diff options
| -rw-r--r-- | NEWS.txt | 3 | ||||
| -rw-r--r-- | bs4/element.py | 8 | ||||
| -rw-r--r-- | bs4/tests/test_tree.py | 10 |
3 files changed, 17 insertions, 4 deletions
@@ -9,6 +9,9 @@ * Fixed a test failure that occured on Python 3.x when chardet was installed. +* Made prettify() return Unicode by default, so it will look nice on + Python 3 when passed into print(). + = 4.0.0b8 (20110224) = * All tree builders now preserve namespace information in the diff --git a/bs4/element.py b/bs4/element.py index e50f639..650bacf 100644 --- a/bs4/element.py +++ b/bs4/element.py @@ -848,9 +848,11 @@ class Tag(PageElement): s = ''.join(s) return s - def prettify(self, encoding=DEFAULT_OUTPUT_ENCODING, - formatter="minimal"): - return self.encode(encoding, True, formatter) + def prettify(self, encoding=None, formatter="minimal"): + if encoding is None: + return self.decode(True, formatter=formatter) + else: + return self.encode(encoding, True, formatter=formatter) def decode_contents(self, indent_level=None, eventual_encoding=DEFAULT_OUTPUT_ENCODING, diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index c75b561..4dda90e 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -1201,7 +1201,15 @@ class TestSubstitutions(SoupTest): def test_prettify_accepts_formatter(self): soup = BeautifulSoup("<html><body>foo</body></html>") pretty = soup.prettify(formatter = lambda x: x.upper()) - self.assertTrue(b"FOO" in pretty) + self.assertTrue("FOO" in pretty) + + def test_prettify_outputs_unicode_by_default(self): + soup = self.soup("<a></a>") + self.assertEqual(unicode, 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>" |