import sys
reload(sys)
sys.setdefaultencoding('utf-8')
from docx import Document
import pandas as pd

# 打开文件
doc = Document(ur'test_1.docx')

# 取出对号勾选的项目
print doc.tables[0].rows[3].cells[2].text
print doc.tables[0].rows[3].cells[2].text.split(u'√')[1].strip().split(' ')[0][2:]
'√' in doc.tables[0].rows[3].cells[2].text # 这个语句可以测试是否含有对勾，
# 有的话就取出对勾后面的item，否则直接返回填空的text

num_rows = len(doc.tables[0].rows)
print num_rows

print xls.columns[0]
diction = {}

# 找到每个excel文档中需要被记录的键值在docx文档表格中的位置
for xlskey in xls.columns:
 for row_id in range(num_rows):
  row = doc.tables[0].rows[row_id]
  for cell_id in range(len(row.cells)):
   if row.cells[cell_id].text.strip() == xlskey.strip():
    diction[xlskey] = [row_id, cell_id]

# 查看一下获得的键值位置
for key in list(diction.keys()):
 print key, diction[key]

# 开始填表！！！
for each_column in xls.columns:
 pos = diction[each_column]
 textion = doc.tables[0].rows[pos[0]].cells[pos[1] + 1].text
 if u'√' in textion:
  this_text = textion.strip(' ').split(u'√')[1].split()[0][2:]
 else:
  this_text = textion
 xls.loc[0, each_column] = this_text