python-docx get tables from paragraph

Question

I have .docx file with many paragraphs and tables like:

1. par1
   • table1
   • table2
   • table3

2. par2

   • table1
   • table2

   2.1 par21

   • table1
   • table2

I need to iterate all objects and make dictionary, maybe in json format like:

   {par1: [table1, table2, table3], par2[table1,table2, {par21: [table1,table2]} ] }

    from docx.api import Document

    filename = 'test.docx'
    document = Document(docx=filename)
    for table in document.tables:
        print table

    for paragraph in document.paragraphs:
        print paragraph.text

How can I relate each paragraph and tables?

Can you suggest something ?

Answer 1

from docx import Document
from docx.document import Document as _Document
from docx.oxml.text.paragraph import CT_P
from docx.oxml.table import CT_Tbl
from docx.table import _Cell, Table
from docx.text.paragraph import Paragraph

def iter_block_items(parent):
    """
    Generate a reference to each paragraph and table child within *parent*,
    in document order. Each returned value is an instance of either Table or
    Paragraph. *parent* would most commonly be a reference to a main
    Document object, but also works for a _Cell object, which itself can
    contain paragraphs and tables.
    """
    if isinstance(parent, _Document):
        parent_elm = parent.element.body
    elif isinstance(parent, _Cell):
        parent_elm = parent._tc
    elif isinstance(parent, _Row):
        parent_elm = parent._tr
    else:
        raise ValueError("something's not right")
    for child in parent_elm.iterchildren():
        if isinstance(child, CT_P):
            yield Paragraph(child, parent)
        elif isinstance(child, CT_Tbl):
            yield Table(child, parent)

document = Document('test.docx')
for block in iter_block_items(document):
    #print(block.text if isinstance(block, Paragraph) else '<table>')
    if isinstance(block, Paragraph):
        print(block.text)
    elif isinstance(block, Table):
        for row in block.rows:
            row_data = []
            for cell in row.cells:
                for paragraph in cell.paragraphs:
                    row_data.append(paragraph.text)
            print("\t".join(row_data))