summaryrefslogtreecommitdiff
path: root/bs4/builder
diff options
context:
space:
mode:
authorLeonard Richardson <leonardr@segfault.org>2017-05-06 13:34:52 -0400
committerLeonard Richardson <leonardr@segfault.org>2017-05-06 13:34:52 -0400
commitc8221ac4a36666b775f2f77920b3a5071109d374 (patch)
tree776ddc4cc1f8981c1c868d12c334fae8142c8a5c /bs4/builder
parentf361aacefa877c8b431ace557b27898b3a12568d (diff)
downloadbeautifulsoup4-c8221ac4a36666b775f2f77920b3a5071109d374.tar.gz
HTML parsers treat all HTML4 and HTML5 empty element tags (aka void element tags) correctly. [bug=1656909]
Diffstat (limited to 'bs4/builder')
-rw-r--r--bs4/builder/__init__.py9
1 files changed, 7 insertions, 2 deletions
diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py
index 601979b..fdb3362 100644
--- a/bs4/builder/__init__.py
+++ b/bs4/builder/__init__.py
@@ -232,8 +232,13 @@ class HTMLTreeBuilder(TreeBuilder):
"""
preserve_whitespace_tags = HTMLAwareEntitySubstitution.preserve_whitespace_tags
- empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
- 'spacer', 'link', 'frame', 'base'])
+ empty_element_tags = set([
+ # These are from HTML5.
+ 'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+
+ # These are from HTML4, removed in HTML5.
+ 'spacer', 'frame'
+ ])
# The HTML standard defines these attributes as containing a
# space-separated list of values, not a single value. That is,