It's possible for a TreeBuilder subclass to specify that void

  elements should be represented as <element> rather than
  <element/>, by setting TreeBuilder.void_element_close_prefix to the empty string. [bug=1716272]

3 files changed, 31 insertions, 5 deletions

diff --git a/NEWS.txt b/NEWS.txt
index 4788489..e22e88f 100644
--- a/NEWS.txt
+++ b/NEWS.txt
@@ -14,6 +14,11 @@
 * Stopped HTMLParser from raising an exception in very rare cases of
   bad markup. [bug=1708831]
 
+* It's possible for a TreeBuilder subclass to specify that void
+  elements should be represented as "<element>" rather than
+  "<element/>", by setting TreeBuilder.void_element_close_prefix to
+  the empty string. [bug=1716272]
+
 = 4.6.0 (20170507) =
 
 * Added the `Tag.get_attribute_list` method, which acts like `Tag.get` for
diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py
index fdb3362..d7166bb 100644
--- a/bs4/builder/__init__.py
+++ b/bs4/builder/__init__.py
@@ -93,7 +93,15 @@ class TreeBuilder(object):
     preserve_whitespace_tags = set()
     empty_element_tags = None # A tag will be considered an empty-element
                               # tag when and only when it has no contents.
-
+    void_tags = None # There are no void tags.
+
+    # This string goes just before the end of the start tag for an
+    # void element.
+    #
+    # Leave this alone and you'll get tags like "<br/>". Change it to the
+    # empty string and you'll get tags like "<br>".
+    void_element_close_prefix = '/'
+    
     # A value for these tag/attribute combinations is a space- or
     # comma-separated list of CDATA, rather than a single CDATA.
     cdata_list_attributes = {}
@@ -126,6 +134,17 @@ class TreeBuilder(object):
             return True
         return tag_name in self.empty_element_tags
 
+    def is_void(self, tag_name):
+        """Must a tag with this name be a void tag?
+
+        A void tag cannot have contents and is presented with neither
+        a a closing tag or a closing slash, e.g.:
+            <link href="foo">
+        """
+        if self.void_tags is None:
+            return False
+        return tag_name in self.void_tags
+        
     def feed(self, markup):
         raise NotImplementedError()
 
@@ -235,11 +254,11 @@ class HTMLTreeBuilder(TreeBuilder):
     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,
     # class="foo bar" means that the 'class' attribute has two values,
diff --git a/bs4/element.py b/bs4/element.py
index 5ee9887..181f135 100644
--- a/bs4/element.py
+++ b/bs4/element.py
@@ -871,9 +871,11 @@ class Tag(PageElement):
         if builder is not None:
             builder.set_up_substitutions(self)
             self.can_be_empty_element = builder.can_be_empty_element(name)
+            self.void_element_close_prefix = builder.void_element_close_prefix or ""
         else:
             self.can_be_empty_element = False
-
+            self.void_element_close_prefix = '/'
+            
     parserClass = _alias("parser_class")  # BS3
 
     def __copy__(self):
@@ -1173,7 +1175,7 @@ class Tag(PageElement):
             prefix = self.prefix + ":"
 
         if self.is_empty_element:
-            close = '/'
+            close = self.void_element_close_prefix
         else:
             closeTag = '</%s%s>' % (prefix, self.name)