Python3 urlparse

>>> from urllib.parse import urlparse
>>> o = urlparse('http://www.cwi.nl:80/%7Eguido/Python.html')
>>> o   
ParseResult(scheme='http', netloc='www.cwi.nl:80', path='/%7Eguido/Python.html',
            params='', query='', fragment='')
>>> o.scheme
'http'
>>> o.port
80
>>> o.geturl()
'http://www.cwi.nl:80/%7Eguido/Python.html'

>>> from urllib.parse import urlparse
>>> urlparse('//www.cwi.nl:80/%7Eguido/Python.html')
ParseResult(scheme='', netloc='www.cwi.nl:80', path='/%7Eguido/Python.html',
           params='', query='', fragment='')
>>> urlparse('www.cwi.nl/%7Eguido/Python.html')
ParseResult(scheme='', netloc='', path='www.cwi.nl/%7Eguido/Python.html',
           params='', query='', fragment='')
>>> urlparse('help/Python.html')
ParseResult(scheme='', netloc='', path='help/Python.html', params='',
           query='', fragment='')

Attribute	Index	Value	Value if not present
scheme	0	URL scheme specifier	scheme parameter
netloc	1	Network location part	empty string
path	2	Hierarchical path	empty string
params	3	Parameters for last path element	empty string
query	4	Query component	empty string
fragment	5	Fragment identifier	empty string
username		User name	None
password		Password	None
hostname		Host name (lower case)	None
port		Port number as integer, if present	None

 

来源：https://docs.python.org/3/library/urllib.parse.html?highlight=urlparse#urllib.parse.urlparse

 

from urllib.parse import urljoin
>>> urljoin("http://www.asite.com/folder/currentpage.html", "anotherpage.html")
'http://www.asite.com/folder/anotherpage.html'
>>> urljoin("http://www.asite.com/folder/currentpage.html", "folder2/anotherpage.html")
'http://www.asite.com/folder/folder2/anotherpage.html'
>>> urljoin("http://www.asite.com/folder/currentpage.html", "/folder3/anotherpage.html")
'http://www.asite.com/folder3/anotherpage.html'
>>> urljoin("http://www.asite.com/folder/currentpage.html", "../finalpage.html")
'http://www.asite.com/finalpage.html'

转载于:https://www.cnblogs.com/itlqs/p/6055365.html