-
-
Save jeffxf/ce89ff671c335a5c7e87a612290df332 to your computer and use it in GitHub Desktop.
Simple function to extract text from MS XML Word document (.docx) without any dependencies.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
try: | |
from xml.etree.cElementTree import XML | |
except ImportError: | |
from xml.etree.ElementTree import XML | |
import zipfile | |
import sys | |
""" | |
Extracts formulas from docx document | |
Created to detect malicious docx documents containing DDE formulas | |
Modified @etienned's docx text extracting python script: | |
https://gist.github.com/etienned/7539105 | |
""" | |
WORD_NAMESPACE = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}' | |
PARA = WORD_NAMESPACE + 'p' | |
TEXT = WORD_NAMESPACE + 'instrText' | |
def get_docx_formulas(path): | |
document = zipfile.ZipFile(path) | |
xml_content = document.read('word/document.xml') | |
document.close() | |
tree = XML(xml_content) | |
paragraphs = [] | |
for paragraph in tree.getiterator(PARA): | |
texts = [node.text | |
for node in paragraph.getiterator(TEXT) | |
if node.text] | |
if texts: | |
paragraphs.append(''.join(texts)) | |
return '\n\n'.join(paragraphs) | |
if __name__ == "__main__": | |
try: | |
print(get_docx_formulas(sys.argv[1])) | |
except: | |
print(str('usage: ' + sys.argv[0]) + ' [docx file]') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment