Python3 中文在URL中的编码解码

from urllib.parse import quote
text = quote(text, 'utf-8')

from urllib.parse import unquote
text = unquote(text, 'utf-8')

def quote(string, safe='/', encoding=None, errors=None):
    """quote('abc def') -> 'abc%20def'
 
    Each part of a URL, e.g. the path info, the query, etc., has a
    different set of reserved characters that must be quoted.
 
    RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
    the following reserved characters.
 
    reserved    = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
                  "$" | ","
 
    Each of these characters is reserved in some component of a URL,
    but not necessarily in all of them.
 
    By default, the quote function is intended for quoting the path
    section of a URL.  Thus, it will not encode '/'.  This character
    is reserved, but in typical usage the quote function is being
    called on a path where the existing slash characters are used as
    reserved characters.
 
    string and safe may be either str or bytes objects. encoding and errors
    must not be specified if string is a bytes object.
 
    The optional encoding and errors parameters specify how to deal with
    non-ASCII characters, as accepted by the str.encode method.
    By default, encoding='utf-8' (characters are encoded with UTF-8), and
    errors='strict' (unsupported characters raise a UnicodeEncodeError).
    """
    if isinstance(string, str):
        if not string:
            return string
        if encoding is None:
            encoding = 'utf-8'
        if errors is None:
            errors = 'strict'
        string = string.encode(encoding, errors)
    else:
        if encoding is not None:
            raise TypeError("quote() doesn't support 'encoding' for bytes")
        if errors is not None:
            raise TypeError("quote() doesn't support 'errors' for bytes")
    return quote_from_bytes(string, safe)
 
 
def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.
 
    unquote('abc%20def') -> 'abc def'.
    """
    if '%' not in string:
        string.split
        return string
    if encoding is None:
        encoding = 'utf-8'
    if errors is None:
        errors = 'replace'
    bits = _asciire.split(string)
    res = [bits[0]]
    append = res.append
    for i in range(1, len(bits), 2):
        append(unquote_to_bytes(bits[i]).decode(encoding, errors))
        append(bits[i + 1])
    return ''.join(res)