from calibre.web.feeds.news import BasicNewsRecipe


def classes(classes):
    q = frozenset(classes.split(' '))
    return dict(attrs={
        'class': lambda x: x and frozenset(x.split()).intersection(q)})


class NatureNews(BasicNewsRecipe):
    title = u'Nature News'
    language = 'en'
    __author__ = 'Kovid Goyal'
    oldest_article = 31  # days
    remove_empty_feeds = True
    max_articles_per_feed = 50

    no_stylesheets = True
    use_embedded_content = False
    remove_javascript = True
    keep_only_tags = [
        classes('container-type-article'),
    ]
    remove_tags = [
        dict(id='related-articles'),
        classes('u-hide-print hide-print visually-hidden'),
        dict(name=['meta', 'link', 'source']),
    ]

    # News and comments
    feeds = [(u'Nature News', 'http://feeds.nature.com/nature/rss/current')]

    def preprocess_html(self, soup):
        for img in soup.findAll('img', src=lambda x: x and x.startswith('//')):
            img['src'] = 'https:' + img['src']
            print(img)
        return soup