from urllib import parse
url = 'https://book.qidian.com/info/1004608738?wd=123&page=20#Catalog'

"""
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)  # 协议
print(result.netloc)  # 域名
print(result.path)  # 路径
print(result.params)  # 参数
print(result.query)  # 查询条件，一般都是get请求
print(result.fragment)  # 锚点，用于直接定位页面的下拉位置
"""
https
book.qidian.com
/info/1004608738
""
wd=123&page=20
Catalog

"""

# urlunparse()可以实现URL的构造
url_parmas = ('https', 'book.qidian.com', '/info/1004608738', '', 'wd=123&page=20', 'Catalog')
url_result = parse.urlunparse(url_parmas)
print(url_result)
"""
https://book.qidian.com/info/1004608738?wd=123&page=20#Catalog
"""

# urljoin()传递一个基础链接,根据基础链接可以将某一个不完整的链接拼接为一个完整链接
base_url = 'https://book.qidian.com/info/1004608738?wd=123&page=20#Catalog'
path_sub = '/info/100861102'
full_url = parse.urljoin(base_url, path_sub)
print(full_url)
"""
https://book.qidian.com/info/100861102
"""

# urlencode()将字典构形式的参数序列化为url编码后的字符串（常用来构造get请求和post请求的参数）k1=v1&k2=v2
parmas = {
    'wd':'123',
    'page':20
}
parmas_str = parse.urlencode(parmas)
print(parmas_str)
"""
page=20&wd=123
"""
# parse_qs() 将url编码格式的参数反序列化为字典类型
parmas_str = 'page=20&wd=123'
parmas = parse.parse_qs(parmas_str)
print(parmas)
"""
{'page': ['20'], 'wd': ['123']}
"""

# quote()可以将中文转换为URL编码格式
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
"""

转载：https://www.cnblogs.com/wuzm/p/11655035.html