from calibre.web.feeds.recipes import BasicNewsRecipe


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


class NewZealandHerald(BasicNewsRecipe):

    title = 'New Zealand Herald'
    __author__ = 'Kovid Goyal'
    description = 'Daily news'
    timefmt = ' [%d %b, %Y]'
    language = 'en_NZ'
    oldest_article = 2.5

    keep_only_tags = [
        classes('article-header'),
        dict(id='article-content'),
    ]

    remove_tags = [
        classes('ad-container pb-f-video-video-player pb-f-article-related-articles social-shares')
    ]

    feeds = [
        ('Business',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000003.xml'),
        ('World',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000002.xml'),
        ('National',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000001.xml'),
        ('Entertainment',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_001501119.xml'),
        ('Travel',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000007.xml'),
        ('Opinion',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000466.xml'),
        ('Life & Style',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000006.xml'),
        ('Technology',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000005.xml'),
        ('Sport',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000004.xml'),
        ('Motoring',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000009.xml'),
        ('Property',
         'http://rss.nzherald.co.nz/rss/xml/nzhrsscid_000000008.xml'),
    ]

    def preprocess_html(self, soup, *a):
        for img in soup.findAll('img', attrs={'data-srcset': True}):
            img['src'] = img['data-srcset'].split()[0]
        return soup