Python urllib.parse.urlunparse() Examples

def get_version_files(cls, version):
        parsed_version_path = urlparse(version)
        content_list = cls.gs_list_content(version)
        xml_pattern = re.compile(
            parsed_version_path.path[1:-1] + r'/[^/]+\.xml$')
        bin_pattern = re.compile(
            parsed_version_path.path[1:-1] + r'/[^/]+\.bin$')
        xml_file = list(filter(xml_pattern.match, content_list))
        bin_file = list(filter(bin_pattern.match, content_list))
        if len(xml_file) != 0 and len(bin_file) != 0:
            if os.path.splitext(xml_file[0])[0] == \
                    os.path.splitext(bin_file[0])[0]:
                xml_file[0] = urlunparse(
                    (parsed_version_path.scheme, parsed_version_path.netloc,
                     xml_file[0], parsed_version_path.params,
                     parsed_version_path.query, parsed_version_path.fragment))
                bin_file[0] = urlunparse(
                    (parsed_version_path.scheme, parsed_version_path.netloc,
                     bin_file[0], parsed_version_path.params,
                     parsed_version_path.query, parsed_version_path.fragment))
                mapping_config = cls._get_mapping_config(version)
                return xml_file[0], bin_file[0], mapping_config
        return None, None, None 

def validate_link(self, link, bookmark=False):
        """Checks if the given link can get correct data."""
        # removes the scheme and net location parts of the link
        url_parts = list(urlparse.urlparse(link))
        url_parts[0] = url_parts[1] = ''

        # bookmark link should not have the version in the URL
        if bookmark and url_parts[2].startswith(PATH_PREFIX):
            return False

        full_path = urlparse.urlunparse(url_parts)
        try:
            self.get_json(full_path, path_prefix='')
            return True
        except Exception:
            return False 

def do_GET(self):
        (scm, netloc, path, params, query, fragment) = urlparse(self.path, "http")
        if scm != "http" or fragment or not netloc:
            self.send_error(400, "bad url %s" % self.path)
            return
        soc = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(netloc, soc):
                self.log_request()
                soc.send(
                    "%s %s %s\r\n" % (self.command, urlunparse(("", "", path, params, query, "")), self.request_version)
                )
                self.headers["Connection"] = "close"
                del self.headers["Proxy-Connection"]
                for key_val in self.headers.items():
                    soc.send("%s: %s\r\n" % key_val)
                soc.send("\r\n")
                self._read_write(soc)
        finally:
            logging.warning("Finished do_GET()")
            soc.close()
            self.connection.close() 

def urlparams(url, fragment=None, **kwargs):
    """
    Add a fragment and/or query parameters to a URL.

    Existing query string parameters are preserved, unless they conflict
    with the new parameters, in which case they're overridden.
    """
    parsed = urlparse(url)
    query = dict(parse_qs(parsed.query), **kwargs)
    return urlunparse(
        (
            parsed.scheme,
            parsed.netloc,
            parsed.path,
            parsed.params,
            urlencode(query, doseq=True),
            fragment if fragment is not None else parsed.fragment,
        )
    ) 

def make_next_param(login_url, current_url):
    '''
    Reduces the scheme and host from a given URL so it can be passed to
    the given `login` URL more efficiently.

    :param login_url: The login URL being redirected to.
    :type login_url: str
    :param current_url: The URL to reduce.
    :type current_url: str
    '''
    l = urlparse(login_url)
    c = urlparse(current_url)

    if (not l.scheme or l.scheme == c.scheme) and \
            (not l.netloc or l.netloc == c.netloc):
        return urlunparse(('', '', c.path, c.params, c.query, ''))
    return current_url 

def get_local_uri(self, uri):
        """
        Convert a remote uri to a local one.

        This method takes a remote service uri accessible to the remote host and
        returns a local uri accessible directly on the local host, establishing
        any necessary port forwarding in the process.

        Args:
            uri (str): The remote uri to be made local.

        Returns:
            str: A local uri that tunnels all traffic to the remote host.
        """
        parsed_uri = urlparse(uri)
        return urlunparse(parsed_uri._replace(netloc='localhost:{}'.format(self.port_forward(parsed_uri.netloc)))) 

def get_redirect_url(request):
    """Redirects to referring page, or CAS_REDIRECT_URL if no referrer is
    set.
    """

    next_ = request.GET.get(REDIRECT_FIELD_NAME)
    if not next_:
        redirect_url = resolve_url(django_settings.CAS_REDIRECT_URL)
        if django_settings.CAS_IGNORE_REFERER:
            next_ = redirect_url
        else:
            next_ = request.META.get('HTTP_REFERER', redirect_url)
        prefix = urllib_parse.urlunparse(
            (get_protocol(request), request.get_host(), '', '', '', ''),
        )
        if next_.startswith(prefix):
            next_ = next_[len(prefix):]
    return next_ 

def get_service_url(request, redirect_to=None):
    """Generates application django service URL for CAS"""
    if hasattr(django_settings, 'CAS_ROOT_PROXIED_AS'):
        service = django_settings.CAS_ROOT_PROXIED_AS + request.path
    else:
        if django_settings.CAS_FORCE_SSL_SERVICE_URL:
            protocol = 'https'
        else:
            protocol = get_protocol(request)
        host = request.get_host()
        service = urllib_parse.urlunparse(
            (protocol, host, request.path, '', '', ''),
        )
    if not django_settings.CAS_STORE_NEXT:
        if '?' in service:
            service += '&'
        else:
            service += '?'
        service += urllib_parse.urlencode({
            REDIRECT_FIELD_NAME: redirect_to or get_redirect_url(request)
        })
    return service 

def _scripts(self):
        url_parts = urlparse(self._base or self._url)
        scheme = url_parts.scheme

        for tag in self.soup.find_all("script", src=True):
            parts = urlparse(tag["src"])

            if parts.scheme:
                if parts.netloc:
                    # Full absolute URL
                    script_url = urlunparse((parts.scheme, parts.netloc, parts.path, parts.params, parts.query, ''))
                else:
                    # Malformed absolute URL (no host)
                    continue
            elif parts.netloc:
                # Protocol relative URL
                script_url = urlunparse((scheme, parts.netloc, parts.path, parts.params, parts.query, ''))
            else:
                # Internal relative URL
                script_url = urlunparse(('', '', parts.path, parts.params, parts.query, ''))
            yield script_url 

def _BuildUrl(self, url, path_elements=None, extra_params=None):
        # Break url into constituent parts
        (scheme, netloc, path, params, query, fragment) = urlparse(url)

        # Add any additional path elements to the path
        if path_elements:
            # Filter out the path elements that have a value of None
            p = [i for i in path_elements if i]
            if not path.endswith('/'):
                path += '/'
            path += '/'.join(p)

        # Add any additional query parameters to the query string
        if extra_params and len(extra_params) > 0:
            extra_query = self._EncodeParameters(extra_params)
            # Add it to the existing query
            if query:
                query += '&' + extra_query
            else:
                query = extra_query

        # Return the rebuilt URL
        return urlunparse((scheme, netloc, path, params, query, fragment)) 

def redirect_to_sudo(next_url, sudo_url=None):
    """
    Redirects the user to the login page, passing the given 'next' page
    """
    if sudo_url is None:
        sudo_url = URL

    try:
        # django 1.10 and greater can't resolve the string 'sudo.views.sudo' to a URL
        # https://docs.djangoproject.com/en/1.10/releases/1.10/#removed-features-1-10
        sudo_url = import_string(sudo_url)
    except (ImportError, ImproperlyConfigured):
        pass  # wasn't a dotted path

    sudo_url_parts = list(urlparse(resolve_url(sudo_url)))

    querystring = QueryDict(sudo_url_parts[4], mutable=True)
    querystring[REDIRECT_FIELD_NAME] = next_url
    sudo_url_parts[4] = querystring.urlencode(safe="/")

    return HttpResponseRedirect(urlunparse(sudo_url_parts)) 

def add_params(url, extra=None, remove=None):
    """Given a URL, add new query parameters by merging in the contents of the
    `extra` dictionary.

    :param url: (str)
    :param extra: (dict)
    :param remove: (list or set)

    :returns: (str) URL including new parameters
    """
    if not (extra or remove):
        return url

    parsed = parse.urlparse(url)._asdict()
    params = parse.parse_qsl(parsed["query"])

    if extra:
        params += list(extra.items())
    if remove:
        params = [pair for pair in params if pair[0] not in remove]

    parsed["query"] = parse.urlencode(params, doseq=True)

    return parse.urlunparse(parse.ParseResult(**parsed)) 

def get_events_list():
        page_index_url = Events.host + 'index.php'
        url_parts = list(urlparse.urlparse(page_index_url))
        events_links, events_dates = [], []
        paging_index = 1
        events_count = 10

        while events_count == 10:
            params = {
                'p': paging_index
            }
            url_parts[4] = urlencode(params)
            paging_index += 1
            html = Scraper.get(urlparse.urlunparse(url_parts))
            soup = BeautifulSoup(html, 'html.parser')
            events_dom_arr = soup.select('#results')[0].find_all('li')
            events_count = len(events_dom_arr)
            events_links += list(map(lambda e: e.a['href'], events_dom_arr))
            events_dates += list(map(lambda e: e.find('p').text.split(' : ')[1].split(', ')[0], events_dom_arr))

        return zip(events_links, events_dates) 

def redirect_to_login(next, login_url=None, redirect_field_name=REDIRECT_FIELD_NAME):
    """
    Redirect the user to the login page, passing the given 'next' page.
    """
    resolved_url = resolve_url(login_url or settings.LOGIN_URL)

    login_url_parts = list(urlparse(resolved_url))
    if redirect_field_name:
        querystring = QueryDict(login_url_parts[4], mutable=True)
        querystring[redirect_field_name] = next
        login_url_parts[4] = querystring.urlencode(safe='/')

    return HttpResponseRedirect(urlunparse(login_url_parts))


# 4 views for password reset:
# - password_reset sends the mail
# - password_reset_done shows a success message for the above
# - password_reset_confirm checks the link the user clicked and
#   prompts for a new password
# - password_reset_complete shows a success message for the above 

def get_logo_url(base_url, logo_file):
    base_url = parse.urlparse(base_url)
    netloc = base_url.netloc

    if base_url.netloc.startswith('localhost'):
        netloc = 'notify.tools'
    elif base_url.netloc.startswith('www'):
        # strip "www."
        netloc = base_url.netloc[4:]

    logo_url = parse.ParseResult(
        scheme=base_url.scheme,
        netloc='static-logos.' + netloc,
        path=logo_file,
        params=base_url.params,
        query=base_url.query,
        fragment=base_url.fragment
    )
    return parse.urlunparse(logo_url) 

def get_version_files(cls, version):
        parsed_version_path = urlparse(version)
        content_list = cls.s3_list_content(version)
        xml_pattern = re.compile(
            parsed_version_path.path[1:-1] + r'/[^/]+\.xml$')
        bin_pattern = re.compile(
            parsed_version_path.path[1:-1] + r'/[^/]+\.bin$')
        xml_file = list(filter(xml_pattern.match, content_list))
        bin_file = list(filter(bin_pattern.match, content_list))
        if len(xml_file) != 0 and len(bin_file) != 0:
            if os.path.splitext(xml_file[0])[0] == \
                    os.path.splitext(bin_file[0])[0]:
                xml_file[0] = urlunparse(
                    (parsed_version_path.scheme, parsed_version_path.netloc,
                     xml_file[0], parsed_version_path.params,
                     parsed_version_path.query, parsed_version_path.fragment))
                bin_file[0] = urlunparse(
                    (parsed_version_path.scheme, parsed_version_path.netloc,
                     bin_file[0], parsed_version_path.params,
                     parsed_version_path.query, parsed_version_path.fragment))
                mapping_config = cls._get_mapping_config(version)
                return xml_file[0], bin_file[0], mapping_config
        return None, None, None 

def set_proxy(self, proxy=""):
        """Set a proxy to use for HTTP requests."""
        url_parts = urlparse(proxy)
        protocol = url_parts.scheme.lower()

        if protocol in ("http", "https", "socks"):
            if protocol == "socks":
                # socks5h proxy type won't leak DNS requests
                proxy = urlunparse(("socks5h", url_parts.netloc, '/', '', '', ''))
            else:
                proxy = urlunparse((url_parts.scheme, url_parts.netloc, '/', '', '', ''))

            # attach the proxy for http and https URLs
            self._session.proxies["http"] = proxy
            self._session.proxies["https"] = proxy
        else:
            raise ValueError("Unknown proxy type '{}'".format(protocol)) 

def urlunparse(parts):
        result = _urlunparse(tuple([p.decode("charmap") for p in parts]))
        return result.encode("charmap") 

def to_url(self, api_path=None):
        path = api_path or ''
        if self.port:
            result_url = urlunparse((self.scheme, self.hostname + ":" + str(self.port), path, None, None, None))
        else:
            result_url = urlunparse((self.scheme, self.hostname, path, None, None, None))

        return result_url 

def unparse(self, urparse):
		return urlparse.urlunparse(urparse) 

def _remove_md5_fragment(location):
    if not location:
        return ''
    parsed = urlparse(location)
    if parsed[-1].startswith('md5='):
        return urlunparse(parsed[:-1] + ('',))
    return location 

def nice_join(self, url):
        url1 = urljoin(self.request.url, url)
        arr = urlparse(url1)
        path = normpath(arr[2])
        return urlunparse((arr.scheme, arr.netloc, path, arr.params, arr.query, arr.fragment)) 

def nice_join(self, url):
        url1 = urljoin(self.request.url, url)
        arr = urlparse(url1)
        path = normpath(arr[2])
        return urlunparse((arr.scheme, arr.netloc, path, arr.params, arr.query, arr.fragment)) 

def _remove_md5_fragment(location):
    if not location:
        return ''
    parsed = urlparse(location)
    if parsed[-1].startswith('md5='):
        return urlunparse(parsed[:-1] + ('',))
    return location 

def vpn_url(self):
        parts = urlparse(self.address)
        group = self.user_group or parts.path
        if parts.path == self.address and not self.user_group:
            group = ""
        return urlunparse(
            (parts.scheme or "https", parts.netloc or self.address, group, "", "", "")
        ) 

def url_concat(url, args):
    """Concatenate url and arguments regardless of whether
    url has existing query parameters.

    ``args`` may be either a dictionary or a list of key-value pairs
    (the latter allows for multiple values with the same key.

    >>> url_concat("http://example.com/foo", dict(c="d"))
    'http://example.com/foo?c=d'
    >>> url_concat("http://example.com/foo?a=b", dict(c="d"))
    'http://example.com/foo?a=b&c=d'
    >>> url_concat("http://example.com/foo?a=b", [("c", "d"), ("c", "d2")])
    'http://example.com/foo?a=b&c=d&c=d2'
    """
    if args is None:
        return url
    parsed_url = urlparse(url)
    if isinstance(args, dict):
        parsed_query = parse_qsl(parsed_url.query, keep_blank_values=True)
        parsed_query.extend(args.items())
    elif isinstance(args, list) or isinstance(args, tuple):
        parsed_query = parse_qsl(parsed_url.query, keep_blank_values=True)
        parsed_query.extend(args)
    else:
        err = "'args' parameter should be dict, list or tuple. Not {0}".format(
            type(args))
        raise TypeError(err)
    final_query = urlencode(parsed_query)
    url = urlunparse((
        parsed_url[0],
        parsed_url[1],
        parsed_url[2],
        parsed_url[3],
        final_query,
        parsed_url[5]))
    return url 

def process_redirect_url(redirect_url, new_entries):
  # Prepare the redirect URL
  url_parts = list(urlparse.urlparse(redirect_url))
  queries = dict(urlparse.parse_qsl(url_parts[4]))
  queries.update(new_entries)
  url_parts[4] = urlencode(queries)
  url = urlparse.urlunparse(url_parts)
  return url 

def filter_request_uri(request):
    request.uri = urlunparse(urlparse(request.uri)._replace(netloc="foreman.example.org"))
    return request 

def url(self):
        return urlunparse(
            (self.scheme, self.host, self.path, None, self.query_string, None)
        ) 

def _absolute_file_location(tus_endpoint, file_endpoint):
    parsed_file_endpoint = urlparse(file_endpoint)
    if parsed_file_endpoint.netloc:
        return file_endpoint

    parsed_tus_endpoint = urlparse(tus_endpoint)
    return urlunparse((
        parsed_tus_endpoint.scheme,
        parsed_tus_endpoint.netloc,
    ) + parsed_file_endpoint[2:])