dinislage/CouchPotatoServer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

BeautifulSoup4 python 3

Browse Source
This commit is contained in:
Ruud
2014-10-06 11:12:35 +02:00
parent 5b7e814166
commit 6b4e6857de
9 changed files with 138 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files
libs/bs4/testing.py
+16 -16
View File
@@ -225,14 +225,14 @@ class HTMLTreeBuilderSmokeTest(object):
self.assertSoupEquals('<a b="<a>"></a>', '<a b="&lt;a&gt;"></a>')
def test_entities_in_attributes_converted_to_unicode(self):
expect = u'<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
expect = '<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
self.assertSoupEquals('<p id="pi&#241;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#Xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&ntilde;ata"></p>', expect)
def test_entities_in_text_converted_to_unicode(self):
expect = u'<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
expect = '<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
self.assertSoupEquals("<p>pi&#241;ata</p>", expect)
self.assertSoupEquals("<p>pi&#xf1;ata</p>", expect)
self.assertSoupEquals("<p>pi&#Xf1;ata</p>", expect)
@@ -243,7 +243,7 @@ class HTMLTreeBuilderSmokeTest(object):
'<p>I said "good day!"</p>')
def test_out_of_range_entity(self):
expect = u"\N{REPLACEMENT CHARACTER}"
expect = "\N{REPLACEMENT CHARACTER}"
self.assertSoupEquals("&#10000000000000;", expect)
self.assertSoupEquals("&#x10000000000000;", expect)
self.assertSoupEquals("&#1000000000;", expect)
@@ -285,9 +285,9 @@ class HTMLTreeBuilderSmokeTest(object):
# A seemingly innocuous document... but it's in Unicode! And
# it contains characters that can't be represented in the
# encoding found in the declaration! The horror!
markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
markup = '<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
soup = self.soup(markup)
self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string)
self.assertEqual('Sacr\xe9 bleu!', soup.body.string)
def test_soupstrainer(self):
"""Parsers should be able to work with SoupStrainers."""
@@ -327,7 +327,7 @@ class HTMLTreeBuilderSmokeTest(object):
# Both XML and HTML entities are converted to Unicode characters
# during parsing.
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
expected = "<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
self.assertSoupEquals(text, expected)
def test_smart_quotes_converted_on_the_way_in(self):
@@ -337,15 +337,15 @@ class HTMLTreeBuilderSmokeTest(object):
soup = self.soup(quote)
self.assertEqual(
soup.p.string,
u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
def test_non_breaking_spaces_converted_on_the_way_in(self):
soup = self.soup("<a>&nbsp;&nbsp;</a>")
self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
self.assertEqual(soup.a.string, "\N{NO-BREAK SPACE}" * 2)
def test_entities_converted_on_the_way_out(self):
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
expected = "<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
soup = self.soup(text)
self.assertEqual(soup.p.encode("utf-8"), expected)
@@ -354,7 +354,7 @@ class HTMLTreeBuilderSmokeTest(object):
# easy-to-understand document.
# Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
unicode_html = u'<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
unicode_html = '<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
# That's because we're going to encode it into ISO-Latin-1, and use
# that to test.
@@ -493,15 +493,15 @@ class XMLTreeBuilderSmokeTest(object):
self.assertTrue(b"&lt; &lt; hey &gt; &gt;" in encoded)
def test_can_parse_unicode_document(self):
markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
markup = '<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
soup = self.soup(markup)
self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string)
self.assertEqual('Sacr\xe9 bleu!', soup.root.string)
def test_popping_namespaced_tag(self):
markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
soup = self.soup(markup)
self.assertEqual(
unicode(soup.rss), markup)
str(soup.rss), markup)
def test_docstring_includes_correct_encoding(self):
soup = self.soup("<root/>")
@@ -532,17 +532,17 @@ class XMLTreeBuilderSmokeTest(object):
def test_closing_namespaced_tag(self):
markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.p), markup)
self.assertEqual(str(soup.p), markup)
def test_namespaced_attributes(self):
markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.foo), markup)
self.assertEqual(str(soup.foo), markup)
def test_namespaced_attributes_xml_namespace(self):
markup = '<foo xml:lang="fr">bar</foo>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.foo), markup)
self.assertEqual(str(soup.foo), markup)
class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
"""Smoke test for a tree builder that supports HTML5."""