Last active
January 7, 2020 17:55
-
-
Save DamienGarrido/457d0a3a6d4f0a5f80081ca4262260c4 to your computer and use it in GitHub Desktop.
Python URL path join
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
# coding: utf8 | |
import re | |
import urllib.parse | |
def url_path_join(base_url, *paths): | |
parsed_url = urllib.parse.urlsplit(base_url) | |
base_path = re.sub('/+', '/', parsed_url.path) | |
if paths: | |
if len(base_path) and base_path[-1] != '/': | |
base_path += '/' | |
for path in paths[:-1]: | |
path = re.sub('/+', '/', path).lstrip('/') + '/' | |
base_path = urllib.parse.urljoin(base_path, path) | |
path = paths[-1] | |
path = re.sub('/+', '/', path).lstrip('/') | |
base_path = urllib.parse.urljoin(base_path, path) | |
return urllib.parse.urlunsplit(parsed_url._replace(path=base_path)) | |
# Some random tests | |
urls = [ | |
('http://example.com/relative/url/to/file', 'http://example.com', 'relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/', 'relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com//', 'relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/', '/relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/', '../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/', '/../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/base', '../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/base/', '../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com//base/', '../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file/', 'http://example.com/base//', '../relative/url/to/file/' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/base', '/../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file', 'http://example.com/base/', '/../relative/url/to/file' ), | |
('http://example.com/relative/url/to/file/', 'http://example.com/base/', '/../relative/url/to/file/' ), | |
('http://example.com/base/relative/url/to/file', 'http://example.com/base', '/relative/url/to/file' ), | |
('http://example.com/base/relative/url/to/file', 'http://example.com/base/', '/relative/url/to/file' ), | |
('http://example.com/base/relative/url/to/file', 'http://example.com/base', 'relative/url/to/file' ), | |
('http://example.com/base/relative/url/to/file', 'http://example.com/base/', '//relative//url//', '/to/file' ), | |
('http://example.com/base/relative/url/to/my/file', 'http://example.com/base/', 'relative/url', '/to/', 'my/file' ), | |
('http://example.com/base/relative/url/to/my/file/', 'http://example.com/base/', 'relative/url', '/to/', 'my/file/' ), | |
('http://example.com/base/relative/url/to/file?a=a/b/c#here', 'http://example.com/base/', 'relative//url', '//to//file?a=a/b/c#here' ), | |
('https://username:password@example.com:8443/base/relative/url/to/new/path/to/file/?a=a/b/c&b=//d//e//f//#here', 'https://username:password@example.com:8443/base/relative/url/to/file?a=a/b/c&b=//d//e//f//#here', '//..//new//path//', '//to//file//') | |
] | |
def test(func): | |
counter = 0 | |
for joined_url, base_url, *relative_urls in urls: | |
print("Test {num}:".format(num=counter)) | |
print("Base URL : '{url}'".format(url=base_url)) | |
print("Relative URL: '{url}'".format(url=relative_urls)) | |
computed_url = func(base_url, *relative_urls) | |
print("Computed URL: {url}".format(url=computed_url)) | |
print("Joined URL : {url}".format(url=joined_url)) | |
assert computed_url == joined_url | |
counter += 1 | |
test(url_path_join) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment