def tree_words(node):
"""Return all the significant text below the given node as a list of words.
>>> list(tree_words(parse_minidom('<h1>one</h1> two <div>three<em>four</em></div>')))
['one', 'two', 'three', 'four']
"""
for word in split_text(tree_text(node)):
word = word.strip()
if word:
yield word
def split_node(node):
# Split text node in into user-friendly chunks.
pieces = split_text(node.nodeValue)
if len(pieces) <= 1:
return
parent = node.parentNode
for piece in pieces:
piece_node = node.ownerDocument.createTextNode(piece)
parent.insertBefore(piece_node, node)
remove_node(node)
def split_node(node):
# Split text node in into user-friendly chunks.
pieces = split_text(node.nodeValue)
if len(pieces) <= 1:
return
parent = node.parentNode
for piece in pieces:
piece_node = node.ownerDocument.createTextNode(piece)
parent.insertBefore(piece_node, node)
remove_node(node)
def test():
assert_equal(split_text(text), target)
def test():
assert_equal(split_text(text), target)