破解 NationalReview 的订阅限制

    def parse_index(self):
    '''
    This method should be implemented in recipes that parse a website
    instead of feeds to generate a list of articles. Typical uses are for
    news sources that have a "Print Edition" webpage that lists all the
    articles in the current print edition. If this function is implemented,
    it will be used in preference to :meth:`BasicNewsRecipe.parse_feeds`.

    It must return a list. Each element of the list must be a 2-element tuple
    of the form ``('feed title', list of articles)``.

    Each list of articles must contain dictionaries of the form::

        {
        'title'       : article title,
        'url'         : URL of print version,
        'date'        : The publication date of the article as a string,
        'description' : A summary of the article
        'content'     : The full article (can be an empty string). Obsolete
                        do not use, instead save the content to a temporary
                        file and pass a file:///path/to/temp/file.html as
                        the URL.
        }

    For an example, see the recipe for downloading `The Atlantic`.
    In addition, you can add 'author' for the author of the article.

    If you want to abort processing for some reason and have
    calibre show the user a simple message instead of an error, call
    :meth:`abort_recipe_processing`.
    '''
    raise NotImplementedError()

    def preprocess_html(self, soup):
    '''
    This method is called with the source of each downloaded :term:`HTML` file, before
    it is parsed for links and images. It is called after the cleanup as
    specified by remove_tags etc.
    It can be used to do arbitrarily powerful pre-processing on the :term:`HTML`.
    It should return `soup` after processing it.

    `soup`: A `BeautifulSoup <https://www.crummy.com/software/BeautifulSoup/bs4/doc/>`__
    instance containing the downloaded :term:`HTML`.
    '''
    return soup

#: List of tags to be removed. Specified tags are removed from downloaded HTML.
#: A tag is specified as a dictionary of the form::
#:
#:    {
#:     name      : 'tag name',   #e.g. 'div'
#:     attrs     : a dictionary, #e.g. {'class': 'advertisment'}
#:    }
#:
#: All keys are optional. For a full explanation of the search criteria, see
#: `Beautiful Soup <https://www.crummy.com/software/BeautifulSoup/bs4/doc/#searching-the-tree>`__
#: A common example::
#:
#:   remove_tags = [dict(name='div', class_='advert')]
#:
#: This will remove all `<div class="advert">` tags and all
#: their children from the downloaded :term:`HTML`.
remove_tags           = []