我需要将RFC 3339字符串(如“2008-09-03T20:56:55.450686Z”)解析为Python的datetime类型。

我在Python标准库中找到了strptime,但它不是很方便。

最好的方法是什么?


当前回答

注意,在Python 2.6+和Py3K中,%f字符捕获微秒。

>>> datetime.datetime.strptime("2008-09-03T20:56:35.450686Z", "%Y-%m-%dT%H:%M:%S.%fZ")

请参阅此处的问题

其他回答

如果您使用的是Django,它提供了日期解析模块,它接受一系列类似于ISO格式的格式,包括时区。

如果您没有使用Django,并且不想使用这里提到的其他库之一,那么您可能会将Django的dateparse源代码调整为适合您的项目。

def parseISO8601DateTime(datetimeStr):
    import time
    from datetime import datetime, timedelta

    def log_date_string(when):
        gmt = time.gmtime(when)
        if time.daylight and gmt[8]:
            tz = time.altzone
        else:
            tz = time.timezone
        if tz > 0:
            neg = 1
        else:
            neg = 0
            tz = -tz
        h, rem = divmod(tz, 3600)
        m, rem = divmod(rem, 60)
        if neg:
            offset = '-%02d%02d' % (h, m)
        else:
            offset = '+%02d%02d' % (h, m)

        return time.strftime('%d/%b/%Y:%H:%M:%S ', gmt) + offset

    dt = datetime.strptime(datetimeStr, '%Y-%m-%dT%H:%M:%S.%fZ')
    timestamp = dt.timestamp()
    return dt + timedelta(hours=dt.hour-time.gmtime(timestamp).tm_hour)

注意,如果字符串不以Z结尾,我们可以使用%Z进行解析。

最初我尝试了:

from operator import neg, pos
from time import strptime, mktime
from datetime import datetime, tzinfo, timedelta

class MyUTCOffsetTimezone(tzinfo):
    @staticmethod
    def with_offset(offset_no_signal, signal):  # type: (str, str) -> MyUTCOffsetTimezone
        return MyUTCOffsetTimezone((pos if signal == '+' else neg)(
            (datetime.strptime(offset_no_signal, '%H:%M') - datetime(1900, 1, 1))
          .total_seconds()))

    def __init__(self, offset, name=None):
        self.offset = timedelta(seconds=offset)
        self.name = name or self.__class__.__name__

    def utcoffset(self, dt):
        return self.offset

    def tzname(self, dt):
        return self.name

    def dst(self, dt):
        return timedelta(0)


def to_datetime_tz(dt):  # type: (str) -> datetime
    fmt = '%Y-%m-%dT%H:%M:%S.%f'
    if dt[-6] in frozenset(('+', '-')):
        dt, sign, offset = strptime(dt[:-6], fmt), dt[-6], dt[-5:]
        return datetime.fromtimestamp(mktime(dt),
                                      tz=MyUTCOffsetTimezone.with_offset(offset, sign))
    elif dt[-1] == 'Z':
        return datetime.strptime(dt, fmt + 'Z')
    return datetime.strptime(dt, fmt)

但这在负时区不起作用。然而,我在Python 3.7.3中工作得很好:

from datetime import datetime


def to_datetime_tz(dt):  # type: (str) -> datetime
    fmt = '%Y-%m-%dT%H:%M:%S.%f'
    if dt[-6] in frozenset(('+', '-')):
        return datetime.strptime(dt, fmt + '%z')
    elif dt[-1] == 'Z':
        return datetime.strptime(dt, fmt + 'Z')
    return datetime.strptime(dt, fmt)

一些测试注意到,输出只在微秒的精度上有所不同。我的机器精度达到6位数,但YMMV:

for dt_in, dt_out in (
        ('2019-03-11T08:00:00.000Z', '2019-03-11T08:00:00'),
        ('2019-03-11T08:00:00.000+11:00', '2019-03-11T08:00:00+11:00'),
        ('2019-03-11T08:00:00.000-11:00', '2019-03-11T08:00:00-11:00')
    ):
    isoformat = to_datetime_tz(dt_in).isoformat()
    assert isoformat == dt_out, '{} != {}'.format(isoformat, dt_out)

感谢Mark Amery的出色回答,我设计了一个函数来解释所有可能的ISO日期时间格式:

class FixedOffset(tzinfo):
    """Fixed offset in minutes: `time = utc_time + utc_offset`."""
    def __init__(self, offset):
        self.__offset = timedelta(minutes=offset)
        hours, minutes = divmod(offset, 60)
        #NOTE: the last part is to remind about deprecated POSIX GMT+h timezones
        #  that have the opposite sign in the name;
        #  the corresponding numeric value is not used e.g., no minutes
        self.__name = '<%+03d%02d>%+d' % (hours, minutes, -hours)
    def utcoffset(self, dt=None):
        return self.__offset
    def tzname(self, dt=None):
        return self.__name
    def dst(self, dt=None):
        return timedelta(0)
    def __repr__(self):
        return 'FixedOffset(%d)' % (self.utcoffset().total_seconds() / 60)
    def __getinitargs__(self):
        return (self.__offset.total_seconds()/60,)

def parse_isoformat_datetime(isodatetime):
    try:
        return datetime.strptime(isodatetime, '%Y-%m-%dT%H:%M:%S.%f')
    except ValueError:
        pass
    try:
        return datetime.strptime(isodatetime, '%Y-%m-%dT%H:%M:%S')
    except ValueError:
        pass
    pat = r'(.*?[+-]\d{2}):(\d{2})'
    temp = re.sub(pat, r'\1\2', isodatetime)
    naive_date_str = temp[:-5]
    offset_str = temp[-5:]
    naive_dt = datetime.strptime(naive_date_str, '%Y-%m-%dT%H:%M:%S.%f')
    offset = int(offset_str[-4:-2])*60 + int(offset_str[-2:])
    if offset_str[0] == "-":
        offset = -offset
    return naive_dt.replace(tzinfo=FixedOffset(offset))

如今,Arrow还可以作为第三方解决方案:

>>> import arrow
>>> date = arrow.get("2008-09-03T20:56:35.450686Z")
>>> date.datetime
datetime.datetime(2008, 9, 3, 20, 56, 35, 450686, tzinfo=tzutc())