使用python批量读取word文档并整理关键信息到excel表格的实例

# -*- coding:utf-8 -*-
 
# 此程序可扫描Log中的docx文件并返回基本信息
 
import docx
from docx import Document
 
test_d = '../log/sublime搭建python的集成开发环境.docx'
 
def docxInfo(addr):
 document = Document(addr)
 
 info = {'title':[],
 'keywords':[],
 'author':[],
 'date':[],
 'question':[]}
 
 lines = [0 for i in range(len(document.paragraphs))]
 k = 0
 for paragraph in document.paragraphs:
 lines[k] = paragraph.text
 k = k+1
 
 index = [0 for i in range(5)]
 k = 0
 for line in lines:
 if line.startswith('标题'):
 index[0] = k
 if line.startswith('关键词'):
 index[1] = k
 if line.startswith('作者'):
 index[2] = k
 if line.startswith('日期'):
 index[3] = k
 if line.startswith('问题描述'):
 index[4] = k
 k = k+1
 
 info['title'] = lines[index[0]+1]
 
 keywords = []
 for line in lines[index[1]+1:index[2]]:
 keywords.append(line)
 info['keywords'] = keywords
 
 info['author'] = lines[index[2]+1]
 
 info['date'] = lines[index[3]+1]
 
 info['question'] = lines[index[4]+1]
 
 return info
 
if __name__ == '__main__':
 print(docxInfo(test_d))

# -*- coding:utf-8 -*-
 
# 此程序可以批量扫描log中的文件，如果碰到docx文档，
# 则调用readfile()提取文档信息，并将信息保存到digger
# 日志列表.xls之中，方便后期快速检索
 
import os,datetime
import time
import xlrd
from xlrd import xldate_as_tuple
import xlwt
from readfile import docxInfo
from xlutils.copy import copy
 
# 打开日志列表读取最近一条记录的更新日期
memo_d = '../log/digger日志列表.xls'
memo = xlrd.open_workbook(memo_d) #读取excel
sheet0 = memo.sheet_by_index(0) #读取第1张表
memo_date = sheet0.col_values(5) #读取第5列
memo_n = len(memo_date) #去掉标题
if memo_n>0:
 xlsx_date = memo_date[memo_n-1] #读取最后一条记录的日期,
 latest_date = sheet0.cell_value(memo_n-1,5)
 # 返回时间戳
 
# 新建一个xlsx
memo_new = copy(memo)
sheet1 = memo_new.get_sheet(0)
 
# 重建超链接
hyperlinks = sheet0.col_values(6) # xlrd读取的也是text,造成超链接丢失
k = 1
n_hyperlink = len(hyperlinks)
for k in range(n_hyperlink):
 link = 'HYPERLINK("%s";"%s")' %(hyperlinks[k],hyperlinks[k])
 sheet1.write(k,6,xlwt.Formula(link))
 k = k+1
 
 
# 判断文件后缀
def endWith(s,*endstring):
 array = map(s.endswith,endstring)
 if True in array:
  return True
 else:
  return False
 
# 遍历log文件夹并进行查询
log_d = '../log'
logFiles = os.listdir(log_d)
for file in logFiles:
 if endWith(file,'.docx'):
 timestamp = os.path.getmtime(log_d+'/'+file)
 if timestamp>latest_date:
 info = docxInfo(log_d+'/'+file)
 sheet1.write(memo_n,0,info['title'])
 keywords_text = ','.join(info['keywords'])
 sheet1.write(memo_n,1,keywords_text)
 sheet1.write(memo_n,2,info['author'])
 sheet1.write(memo_n,3,info['date'])
 sheet1.write(memo_n,4,info['question'])
 #获取当前时间
 time_now = time.time() #浮点值，精确到毫秒
 sheet1.write(memo_n,5, time_now)
 link = 'HYPERLINK("%s";"%s")' %(file,file)
 sheet1.write(memo_n,6,xlwt.Formula(link))
 memo_n = memo_n+1
os.remove(memo_d)
memo_new.save(memo_d)
print('memo was updated!')