python之读写.docx文件实例

.docx文件是一种由Microsoft Word处理的二进制文件格式，取代了早期版本的.doc格式。它包含文本、图像、表格和其他文档元素，并用于Microsoft Office Word 2007及更高版本。

.docx文件通常使用Office Open XML标准（ISO/IEC 29500）进行编码，并使用ZIP存档格式进行封装。可以使用Microsoft Word或兼容的第三方应用程序打开和编辑.docx文件。

1、写入.docx文件文件

from docx import Document
from docx.shared import Pt
from docx.shared import RGBColor
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT

# 创建一个新的文档
doc = Document()

# 添加标题,level为标题等级
doc.add_heading('Document Title', level=0)

# 添加段落
p = doc.add_paragraph('A plain paragraph having some ')
#加粗
p.add_run('bold').bold = True
p.add_run(' and some ')
#斜体
p.add_run('italic.').italic = True
#分页
doc.add_page_break()
# 添加带有样式的段落
styled_para = doc.add_paragraph()
styled_para.add_run('This paragraph has a style.').bold = True
styled_para.alignment = WD_PARAGRAPH_ALIGNMENT.JUSTIFY

# 添加带有图片的段落
doc.add_picture(r'C:\Users\yh\Pictures\rm.png', width=Pt(120))

# 添加表格
table = doc.add_table(rows=3, cols=3)
for i in range(3):
    for j in range(3):
        table.cell(i, j).text = f'Cell {i + 1}-{j + 1}'

# 添加带有颜色的文本
pcolor=doc.add_paragraph('This text is colored.', style='IntenseQuote')
pcolor.add_run('This text is also colored and in bold.').bold = True
pcolor.add_run('This text is also colored and in italic.').italic = True
pcolor.add_run('This text is also colored and underlined.').underline = True

# 保存文档
doc.save('demo.docx')

import docx


def getText(fileName):
    doc = docx.Document(fileName)
    TextList = []
    for paragraph in doc.paragraphs:
        TextList.append(paragraph.text)

    return '\n'.join(TextList)
p1='''子曰：“学而时习之，不亦说乎？”'''
p2='''子曰：“温故而知新，可以为师。”'''
p3='''子曰：“学而不思则罔，思而不学则殆。”'''
p4='''子曰：“由，诲女知之乎！知之为知之，不知为不知，是知也”'''
doc = docx.Document()
print(len(doc.paragraphs))
doc.add_paragraph(p1)
doc.add_paragraph(p2)
doc.add_paragraph(p3)
doc.add_paragraph(p4)
doc.add_heading("论语十则",0)
doc.save(r'C:\\Users\\user\\Documents\\1.docx')
print("over!")

2、读取.docx文件

import docx
import matplotlib.pyplot as plt
import base64
import io

# 打开文档
doc = docx.Document('demo.docx')

# 遍历文档中的段落
for para in doc.paragraphs:
    # 打印段落的文本内容
    print(para.text)

# 遍历文档中的表格
for table in doc.tables:
    # 遍历表格中的行
    for row in table.rows:
        # 遍历行中的单元格
        for cell in row.cells:
            # 打印单元格的文本内容
            print(cell.text)

Document Title
A plain paragraph having some bold and some italic.

This paragraph has a style.

This text is colored.This text is also colored and in bold.This text is also colored and in italic.This text is also colored and underlined.
Cell 1-1
Cell 1-2
Cell 1-3
Cell 2-1
Cell 2-2
Cell 2-3
Cell 3-1
Cell 3-2
Cell 3-3