diff options
Diffstat (limited to 'bs4/tests/test_tree.py')
| -rw-r--r-- | bs4/tests/test_tree.py | 130 |
1 files changed, 65 insertions, 65 deletions
diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index 26004ce..59b51d0 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -75,13 +75,13 @@ class TestFind(TreeTest): self.assertEqual(soup.find("b").string, "2") def test_unicode_text_find(self): - soup = self.soup(u'<h1>Räksmörgås</h1>') - self.assertEqual(soup.find(string=u'Räksmörgås'), u'Räksmörgås') + soup = self.soup('<h1>Räksmörgås</h1>') + self.assertEqual(soup.find(string='Räksmörgås'), 'Räksmörgås') def test_unicode_attribute_find(self): - soup = self.soup(u'<h1 id="Räksmörgås">here it is</h1>') + soup = self.soup('<h1 id="Räksmörgås">here it is</h1>') str(soup) - self.assertEqual("here it is", soup.find(id=u'Räksmörgås').text) + self.assertEqual("here it is", soup.find(id='Räksmörgås').text) def test_find_everything(self): @@ -101,17 +101,17 @@ class TestFindAll(TreeTest): """You can search the tree for text nodes.""" soup = self.soup("<html>Foo<b>bar</b>\xbb</html>") # Exact match. - self.assertEqual(soup.find_all(string="bar"), [u"bar"]) - self.assertEqual(soup.find_all(text="bar"), [u"bar"]) + self.assertEqual(soup.find_all(string="bar"), ["bar"]) + self.assertEqual(soup.find_all(text="bar"), ["bar"]) # Match any of a number of strings. self.assertEqual( - soup.find_all(text=["Foo", "bar"]), [u"Foo", u"bar"]) + soup.find_all(text=["Foo", "bar"]), ["Foo", "bar"]) # Match a regular expression. self.assertEqual(soup.find_all(text=re.compile('.*')), - [u"Foo", u"bar", u'\xbb']) + ["Foo", "bar", '\xbb']) # Match anything. self.assertEqual(soup.find_all(text=True), - [u"Foo", u"bar", u'\xbb']) + ["Foo", "bar", '\xbb']) def test_find_all_limit(self): """You can limit the number of items returned by find_all.""" @@ -254,8 +254,8 @@ class TestFindAllByAttribute(TreeTest): ["Matching a.", "Matching b."]) def test_find_all_by_utf8_attribute_value(self): - peace = u"םולש".encode("utf8") - data = u'<a title="םולש"></a>'.encode("utf8") + peace = "םולש".encode("utf8") + data = '<a title="םולש"></a>'.encode("utf8") soup = self.soup(data) self.assertEqual([soup.a], soup.find_all(title=peace)) self.assertEqual([soup.a], soup.find_all(title=peace.decode("utf8"))) @@ -444,7 +444,7 @@ class TestSmooth(TreeTest): # output. # Since the <span> tag has two children, its .string is None. - self.assertEquals(None, div.span.string) + self.assertEqual(None, div.span.string) self.assertEqual(7, len(div.contents)) div.smooth() @@ -755,18 +755,18 @@ class TestTag(SoupTest): # No list of whitespace-preserving tags -> pretty-print tag._preserve_whitespace_tags = None - self.assertEquals(True, tag._should_pretty_print(0)) + self.assertEqual(True, tag._should_pretty_print(0)) # List exists but tag is not on the list -> pretty-print tag.preserve_whitespace_tags = ["some_other_tag"] - self.assertEquals(True, tag._should_pretty_print(1)) + self.assertEqual(True, tag._should_pretty_print(1)) # Indent level is None -> don't pretty-print - self.assertEquals(False, tag._should_pretty_print(None)) + self.assertEqual(False, tag._should_pretty_print(None)) # Tag is on the whitespace-preserving list -> don't pretty-print tag.preserve_whitespace_tags = ["some_other_tag", "a_tag"] - self.assertEquals(False, tag._should_pretty_print(1)) + self.assertEqual(False, tag._should_pretty_print(1)) class TestTagCreation(SoupTest): @@ -905,10 +905,10 @@ class TestTreeModification(SoupTest): assert not isinstance(i, BeautifulSoup) p1, p2, p3, p4 = list(soup.children) - self.assertEquals("And now, a word:", p1.string) - self.assertEquals("p2", p2.string) - self.assertEquals("p3", p3.string) - self.assertEquals("And we're back.", p4.string) + self.assertEqual("And now, a word:", p1.string) + self.assertEqual("p2", p2.string) + self.assertEqual("p3", p3.string) + self.assertEqual("And we're back.", p4.string) def test_replace_with_maintains_next_element_throughout(self): @@ -1015,8 +1015,8 @@ class TestTreeModification(SoupTest): d1 = soup.find('div', id='d1') d2 = soup.find('div', id='d2') d2.extend(d1) - self.assertEqual(u'<div id="d1"></div>', d1.decode()) - self.assertEqual(u'<div id="d2"><a>1</a><a>2</a><a>3</a><a>4</a></div>', d2.decode()) + self.assertEqual('<div id="d1"></div>', d1.decode()) + self.assertEqual('<div id="d2"><a>1</a><a>2</a><a>3</a><a>4</a></div>', d2.decode()) def test_move_tag_to_beginning_of_parent(self): data = "<a><b></b><c></c><d></d></a>" @@ -1293,7 +1293,7 @@ class TestTreeModification(SoupTest): <script>baz</script> </html>""") [soup.script.extract() for i in soup.find_all("script")] - self.assertEqual("<body>\n\n<a></a>\n</body>", unicode(soup.body)) + self.assertEqual("<body>\n\n<a></a>\n</body>", str(soup.body)) def test_extract_works_when_element_is_surrounded_by_identical_strings(self): @@ -1589,7 +1589,7 @@ class TestPersistence(SoupTest): soup = BeautifulSoup(b'<p> </p>', 'html.parser') encoding = soup.original_encoding copy = soup.__copy__() - self.assertEqual(u"<p> </p>", unicode(copy)) + self.assertEqual("<p> </p>", str(copy)) self.assertEqual(encoding, copy.original_encoding) def test_copy_preserves_builder_information(self): @@ -1619,14 +1619,14 @@ class TestPersistence(SoupTest): def test_unicode_pickle(self): # A tree containing Unicode characters can be pickled. - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) dumped = pickle.dumps(soup, pickle.HIGHEST_PROTOCOL) loaded = pickle.loads(dumped) self.assertEqual(loaded.decode(), soup.decode()) def test_copy_navigablestring_is_not_attached_to_tree(self): - html = u"<b>Foo<a></a></b><b>Bar</b>" + html = "<b>Foo<a></a></b><b>Bar</b>" soup = self.soup(html) s1 = soup.find(string="Foo") s2 = copy.copy(s1) @@ -1638,7 +1638,7 @@ class TestPersistence(SoupTest): self.assertEqual(None, s2.previous_element) def test_copy_navigablestring_subclass_has_same_type(self): - html = u"<b><!--Foo--></b>" + html = "<b><!--Foo--></b>" soup = self.soup(html) s1 = soup.string s2 = copy.copy(s1) @@ -1646,19 +1646,19 @@ class TestPersistence(SoupTest): self.assertTrue(isinstance(s2, Comment)) def test_copy_entire_soup(self): - html = u"<div><b>Foo<a></a></b><b>Bar</b></div>end" + html = "<div><b>Foo<a></a></b><b>Bar</b></div>end" soup = self.soup(html) soup_copy = copy.copy(soup) self.assertEqual(soup, soup_copy) def test_copy_tag_copies_contents(self): - html = u"<div><b>Foo<a></a></b><b>Bar</b></div>end" + html = "<div><b>Foo<a></a></b><b>Bar</b></div>end" soup = self.soup(html) div = soup.div div_copy = copy.copy(div) # The two tags look the same, and evaluate to equal. - self.assertEqual(unicode(div), unicode(div_copy)) + self.assertEqual(str(div), str(div_copy)) self.assertEqual(div, div_copy) # But they're not the same object. @@ -1674,17 +1674,17 @@ class TestPersistence(SoupTest): class TestSubstitutions(SoupTest): def test_default_formatter_is_minimal(self): - markup = u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + markup = "<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) decoded = soup.decode(formatter="minimal") # The < is converted back into < but the e-with-acute is left alone. self.assertEqual( decoded, self.document_for( - u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) + "<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) def test_formatter_html(self): - markup = u"<br><b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + markup = "<br><b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) decoded = soup.decode(formatter="html") self.assertEqual( @@ -1692,7 +1692,7 @@ class TestSubstitutions(SoupTest): self.document_for("<br/><b><<Sacré bleu!>></b>")) def test_formatter_html5(self): - markup = u"<br><b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + markup = "<br><b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) decoded = soup.decode(formatter="html5") self.assertEqual( @@ -1700,49 +1700,49 @@ class TestSubstitutions(SoupTest): self.document_for("<br><b><<Sacré bleu!>></b>")) def test_formatter_minimal(self): - markup = u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + markup = "<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) decoded = soup.decode(formatter="minimal") # The < is converted back into < but the e-with-acute is left alone. self.assertEqual( decoded, self.document_for( - u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) + "<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) def test_formatter_null(self): - markup = u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" + markup = "<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>" soup = self.soup(markup) decoded = soup.decode(formatter=None) # Neither the angle brackets nor the e-with-acute are converted. # This is not valid HTML, but it's what the user wanted. self.assertEqual(decoded, - self.document_for(u"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) + self.document_for("<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>")) def test_formatter_custom(self): - markup = u"<b><foo></b><b>bar</b><br/>" + markup = "<b><foo></b><b>bar</b><br/>" soup = self.soup(markup) decoded = soup.decode(formatter = lambda x: x.upper()) # Instead of normal entity conversion code, the custom # callable is called on every string. self.assertEqual( decoded, - self.document_for(u"<b><FOO></b><b>BAR</b><br/>")) + self.document_for("<b><FOO></b><b>BAR</b><br/>")) def test_formatter_is_run_on_attribute_values(self): - markup = u'<a href="http://a.com?a=b&c=é">e</a>' + markup = '<a href="http://a.com?a=b&c=é">e</a>' soup = self.soup(markup) a = soup.a - expect_minimal = u'<a href="http://a.com?a=b&c=é">e</a>' + expect_minimal = '<a href="http://a.com?a=b&c=é">e</a>' self.assertEqual(expect_minimal, a.decode()) self.assertEqual(expect_minimal, a.decode(formatter="minimal")) - expect_html = u'<a href="http://a.com?a=b&c=é">e</a>' + expect_html = '<a href="http://a.com?a=b&c=é">e</a>' self.assertEqual(expect_html, a.decode(formatter="html")) self.assertEqual(markup, a.decode(formatter=None)) - expect_upper = u'<a href="HTTP://A.COM?A=B&C=É">E</a>' + expect_upper = '<a href="HTTP://A.COM?A=B&C=É">E</a>' self.assertEqual(expect_upper, a.decode(formatter=lambda x: x.upper())) def test_formatter_skips_script_tag_for_html_documents(self): @@ -1768,7 +1768,7 @@ class TestSubstitutions(SoupTest): # Everything outside the <pre> tag is reformatted, but everything # inside is left alone. self.assertEqual( - u'<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n <textarea> eee\nfff\t</textarea>\n</div>', + '<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n <textarea> eee\nfff\t</textarea>\n</div>', soup.div.prettify()) def test_prettify_accepts_formatter_function(self): @@ -1778,14 +1778,14 @@ class TestSubstitutions(SoupTest): def test_prettify_outputs_unicode_by_default(self): soup = self.soup("<a></a>") - self.assertEqual(unicode, type(soup.prettify())) + self.assertEqual(str, type(soup.prettify())) def test_prettify_can_encode_data(self): soup = self.soup("<a></a>") self.assertEqual(bytes, type(soup.prettify("utf-8"))) def test_html_entity_substitution_off_by_default(self): - markup = u"<b>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</b>" + markup = "<b>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</b>" soup = self.soup(markup) encoded = soup.b.encode("utf-8") self.assertEqual(encoded, markup.encode('utf-8')) @@ -1829,48 +1829,48 @@ class TestEncoding(SoupTest): """Test the ability to encode objects into strings.""" def test_unicode_string_can_be_encoded(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) self.assertEqual(soup.b.string.encode("utf-8"), - u"\N{SNOWMAN}".encode("utf-8")) + "\N{SNOWMAN}".encode("utf-8")) def test_tag_containing_unicode_string_can_be_encoded(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) self.assertEqual( soup.b.encode("utf-8"), html.encode("utf-8")) def test_encoding_substitutes_unrecognized_characters_by_default(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) self.assertEqual(soup.b.encode("ascii"), b"<b>☃</b>") def test_encoding_can_be_made_strict(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) self.assertRaises( UnicodeEncodeError, soup.encode, "ascii", errors="strict") def test_decode_contents(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) - self.assertEqual(u"\N{SNOWMAN}", soup.b.decode_contents()) + self.assertEqual("\N{SNOWMAN}", soup.b.decode_contents()) def test_encode_contents(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) self.assertEqual( - u"\N{SNOWMAN}".encode("utf8"), soup.b.encode_contents( + "\N{SNOWMAN}".encode("utf8"), soup.b.encode_contents( encoding="utf8")) def test_deprecated_renderContents(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) self.assertEqual( - u"\N{SNOWMAN}".encode("utf8"), soup.b.renderContents()) + "\N{SNOWMAN}".encode("utf8"), soup.b.renderContents()) def test_repr(self): - html = u"<b>\N{SNOWMAN}</b>" + html = "<b>\N{SNOWMAN}</b>" soup = self.soup(html) if PY3K: self.assertEqual(html, repr(soup)) @@ -1952,7 +1952,7 @@ class TestSoupSelector(TreeTest): els = self.soup.select('title') self.assertEqual(len(els), 1) self.assertEqual(els[0].name, 'title') - self.assertEqual(els[0].contents, [u'The title']) + self.assertEqual(els[0].contents, ['The title']) def test_one_tag_many(self): els = self.soup.select('div') @@ -1998,7 +1998,7 @@ class TestSoupSelector(TreeTest): self.assertEqual(dashed[0]['id'], 'dash2') def test_dashed_tag_text(self): - self.assertEqual(self.soup.select('body > custom-dashed-tag')[0].text, u'Hello there.') + self.assertEqual(self.soup.select('body > custom-dashed-tag')[0].text, 'Hello there.') def test_select_dashed_matches_find_all(self): self.assertEqual(self.soup.select('custom-dashed-tag'), self.soup.find_all('custom-dashed-tag')) @@ -2184,12 +2184,12 @@ class TestSoupSelector(TreeTest): # Try to select first paragraph els = self.soup.select('div#inner p:nth-of-type(1)') self.assertEqual(len(els), 1) - self.assertEqual(els[0].string, u'Some text') + self.assertEqual(els[0].string, 'Some text') # Try to select third paragraph els = self.soup.select('div#inner p:nth-of-type(3)') self.assertEqual(len(els), 1) - self.assertEqual(els[0].string, u'Another') + self.assertEqual(els[0].string, 'Another') # Try to select (non-existent!) fourth paragraph els = self.soup.select('div#inner p:nth-of-type(4)') @@ -2202,7 +2202,7 @@ class TestSoupSelector(TreeTest): def test_nth_of_type_direct_descendant(self): els = self.soup.select('div#inner > p:nth-of-type(1)') self.assertEqual(len(els), 1) - self.assertEqual(els[0].string, u'Some text') + self.assertEqual(els[0].string, 'Some text') def test_id_child_selector_nth_of_type(self): self.assertSelects('#inner > p:nth-of-type(2)', ['p1']) @@ -2283,7 +2283,7 @@ class TestSoupSelector(TreeTest): markup = '<div class="c1"/><div class="c2"/><div class="c1"/>' soup = BeautifulSoup(markup, 'html.parser') selected = soup.select(".c1, .c2") - self.assertEquals(3, len(selected)) + self.assertEqual(3, len(selected)) # Verify that find_all finds the same elements, though because # of an implementation detail it finds them in a different |