from urllib import parse

url = 'https://www.cnblogs.com/angelyan/'

"""

url：待解析的url

scheme=''：假如解析的url没有协议,可以设置默认的协议,如果url有协议，设置此参数无效

allow_fragments=True：是否忽略锚点,默认为True表示不忽略,为False表示忽略

"""

result = parse.urlparse(url=url,scheme='http',allow_fragments=True)

print(result)

print(result.scheme)

"""

(scheme='https', netloc='www.cnblogs.com', path='/angelyan/', params='', query='', fragment='')

scheme:表示协议

netloc:域名

path:路径

params:参数

query:查询条件，一般都是get请求的url

fragment:锚点，用于直接定位页

面的下拉位置，跳转到网页的指定位置

"""

url_parmas = ('https', 'www.cnblogs.com', '/angelyan/', '', 'name=maple', 'log')

#components:是一个可迭代对象，长度必须为6

result = parse.urlunparse(url_parmas)

print(result)

"""

https://www.cnblogs.com/angelyan/?name=maple#log

"""

base_url = 'https://www.cnblogs.com'

sub_url = '/angelyan/?name=maple#log'

full_url = parse.urljoin(base_url,sub_url)

print(full_url)

"""

https://www.cnblogs.com/angelyan/?name=maple#log

"""

parmas = {

    'name':'maple',

    'age':18

}

parmas_str = parse.urlencode(parmas)

print(parmas_str)

"""

name=maple&age=18

"""

parmas_str = 'name=maple&age=18'

# 将url编码格式的参数反序列化为字典类型

parmas = parse.parse_qs(parmas_str)

print(parmas)

"""

{'name': ['maple'], 'age': ['18']}

"""

word = '中国梦'

url = 'http://www.baidu.com/s?wd='+parse.quote(word)

print(parse.quote(word))

print(url)

"""

%E4%B8%AD%E5%9B%BD%E6%A2%A6

http://www.baidu.com/s?wd=%E4%B8%AD%E5%9B%BD%E6%A2%A6

"""

# unquote:可以将URL编码进行解码

url = 'http://www.baidu.com/s?wd=%E4%B8%AD%E5%9B%BD%E6%A2%A6'

print(parse.unquote(url))

"""

http://www.baidu.com/s?wd=中国梦

"""