django/docs/ref/contrib/syndication.txt

==============================
The syndication feed framework
==============================

.. module:: django.contrib.syndication
   :synopsis: A framework for generating syndication feeds, in RSS and Atom,
              quite easily.

Django comes with a high-level syndication-feed-generating framework for
creating RSS_ and :rfc:`Atom <4287>` feeds.

To create any syndication feed, all you have to do is write a short
Python class. You can create as many feeds as you want.

Django also comes with a lower-level feed-generating API. Use this if
you want to generate feeds outside of a Web context, or in some other
lower-level way.

.. _RSS: http://www.whatisrss.com/

The high-level framework
========================

Overview
--------

The high-level feed-generating framework is supplied by the
:class:`~django.contrib.syndication.views.Feed` class. To create a
feed, write a :class:`~django.contrib.syndication.views.Feed` class
and point to an instance of it in your :doc:`URLconf
</topics/http/urls>`.

``Feed`` classes
----------------

A :class:`~django.contrib.syndication.views.Feed` class is a Python
class that represents a syndication feed. A feed can be simple (e.g.,
a "site news" feed, or a basic feed displaying the latest entries of a
blog) or more complex (e.g., a feed displaying all the blog entries in
a particular category, where the category is variable).

Feed classes subclass :class:`django.contrib.syndication.views.Feed`.
They can live anywhere in your codebase.

Instances of :class:`~django.contrib.syndication.views.Feed` classes
are views which can be used in your :doc:`URLconf </topics/http/urls>`.

A simple example
----------------

This simple example, taken from a hypothetical police beat news site describes
a feed of the latest five news items::

    from django.contrib.syndication.views import Feed
    from django.urls import reverse
    from policebeat.models import NewsItem

    class LatestEntriesFeed(Feed):
        title = "Police beat site news"
        link = "/sitenews/"
        description = "Updates on changes and additions to police beat central."

        def items(self):
            return NewsItem.objects.order_by('-pub_date')[:5]

        def item_title(self, item):
            return item.title

        def item_description(self, item):
            return item.description

        # item_link is only needed if NewsItem has no get_absolute_url method.
        def item_link(self, item):
            return reverse('news-item', args=[item.pk])

To connect a URL to this feed, put an instance of the Feed object in
your :doc:`URLconf </topics/http/urls>`. For example::

    from django.urls import path
    from myproject.feeds import LatestEntriesFeed

    urlpatterns = [
        # ...
        path('latest/feed/', LatestEntriesFeed()),
        # ...
    ]

Note:

* The Feed class subclasses :class:`django.contrib.syndication.views.Feed`.

* ``title``, ``link`` and ``description`` correspond to the
  standard RSS ``<title>``, ``<link>`` and ``<description>`` elements,
  respectively.

* ``items()`` is, a method that returns a list of objects that should be
  included in the feed as ``<item>`` elements. Although this example returns
  ``NewsItem`` objects using Django's :doc:`object-relational mapper
  </ref/models/querysets>`, ``items()`` doesn't have to return model instances.
  Although you get a few bits of functionality "for free" by using Django
  models, ``items()`` can return any type of object you want.

* If you're creating an Atom feed, rather than an RSS feed, set the
  ``subtitle`` attribute instead of the ``description`` attribute.
  See `Publishing Atom and RSS feeds in tandem`_, later, for an example.

One thing is left to do. In an RSS feed, each ``<item>`` has a ``<title>``,
``<link>`` and ``<description>``. We need to tell the framework what data to put
into those elements.

* For the contents of ``<title>`` and ``<description>``, Django tries
  calling the methods ``item_title()`` and ``item_description()`` on
  the :class:`~django.contrib.syndication.views.Feed` class. They are passed
  a single parameter, ``item``, which is the object itself. These are
  optional; by default, the string representation of the object is used for
  both.

  If you want to do any special formatting for either the title or
  description, :doc:`Django templates </ref/templates/language>` can be used
  instead. Their paths can be specified with the ``title_template`` and
  ``description_template`` attributes on the
  :class:`~django.contrib.syndication.views.Feed` class. The templates are
  rendered for each item and are passed two template context variables:

  * ``{{ obj }}`` -- The current object (one of whichever objects you
    returned in ``items()``).

  * ``{{ site }}`` -- A :class:`django.contrib.sites.models.Site` object
    representing the current site. This is useful for ``{{ site.domain
    }}`` or ``{{ site.name }}``. If you do *not* have the Django sites
    framework installed, this will be set to a
    :class:`~django.contrib.sites.requests.RequestSite` object. See the
    :ref:`RequestSite section of the sites framework documentation
    <requestsite-objects>` for more.

  See `a complex example`_ below that uses a description template.

  .. method:: Feed.get_context_data(**kwargs)

      There is also a way to pass additional information to title and description
      templates, if you need to supply more than the two variables mentioned
      before. You can provide your implementation of ``get_context_data`` method
      in your ``Feed`` subclass. For example::

        from mysite.models import Article
        from django.contrib.syndication.views import Feed

        class ArticlesFeed(Feed):
            title = "My articles"
            description_template = "feeds/articles.html"

            def items(self):
                return Article.objects.order_by('-pub_date')[:5]

            def get_context_data(self, **kwargs):
                context = super().get_context_data(**kwargs)
                context['foo'] = 'bar'
                return context

  And the template:

  .. code-block:: html+django

    Something about {{ foo }}: {{ obj.description }}

  This method will be called once per each item in the list returned by
  ``items()`` with the following keyword arguments:

  * ``item``: the current item. For backward compatibility reasons, the name
    of this context variable is ``{{ obj }}``.

  * ``obj``: the object returned by ``get_object()``. By default this is not
    exposed to the templates to avoid confusion with ``{{ obj }}`` (see above),
    but you can use it in your implementation of ``get_context_data()``.

  * ``site``: current site as described above.

  * ``request``: current request.

  The behavior of ``get_context_data()`` mimics that of
  :ref:`generic views <adding-extra-context>` - you're supposed to call
  ``super()`` to retrieve context data from parent class, add your data
  and return the modified dictionary.

* To specify the contents of ``<link>``, you have two options. For each item
  in ``items()``, Django first tries calling the
  ``item_link()`` method on the
  :class:`~django.contrib.syndication.views.Feed` class. In a similar way to
  the title and description, it is passed it a single parameter,
  ``item``. If that method doesn't exist, Django tries executing a
  ``get_absolute_url()`` method on that object. Both
  ``get_absolute_url()`` and ``item_link()`` should return the
  item's URL as a normal Python string. As with ``get_absolute_url()``, the
  result of ``item_link()`` will be included directly in the URL, so you
  are responsible for doing all necessary URL quoting and conversion to
  ASCII inside the method itself.

A complex example
-----------------

The framework also supports more complex feeds, via arguments.

For example, a website could offer an RSS feed of recent crimes for every
police beat in a city. It'd be silly to create a separate
:class:`~django.contrib.syndication.views.Feed` class for each police beat; that
would violate the :ref:`DRY principle <dry>` and would couple data to
programming logic. Instead, the syndication framework lets you access the
arguments passed from your :doc:`URLconf </topics/http/urls>` so feeds can output
items based on information in the feed's URL.

The police beat feeds could be accessible via URLs like this:

* :file:`/beats/613/rss/` -- Returns recent crimes for beat 613.
* :file:`/beats/1424/rss/` -- Returns recent crimes for beat 1424.

These can be matched with a :doc:`URLconf </topics/http/urls>` line such as::

    path('beats/<int:beat_id>/rss/', BeatFeed()),

Like a view, the arguments in the URL are passed to the ``get_object()``
method along with the request object.

Here's the code for these beat-specific feeds::

    from django.contrib.syndication.views import Feed

    class BeatFeed(Feed):
        description_template = 'feeds/beat_description.html'

        def get_object(self, request, beat_id):
            return Beat.objects.get(pk=beat_id)

        def title(self, obj):
            return "Police beat central: Crimes for beat %s" % obj.beat

        def link(self, obj):
            return obj.get_absolute_url()

        def description(self, obj):
            return "Crimes recently reported in police beat %s" % obj.beat

        def items(self, obj):
            return Crime.objects.filter(beat=obj).order_by('-crime_date')[:30]

To generate the feed's ``<title>``, ``<link>`` and ``<description>``, Django
uses the ``title()``, ``link()`` and ``description()`` methods. In
the previous example, they were string class attributes, but this example
illustrates that they can be either strings *or* methods. For each of
``title``, ``link`` and ``description``, Django follows this
algorithm:

* First, it tries to call a method, passing the ``obj`` argument, where
  ``obj`` is the object returned by ``get_object()``.

* Failing that, it tries to call a method with no arguments.

* Failing that, it uses the class attribute.

Also note that ``items()`` also follows the same algorithm -- first, it
tries ``items(obj)``, then ``items()``, then finally an ``items``
class attribute (which should be a list).

We are using a template for the item descriptions. It can be as minimal as
this:

.. code-block:: html+django

    {{ obj.description }}

However, you are free to add formatting as desired.

The ``ExampleFeed`` class below gives full documentation on methods and
attributes of :class:`~django.contrib.syndication.views.Feed` classes.

Specifying the type of feed
---------------------------

By default, feeds produced in this framework use RSS 2.0.

To change that, add a ``feed_type`` attribute to your
:class:`~django.contrib.syndication.views.Feed` class, like so::

    from django.utils.feedgenerator import Atom1Feed

    class MyFeed(Feed):
        feed_type = Atom1Feed

Note that you set ``feed_type`` to a class object, not an instance.

Currently available feed types are:

* :class:`django.utils.feedgenerator.Rss201rev2Feed` (RSS 2.01. Default.)
* :class:`django.utils.feedgenerator.RssUserland091Feed` (RSS 0.91.)
* :class:`django.utils.feedgenerator.Atom1Feed` (Atom 1.0.)

Enclosures
----------

To specify enclosures, such as those used in creating podcast feeds, use the
``item_enclosures`` hook or, alternatively and if you only have a single
enclosure per item, the ``item_enclosure_url``, ``item_enclosure_length``, and
``item_enclosure_mime_type`` hooks. See the ``ExampleFeed`` class below for
usage examples.

Language
--------

Feeds created by the syndication framework automatically include the
appropriate ``<language>`` tag (RSS 2.0) or ``xml:lang`` attribute (Atom). By
default, this is :func:`django.utils.translation.get_language()`. You can change it
by setting the ``language`` class attribute.

URLs
----

The ``link`` method/attribute can return either an absolute path (e.g.
:file:`"/blog/"`) or a URL with the fully-qualified domain and protocol (e.g.
``"https://www.example.com/blog/"``). If ``link`` doesn't return the domain,
the syndication framework will insert the domain of the current site, according
to your :setting:`SITE_ID setting <SITE_ID>`.

Atom feeds require a ``<link rel="self">`` that defines the feed's current
location. The syndication framework populates this automatically, using the
domain of the current site according to the :setting:`SITE_ID` setting.

Publishing Atom and RSS feeds in tandem
---------------------------------------

Some developers like to make available both Atom *and* RSS versions of their
feeds. To do that, you can create a subclass of your
:class:`~django.contrib.syndication.views.Feed` class and set the ``feed_type``
to something different. Then update your URLconf to add the extra versions.

Here's a full example::

    from django.contrib.syndication.views import Feed
    from policebeat.models import NewsItem
    from django.utils.feedgenerator import Atom1Feed

    class RssSiteNewsFeed(Feed):
        title = "Police beat site news"
        link = "/sitenews/"
        description = "Updates on changes and additions to police beat central."

        def items(self):
            return NewsItem.objects.order_by('-pub_date')[:5]

    class AtomSiteNewsFeed(RssSiteNewsFeed):
        feed_type = Atom1Feed
        subtitle = RssSiteNewsFeed.description

.. Note::
    In this example, the RSS feed uses a ``description`` while the Atom
    feed uses a ``subtitle``. That's because Atom feeds don't provide for
    a feed-level "description," but they *do* provide for a "subtitle."

    If you provide a ``description`` in your
    :class:`~django.contrib.syndication.views.Feed` class, Django will *not*
    automatically put that into the ``subtitle`` element, because a
    subtitle and description are not necessarily the same thing. Instead, you
    should define a ``subtitle`` attribute.

    In the above example, we set the Atom feed's ``subtitle`` to the RSS feed's
    ``description``, because it's quite short already.

And the accompanying URLconf::

    from django.urls import path
    from myproject.feeds import AtomSiteNewsFeed, RssSiteNewsFeed

    urlpatterns = [
        # ...
        path('sitenews/rss/', RssSiteNewsFeed()),
        path('sitenews/atom/', AtomSiteNewsFeed()),
        # ...
    ]

``Feed`` class reference
------------------------

.. class:: views.Feed

This example illustrates all possible attributes and methods for a
:class:`~django.contrib.syndication.views.Feed` class::

    from django.contrib.syndication.views import Feed
    from django.utils import feedgenerator

    class ExampleFeed(Feed):

        # FEED TYPE -- Optional. This should be a class that subclasses
        # django.utils.feedgenerator.SyndicationFeed. This designates
        # which type of feed this should be: RSS 2.0, Atom 1.0, etc. If
        # you don't specify feed_type, your feed will be RSS 2.0. This
        # should be a class, not an instance of the class.

        feed_type = feedgenerator.Rss201rev2Feed

        # TEMPLATE NAMES -- Optional. These should be strings
        # representing names of Django templates that the system should
        # use in rendering the title and description of your feed items.
        # Both are optional. If a template is not specified, the
        # item_title() or item_description() methods are used instead.

        title_template = None
        description_template = None

        # LANGUAGE -- Optional. This should be a string specifying a language
        # code. Defaults to django.utils.translation.get_language().
        language = 'de'

        # TITLE -- One of the following three is required. The framework
        # looks for them in this order.

        def title(self, obj):
            """
            Takes the object returned by get_object() and returns the
            feed's title as a normal Python string.
            """

        def title(self):
            """
            Returns the feed's title as a normal Python string.
            """

        title = 'foo' # Hard-coded title.

        # LINK -- One of the following three is required. The framework
        # looks for them in this order.

        def link(self, obj):
            """
            # Takes the object returned by get_object() and returns the URL
            # of the HTML version of the feed as a normal Python string.
            """

        def link(self):
            """
            Returns the URL of the HTML version of the feed as a normal Python
            string.
            """

        link = '/blog/' # Hard-coded URL.

        # FEED_URL -- One of the following three is optional. The framework
        # looks for them in this order.

        def feed_url(self, obj):
            """
            # Takes the object returned by get_object() and returns the feed's
            # own URL as a normal Python string.
            """

        def feed_url(self):
            """
            Returns the feed's own URL as a normal Python string.
            """

        feed_url = '/blog/rss/' # Hard-coded URL.

        # GUID -- One of the following three is optional. The framework looks
        # for them in this order. This property is only used for Atom feeds
        # (where it is the feed-level ID element). If not provided, the feed
        # link is used as the ID.

        def feed_guid(self, obj):
            """
            Takes the object returned by get_object() and returns the globally
            unique ID for the feed as a normal Python string.
            """

        def feed_guid(self):
            """
            Returns the feed's globally unique ID as a normal Python string.
            """

        feed_guid = '/foo/bar/1234' # Hard-coded guid.

        # DESCRIPTION -- One of the following three is required. The framework
        # looks for them in this order.

        def description(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            description as a normal Python string.
            """

        def description(self):
            """
            Returns the feed's description as a normal Python string.
            """

        description = 'Foo bar baz.' # Hard-coded description.

        # AUTHOR NAME --One of the following three is optional. The framework
        # looks for them in this order.

        def author_name(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            author's name as a normal Python string.
            """

        def author_name(self):
            """
            Returns the feed's author's name as a normal Python string.
            """

        author_name = 'Sally Smith' # Hard-coded author name.

        # AUTHOR EMAIL --One of the following three is optional. The framework
        # looks for them in this order.

        def author_email(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            author's email as a normal Python string.
            """

        def author_email(self):
            """
            Returns the feed's author's email as a normal Python string.
            """

        author_email = 'test@example.com' # Hard-coded author email.

        # AUTHOR LINK --One of the following three is optional. The framework
        # looks for them in this order. In each case, the URL should include
        # the "http://" and domain name.

        def author_link(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            author's URL as a normal Python string.
            """

        def author_link(self):
            """
            Returns the feed's author's URL as a normal Python string.
            """

        author_link = 'https://www.example.com/' # Hard-coded author URL.

        # CATEGORIES -- One of the following three is optional. The framework
        # looks for them in this order. In each case, the method/attribute
        # should return an iterable object that returns strings.

        def categories(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            categories as iterable over strings.
            """

        def categories(self):
            """
            Returns the feed's categories as iterable over strings.
            """

        categories = ("python", "django") # Hard-coded list of categories.

        # COPYRIGHT NOTICE -- One of the following three is optional. The
        # framework looks for them in this order.

        def feed_copyright(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            copyright notice as a normal Python string.
            """

        def feed_copyright(self):
            """
            Returns the feed's copyright notice as a normal Python string.
            """

        feed_copyright = 'Copyright (c) 2007, Sally Smith' # Hard-coded copyright notice.

        # TTL -- One of the following three is optional. The framework looks
        # for them in this order. Ignored for Atom feeds.

        def ttl(self, obj):
            """
            Takes the object returned by get_object() and returns the feed's
            TTL (Time To Live) as a normal Python string.
            """

        def ttl(self):
            """
            Returns the feed's TTL as a normal Python string.
            """

        ttl = 600 # Hard-coded Time To Live.

        # ITEMS -- One of the following three is required. The framework looks
        # for them in this order.

        def items(self, obj):
            """
            Takes the object returned by get_object() and returns a list of
            items to publish in this feed.
            """

        def items(self):
            """
            Returns a list of items to publish in this feed.
            """

        items = ('Item 1', 'Item 2') # Hard-coded items.

        # GET_OBJECT -- This is required for feeds that publish different data
        # for different URL parameters. (See "A complex example" above.)

        def get_object(self, request, *args, **kwargs):
            """
            Takes the current request and the arguments from the URL, and
            returns an object represented by this feed. Raises
            django.core.exceptions.ObjectDoesNotExist on error.
            """

        # ITEM TITLE AND DESCRIPTION -- If title_template or
        # description_template are not defined, these are used instead. Both are
        # optional, by default they will use the string representation of the
        # item.

        def item_title(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            title as a normal Python string.
            """

        def item_title(self):
            """
            Returns the title for every item in the feed.
            """

        item_title = 'Breaking News: Nothing Happening' # Hard-coded title.

        def item_description(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            description as a normal Python string.
            """

        def item_description(self):
            """
            Returns the description for every item in the feed.
            """

        item_description = 'A description of the item.' # Hard-coded description.

        def get_context_data(self, **kwargs):
            """
            Returns a dictionary to use as extra context if either
            description_template or item_template are used.

            Default implementation preserves the old behavior
            of using {'obj': item, 'site': current_site} as the context.
            """

        # ITEM LINK -- One of these three is required. The framework looks for
        # them in this order.

        # First, the framework tries the two methods below, in
        # order. Failing that, it falls back to the get_absolute_url()
        # method on each item returned by items().

        def item_link(self, item):
            """
            Takes an item, as returned by items(), and returns the item's URL.
            """

        def item_link(self):
            """
            Returns the URL for every item in the feed.
            """

        # ITEM_GUID -- The following method is optional. If not provided, the
        # item's link is used by default.

        def item_guid(self, obj):
            """
            Takes an item, as return by items(), and returns the item's ID.
            """

        # ITEM_GUID_IS_PERMALINK -- The following method is optional. If
        # provided, it sets the 'isPermaLink' attribute of an item's
        # GUID element. This method is used only when 'item_guid' is
        # specified.

        def item_guid_is_permalink(self, obj):
            """
            Takes an item, as returned by items(), and returns a boolean.
            """

        item_guid_is_permalink = False  # Hard coded value

        # ITEM AUTHOR NAME -- One of the following three is optional. The
        # framework looks for them in this order.

        def item_author_name(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            author's name as a normal Python string.
            """

        def item_author_name(self):
            """
            Returns the author name for every item in the feed.
            """

        item_author_name = 'Sally Smith' # Hard-coded author name.

        # ITEM AUTHOR EMAIL --One of the following three is optional. The
        # framework looks for them in this order.
        #
        # If you specify this, you must specify item_author_name.

        def item_author_email(self, obj):
            """
            Takes an item, as returned by items(), and returns the item's
            author's email as a normal Python string.
            """

        def item_author_email(self):
            """
            Returns the author email for every item in the feed.
            """

        item_author_email = 'test@example.com' # Hard-coded author email.

        # ITEM AUTHOR LINK -- One of the following three is optional. The
        # framework looks for them in this order. In each case, the URL should
        # include the "http://" and domain name.
        #
        # If you specify this, you must specify item_author_name.

        def item_author_link(self, obj):
            """
            Takes an item, as returned by items(), and returns the item's
            author's URL as a normal Python string.
            """

        def item_author_link(self):
            """
            Returns the author URL for every item in the feed.
            """

        item_author_link = 'https://www.example.com/' # Hard-coded author URL.

        # ITEM ENCLOSURES -- One of the following three is optional. The
        # framework looks for them in this order. If one of them is defined,
        # ``item_enclosure_url``, ``item_enclosure_length``, and
        # ``item_enclosure_mime_type`` will have no effect.

        def item_enclosures(self, item):
            """
            Takes an item, as returned by items(), and returns a list of
            ``django.utils.feedgenerator.Enclosure`` objects.
            """

        def item_enclosures(self):
            """
            Returns the ``django.utils.feedgenerator.Enclosure`` list for every
            item in the feed.
            """

        item_enclosures = []  # Hard-coded enclosure list

        # ITEM ENCLOSURE URL -- One of these three is required if you're
        # publishing enclosures and you're not using ``item_enclosures``. The
        # framework looks for them in this order.

        def item_enclosure_url(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            enclosure URL.
            """

        def item_enclosure_url(self):
            """
            Returns the enclosure URL for every item in the feed.
            """

        item_enclosure_url = "/foo/bar.mp3" # Hard-coded enclosure link.

        # ITEM ENCLOSURE LENGTH -- One of these three is required if you're
        # publishing enclosures and you're not using ``item_enclosures``. The
        # framework looks for them in this order. In each case, the returned
        # value should be either an integer, or a string representation of the
        # integer, in bytes.

        def item_enclosure_length(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            enclosure length.
            """

        def item_enclosure_length(self):
            """
            Returns the enclosure length for every item in the feed.
            """

        item_enclosure_length = 32000 # Hard-coded enclosure length.

        # ITEM ENCLOSURE MIME TYPE -- One of these three is required if you're
        # publishing enclosures and you're not using ``item_enclosures``. The
        # framework looks for them in this order.

        def item_enclosure_mime_type(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            enclosure MIME type.
            """

        def item_enclosure_mime_type(self):
            """
            Returns the enclosure MIME type for every item in the feed.
            """

        item_enclosure_mime_type = "audio/mpeg" # Hard-coded enclosure MIME type.

        # ITEM PUBDATE -- It's optional to use one of these three. This is a
        # hook that specifies how to get the pubdate for a given item.
        # In each case, the method/attribute should return a Python
        # datetime.datetime object.

        def item_pubdate(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            pubdate.
            """

        def item_pubdate(self):
            """
            Returns the pubdate for every item in the feed.
            """

        item_pubdate = datetime.datetime(2005, 5, 3) # Hard-coded pubdate.

        # ITEM UPDATED -- It's optional to use one of these three. This is a
        # hook that specifies how to get the updateddate for a given item.
        # In each case, the method/attribute should return a Python
        # datetime.datetime object.

        def item_updateddate(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            updateddate.
            """

        def item_updateddate(self):
            """
            Returns the updateddate for every item in the feed.
            """

        item_updateddate = datetime.datetime(2005, 5, 3) # Hard-coded updateddate.

        # ITEM CATEGORIES -- It's optional to use one of these three. This is
        # a hook that specifies how to get the list of categories for a given
        # item. In each case, the method/attribute should return an iterable
        # object that returns strings.

        def item_categories(self, item):
            """
            Takes an item, as returned by items(), and returns the item's
            categories.
            """

        def item_categories(self):
            """
            Returns the categories for every item in the feed.
            """

        item_categories = ("python", "django") # Hard-coded categories.

        # ITEM COPYRIGHT NOTICE (only applicable to Atom feeds) -- One of the
        # following three is optional. The framework looks for them in this
        # order.

        def item_copyright(self, obj):
            """
            Takes an item, as returned by items(), and returns the item's
            copyright notice as a normal Python string.
            """

        def item_copyright(self):
            """
            Returns the copyright notice for every item in the feed.
            """

        item_copyright = 'Copyright (c) 2007, Sally Smith' # Hard-coded copyright notice.

        # ITEM COMMENTS URL -- It's optional to use one of these three. This is
        # a hook that specifies how to get the URL of a page for comments for a
        # given item.

        def item_comments(self, obj):
            """
            Takes an item, as returned by items(), and returns the item's
            comments URL as a normal Python string.
            """

        def item_comments(self):
            """
            Returns the comments URL for every item in the feed.
            """

        item_comments = 'https://www.example.com/comments' # Hard-coded comments URL

.. versionchanged:: 3.2

    Support for a comments URL per feed item was added through the
    ``item_comments`` hook.

The low-level framework
=======================

Behind the scenes, the high-level RSS framework uses a lower-level framework
for generating feeds' XML. This framework lives in a single module:
:source:`django/utils/feedgenerator.py`.

You use this framework on your own, for lower-level feed generation. You can
also create custom feed generator subclasses for use with the ``feed_type``
``Feed`` option.

.. currentmodule:: django.utils.feedgenerator

``SyndicationFeed`` classes
---------------------------

The :mod:`~django.utils.feedgenerator` module contains a base class:

* :class:`django.utils.feedgenerator.SyndicationFeed`

and several subclasses:

* :class:`django.utils.feedgenerator.RssUserland091Feed`
* :class:`django.utils.feedgenerator.Rss201rev2Feed`
* :class:`django.utils.feedgenerator.Atom1Feed`

Each of these three classes knows how to render a certain type of feed as XML.
They share this interface:

:meth:`.SyndicationFeed.__init__`
    Initialize the feed with the given dictionary of metadata, which applies to
    the entire feed. Required keyword arguments are:

    * ``title``
    * ``link``
    * ``description``

    There's also a bunch of other optional keywords:

    * ``language``
    * ``author_email``
    * ``author_name``
    * ``author_link``
    * ``subtitle``
    * ``categories``
    * ``feed_url``
    * ``feed_copyright``
    * ``feed_guid``
    * ``ttl``

    Any extra keyword arguments you pass to ``__init__`` will be stored in
    ``self.feed`` for use with `custom feed generators`_.

    All parameters should be strings, except ``categories``, which should be a
    sequence of strings. Beware that some control characters
    are `not allowed <https://www.w3.org/International/questions/qa-controls>`_
    in XML documents. If your content has some of them, you might encounter a
    :exc:`ValueError` when producing the feed.

:meth:`.SyndicationFeed.add_item`
    Add an item to the feed with the given parameters.

    Required keyword arguments are:

    * ``title``
    * ``link``
    * ``description``

    Optional keyword arguments are:

    * ``author_email``
    * ``author_name``
    * ``author_link``
    * ``pubdate``
    * ``comments``
    * ``unique_id``
    * ``enclosures``
    * ``categories``
    * ``item_copyright``
    * ``ttl``
    * ``updateddate``

    Extra keyword arguments will be stored for `custom feed generators`_.

    All parameters, if given, should be strings, except:

    * ``pubdate`` should be a Python  :class:`~datetime.datetime` object.
    * ``updateddate`` should be a Python  :class:`~datetime.datetime` object.
    * ``enclosures`` should be a list of
      :class:`django.utils.feedgenerator.Enclosure` instances.
    * ``categories`` should be a sequence of strings.

:meth:`.SyndicationFeed.write`
    Outputs the feed in the given encoding to outfile, which is a file-like object.

:meth:`.SyndicationFeed.writeString`
    Returns the feed as a string in the given encoding.

For example, to create an Atom 1.0 feed and print it to standard output::

    >>> from django.utils import feedgenerator
    >>> from datetime import datetime
    >>> f = feedgenerator.Atom1Feed(
    ...     title="My Weblog",
    ...     link="https://www.example.com/",
    ...     description="In which I write about what I ate today.",
    ...     language="en",
    ...     author_name="Myself",
    ...     feed_url="https://example.com/atom.xml")
    >>> f.add_item(title="Hot dog today",
    ...     link="https://www.example.com/entries/1/",
    ...     pubdate=datetime.now(),
    ...     description="<p>Today I had a Vienna Beef hot dog. It was pink, plump and perfect.</p>")
    >>> print(f.writeString('UTF-8'))
    <?xml version="1.0" encoding="UTF-8"?>
    <feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
    ...
    </feed>

.. currentmodule:: django.contrib.syndication

Custom feed generators
----------------------

If you need to produce a custom feed format, you've got a couple of options.

If the feed format is totally custom, you'll want to subclass
``SyndicationFeed`` and completely replace the ``write()`` and
``writeString()`` methods.

However, if the feed format is a spin-off of RSS or Atom (i.e. GeoRSS_, Apple's
`iTunes podcast format`_, etc.), you've got a better choice. These types of
feeds typically add extra elements and/or attributes to the underlying format,
and there are a set of methods that ``SyndicationFeed`` calls to get these extra
attributes. Thus, you can subclass the appropriate feed generator class
(``Atom1Feed`` or ``Rss201rev2Feed``) and extend these callbacks. They are:

.. _georss: http://georss.org/
.. _itunes podcast format: https://help.apple.com/itc/podcasts_connect/#/itcb54353390

``SyndicationFeed.root_attributes(self)``
    Return a ``dict`` of attributes to add to the root feed element
    (``feed``/``channel``).

``SyndicationFeed.add_root_elements(self, handler)``
    Callback to add elements inside the root feed element
    (``feed``/``channel``). ``handler`` is an
    :class:`~xml.sax.saxutils.XMLGenerator` from Python's built-in SAX library;
    you'll call methods on it to add to the XML document in process.

``SyndicationFeed.item_attributes(self, item)``
    Return a ``dict`` of attributes to add to each item (``item``/``entry``)
    element. The argument, ``item``, is a dictionary of all the data passed to
    ``SyndicationFeed.add_item()``.

``SyndicationFeed.add_item_elements(self, handler, item)``
    Callback to add elements to each item (``item``/``entry``) element.
    ``handler`` and ``item`` are as above.

.. warning::

    If you override any of these methods, be sure to call the superclass methods
    since they add the required elements for each feed format.

For example, you might start implementing an iTunes RSS feed generator like so::

    class iTunesFeed(Rss201rev2Feed):
        def root_attributes(self):
            attrs = super().root_attributes()
            attrs['xmlns:itunes'] = 'http://www.itunes.com/dtds/podcast-1.0.dtd'
            return attrs

        def add_root_elements(self, handler):
            super().add_root_elements(handler)
            handler.addQuickElement('itunes:explicit', 'clean')

There's a lot more work to be done for a complete custom feed class, but the
above example should demonstrate the basic idea.