Python顺序读取word文档中的文本与表格
在网上找了好久都没有找到顺序读取word中表格和文本的发方法,看源码看着看着就被绕晕了,最后在某篇博客的评论区里找到了这个代码的链接,原网站也是在评论区里不断讨论完善了代码,貌似中间还经历了python-docx模块的更新,放这里希望有需要的人可以省得找了,真的不好找啊!!!
代码
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)
参考文献
https://github.com/python-openxml/python-docx/issues/40.