Python parse.urlunparse函数代码示例

    def _secure_request(self, url, method, data=None, files=None, headers=None,
                        raw=False, send_as_json=True, content_type=None,
                        **request_kwargs):

        full_url = self.build_url(url)

        # Add token (if it's not already there)
        if self._token:
            parsed = list(urlparse(full_url))
            if not parsed[4]:  # query
                parsed[4] = 'token=%s' % self._token
                full_url = urlunparse(parsed)
            elif 'token' not in parse_qs(parsed[4]):
                parsed[4] += '&token=%s' % self._token
                full_url = urlunparse(parsed)
        headers = headers or {}

        # If files are being sent, we cannot encode data as JSON
        if send_as_json and not files:
            headers['content-type'] = 'application/json'
            data = json.dumps(data or {})
        else:
            if content_type:
                headers['content-type'] = content_type
            data = data or ''

        method = getattr(requests, method, None)
        response = method(full_url, data=data, files=files, headers=headers,
                          **request_kwargs)
        self.check_for_errors(response)  # Raise exception if something failed

        if raw or not response.content:
            return response.content
        return json.loads(response.text)

def get_canonical_and_alternates_urls(url, drop_ln=True, washed_argd=None, quote_path=False):
    """
    Given an Invenio URL returns a tuple with two elements. The first is the
    canonical URL, that is the original URL with CFG_SITE_URL prefix, and
    where the ln= argument stripped. The second element element is mapping,
    language code -> alternate URL

    @param quote_path: if True, the path section of the given C{url}
                       is quoted according to RFC 2396
    """
    dummy_scheme, dummy_netloc, path, dummy_params, query, fragment = urlparse(url)
    canonical_scheme, canonical_netloc = urlparse(cfg.get("CFG_SITE_URL"))[0:2]
    parsed_query = washed_argd or parse_qsl(query)
    no_ln_parsed_query = [(key, value) for (key, value) in parsed_query if key != "ln"]
    if drop_ln:
        canonical_parsed_query = no_ln_parsed_query
    else:
        canonical_parsed_query = parsed_query
    if quote_path:
        path = urllib.quote(path)
    canonical_query = urlencode(canonical_parsed_query)
    canonical_url = urlunparse((canonical_scheme, canonical_netloc, path, dummy_params, canonical_query, fragment))
    alternate_urls = {}
    for ln in cfg.get("CFG_SITE_LANGS"):
        alternate_query = urlencode(no_ln_parsed_query + [("ln", ln)])
        alternate_url = urlunparse((canonical_scheme, canonical_netloc, path, dummy_params, alternate_query, fragment))
        alternate_urls[ln] = alternate_url
    return canonical_url, alternate_urls

def get_commit_url(commit, pkg):
    try:
        upstream_url = parse.urlsplit(pkg["upstream"])

        if upstream_url.netloc == "git.openstack.org":
            commit_url = ("http",
                          upstream_url.netloc,
                          "/cgit%s/commit/?id=" % upstream_url.path,
                          "", "", "")
            commit_url = parse.urlunparse(commit_url)
        elif upstream_url.netloc == "github.com":
            commit_url = ("https",
                          upstream_url.netloc,
                          "%s/commit/" % upstream_url.path,
                          "", "", "")
            commit_url = parse.urlunparse(commit_url)
        else:
            # Fallback when no cgit URL can be defined
            commit_url = pkg["upstream"]
    except KeyError:
        # This should not happen, but pkg['upstream'] may not be present
        # after some error in the gitrepo driver
        commit_url = ''

    return commit_url

    def base_url(self, filters, auth_data=None):
        """Base URL from catalog

        Filters can be:
        - service: compute, image, etc
        - region: the service region
        - endpoint_type: adminURL, publicURL, internalURL
        - api_version: replace catalog version with this
        - skip_path: take just the base URL
        """
        if auth_data is None:
            auth_data = self.auth_data
        token, _auth_data = auth_data
        service = filters.get('service')
        region = filters.get('region')
        endpoint_type = filters.get('endpoint_type', 'publicURL')

        if service is None:
            raise exceptions.EndpointNotFound("No service provided")

        _base_url = None
        for ep in _auth_data['serviceCatalog']:
            if ep["type"] == service:
                for _ep in ep['endpoints']:
                    if region is not None and _ep['region'] == region:
                        _base_url = _ep.get(endpoint_type)
                if not _base_url:
                    # No region matching, use the first
                    _base_url = ep['endpoints'][0].get(endpoint_type)
                break
        if _base_url is None:
            raise exceptions.EndpointNotFound(
                "service: %s, region: %s, endpoint_type: %s" %
                (service, region, endpoint_type))

        parts = urlparse.urlparse(_base_url)
        if filters.get('api_version', None) is not None:
            version_path = '/%s' % filters['api_version']
            path = re.sub(r'(^|/)+v\d+(?:\.\d+)?',
                          version_path,
                          parts.path,
                          count=1)
            _base_url = urlparse.urlunparse((parts.scheme,
                                             parts.netloc,
                                             path or version_path,
                                             parts.params,
                                             parts.query,
                                             parts.fragment))
        if filters.get('skip_path', None) is not None and parts.path != '':
            _base_url = urlparse.urlunparse((parts.scheme,
                                             parts.netloc,
                                             '/',
                                             parts.params,
                                             parts.query,
                                             parts.fragment))

        return _base_url

 def output(self, key, obj):
     try:
         data = to_marshallable_type(obj)
         endpoint = self.endpoint if self.endpoint is not None else request.endpoint
         o = urlparse(url_for(endpoint, _external=self.absolute, **data))
         if self.absolute:
             scheme = self.scheme if self.scheme is not None else o.scheme
             return urlunparse((scheme, o.netloc, o.path, "", "", ""))
         return urlunparse(("", "", o.path, "", "", ""))
     except TypeError as te:
         raise MarshallingError(te)

def clean_ows_url(url):
    """
    clean an OWS URL of basic service elements

    source: https://stackoverflow.com/a/11640565
    """

    if url is None or not url.startswith('http'):
        return url

    filtered_kvp = {}
    basic_service_elements = ('service', 'version', 'request')

    parsed = urlparse(url)
    qd = parse_qs(parsed.query, keep_blank_values=True)

    for key, value in qd.items():
        if key.lower() not in basic_service_elements:
            filtered_kvp[key] = value

    newurl = urlunparse([
        parsed.scheme,
        parsed.netloc,
        parsed.path,
        parsed.params,
        urlencode(filtered_kvp, doseq=True),
        parsed.fragment
    ])

    return newurl

    def methodNext(self, previous_request, previous_response):
        """Retrieves the next page of results.

Args:
  previous_request: The request for the previous page. (required)
  previous_response: The response from the request for the previous page. (required)

Returns:
  A request object that you can call 'execute()' on to request the next
  page. Returns None if there are no more items in the collection.
    """
        # Retrieve nextPageToken from previous_response
        # Use as pageToken in previous_request to create new request.

        if "nextPageToken" not in previous_response or not previous_response["nextPageToken"]:
            return None

        request = copy.copy(previous_request)

        pageToken = previous_response["nextPageToken"]
        parsed = list(urlparse(request.uri))
        q = parse_qsl(parsed[4])

        # Find and remove old 'pageToken' value from URI
        newq = [(key, value) for (key, value) in q if key != "pageToken"]
        newq.append(("pageToken", pageToken))
        parsed[4] = urlencode(newq)
        uri = urlunparse(parsed)

        request.uri = uri

        logger.info("URL being requested: {0!s} {1!s}".format(methodName, uri))

        return request

def update_content( article, content, siteurl ):
    self = article
    
    stripped_content = content.strip()
    if not stripped_content.startswith( PREFIX ):
        return content
    
    # remove {filename}
    url = stripped_content[ len( PREFIX ): ]
    
    parse_result = urlparse( url )
    path = parse_result.path
    
    if path.startswith( '/' ):
        path = path[ 1: ]
    else:
        # relative link
        path = self.get_relative_source_path( os.path.join( self.relative_dir, path ) )
    
    # unescape spaces if necessary
    if path not in self._context[ 'filenames' ]:
        path = path.replace( '%20', ' ' )

        if path not in self._context[ 'filenames' ]:
            logger.warning(
                "Unable to find `%s`, skipping url replacement.", url,
                extra = { 'limit_msg': ( "Other resources were not found and their urls not replaced" ) }
            )
            return content
    
    linked_content = self._context[ 'filenames' ][ path ]
    parts = list( parse_result )
    parts[ 2 ] = '/'.join( [ siteurl, linked_content.url ] )
    return urlunparse( parts )

def strip_url(url, strip_credentials=True, strip_default_port=True, origin_only=False, strip_fragment=True):

    """Strip URL string from some of its components:

    - ``strip_credentials`` removes "user:[email protected]"
    - ``strip_default_port`` removes ":80" (resp. ":443", ":21")
      from http:// (resp. https://, ftp://) URLs
    - ``origin_only`` replaces path component with "/", also dropping
      query and fragment components ; it also strips credentials
    - ``strip_fragment`` drops any #fragment component
    """

    parsed_url = urlparse(url)
    netloc = parsed_url.netloc
    if (strip_credentials or origin_only) and (parsed_url.username or parsed_url.password):
        netloc = netloc.split('@')[-1]
    if strip_default_port and parsed_url.port:
        if (parsed_url.scheme, parsed_url.port) in (('http', 80),
                                                    ('https', 443),
                                                    ('ftp', 21)):
            netloc = netloc.replace(':{p.port}'.format(p=parsed_url), '')
    return urlunparse((
        parsed_url.scheme,
        netloc,
        '/' if origin_only else parsed_url.path,
        '' if origin_only else parsed_url.params,
        '' if origin_only else parsed_url.query,
        '' if strip_fragment else parsed_url.fragment
    ))

def url_add_parameters(url, params):
    """Adds parameters to URL, parameter will be repeated if already present"""
    if params:
        fragments = list(urlparse(url))
        fragments[4] = urlencode(parse_qsl(fragments[4]) + params.items())
        url = urlunparse(fragments)
    return url

    def _parse_contents(self, response):
        # Wix pages aren't really parseable, so anytime we see them,
        # let's re-run it (depth-1) with an escaped-fragment to get the real html source
        if 'https://static.wixstatic.com/' in response.body and '_escaped_fragment_' not in response.url:
            parsed_url = urlparse(response.url)
            qs = parse_qs(parsed_url.query)
            qs['_escaped_fragment_'] = ''
            wix_scrapeable_url = urlunparse(
                (parsed_url.scheme, parsed_url.netloc, parsed_url.path, parsed_url.params, urlencode(qs), parsed_url.fragment)
            )
            response.meta['depth'] -= 1
            return [scrapy.Request(wix_scrapeable_url, self.parse)]

        return
        if not hasattr(response, 'selector'):
            logging.info('Skipping unknown file from: %s', response.url)
            return
        # Get all text contents of tags (unless they are script or style tags)
        text_contents = ' '.join(response.selector.xpath('//*[not(self::script|self::style)]/text()').extract()).lower()

        processed_text = grammar_matcher.StringProcessor(text_contents, regex_keywords.WORD_BOUNDARIES)
        wrong = processed_text.get_tokens(all_styles.DANCE_WRONG_STYLE)
        good = processed_text.get_tokens(rules.STREET_STYLE)
        if (wrong or good):
            #print response.url, set(wrong), set(good)
            pass

def canonicalize_url(url, keep_blank_values=True, keep_fragments=False,
                     encoding=None):
    """Canonicalize the given url by applying the following procedures:

    - sort query arguments, first by key, then by value
    - percent encode paths and query arguments. non-ASCII characters are
      percent-encoded using UTF-8 (RFC-3986)
    - normalize all spaces (in query arguments) '+' (plus symbol)
    - normalize percent encodings case (%2f -> %2F)
    - remove query arguments with blank values (unless keep_blank_values is True)
    - remove fragments (unless keep_fragments is True)

    The url passed can be a str or unicode, while the url returned is always a
    str.

    For examples see the tests in tests/test_utils_url.py
    """

    scheme, netloc, path, params, query, fragment = parse_url(url)
    keyvals = parse_qsl(query, keep_blank_values)
    keyvals.sort()
    query = urlencode(keyvals)

    # XXX: copied from w3lib.url.safe_url_string to add encoding argument
    # path = to_native_str(path, encoding)
    # path = moves.urllib.parse.quote(path, _safe_chars, encoding='latin1') or '/'

    path = safe_url_string(_unquotepath(path)) or '/'
    fragment = '' if not keep_fragments else fragment
    return urlunparse((scheme, netloc.lower(), path, params, query, fragment))

    def get(self, request, *args, **kwargs):
        validate_session_for_mturk(request, self.session)
        mturk_settings = self.session.config['mturk_hit_settings']
        initial = {
            'title': mturk_settings['title'],
            'description': mturk_settings['description'],
            'keywords': ', '.join(mturk_settings['keywords']),
            'money_reward': self.session.config['participation_fee'],
            'in_sandbox': settings.DEBUG,
            'minutes_allotted_per_assignment': (
                mturk_settings['minutes_allotted_per_assignment']
            ),
            'expiration_hours': mturk_settings['expiration_hours'],
            'assignments': self.session.mturk_num_participants,
        }
        form = self.get_form(initial=initial)
        context = self.get_context_data(form=form)
        context['mturk_enabled'] = (
            bool(settings.AWS_ACCESS_KEY_ID) and
            bool(settings.AWS_SECRET_ACCESS_KEY)
        )
        context['runserver'] = 'runserver' in sys.argv
        url = self.request.build_absolute_uri(
            reverse('MTurkCreateHIT', args=(self.session.code,))
        )
        secured_url = urlunparse(urlparse(url)._replace(scheme='https'))
        context['secured_url'] = secured_url

        return self.render_to_response(context)

    def __init__(self, info_yaml, basedir=''):
        """Import the solution's info.yaml file."""
        f, url_parts = self._open(info_yaml, basedir)
        solution_yaml = f.read().decode('utf-8')
        self.basedir = urlunparse((url_parts.scheme, url_parts.netloc,
                                   os.path.dirname(url_parts.path),
                                   None, None, None))

        # create a markdown converter and modify it to rebase image links
        markdown = Markdown()
        markdown.inlinePatterns['image_link'] = _RebasedImageLinkPattern(
            self.basedir, IMAGE_LINK_RE, markdown)
        markdown.inlinePatterns['image_reference'] = _RebasedImageRefPattern(
            self.basedir, IMAGE_REFERENCE_RE, markdown)

        # import the solution's metadata
        info = yaml.load(solution_yaml)
        self.id = hashlib.md5(solution_yaml.encode('utf-8')).hexdigest()
        self.title = info['name']
        self.release = str(info['release'])
        if 'logo' in info:
            self.logo = self._make_absolute_path(info.get('logo'),
                                                 self.basedir)[0]
        # in all the following fields, newlines are suppressed because they
        # are not rendered properly in Javascript strings by Django
        self.short_description = \
            markdown.convert(info['short_desc']).replace('\n', '')
        self.long_description = \
            markdown.convert(info['long_desc']).replace('\n', '')
        self.architecture = \
            markdown.convert(info['architecture']).replace('\n', '')
        self.design_specs = info.get('design_specs', [])
        self.heat_template = info['heat_template']
        self.env_file = info.get('env_file')  # environments are optional

def build_url(base, additional_params=None):
    """Construct a URL based off of base containing all parameters in
    the query portion of base plus any additional parameters.

    :param base: Base URL
    :type base: str
    ::param additional_params: Additional query parameters to include.
    :type additional_params: dict
    :rtype: str
    """
    url = urlparse(base)
    query_params = {}
    query_params.update(parse_qsl(url.query, True))
    if additional_params is not None:
        query_params.update(additional_params)
        for k, v in six.iteritems(additional_params):
            if v is None:
                query_params.pop(k)

    return urlunparse((url.scheme,
                                url.netloc,
                                url.path,
                                url.params,
                                urlencode(query_params),
                                url.fragment))