diff options
| -rw-r--r-- | NEWS.txt | 6 | ||||
| -rw-r--r-- | bs4/element.py | 2 | ||||
| -rw-r--r-- | bs4/tests/test_tree.py | 25 | ||||
| -rw-r--r-- | doc/source/index.rst | 2 |
4 files changed, 33 insertions, 2 deletions
@@ -1,8 +1,12 @@ -= Unreleased += 4.4.1 (20150928) = * Fixed the test_detect_utf8 test so that it works when chardet is installed. [bug=1471359] +* Fixed a bug that deranged the tree when part of it was + removed. Thanks to Eric Weiser for the patch and John Wiseman for a + test. [bug=1481520] + = 4.4.0 (20150703) = Especially important changes: diff --git a/bs4/element.py b/bs4/element.py index 60464b6..02fd1b7 100644 --- a/bs4/element.py +++ b/bs4/element.py @@ -294,6 +294,8 @@ class PageElement(object): _lastRecursiveChild = _last_descendant def insert(self, position, new_child): + if new_child is None: + raise ValueError("Cannot insert None into a tag.") if new_child is self: raise ValueError("Cannot insert a tag into itself.") if (isinstance(new_child, basestring) diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index 2371591..ab21a50 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -1084,6 +1084,31 @@ class TestTreeModification(SoupTest): self.assertEqual(foo_2, soup.a.string) self.assertEqual(bar_2, soup.b.string) + def test_extract_multiples_of_same_tag(self): + soup = self.soup(""" +<html> +<head> +<script>foo</script> +</head> +<body> + <script>bar</script> + <a></a> +</body> +<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)) + + + def test_extract_works_when_element_is_surrounded_by_identical_strings(self): + soup = self.soup( + '<html>\n' + '<body>hi</body>\n' + '</html>') + soup.find('body').extract() + self.assertEqual(None, soup.find('body')) + + def test_clear(self): """Tag.clear()""" soup = self.soup("<p><a>String <em>Italicized</em></a> and another</p>") diff --git a/doc/source/index.rst b/doc/source/index.rst index ba3b54e..3bc9537 100644 --- a/doc/source/index.rst +++ b/doc/source/index.rst @@ -29,7 +29,7 @@ Soup 3 and Beautiful Soup 4, see `Porting code to BS4`_. This documentation has been translated into other languages by Beautiful Soup users: -* `这篇文档当然还有中文版. <http://www.crummy.com/software/BeautifulSoup/bs4/doc/index.cn.html>`_ +* `这篇文档当然还有中文版. <http://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/>`_ * このページは日本語で利用できます(`外部リンク <http://kondou.com/BS4/>`_) * 이 문서는 한국어 번역도 가능합니다. (`외부 링크 <http://coreapython.hosting.paran.com/etc/beautifulsoup4.html>`_) |