目標(biāo)

最近實(shí)驗(yàn)室里成立了一個計算機(jī)興趣小組

倡議大家多把自己解決問題的經(jīng)驗(yàn)記錄并分享

就像在CSDN寫博客一樣

雖然剛剛起步

但考慮到后面此類經(jīng)驗(yàn)記錄的資料會越來越多

所以一開始就要做好模板設(shè)計（如下所示）

方便后面建立電子數(shù)據(jù)庫

從而使得其他人可以迅速地搜索到相關(guān)記錄

據(jù)說“人生苦短，我用python”

所以決定用python從docx文檔中提取文件頭的信息

然后把信息更新到一個xls電子表格中，像下面這樣（直接po結(jié)果好了）

而且點(diǎn)擊文件路徑可以直接打開對應(yīng)的文件（含超鏈接）

代碼實(shí)現(xiàn)

1. 采集docx里面文件頭信息

# -*- coding:utf-8 -*- # 此程序可掃描Log中的docx文件并返回基本信息 import docxfrom docx import Document test_d = '../log/sublime搭建python的集成開發(fā)環(huán)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('標(biāo)題'): index[0] = k if line.startswith('關(guān)鍵詞'): index[1] = k if line.startswith('作者'): index[2] = k if line.startswith('日期'): index[3] = k if line.startswith('問題描述'): 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))

2. 遍歷log文件夾，進(jìn)行信息更新

# -*- coding:utf-8 -*- # 此程序可以批量掃描log中的文件，如果碰到docx文檔，# 則調(diào)用readfile()提取文檔信息，并將信息保存到digger# 日志列表.xls之中，方便后期快速檢索 import os,datetimeimport timeimport xlrdfrom xlrd import xldate_as_tupleimport xlwtfrom readfile import docxInfofrom xlutils.copy import copy # 打開日志列表讀取最近一條記錄的更新日期memo_d = '../log/digger日志列表.xls'memo = xlrd.open_workbook(memo_d) #讀取excelsheet0 = memo.sheet_by_index(0) #讀取第1張表memo_date = sheet0.col_values(5) #讀取第5列memo_n = len(memo_date) #去掉標(biāo)題if memo_n>0: xlsx_date = memo_date[memo_n-1] #讀取最后一條記錄的日期, latest_date = sheet0.cell_value(memo_n-1,5) # 返回時間戳 # 新建一個xlsxmemo_new = copy(memo)sheet1 = memo_new.get_sheet(0) # 重建超鏈接hyperlinks = sheet0.col_values(6) # xlrd讀取的也是text,造成超鏈接丟失k = 1n_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  # 判斷文件后綴def endWith(s,*endstring): array = map(s.endswith,endstring) if True in array:  return True else:  return False # 遍歷log文件夾并進(jìn)行查詢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']) #獲取當(dāng)前時間 time_now = time.time() #浮點(diǎn)值，精確到毫秒 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+1os.remove(memo_d)memo_new.save(memo_d)print('memo was updated!')