Lord Heffe Lord Heffe - 1 month ago 313
CSS Question

This is marked for deletion

This question is marked for deletion

Answer Source

This might not look very pretty (or professional) but it gets the job done:

from docx import Document
from docx.enum.text import WD_BREAK
import re

doc = Document('temp.docx')
new_doc = Document()
word = 'Hello'

'''Get the whole document text from all paragraphs'''
whole_text=''
for p in doc.paragraphs:
    if whole_text!='':
        whole_text+='\n'
    whole_text += p.text

'''To split whole_text but include Hello in the created list
put parentheses around the word and use re.split'''
split_p = re.split(word.join('()'),whole_text)

'''Now if 'Hello' was the first word of whole_text re.split will create
['','Hello','...']
if that's the case, remove first '' to avoid unwanted page_break at the
start'''
if split_p[0]=='':
    split_p.remove('')

i = 0
while i<len(split_p):
    if split_p[i] == word:
        '''We don't want to add break at the start of document'''
        if len(new_doc.paragraphs)>0:
            '''new_doc.add_page_break() creates a newline with page break on it
            but the below command will put page break on the last paragraph
            so there won't be additional empty lines

            If you don't want to have an additional import line
            then just put 7 instead of WD_BREAK.PAGE'''
            new_doc.paragraphs[-1].add_run().add_break(WD_BREAK.PAGE)
        '''Add 'Hello' + the text coming after it'''
        new_doc.add_paragraph(split_p[i]+split_p[i+1])
        i+=2
    else:
        '''If the first Hello is not at the start of document just add the
        text'''
        new_doc.add_paragraph(split_p[i])
        i+=1

new_doc.save('hello.docx')