python - 在 Python 中将货币解析为数字

Question

刚刚从Format numbers as currency in Python了解到，Python模块babel提供了babel.numbers.format_currency来将数字格式化为货币。例如，

from babel.numbers import format_currency

s = format_currency(123456.789, 'USD', locale='en_US')  # u'$123,456.79'
s = format_currency(123456.789, 'EUR', locale='fr_FR')  # u'123\xa0456,79\xa0\u20ac'

反过来如何，从货币到数字，比如$123,456,789.00 --> 123456789？ babel提供了babel.numbers.parse_number来解析本地数字，但是我没有找到类似parse_currency的东西。那么，将本地货币解析为数字的理想方式是什么？

---

我经历了 Python: removing characters except digits from string 。

# Way 1
import string
all=string.maketrans('','')
nodigs=all.translate(all, string.digits)

s = '$123,456.79'
n = s.translate(all, nodigs)    # 12345679, lost `.`

# Way 2
import re
n = re.sub("\D", "", s)         # 12345679

它不关心小数点分隔符。。

---

从字符串中删除所有非数字字符，. 除外(引用 here )，

import re

# Way 1:
s = '$123,456.79'
n = re.sub("[^0-9|.]", "", s)   # 123456.79

# Way 2:
non_decimal = re.compile(r'[^\d.]+')
s = '$123,456.79'
n = non_decimal.sub('', s)      # 123456.79

它确实处理小数点分隔符。。

---

但是上面的解决方案在来时不起作用，例如，

from babel.numbers import format_currency
s = format_currency(123456.789, 'EUR', locale='fr_FR')  # u'123\xa0456,79\xa0\u20ac'
new_s = s.encode('utf-8') # 123 456,79 €

如您所见，货币的格式各不相同。 以通用方式将货币解析为数字的理想方法是什么？

Answer 1

下面是一个不依赖 babel 库的通用货币解析器。

import numpy as np
import re

def currency_parser(cur_str):
    # Remove any non-numerical characters
    # except for ',' '.' or '-' (e.g. EUR)
    cur_str = re.sub("[^-0-9.,]", '', cur_str)
    # Remove any 000s separators (either , or .)
    cur_str = re.sub("[.,]", '', cur_str[:-3]) + cur_str[-3:]

    if '.' in list(cur_str[-3:]):
        num = float(cur_str)
    elif ',' in list(cur_str[-3:]):
        num = float(cur_str.replace(',', '.'))
    else:
        num = float(cur_str)

    return np.round(num, 2)

这是一个测试函数的pytest脚本:

import numpy as np
import pytest
import re


def currency_parser(cur_str):
    # Remove any non-numerical characters
    # except for ',' '.' or '-' (e.g. EUR)
    cur_str = re.sub("[^-0-9.,]", '', cur_str)
    # Remove any 000s separators (either , or .)
    cur_str = re.sub("[.,]", '', cur_str[:-3]) + cur_str[-3:]

    if '.' in list(cur_str[-3:]):
        num = float(cur_str)
    elif ',' in list(cur_str[-3:]):
        num = float(cur_str.replace(',', '.'))
    else:
        num = float(cur_str)

    return np.round(num, 2)


@pytest.mark.parametrize('currency_str, expected', [
    (
            '.3', 0.30
    ),
    (
            '1', 1.00
    ),
    (
            '1.3', 1.30
    ),
    (
            '43,324', 43324.00
    ),
    (
            '3,424', 3424.00
    ),
    (
            '-0.00', 0.00
    ),
    (
            'EUR433,432.53', 433432.53
    ),
    (
            '25.675,26 EUR', 25675.26
    ),
    (
            '2.447,93 EUR', 2447.93
    ),
    (
            '-540,89EUR', -540.89
    ),
    (
            '67.6 EUR', 67.60
    ),
    (
            '30.998,63 CHF', 30998.63
    ),
    (
            '0,00 CHF', 0.00
    ),
    (
            '159.750,00 DKK', 159750.00
    ),
    (
            '£ 2.237,85', 2237.85
    ),
    (
            '£ 2,237.85', 2237.85
    ),
    (
            '-1.876,85 SEK', -1876.85
    ),
    (
            '59294325.3', 59294325.30
    ),
    (
            '8,53 NOK', 8.53
    ),
    (
            '0,09 NOK', 0.09
    ),
    (
            '-.9 CZK', -0.9
    ),
    (
            '35.255,40 PLN', 35255.40
    ),
    (
            '-PLN123.456,78', -123456.78
    ),
    (
            'US$123.456,79', 123456.79
    ),
    (
            '-PLN123.456,78', -123456.78
    ),
    (
            'PLN123.456,79', 123456.79
    ),
    (
            'IDR123.457', 123457
    ),
    (
            'JP¥123.457', 123457
    ),
    (
            '-JP\xc2\xa5123.457', -123457
    ),
    (
            'CN\xc2\xa5123.456,79', 123456.79
    ),
    (
            '-CN\xc2\xa5123.456,78', -123456.78
    ),
])
def test_currency_parse(currency_str, expected):
    assert currency_parser(currency_str) == expected