# coding=utf-8
import win32com
from win32com.client import Dispatch, DispatchEx
word = Dispatch('Word.Application') # 打开word应用程序
# word = DispatchEx('Word.Application') #启动独立的进程
word.Visible = 0 # 后台运行,不显示
word.DisplayAlerts = 0 # 不警告
path = 'G:/WorkSpace/Python/tmp/test.docx' # word文件路径
doc = word.Documents.Open(FileName=path, Encoding='gbk')
# content = doc.Range(doc.Content.Start, doc.Content.End)
# content = doc.Range()
print '----------------'
print '段落数: ', doc.Paragraphs.count
# 利用下标遍历段落
for i in range(len(doc.Paragraphs)):
  para = doc.Paragraphs[i]
  print para.Range.text
print '-------------------------'
# 直接遍历段落
for para in doc.paragraphs:
  print para.Range.text
  # print para #只能用于文档内容全英文的情况
doc.Close() # 关闭word文档
# word.Quit #关闭word程序

pip install python-docx

import docx
def read_docx(file_name):
  doc = docx.Document(file_name)
  content = '\n'.join([para.text for para in doc.paragraphs])
  return content

# coding=utf-8
import docx
doc = docx.Document()
table = doc.add_table(rows=1, cols=3, style='Table Grid') #创建带边框的表格
hdr_cells = table.rows[0].cells # 获取第0行所有所有单元格
hdr_cells[0].text = 'Name'
hdr_cells[1].text = 'Id'
hdr_cells[2].text = 'Desc'
# 添加三行数据
data_lines = 3
for i in range(data_lines):
  cells = table.add_row().cells
  cells[0].text = 'Name%s' % i
  cells[1].text = 'Id%s' % i
  cells[2].text = 'Desc%s' % i
rows = 2
cols = 4
table = doc.add_table(rows=rows, cols=cols)
val = 1
for i in range(rows):
  cells = table.rows[i].cells
  for j in range(cols):
    cells[j].text = str(val * 10)
    val += 1
doc.save('tmp.docx')

# coding=utf-8
import docx
doc = docx.Document('tmp.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