python中可以处理word文档的模块：docx模块 - ToB企服应用市场:ToB评测及商务社交产业平台

import docx
file=docx.Document(r"F:\python从入门到放弃\7\2\wenjian.docx")
print('段落:'+str(len(file.paragraphs)))
#
# for para in file.paragraphs:
# print(para.text)
for i in range(len(file.paragraphs)):
print("第"+str(i)+"段的内容是："+file.paragraphs[i].text)

复制代码

import sys
from docx import Document
from docx.shared import Inches
def main():
# reload(sys)
# sys.setdefaultencoding('utf-8')
# 创建文档对象
document = Document()
# 设置文档标题，中文要用unicode字符串
document.add_heading(u'我的一个新文档',0)
# 往文档中添加段落
p = document.add_paragraph('This is a paragraph having some ')
p.add_run('bold ').bold = True
p.add_run('and some ')
p.add_run('italic.').italic = True
# 添加一级标题
document.add_heading(u'一级标题, level = 1',level = 1)
document.add_paragraph('Intense quote',style = 'IntenseQuote')
# 添加无序列表
document.add_paragraph('first item in unordered list',style = 'ListBullet')
# 添加有序列表
document.add_paragraph('first item in ordered list',style = 'ListNumber')
document.add_paragraph('second item in ordered list',style = 'ListNumber')
document.add_paragraph('third item in ordered list',style = 'ListNumber')
# 添加图片，并指定宽度
document.add_picture('cat.png',width = Inches(2.25))
# 添加表格: 1行3列
table = document.add_table(rows = 1,cols = 3)
# 获取第一行的单元格列表对象
hdr_cells = table.rows[0].cells
# 为每一个单元格赋值
# 注：值都要为字符串类型
hdr_cells[0].text = 'Name'
hdr_cells[1].text = 'Age'
hdr_cells[2].text = 'Tel'
# 为表格添加一行
new_cells = table.add_row().cells
new_cells[0].text = 'Tom'
new_cells[1].text = '19'
new_cells[2].text = '12345678'
# 添加分页符
document.add_page_break()
# 往新的一页中添加段落
p = document.add_paragraph('This is a paragraph in new page.')
# 保存文档
document.save('demo1.doc')
if __name__ == '__main__':
main()

复制代码

import docx
doc = docx.Document('wenjian.docx')
for table in doc.tables: # 遍历所有表格
print('----table------')
for row in table.rows: # 遍历表格的所有行
# row_str = '\t'.join([cell.text for cell in row.cells]) # 一行数据
# print row_str
for cell in row.cells:
print(cell.text, '\t',)
print() #换行

复制代码

os.chdir(r'E:\py_prj') #首先改变目录到文件的目录
os.rename('test.docx','test.ZIP') # 重命名为zip文件
f=zipfile.ZipFile('test.zip','r') #进行解压
for file in f.namelist():
f.extract(file)
file=open(r'E:\py_prj\word\embeddings\oleObject1.bin','rb').read() #进入文件路径，读取二进制文件。
for f in file:
print (f)

复制代码