Utility to replace variables enclosed in square brackets with the given value in Microsoft Word docx files. Based upon the following blog post. http://virantha.com/2013/08/16/reading-and-writing-microsoft-word-docx-files-with-python/

docx.py

import os, re, zipfile, shutil, tempfile
from lxml import etree


class docx():
    def __init__(self, docx_filename):
        self.filename = docx_filename

        with open(self.filename) as f:
          self.zipfile = zipfile.ZipFile(f)
          self.xml_content = self.zipfile.read('word/document.xml')

        self.xml_tree = self._get_xml_tree(self.xml_content)
        self._join_tags(self.xml_tree)


    def _get_xml_tree(self, xml_string):
        return etree.fromstring(xml_string)

    def _check_element_is(self, element, type_char):
        word_schema = 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
        return element.tag == '{%s}%s' % (word_schema, type_char)

    def _itertext(self, tree):
        for node in tree.iter(tag=etree.Element):
            if self._check_element_is(node, 't'):
                yield (node, node.text)

    def _join_tags(self, tree):
        chars = []
        openbrac = False
        inside_openbrac_node = False

        for node, text in self._itertext(tree):
            # Scan through every node with text
            for i, c in enumerate(text):
                # Go through each node's text character by character
                if c == '[':
                    openbrac = True # Within a tag
                    inside_openbrac_node = True # Tag was opened in this node
                    openbrac_node = node # Save ptr to open bracket containing node
                    chars = []
                elif c== ']':
                    assert openbrac
                    if inside_openbrac_node:
                        # Open and close inside same node, no need to do anything
                        pass
                    else:
                        # Open bracket in earlier node, now it's closed
                        # So append all the chars we've encountered since the openbrac_node '['
                        # to the openbrac_node
                        chars.append(']')
                        openbrac_node.text += ''.join(chars)
                        # Also, don't forget to remove the characters seen so far from current node
                        node.text = text[i+1:] 
                    openbrac = False
                    inside_openbrac_node = False
                else:
                    # Normal text character
                    if openbrac and inside_openbrac_node:
                        # No need to copy text
                        pass
                    elif openbrac and not inside_openbrac_node:
                        chars.append(c)
                    else:
                        # outside of a open/close
                        pass
            if openbrac and not inside_openbrac_node:
                # Went through all text that is part of an open bracket/close bracket
                # in other nodes
                # need to remove this text completely
                node.text = ""
            inside_openbrac_node = False

    def replace(self, variable, value):
        var = '[%s]' % variable.lower()

        for node, text in self._itertext(self.xml_tree):
            if var in text.lower():
                regex = re.compile(re.escape(var), re.IGNORECASE)
                node.text = regex.sub(value, text)

    def save_as(self, output_filename):
        tmp_dir = tempfile.mkdtemp()
        with open(self.filename) as f:
            self.zipfile = zipfile.ZipFile(f)
            self.zipfile.extractall(tmp_dir)

        with open(os.path.join(tmp_dir,'word/document.xml'), 'w') as f:
            xmlstr = etree.tostring(self.xml_tree, pretty_print=True)
            f.write(xmlstr)

        filenames = self.zipfile.namelist()
        
        zip_copy_filename = output_filename
        with zipfile.ZipFile(zip_copy_filename, "w") as docx:
            for filename in filenames:
                docx.write(os.path.join(tmp_dir, filename), filename)

        # Clean up the temp dir
        shutil.rmtree(tmp_dir)


if __name__ == "__main__":
    doc = docx('test.docx')

    doc.replace('variable', 'value')
    doc.replace('another_variable', 'another value')

    doc.save_as('test_result.docx')

What if we want to change the characters of text not in brackets and simple paragraphs characters one by one by making the dictionary.. how would we do that?? can you please tell me..!!

Search for the required text the same way I am searching/replacing variables with values in the function replace.