Parse an HTTP request Authorization header with Python

Question

I need to take a header like this:

 Authorization: Digest qop=\"chap\",
     realm=\"testrealm@host.com\",
     username=\"Foobear\",
     response=\"6629fae         


        

Answer 1

If your response comes in a single string that that never varies and has as many lines as there are expressions to match, you can split it into an array on the newlines called authentication_array and use regexps:

pattern_array = ['qop', 'realm', 'username', 'response', 'cnonce']
i = 0
parsed_dict = {}

for line in authentication_array:
    pattern = "(" + pattern_array[i] + ")" + "=(\".*\")" # build a matching pattern
    match = re.search(re.compile(pattern), line)         # make the match
    if match:
        parsed_dict[match.group(1)] = match.group(2)
    i += 1

Answer 2

A little regex:

import re
reg=re.compile('(\w+)[:=] ?"?(\w+)"?')

>>>dict(reg.findall(headers))

{'username': 'Foobear', 'realm': 'testrealm', 'qop': 'chap', 'cnonce': '5ccc069c403ebaf9f0171e9517f40e41', 'response': '6629fae49393a05397450978507c4ef1', 'Authorization': 'Digest'}

Answer 3

An older question but one I found very helpful.

I needed a parser to handle any properly formed Authorization header, as defined by RFC7235 (raise your hand if you enjoy reading ABNF).

Authorization = credentials

BWS = <BWS, see [RFC7230], Section 3.2.3>

OWS = <OWS, see [RFC7230], Section 3.2.3>

Proxy-Authenticate = *( "," OWS ) challenge *( OWS "," [ OWS
 challenge ] )
Proxy-Authorization = credentials

WWW-Authenticate = *( "," OWS ) challenge *( OWS "," [ OWS challenge
 ] )

auth-param = token BWS "=" BWS ( token / quoted-string )
auth-scheme = token

challenge = auth-scheme [ 1*SP ( token68 / [ ( "," / auth-param ) *(
 OWS "," [ OWS auth-param ] ) ] ) ]
credentials = auth-scheme [ 1*SP ( token68 / [ ( "," / auth-param )
 *( OWS "," [ OWS auth-param ] ) ] ) ]

quoted-string = <quoted-string, see [RFC7230], Section 3.2.6>

token = <token, see [RFC7230], Section 3.2.6>
token68 = 1*( ALPHA / DIGIT / "-" / "." / "_" / "~" / "+" / "/" )
 *"="

Starting with PaulMcG's answer, I came up with this:

import pyparsing as pp

tchar = '!#$%&\'*+-.^_`|~' + pp.nums + pp.alphas
t68char = '-._~+/' + pp.nums + pp.alphas

token = pp.Word(tchar)
token68 = pp.Combine(pp.Word(t68char) + pp.ZeroOrMore('='))

scheme = token('scheme')

header = pp.Keyword('Authorization')
name = pp.Word(pp.alphas, pp.alphanums)
value = pp.quotedString.setParseAction(pp.removeQuotes)
name_value_pair = name + pp.Suppress('=') + value
params = pp.Dict(pp.delimitedList(pp.Group(name_value_pair)))

credentials = scheme + (token68('token') ^ params('params'))

auth_parser = header + pp.Suppress(':') + credentials

This allows for parsing any Authorization header:

parsed = auth_parser.parseString('Authorization: Basic Zm9vOmJhcg==')
print('Authenticating with {0} scheme, token: {1}'.format(parsed['scheme'], parsed['token']))

which outputs:

Authenticating with Basic scheme, token: Zm9vOmJhcg==

Bringing it all together into an Authenticator class:

import pyparsing as pp
from base64 import b64decode
import re

class Authenticator:
    def __init__(self):
        """
        Use pyparsing to create a parser for Authentication headers
        """
        tchar = "!#$%&'*+-.^_`|~" + pp.nums + pp.alphas
        t68char = '-._~+/' + pp.nums + pp.alphas

        token = pp.Word(tchar)
        token68 = pp.Combine(pp.Word(t68char) + pp.ZeroOrMore('='))

        scheme = token('scheme')

        auth_header = pp.Keyword('Authorization')
        name = pp.Word(pp.alphas, pp.alphanums)
        value = pp.quotedString.setParseAction(pp.removeQuotes)
        name_value_pair = name + pp.Suppress('=') + value
        params = pp.Dict(pp.delimitedList(pp.Group(name_value_pair)))

        credentials = scheme + (token68('token') ^ params('params'))

        # the moment of truth...
        self.auth_parser = auth_header + pp.Suppress(':') + credentials


    def authenticate(self, auth_header):
        """
        Parse auth_header and call the correct authentication handler
        """
        authenticated = False
        try:
            parsed = self.auth_parser.parseString(auth_header)
            scheme = parsed['scheme']
            details = parsed['token'] if 'token' in parsed.keys() else parsed['params']

            print('Authenticating using {0} scheme'.format(scheme))
            try:
                safe_scheme = re.sub("[!#$%&'*+-.^_`|~]", '_', scheme.lower())
                handler = getattr(self, 'auth_handle_' + safe_scheme)
                authenticated = handler(details)
            except AttributeError:
                print('This is a valid Authorization header, but we do not handle this scheme yet.')

        except pp.ParseException as ex:
            print('Not a valid Authorization header')
            print(ex)

        return authenticated


    # The following methods are fake, of course.  They should use what's passed
    # to them to actually authenticate, and return True/False if successful.
    # For this demo I'll just print some of the values used to authenticate.
    @staticmethod
    def auth_handle_basic(token):
        print('- token is {0}'.format(token))
        try:
            username, password = b64decode(token).decode().split(':', 1)
        except Exception:
            raise DecodeError
        print('- username is {0}'.format(username))
        print('- password is {0}'.format(password))
        return True

    @staticmethod
    def auth_handle_bearer(token):
        print('- token is {0}'.format(token))
        return True

    @staticmethod
    def auth_handle_digest(params):
        print('- username is {0}'.format(params['username']))
        print('- cnonce is {0}'.format(params['cnonce']))
        return True

    @staticmethod
    def auth_handle_aws4_hmac_sha256(params):
        print('- Signature is {0}'.format(params['Signature']))
        return True

To test this class:

tests = [
    'Authorization: Digest qop="chap", realm="testrealm@example.com", username="Foobar", response="6629fae49393a05397450978507c4ef1", cnonce="5ccc069c403ebaf9f0171e9517f40e41"',
    'Authorization: Bearer cn389ncoiwuencr',
    'Authorization: Basic Zm9vOmJhcg==',
    'Authorization: AWS4-HMAC-SHA256 Credential="AKIAIOSFODNN7EXAMPLE/20130524/us-east-1/s3/aws4_request", SignedHeaders="host;range;x-amz-date", Signature="fe5f80f77d5fa3beca038a248ff027d0445342fe2855ddc963176630326f1024"',
    'Authorization: CrazyCustom foo="bar", fizz="buzz"',
]

authenticator = Authenticator()

for test in tests:
    authenticator.authenticate(test)
    print()

Which outputs:

Authenticating using Digest scheme
- username is Foobar
- cnonce is 5ccc069c403ebaf9f0171e9517f40e41

Authenticating using Bearer scheme
- token is cn389ncoiwuencr

Authenticating using Basic scheme
- token is Zm9vOmJhcg==
- username is foo
- password is bar

Authenticating using AWS4-HMAC-SHA256 scheme
- signature is fe5f80f77d5fa3beca038a248ff027d0445342fe2855ddc963176630326f1024

Authenticating using CrazyCustom scheme 
This is a valid Authorization header, but we do not handle this scheme yet.

In future if we wish to handle CrazyCustom we'll just add

def auth_handle_crazycustom(params):

Answer 4

The http digest Authorization header field is a bit of an odd beast. Its format is similar to that of rfc 2616's Cache-Control and Content-Type header fields, but just different enough to be incompatible. If you're still looking for a library that's a little smarter and more readable than the regex, you might try removing the Authorization: Digest part with str.split() and parsing the rest with parse_dict_header() from Werkzeug's http module. (Werkzeug can be installed on App Engine.)