diff options
author | Leonard Richardson <leonardr@segfault.org> | 2017-05-06 13:34:52 -0400 |
---|---|---|
committer | Leonard Richardson <leonardr@segfault.org> | 2017-05-06 13:34:52 -0400 |
commit | c556b8a6b42843fac40c55459aa5c494e2798349 (patch) | |
tree | 844e681248fe816addb1187538ba40620d9188db /bs4/builder/__init__.py | |
parent | 49cc750524fb436fa4880eefa6c8d0b3bbbd7175 (diff) |
HTML parsers treat all HTML4 and HTML5 empty element tags (aka void element tags) correctly. [bug=1656909]
Diffstat (limited to 'bs4/builder/__init__.py')
-rw-r--r-- | bs4/builder/__init__.py | 9 |
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, |