Docx is a zip file of xml files. There is a XML file which you can parse to get all the used elements in there. Simple enough, but why not share it? This script extracts all XML or Docx elements from a 'docx' file. Unzipping of docx file is done within the script. For docx references, refer to this url. http://officeopenxml.com/anatomyofOOXML.php

examine_docx_elements.py

try:
	from xml.etree.cElementTree import XML
except ImportError:
	from xml.etree.ElementTree import XML
import zipfile, re


"""
Module that extract text from MS XML Word document (.docx).
(Inspired by python-docx <https://github.com/mikemaccana/python-docx>)
"""

WORD_NAMESPACE = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
PARA = WORD_NAMESPACE + 'p'
TEXT = WORD_NAMESPACE + 't'


def getAllTags(path):
	"""
	Take the path of a docx file as argument, return the text in unicode.
	"""
	document = zipfile.ZipFile(path)
	xml_content = document.read('word/document.xml')
	document.close()
	tree = XML(xml_content)

	all_tags = recursion(tree.getchildren())

	return all_tags

def recursion(children, output=[]):
	for child in children:
		output.append(child.tag)
		sub_children = child.getchildren()
		if len(sub_children) == 0:
			pass
		else:
			recursion(sub_children, output)

	return output

import sys

def run(docx_filepath):
	all_tags = getAllTags(docx_filepath)
	unique_tags = list(set(all_tags))
	simplified_tags = removeNamespaces(unique_tags)
	return simplified_tags	

def main():
	output = run(sys.argv[1])
	print(output)

def removeNamespaces(tags):
	output = []
	for tag in tags:
		simple_tag = re.match(r'{.*}(.*)', tag)[1]
		output.append(simple_tag)

	return output

if __name__=="__main__":
	main()