Python parse.unquote_to_bytes函数代码示例

    def frankiz_auth_check(self, request):
        import logging
        logger = logging.getLogger(__name__)

        student = None
        response_data = {'valid': True, 'student': student}
        RETURN_PAGE = ('http://' + request.get_host() + '/vaneau/').encode()
        logger.error(RETURN_PAGE)

        if not "timestamp" in request.query_params.keys() or not "response" in request.query_params.keys() or not "hash" in request.query_params.keys():
            logger.error('KEYS')
            response_data["valid"] = False

        response = parse.unquote_to_bytes(request.query_params.get("response"))
        ts = parse.unquote_to_bytes(request.query_params.get("timestamp"))
        h = parse.unquote_to_bytes(request.query_params.get("hash"))

        if abs(int(time.time()) - int(ts)) > 3600*3 or abs(int(ts) + 3*3600 - int(time.time())) < 30*60:
            logger.error('TS')
            response_data["valid"] = False

        if hashlib.md5(ts + FKZ_KEY + response).hexdigest() != h.decode():
            logger.error('HASH')
            response_data["valid"] = False

        if response_data["valid"]:
            data = json.loads(response.decode())
            try:
                student = Student.objects.get(hruid=data["hruid"])
            except Student.DoesNotExist:
                student = Student.objects.create(hruid=data["hruid"], lastname=data["lastname"], firstname=data["firstname"], promo=data["promo"])
            finally:
                response_data["student"] = StudentSerializer(student).data

        return Response(response_data, 200)

    def parse_qsl_to_bytes(qs, keep_blank_values=False, strict_parsing=False):
        """Parse a query given as a string argument.

        Data are returned as a list of name, value pairs as bytes.

        Arguments:

        qs: percent-encoded query string to be parsed

        keep_blank_values: flag indicating whether blank values in
            percent-encoded queries should be treated as blank strings.  A
            true value indicates that blanks should be retained as blank
            strings.  The default false value indicates that blank values
            are to be ignored and treated as if they were  not included.

        strict_parsing: flag indicating what to do with parsing errors. If
            false (the default), errors are silently ignored. If true,
            errors raise a ValueError exception.

        """
        # This code is the same as Python3's parse_qsl()
        # (at https://hg.python.org/cpython/rev/c38ac7ab8d9a)
        # except for the unquote(s, encoding, errors) calls replaced
        # with unquote_to_bytes(s)
        qs, _coerce_result = _coerce_args(qs)
        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
        r = []
        for name_value in pairs:
            if not name_value and not strict_parsing:
                continue
            nv = name_value.split('=', 1)
            if len(nv) != 2:
                if strict_parsing:
                    raise ValueError("bad query field: %r" % (name_value,))
                # Handle case of a control-name with no equal sign
                if keep_blank_values:
                    nv.append('')
                else:
                    continue
            if len(nv[1]) or keep_blank_values:
                name = nv[0].replace('+', ' ')
                name = unquote_to_bytes(name)
                name = _coerce_result(name)
                value = nv[1].replace('+', ' ')
                value = unquote_to_bytes(value)
                value = _coerce_result(value)
                r.append((name, value))
        return r

def verify_handshake(token, signature, action):
    """
    Decodes a handshake token (X-Siphon-Handshake-Token header) and verifies
    it against the given signature (X-Siphon-Handshake-Signature header).

    If it passes verification it decodes the payload's JSON. If this is a
    development handshake (i.e. tying a username to an app ID) it returns
    a tuple containing two strings:

        (<username>, <app-id>)

    The given app ID is guaranteed to be owned by the user. Otherwise,
    if this is a production handshake it returns:

        (<submission-id>, <app-id>)

    Note that production handshake's are not tied to a user.
    """
    # Note that rsa.verify() detects the SHA-256 hashing method for us
    payload = base64.b64decode(unquote(token))
    signature_bytes = unquote_to_bytes(signature)
    ok = rsa.verify(payload, signature_bytes, get_public_key())
    if not ok:
        raise HandshakeError()
    try:
        obj = json.loads(payload.decode('utf8'))
        if 'action' in obj and obj['action'] != action:
            raise HandshakeError()
        if 'user_id' in obj and 'app_id' in obj:
            return (obj['user_id'], obj['app_id'])
        else:
            return (obj['submission_id'], obj['app_id'])
    except (ValueError, KeyError):
        raise HandshakeError()

def get_decoder(enc):
    if enc == 'base64':
        return a2b_base64
    elif enc == 'url':
        return lambda x: unquote_to_bytes(x.replace(b'+', b'%20'))
    elif enc in ('lower_hex', 'upper_hex', 'hex'):
        return a2b_hex

def open_data_url(url):
    """Decode URLs with the 'data' scheme. urllib can handle them
    in Python 2, but that is broken in Python 3.

    Inspired from Python 2.7.2’s urllib.py.

    """
    # syntax of data URLs:
    # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
    # mediatype := [ type "/" subtype ] *( ";" parameter )
    # data      := *urlchar
    # parameter := attribute "=" value
    try:
        header, data = url.split(",", 1)
    except ValueError:
        raise IOError("bad data URL")
    header = header[5:]  # len("data:") == 5
    if header:
        semi = header.rfind(";")
        if semi >= 0 and "=" not in header[semi:]:
            encoding = header[semi + 1:]
        else:
            encoding = ""
    else:
        encoding = ""

    data = unquote_to_bytes(data)
    if encoding == "base64":
        missing_padding = 4 - len(data) % 4
        if missing_padding:
            data += b"=" * missing_padding
        return base64.decodestring(data)
    return data

    def parse_querystring(query_string):
        """
        Parse a raw query string.

        Args:
            query_string: raw query string

        Return a list of 2-tuples (key=value).

        Examples:
            >>> parsed = QueryString.parse_querystring('field1=foo&field2=bar')
            >>> expected = [('field1', 'foo'), ('field2', 'bar')]
            >>> parsed == expected
            True
        """
        result = []
        # make sure the string neither begins nor ends with a &
        # the same rule applies to query parameters split by a =
        # ie filter out &field&, =field, field=, =field=value, etc
        for param in query_string.strip('&').split('&'):
            param_split = param.strip('=').split('=', 1)  # max_splits=1
            result.append(tuple([
                unquote_plus(unquote_to_bytes(x.encode('utf-8')).decode('utf-8'))  # 2/3 hack
                for x in (param_split + [''])[:2]  # make sure the param value is present
            ]))
        return result

    def url_unescape(value, encoding='utf-8', plus=True):
        """Decodes the given value from a URL.

        The argument may be either a byte or unicode string.

        If encoding is None, the result will be a byte string.  Otherwise,
        the result is a unicode string in the specified encoding.

        If ``plus`` is true (the default), plus signs will be interpreted
        as spaces (literal plus signs must be represented as "%2B").  This
        is appropriate for query strings and form-encoded values but not
        for the path component of a URL.  Note that this default is the
        reverse of Python's urllib module.

        .. versionadded:: 3.1
           The ``plus`` argument
        """
        if encoding is None:
            if plus:
                # unquote_to_bytes doesn't have a _plus variant
                value = to_basestring(value).replace('+', ' ')
            return urllib_parse.unquote_to_bytes(value)
        else:
            unquote = (urllib_parse.unquote_plus if plus
                       else urllib_parse.unquote)
            return unquote(to_basestring(value), encoding=encoding)

    def _dummy_request(self, **kwargs):
        self.assertIn('body', kwargs)
        self.assertIn('uri', kwargs)
        self.assertIn('site', kwargs)
        if kwargs['body'] is None:
            # use uri and remove script path
            parameters = kwargs['uri']
            prefix = kwargs['site'].scriptpath() + '/api.php?'
            self.assertEqual(prefix, parameters[:len(prefix)])
            parameters = parameters[len(prefix):]
        else:
            parameters = kwargs['body']
        parameters = parameters.encode('ascii')  # it should be bytes anyway
        # Extract parameter data from the body, it's ugly but allows us
        # to verify that we actually test the right request
        parameters = [p.split(b'=', 1) for p in parameters.split(b'&')]
        keys = [p[0].decode('ascii') for p in parameters]
        values = [unquote_to_bytes(p[1]) for p in parameters]
        values = [v.decode(kwargs['site'].encoding()) for v in values]
        values = [v.replace('+', ' ') for v in values]
        values = [set(v.split('|')) for v in values]
        parameters = dict(zip(keys, values))

        if 'fake' not in parameters:
            return False  # do an actual request
        if self.assert_parameters:
            for param, value in self.assert_parameters.items():
                self.assertIn(param, parameters)
                if value is not None:
                    if isinstance(value, UnicodeType):
                        value = value.split('|')
                    self.assertLessEqual(set(value), parameters[param])
        return self.data

def parse_qsl_to_bytes(query_string, keep_blank_values=False,
                       strict_parsing=False):
    """Parse a query given as a string argument.

    Arguments:

    qs: percent-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in
        percent-encoded queries should be treated as blank strings.  A
        true value indicates that blanks should be retained as blank
        strings.  The default false value indicates that blank values
        are to be ignored and treated as if they were  not included.

    strict_parsing: flag indicating what to do with parsing errors. If
        false (the default), errors are silently ignored. If true,
        errors raise a ValueError exception.

    encoding and errors: specify how to decode percent-encoded sequences
        into Unicode characters, as accepted by the bytes.decode() method.

    Returns a list, as G-d intended.
    """
    query_string, _coerce_result = _coerce_args(query_string)
    pairs = [s2 for s1 in query_string.split('&') for s2 in s1.split(';')]
    res = []
    for name_value in pairs:
        if not name_value and not strict_parsing:
            continue
        nval = name_value.split('=', 1)
        if len(nval) != 2:
            if strict_parsing:
                raise ValueError("bad query field: %r" % (name_value,))
            # Handle case of a control-name with no equal sign
            if keep_blank_values:
                nval.append('')
            else:
                continue
        if len(nval[1]) or keep_blank_values:
            name = nval[0].replace('+', ' ')
            name = unquote_to_bytes(name)
            name = _coerce_result(name)
            value = nval[1].replace('+', ' ')
            value = unquote_to_bytes(value)
            value = _coerce_result(value)
            res.append((name, value))
    return res

def visits_for_titles(wiki_title_ptrs, wiki_visits_pagecounts_file, file_index, wikicode, verbosity):
    '''
    Append page visits to the data objects. We expect several of these, so append each to an array, e.g.
    
    {'Q':Qid1, PGviews:[12,19,203]}
    
    In the more recent files, missing values indicate <5 hits in that month, so we set these to 0
    
    Having several values (one per month) allows us to trim off any that show an unusual spike
    
    NB: see https://dumps.wikimedia.org/other/pagecounts-ez/ for format.
    Pageviews totals files have a wikicode project name in ascii followed by .z for wikipedias (e.g. en.z) followed by space, 
    followed by uri-escaped title, followed by space, followed by integer. The format is a very difficult one to parse, as it varies
    e.g. there are multiple differently quoted version of the same title, sometime with spaces not underscores, unicode encoding sometimes fails, 
    the bzip file sometimes appears truncated, etc etc. I've found that the best way to do this is to unquote_to_bytes first 
    (to remove uri-encoding), then convert to unicode.
    In fact, the encoding is unclear, and sometimes utf-8 encoding seems to fail, so we pass on any utf-8 conversion errors. 
    Hopefully this should only affect a few taxa where the page title has odd accents that have not been either uri-escaped, 
    or properly encoded in utf-8.
    '''
    from urllib.parse import unquote_to_bytes
    used = 0
    match_project = (wikicode +' ').encode() 
    start_char = len(match_project)
    
    with bz2.open(wiki_visits_pagecounts_file, 'rb') as PAGECOUNTfile:
        try:
            problem_lines = [] #there are apparently some errors in the unicode dumps
            for n, line in enumerate(PAGECOUNTfile):
                if (n % 10000000 == 0) and verbosity:
                    print("Reading pagecount file of number of page views: {} entries read from file {} ({}): mem usage {} Mb".format(n, file_index, wiki_visits_pagecounts_file.name, memory_usage_resource()), file=sys.stderr)
                if line.startswith(match_project):
                    try:
                        info = line[start_char:].rstrip(b'\r\n\\rn').rsplit(b' ', 1)
                        title = unquote_to_bytes(info[0]).decode('UTF-8').replace(" ", "_") #even though most titles should not have spaces, some can sneak in via uri escaping
                        wiki_title_ptrs[title]['PGviews'][file_index] = (wiki_title_ptrs[title]['PGviews'][file_index] or 0) + int(info[1]) #sometimes there are multiple encodings of the same title, with different visit numbers
                        used += 1
                    except UnicodeDecodeError:
                        problem_lines.append(str(n))
                    except KeyError:
                        pass #title not in wiki_title_ptrs - this is expected for most entries
                    except ValueError as e:
                        if verbosity:
                            print(e, file=sys.stderr)
                            print(" Problem converting page view to an integer for {}".format(line), file=sys.stderr)
        except EOFError as e:
            #this happens sometimes, dunno why
            if verbosity:
                print(" Problem with end of file: {}. Used {} entries (should be {}: {}%. Skipping to next".format(e.args[-1],used, len(wiki_title_ptrs), used/len(wiki_title_ptrs) * 100), file=sys.stderr)
        if len(problem_lines):
            if verbosity>0:
                if verbosity<=2:
                    print(" Problem decoding {} lines, but these will be ones with strange accents etc, so should mostly not be taxa.".format(len(problem_lines)), file=sys.stderr)
                else:
                    print(" Problem decoding certain lines: the following lines have been ignored:\n{}".format("  \n".join(problem_lines)), file=sys.stderr)
    if verbosity:
        print(" NB: of {} WikiData taxon entries, {} ({:.2f}%) have pageview data for {} in '{}'. mem usage {:.1f} Mb".format(len(wiki_title_ptrs), used, used/len(wiki_title_ptrs) * 100, wikicode, wiki_visits_pagecounts_file if isinstance(wiki_visits_pagecounts_file, str) else wiki_visits_pagecounts_file.name, memory_usage_resource()), file=sys.stderr)

	def download(self, key, category, post, file, filename):
		l = self.l

		headers = { "User-Agent": "Mozilla AppleWebKit Chrome Safari" }
		headers = None
		response = requests.get(file, headers=headers)
		if response.ok:
			content = response.content

			if not filename:
				headers = response.headers
				if "Content-disposition" in headers:
					content_disposition = headers["Content-disposition"]
					matched = self.CONTENT_REGEX.match(content_disposition)
					if matched: filename = matched.group(1)

			if not filename:
				parsed = urlparse(file)
				paths = parsed.path.split('/')
				filename = paths[-1]

			if filename:
				try: filename = unquote_to_bytes(filename).decode("utf-8")
				except:
					try: filename = unquote_to_bytes(filename).decode("euc-kr")
					except:
						l.og("Error: Can't find filename.")
						filename = Tools.md5(file)
						l.og("\tSave to: {}".format(filename))

				data = self.dm.find(post, filename)
				if not data:
					l.og("[Download] {}".format(filename))

					wo = open(os.sep.join((self.savedir, filename)), "wb")
					wo.write(content)
					wo.close()

					self.dm.add(key, category, post, file, filename)

					return True
		else:
			l.og("Error: requests.get()")
			l.og("\t{}".format(file))

 def _get_path(self, parsed):
     path = parsed.path
     # If there are parameters, add them
     if parsed.params:
         path += ";" + parsed.params
     path = unquote_to_bytes(path)
     # Replace the behavior where non-ASCII values in the WSGI environ are
     # arbitrarily decoded with ISO-8859-1.
     # Refs comment in `get_bytes_from_wsgi()`.
     return path.decode('iso-8859-1')

def createQrcode(url):
    data = {"device_num":"1", "device_id_list":["koovox_02"]}
    data = json.dumps(data, ensure_ascii=False)
    request = req.Request(url, method = 'POST')
    request.add_header('Content-Type', 'application/json')
    request.add_header('encoding', 'utf-8')
    response = req.urlopen(request, parse.unquote_to_bytes(data))
    result = response.read()
    print(result)
    return result

def unescapeRepeatedly(input):
    '''Argument may be str or bytes. Returns bytes.'''
    if None == input:
        return None

    while True:
        un = unquote_to_bytes(input)
        if un == input:
            return input
        input = un

def createMenu(token, menu):
    url = 'https://api.weixin.qq.com/cgi-bin/menu/create?access_token=%s' %token
    data = menu
    data = json.dumps(data,ensure_ascii=False)
    request = req.Request(url, method='POST')
    request.add_header('Content-Type', 'application/json')
    request.add_header('encoding', 'utf-8')
	
    response = req.urlopen(request, parse.unquote_to_bytes(data))
    result = response.read()
    print(result)
    return result