python3 URL拼接代碼

from urllib.parse import urljoin
from urllib.parse import urlparse
from urllib.parse import urlunparse
from posixpath import normpath
 
 
def myjoin(base, url):
    url1 = urljoin(base, url)
    arr = urlparse(url1)
    path = normpath(arr[2])
    return urlunparse((arr.scheme, arr.netloc, path, arr.params, arr.query, arr.fragment))
 
print(myjoin("http://www.baidu.com", "abc.html"))
print(myjoin("http://www.baidu.com", "/../../abc.html"))
print(myjoin("http://www.baidu.com/xxx/yy/zz/xyz", "./../../abc.html"))
print(myjoin("http://www.baidu.com", "abc.html?key=value&m=x"))

結果：

http://www.baidu.com/abc.html
http://www.baidu.com/abc.html
http://www.baidu.com/xxx/abc.html
http://www.baidu.com/abc.html?key=value&m=x