Best way to convert a Unicode URL to ASCII (UTF-8 percent-escaped) in Python?

Question

I\'m wondering what\'s the best way -- or if there\'s a simple way with the standard library -- to convert a URL with Unicode chars in the domain name and path to the equiva

Answer 1

Okay, with these comments and some bug-fixing in my own code (it didn't handle fragments at all), I've come up with the following canonurl() function -- returns a canonical, ASCII form of the URL:

import re
import urllib
import urlparse

def canonurl(url):
    r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or ''
    if the URL looks invalid.

    >>> canonurl('    ')
    ''
    >>> canonurl('www.google.com')
    'http://www.google.com/'
    >>> canonurl('bad-utf8.com/path\xff/file')
    ''
    >>> canonurl('svn://blah.com/path/file')
    'svn://blah.com/path/file'
    >>> canonurl('1234://badscheme.com')
    ''
    >>> canonurl('bad$scheme://google.com')
    ''
    >>> canonurl('site.badtopleveldomain')
    ''
    >>> canonurl('site.com:badport')
    ''
    >>> canonurl('http://123.24.8.240/blah')
    'http://123.24.8.240/blah'
    >>> canonurl('http://123.24.8.240:1234/blah?q#f')
    'http://123.24.8.240:1234/blah?q#f'
    >>> canonurl('\xe2\x9e\xa1.ws')  # tinyarro.ws
    'http://xn--hgi.ws/'
    >>> canonurl('  http://www.google.com:80/path/file;params?query#fragment  ')
    'http://www.google.com:80/path/file;params?query#fragment'
    >>> canonurl('http://\xe2\x9e\xa1.ws/\xe2\x99\xa5')
    'http://xn--hgi.ws/%E2%99%A5'
    >>> canonurl('http://\xe2\x9e\xa1.ws/\xe2\x99\xa5/pa%2Fth')
    'http://xn--hgi.ws/%E2%99%A5/pa/th'
    >>> canonurl('http://\xe2\x9e\xa1.ws/\xe2\x99\xa5/pa%2Fth;par%2Fams?que%2Fry=a&b=c')
    'http://xn--hgi.ws/%E2%99%A5/pa/th;par/ams?que/ry=a&b=c'
    >>> canonurl('http://\xe2\x9e\xa1.ws/\xe2\x99\xa5?\xe2\x99\xa5#\xe2\x99\xa5')
    'http://xn--hgi.ws/%E2%99%A5?%E2%99%A5#%E2%99%A5'
    >>> canonurl('http://\xe2\x9e\xa1.ws/%e2%99%a5?%E2%99%A5#%E2%99%A5')
    'http://xn--hgi.ws/%E2%99%A5?%E2%99%A5#%E2%99%A5'
    >>> canonurl('http://badutf8pcokay.com/%FF?%FE#%FF')
    'http://badutf8pcokay.com/%FF?%FE#%FF'
    >>> len(canonurl('google.com/' + 'a' * 16384))
    4096
    """
    # strip spaces at the ends and ensure it's prefixed with 'scheme://'
    url = url.strip()
    if not url:
        return ''
    if not urlparse.urlsplit(url).scheme:
        url = 'http://' + url

    # turn it into Unicode
    try:
        url = unicode(url, 'utf-8')
    except UnicodeDecodeError:
        return ''  # bad UTF-8 chars in URL

    # parse the URL into its components
    parsed = urlparse.urlsplit(url)
    scheme, netloc, path, query, fragment = parsed

    # ensure scheme is a letter followed by letters, digits, and '+-.' chars
    if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I):
        return ''
    scheme = str(scheme)

    # ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port]
    match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I)
    if not match:
        return ''
    domain, port = match.groups()
    netloc = domain + (port if port else '')
    netloc = netloc.encode('idna')

    # ensure path is valid and convert Unicode chars to %-encoded
    if not path:
        path = '/'  # eg: 'http://google.com' -> 'http://google.com/'
    path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;')

    # ensure query is valid
    query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/')

    # ensure fragment is valid
    fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8')))

    # piece it all back together, truncating it to a maximum of 4KB
    url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
    return url[:4096]

if __name__ == '__main__':
    import doctest
    doctest.testmod()