微博 url 与 mid 互转工具

weibo_url_mid_convert.py

"""
:author Jermic
:date 2019-02-13
:weibo https://weibo.com/Jermic/
"""

ALPHABET = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"


def base62_encode(num, alphabet=ALPHABET):
    num = int(num)
    if num == 0:
        return alphabet[0]
    arr = []
    base = len(alphabet)
    while num:
        rem = num % base
        num = num // base
        arr.append(alphabet[rem])
    arr.reverse()
    return ''.join(arr)


def base62_decode(string, alphabet=ALPHABET):
    string = str(string)
    num = 0
    idx = 0
    for char in string:
        power = (len(string) - (idx + 1))
        num += alphabet.index(char) * (len(alphabet) ** power)
        idx += 1

    return num


def reverse_cut_to_length(content, code_func, cut_num=4, fill_num=7):
    content = str(content)
    cut_list = [content[i - cut_num if i >= cut_num else 0:i] for i in range(len(content), 0, (-1 * cut_num))]
    cut_list.reverse()
    result = []
    for i, item in enumerate(cut_list):
        s = str(code_func(item))
        if i > 0 and len(s) < fill_num:
            s = (fill_num - len(s)) * '0' + s
        result.append(s)
    return ''.join(result)


def url_to_mid(url: str):
    """
    >>> url_to_mid('z0JH2lOMb')
    3501756485200075
    >>> url_to_mid('z0IgABdSn')
    3501701648871479
    >>> url_to_mid('z08AUBmUe')
    3500330408906190
    >>> url_to_mid('z06qL6b28')
    3500247231472384
    >>> url_to_mid('yAt1n2xRa')
    3486913690606804
    """
    result = reverse_cut_to_length(url, base62_decode, 4, 7)
    return int(result)


def mid_to_url(mid_int: int):
    """
    >>> mid_to_url(3501756485200075)
    'z0JH2lOMb'
    >>> mid_to_url(3501701648871479)
    'z0IgABdSn'
    >>> mid_to_url(3500330408906190)
    'z08AUBmUe'
    >>> mid_to_url(3500247231472384)
    'z06qL6b28'
    >>> mid_to_url(3486913690606804)
    'yAt1n2xRa'
    """
    result = reverse_cut_to_length(mid_int, base62_encode, 7, 4)
    return result


if __name__ == "__main__":
    print(url_to_mid('Hd1N2qpta'))
    print(mid_to_url(4331051486294436))