Quick and direct search for term inside docx file

docx_term_search.py

"""
    A quick and dirty search within the contents of a docx file
    Author: Israel Dryer
    Modified: 2020-07-21
"""

from zipfile import ZipFile

# file path
doc_path = 'senior_paper.docx'

# the term you want to search for
term1 = 'portfolio'
term2 = 'administration'

# unzip the contents of the docx file (a docx is a compressed collection of file)
zip_file = ZipFile(doc_path)
zip_list = {name: zip_file.read(name) for name in zip_file.namelist()}
docx = zip_list['word/document.xml']

# look for the search term in the document.xml file contents
# the search term must be converted to bytes to match the xml content
check1 = bytes(term1, encoding='utf-8') in docx
check2 = bytes(term2, encoding='utf-8') in docx

# print results
print('\nSEARCH RESULTS\n')
print(f'Search term {term1} in {doc_path}: {check1}')
print(f'Search term {term2} in {doc_path}: {check2}')