python-docx顺序读取word内容

wozwdaqian2024-06-23 18:28

来源How to use Python iteration to read paragraphs, tables and pictures in word？ · Issue #650 · python-openxml/python-docx (github.com)

python 复制代码

from docx import Document
from docx.oxml.ns import qn

def iter_block_items(parent):
    """
    生成 `parent` 元素的每个块级元素，包括段落和表格。
    """
    parent_elm = parent.element.body

    for child in parent_elm.iterchildren():
        if child.tag == qn('w:p'):
            yield 'p', child
        elif child.tag == qn('w:tbl'):
            yield 'tbl', child

# 打开文档
doc = Document("example.docx")

paragraphs = doc.paragraphs
tables = doc.tables

paragraph_index = 0
table_index = 0

for block_type, block in iter_block_items(doc):
    if block_type == 'p':
        paragraph = paragraphs[paragraph_index]
        print("Paragraph:", paragraph.text)
        paragraph_index += 1
    elif block_type == 'tbl':
        table = tables[table_index]
        table_index += 1
        if table:
            print("Table:")
            for n_r, row in enumerate(table.rows):
                print(f"    Row {n_r}: ")
                for n_c, cell in enumerate(row.cells):
                    print(f"        Column {n_c}:", cell.text, end=' ')
                print()