in python/mhtml_to_json.py [0:0]
def remove_all_but_text_nodes(node, valid_tags):
for child in node:
remove_all_but_text_nodes(child, valid_tags)
if node.tag not in valid_tags and "itemprop" not in node.keys():
for valid_child in node:
node.addnext(valid_child)
if node.getparent() is not None:
node.getparent().remove(node)