详解python内置模块urllib

>>> from urllib import parse
>>> url = 'https://mp.weixin.qq.com/s?__biz=MjM5MzgyODQxMQ==&mid=2650366919&idx=1&sn=1b36a9f2c0921cdeac52942ec591a923#rd'
>>> result = parse.urlparse(url)

# 返回ParseResult对象
>>> print(result)
ParseResult(scheme='https', netloc='mp.weixin.qq.com', path='/s', params='', query='__biz=MjM5MzgyODQxMQ==&mid=2650366919&idx=1&sn=1b36a9f2c0921cdeac52942ec591a923', fragment='rd')

# 通过下标获取协议
>>> result[0]
'https'

# 协议
>>> result.scheme
'https'

# url资源路径
>>> result.path
'/s'

# 查询参数
>>> result.query
'__biz=MjM5MzgyODQxMQ==&mid=2650366919&idx=1&sn=1b36a9f2c0921cdeac52942ec591a923'

# 获取主机名
>>> result.hostname
'mp.weixin.qq.com'

>>> parse.parse_qs(result.query)
{'__biz': ['MjM5MzgyODQxMQ=='], 'mid': ['2650366919'], 'idx': ['1'], 'sn': ['1b36a9f2c0921cdeac52942ec591a923']}
>>>

>>> {name: value[0] for name, value in parse.parse_qs(result.query).items()}
{'__biz': 'MjM5MzgyODQxMQ==', 'mid': '2650366919', 'idx': '1', 'sn': '1b36a9f2c0921cdeac52942ec591a923'}

>>> d = {'__biz': 'MjM5MzgyODQxMQ==', 'mid': '2650366919', 'idx': '1'}
>>> parse.urlencode(d)
'__biz=MjM5MzgyODQxMQ%3D%3D&mid=2650366919&idx=1'

>>> "中".encode()
b'\xe4\xb8\xad'

>>> parse.quote("q=中")
'q%3D%E4%B8%AD'
>>>

>>> parse.quote_plus("a b")
'a+b'
>>> parse.quote("a b")
'a%20b'

>>> parse.unquote("q%3D%E4%B8%AD")
'q=中'