顺序遍历doc文档的核心代码如下：
from docx import Document
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
from docx.text.paragraph import Paragraph
"""
Generate a reference to 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.
"""
def iter_block_items(parent):
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)
"""
main function to extract tables
"""
def extract_tables(document):
count = 0
current_context=''
#iterator the blocks in doc
for block in iter_block_items(document):
# print(block.text if isinstance(block, Paragraph) else '<table>')
if isinstance(block, Paragraph):
# print("------------------text--------------------")
print("text: " + block.text)
elif isinstance(block, Table):
current_context=''
for row in block.rows:
row_data = []
for cell in row.cells:
text_cell=''
for paragraph in cell.paragraphs:
text_cell += paragraph.text.strip()
if text_cell is '':
text_cell="NULL"
row_data.append(text_cell)
print("|".join(row_data))
if __name__ == '__main__':
document = Document('./xxxxx.docx')
extract_tables(document)以上代码核心思想是顺序取出docx中的每个block然后判断该block是table还是paragraph对象，如果是table在解析table,将里面的内容按行输出。