python-docx 从段落中获取表格

Question

我有包含许多段落和表格的 .docx 文件，例如:

1. 标准杆1
   • 表1
   • 表2
   • 表3

2. par2

   • 表1
   • 表2

   2.1 par21

   • 表1
   • 表2

我需要迭代所有对象并生成字典，可能是 json 格式，例如:

   {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

如何关联每个段落和表格？

你能推荐点什么吗？

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))