultSet of Tag objects. - :rtype: bs4.element.ResultSet - - """ - return self._rs( - soupsieve.filter( - select, self.tag, self._ns(namespaces), flags, **kwargs - ) - ) diff --git a/bs4/tests/test_css.py b/bs4/tests/test_css.py new file mode 100644 index 0000000..3da9aed --- /dev/null +++ b/bs4/tests/test_css.py @@ -0,0 +1,468 @@ +import pytest +import types + +from bs4 import ( + 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 = """ + + + +The title + + + +Hello there. +
+
+

An H1

+

Some text

+

Some more text

+

An H2

+

Another

+Bob +

Another H2

+me + +span1a1 +span1a2 test + +span2a1 + + + +
+ +
+ + + + + + + + +

English

+

English UK

+

English US

+

French

+
+ + +""" + + 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_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 = """
nope
+
yes
+ """ + 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
tag was selected. The