date到类别
我有一个Excel电子表格，我准备迁移到Access和date列有多个格式的条目，如：1963年至1969年，1968年8月至1968年9月，1972年，3月73日，7月24日，7月2日，1980年8月29日，1946年7月等。 我将把将是关键（地图编号）和date列的列转换为csv并写回到csv。 我可以去掉4位数字，但不是范围。 而且我不知道如何提取几天和两个数字年的手工重新格式化。 我的代码不是很优雅，可能不是最好的做法：
import csv, xlwt, re # create new Excel document and add sheet # from tempfile import TemporaryFile from xlwt import Workbook book = Workbook() sheet1 = book.add_sheet('Sheet 1') # populate first row with header sheet1.write(0,0,"Year") sheet1.write(0,1,"Map") sheet1.write(0,2,"As Entered") # count variable for populating sheet rowCount=0 # open csv file and read with open('C:\dateTestMSDOs.csv', 'rb') as f: reader=csv.reader(f) for row in reader: map = row[0] # first row is map number dateRaw = row[1] # second row is raw date as entered # write undated and blank entries if dateRaw == 'undated': yearStr = '0000' rowCount +=1 sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' yearStr='' if dateRaw == '': yearStr = 'NoEntry' rowCount +=1 sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' yearStr='' # search and write instances of four consecutive digits try: year = re.search(r'\d\d\d\d', dateRaw) yearStr= year.group() #print yearStr, map, dateRaw rowCount +=1 sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' yearStr='' # if none exist flag for cleaning spreadsheet and print except: #print 'Nope', map, dateRaw rowCount +=1 yearStr='Format' sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' yearStr='' yearStr='' dateRaw='' book.save('D:\dateProperty.xls') print "Done!" 我想写一个date和月份到一个额外的列，以及拉出范围条目的第二个4位数字date。
你可以尝试使用dateutil这个。 我认为你仍然需要以不同的方式处理一些更难的格式。 请参阅下面的示例实现：
码：
import dateutil.parser as dateparser date_list = ['1963 to 1969', 'Aug. 1968 to Sept. 1968', 'Mar-73', '24-Jul', 'Oct. 2 1980', 'Aug 29, 1980', 'July 1946', 'undated'] for d in date_list: if 'to' in d: a, b = d.split('to') # Get the higher number. Use min to get lower of two. print max(dateparser.parse(a.strip()).year, dateparser.parse(b.strip()).year) elif d == 'undated': print '0000' else: yr = dateparser.parse(d).year print yr
结果：
1969 1968 1973 2014 1980 1980 1946 0000 [Finished in 0.4s]
只有明显的问题，我可以看到， 24-Jul返回2014的date，因为parsing器假定当前的一天，一个月或一年，而不是丢失的组件，即。 如果今天是本月20日，那么Mar-73将成为1973-03-20
不完全确定这是否是你要做的，但是我只是使用了一个“简单的”正则expression式search，然后遍历了匹配的组的集合，应用给定的函数定义。 如果find匹配，那么被调用的函数（在regex_groupsvariables中find）将返回一个包含以下关键字的字典： start_day, start_month, start_year, end_day, end_month, end_year
那么你可以做任何你想要的那些价值观。 绝对不是最干净的解决scheme，但它工作，据我所知。
#!/usr/local/bin/python2.7 import re # Crazy regex regex_pattern = '(?:(\d{4}) to (\d{4}))|(?:(\w+)\. (\d{4}) to (\w+)\. (\d{4}))|(?:(\w+)-(\d{2}))|(?:(\d{2})-(\w+))|(?:(\w+)\. (\d+), (\d{4}))|(?:(\w+) (\d+), (\d{4}))|(?:(\w+) (\d{4}))|(?:(\d{4}))' date_strings = [ '1963 to 1969', 'Aug. 1968 to Sept. 1968', '1972', 'Mar-73', '24-Jul', 'Oct. 2, 1980', 'Aug 29, 1980', 'July 1946', ] # Here you set the group matching functions that will be called for a matching group regex_groups = { (1,2): lambda group_matches: { 'start_day': '', 'start_month': '', 'start_year': group_matches[0], 'end_day': '', 'end_month': '', 'end_year': group_matches[1] }, (3,4,5,6): lambda group_matches: { 'start_day': '', 'start_month': group_matches[0], 'start_year': group_matches[1], 'end_day': '', 'end_month': group_matches[2], 'end_year': group_matches[3] }, (7,8): lambda group_matches: { 'start_day': '', 'start_month': group_matches[0], 'start_year': group_matches[1], 'end_day': '', 'end_month': '', 'end_year': '' }, (9,10): lambda group_matches: { 'start_day': group_matches[1], 'start_month': '', 'start_year': group_matches[0], 'end_day': '', 'end_month': '', 'end_year': '' }, (11,12,13): lambda group_matches: { 'start_day': group_matches[1], 'start_month': group_matches[0], 'start_year': group_matches[2], 'end_day': '', 'end_month': '', 'end_year': '' }, (14,15,16): lambda group_matches: { 'start_day': group_matches[1], 'start_month': group_matches[0], 'start_year': group_matches[2], 'end_day': '', 'end_month': '', 'end_year': '' }, (17,18): lambda group_matches: { 'start_day': '', 'start_month': group_matches[0], 'start_year': group_matches[1], 'end_day': '', 'end_month': '', 'end_year': '' }, (19,): lambda group_matches: { 'start_day': '', 'start_month': '', 'start_year': group_matches[0], 'end_day': '', 'end_month': '', 'end_year': '' }, } for ds in date_strings: matches = re.search(regex_pattern, ds) start_month = '' start_year = '' end_month = '' end_year = '' for regex_group, group_func in regex_groups.items(): group_matches = [matches.group(sub_group_num) for sub_group_num in regex_group] if all(group_matches): match_data = group_func(group_matches) print print 'Matched:', ds print '%s to %s' % ('-'.join([match_data['start_day'], match_data['start_month'], match_data['start_year']]), '-'.join([match_data['end_day'], match_data['end_month'], match_data['end_year']])) # match_data is a dictionary with keys: # * start_day # * start_month # * start_year # * end_day # * end_month # * end_year # If a group doesn't contain one of those items, then it is set to a blank string
输出：
Matched: 1963 to 1969 --1963 to --1969 Matched: Aug. 1968 to Sept. 1968 -Aug-1968 to -Sept-1968 Matched: 1972 --1972 to -- Matched: Mar-73 -Mar-73 to -- Matched: 24-Jul Jul--24 to -- Matched: Oct. 2, 1980 2-Oct-1980 to -- Matched: Aug 29, 1980 29-Aug-1980 to -- Matched: July 1946 -July-1946 to --
你可以使用正则expression式来定义所有可能的date情况，如下所示：
import re s = ['1963 to 1969', 'Aug. 1968 to Sept. 1968', '1972', 'Mar-73', '03-Jun', '24-Jul', 'Oct. 2, 1980', 'Oct. 26, 1980', 'Aug 29 1980', 'July 1946'] def get_year(date): mm = re.findall("\d{4}", date) if mm: return mm mm = re.search("\w+-(\d{2})", date) if mm: return [mm.group(1)] def get_month(date): mm = re.findall("[AZ][az]+", date) if mm: return mm def get_day(date): d_expr = ["(\d|\d{2})\-[AZ][az]+","[AZ][az]+[\. ]+(\d|\d{2}),"] for expr in d_expr: mm = re.search(expr, date) if mm: return [mm.group(1)] d = {} m = {} y = {} for idx, date in enumerate(s): d[idx] = get_day(date) m[idx] = get_month(date) y[idx] = get_year(date) print "Year Dict: ", y print "Month Dict: ", m print "Day Dict: ", d
结果你得到了几天，几个月和几年的字典。 他们可以用来填充行。
输出：
Year Dict: {0: ['1963', '1969'], 1: ['1968', '1968'], 2: ['1972'], 3: ['73'], 4: None, 5: None, 6: ['1980'], 7: ['1980'], 8: ['1980'], 9: ['1946']} Month Dict: {0: None, 1: ['Aug', 'Sept'], 2: None, 3: ['Mar'], 4: ['Jun'], 5: ['Jul'], 6: ['Oct'], 7: ['Oct'], 8: ['Aug'], 9: ['July']} Day Dict: {0: None, 1: None, 2: None, 3: None, 4: ['03'], 5: ['24'], 6: ['2'], 7: ['26'], 8: None, 9: None}
感谢您的创新build议。 经过考虑，我们决定从数据库中可以search到的date和月份中删除，因为只有相对较less的数据具有这种详细程度。 这里是我用来从一个漫长而杂乱的列表中提取和生成我需要的数据的代码。
import csv, xlwt, re # create new Excel document and add sheet from xlwt import Workbook book = Workbook() sheet1 = book.add_sheet('Sheet 1') # populate first row with header sheet1.write(0,0,"MapYear_(Parsed)") sheet1.write(0,1,"Map_Number") sheet1.write(0,2,"As_Entered") # count variable for populating sheet rowCount=0 # open csv file and read yearStr = '' with open('C:\mapsDateFix.csv', 'rb') as f: reader=csv.reader(f) for row in reader: map = row[0] # first row is map number dateRaw = row[1] # second row is raw date as entered # write undated and blank entries if dateRaw == 'undated': yearStr = 'undated' rowCount +=1 sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' #yearStr='' if yearStr != 'undated': if dateRaw == '': yearStr = 'NoEntry' rowCount +=1 sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' #yearStr='' # search and write instances of four consecutive digits if yearStr != dateRaw: try: year = re.search(r'\d\d\d\d', dateRaw) yearStr= year.group() #print yearStr, map, dateRaw rowCount +=1 sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' yearStr='' # if none exist flag for cleaning spreadsheet and print except: #print 'Nope', map, dateRaw rowCount +=1 yearStr='Format' sheet1.write(rowCount, 0, yearStr) sheet1.write(rowCount, 1, map) sheet1.write(rowCount, 2, dateRaw) #print rowCount, yearStr, map, dateRaw, '\n' yearStr='' yearStr='' dateRaw='' book.save('D:\dateProperty.xls') print "Done!"