由于工作需要提取一个word文档中的表格,及其所在的章节,普通的Document.paragraphs 和Document.tables无法满足需求。所以综合GitHub作者的代码及我自己的需求代码如下:
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
import docx
import openpyxl
import xlsxwriter
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)
# table = Table(child, parent)
# for row in table.rows:
# for cell in row.cells:
# for paragraph in cell.paragraphs:
# yield paragraph
doc = docx.Document('C:\\Users\\Citect2016\\Desktop\\A19-42000.docx')
for block in iter_block_items(doc):
if block.style.name == 'Table Grid':
pass
if block.style.name == 'Heading 1':
pass
值得一提的是,本文的docx版本是0.8.6,适用于python3.x,各位道友请到官网自行下载。