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, _Row
from docx.text.paragraph import Paragraph
import docx
path = './test.docx'
doc = docx.Document(path)
def iter_block_items(parent):
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)
for block in iter_block_items(doc):
# read Paragraph
if isinstance(block, Paragraph):
print(block.text)
# read table
elif isinstance(block, Table):
print(block.style.name)
3. 访问图片
接下来，我们可以通过遍历文档中的每个段落，找到其中包含的图片。具体代码如下：
for paragraph in document.paragraphs:
for run in paragraph.runs:
if run._element.xml.startswith('
print('Found a picture!')
其中，“runs”是指段落中的一小部分文本。如果该“run”对象的XML标记以“
4. 保存图片
最后，我们可以使用Python中的“open”函数将图片保存到本地。具体代码如下：
for paragraph in document.paragraphs:
for run in paragraph.runs:
if run._element.xml.startswith('
image_name = run.part.rels[0]._target
with open(image_name, 'wb') as f:
f.write(run.part.blob)