Python URL模块

from urllib.parse import *
 
params = {
    'name': 'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'

urlencode + parse_qs

> urlencode(params)  # 输出：'name=germey&age=22'
> parse_qs('name=germey&age=22')  # 输出：{'name': ['germey'], 'age': ['22']}
> parse_qsl('name=germey&age=22') # 输出：[('name', 'germey'), ('age', '22')]

quote + unquote :

quote()将内容转化为URL编码的格式, 防止中文乱码。

>  quote("高清")    # 输出：'%E9%AB%98%E6%B8%85'

urlparse + urlunparse

解析URL得到6parts: <scheme>://<netloc>/<path>;<params>?<query>#<fragment>

> url = 'http://www.baidu.com/index.php?username=guo'
> urlparse(url)
Out: ParseResult(scheme='http', netloc='www.baidu.com', path='/index.php', params='', query='username=guo', fragment='')

> urlunparse(ret)  # 从元祖构建url

urlsplit + urlunsplit

解析URL得到5parts: <scheme>://<netloc>/<path>?<query>#<fragment>

> ret= urlparse.urlsplit(url)  
输出： SplitResult(scheme='http', netloc='www.baidu.com', path='/index.php', query='username=guo', fragment='')

> urlunsplit(ret)

urljoin

urljoin('http://www.oschina.com/tieba','index.php')   # 'http://www.oschina.com/index.php'   base不是以字符/结尾时，
urljoin('http://www.oschina.com/tieba/','index.php')  # 'http://www.oschina.com/tieba/index.php'