使用 Python 从 docx 中提取非结构化数据/文本

Question

我是 python 的新手。 我想从 docx 文件中提取非结构化数据作为键值对。 数据为表格格式和原始文本格式。 我以前曾从表中提取过值，但我不知道该怎么做。 有人可以告诉我哪个 package 或我参考的链接以了解这一点吗？提前致谢。

Answer 1

安装python-docx

pip install python-docx

并尝试下面的代码

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


def iter_block_items(parent):
    if isinstance(parent, Document):
        parent_elm = parent.element.body
    elif isinstance(parent, _Cell):
        parent_elm = parent._tc
    else:
        raise ValueError("Error in reading docx file")

    for child in parent_elm.iterchildren():
        if isinstance(child, CT_P):
            yield Paragraph(child, parent)
        elif isinstance(child, CT_Tbl):
            yield Table(child, parent)


def convert_docx_to_text(file_path):
    doc = docx.Document(file_path)
    for block in iter_block_items(doc):
        if isinstance(block, Table):  # check block is table
            keys = []
            for row in block.rows:  # each table row
                if not keys:
                    keys = [cell.text for cell in row.cells] # keys (table headers)
                    continue
                values = [cell.text for cell in row.cells] # values
                print(dict(zip(keys, values)))
        else:
            print(block.text)  # paragraph text

convert_docx_to_text(file_path="/home/karmveer/Downloads/my.docx")