import docx
file=docx.Document(r"F:\python從入門到放棄\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)+"段的內(nèi)容是："+file.paragraphs[i].text)  

import sys
from docx import Document
from docx.shared import Inches
def main():
#     reload(sys)
#     sys.setdefaultencoding('utf-8')
    # 創(chuàng)建文檔對(duì)象
    document = Document()
    # 設(shè)置文檔標(biāo)題，中文要用unicode字符串
    document.add_heading(u'我的一個(gè)新文檔',0)
    # 往文檔中添加段落
    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
    # 添加一級(jí)標(biāo)題
    document.add_heading(u'一級(jí)標(biāo)題, level = 1',level = 1)
    document.add_paragraph('Intense quote',style = 'IntenseQuote')
    # 添加無(wú)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')
    # 添加圖片，并指定寬度
    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)
    # 獲取第一行的單元格列表對(duì)象
    hdr_cells = table.rows[0].cells
    # 為每一個(gè)單元格賦值
    # 注：值都要為字符串類型
    hdr_cells[0].text = 'Name'
    hdr_cells[1].text = 'Age'
    hdr_cells[2].text = 'Tel'
    # 為表格添加一行
    new_cells = table.add_row().cells
    new_cells[0].text = 'Tom'
    new_cells[1].text = '19'
    new_cells[2].text = '12345678'
    # 添加分頁(yè)符
    document.add_page_break()
    # 往新的一頁(yè)中添加段落
    p = document.add_paragraph('This is a paragraph in new page.')
    # 保存文檔
    document.save('demo1.doc')
if __name__ == '__main__':
    main()

import docx
doc = docx.Document('wenjian.docx')
for table in doc.tables:  # 遍歷所有表格
    print('----table------')
    for row in table.rows:  # 遍歷表格的所有行
        # row_str = '\t'.join([cell.text for cell in row.cells])  # 一行數(shù)據(jù)
        # print row_str
        for cell in row.cells:
            print(cell.text, '\t',)
        print() #換行

os.chdir(r'E:\py_prj')  #首先改變目錄到文件的目錄
os.rename('test.docx','test.ZIP')  # 重命名為zip文件
f=zipfile.ZipFile('test.zip','r')  #進(jìn)行解壓
for file in f.namelist():
    f.extract(file)
file=open(r'E:\py_prj\word\embeddings\oleObject1.bin','rb').read() #進(jìn)入文件路徑，讀取二進(jìn)制文件。
for f in file:
    print (f)