python_docx依次读取word文档中的文本与表格

因为要文档数量太多,所以使用python_docx批量读取word文档中的文本与表格

环境

Mac
Python 3.5.6
python_docx

安装依赖

sudo pip install -i https://pypi.tuna.tsinghua.edu.cn/simple python_docx

Python脚本

# -*- coding: utf-8 -*
import os
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):
    """
    Yield 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
    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)


def read_table(table):
    return [[cell.text for cell in row.cells] for row in table.rows]


def read_word(word_path):
    doc = docx.Document(word_path)
    for block in iter_block_items(doc):
        if isinstance(block, Paragraph):
            print("text", [block.text])
        elif isinstance(block, Table):
            print("table", read_table(block))


if __name__ == '__main__':
    ROOT_DIR_P = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))  # 项目根目录
    word_path = os.path.join(ROOT_DIR_P, "data/test_to_word.docx")  # pdf文件路径及文件名
    # word_path = os.path.join(ROOT_DIR_P, "data/test_to_word2.docx")  # pdf文件路径及文件名
    read_word(word_path)