from calibre.web.feeds.news import BasicNewsRecipe, classes


class DeutscheWelle(BasicNewsRecipe):
    title = u'Deutsche Welle \u043D\u0430 \u0440\u0443\u0441\u0441\u043A\u043E\u043C'
    description = u'\u0420\u0443\u0441\u0441\u043A\u0430\u044F \u0440\u0435\u0434\u0430\u043A\u0446\u0438\u044F Deutsche Welle: \u043D\u043E\u0432\u043E\u0441\u0442\u0438, \u0430\u043D\u0430\u043B\u0438\u0442\u0438\u043A\u0430, \u043A\u043E\u043C\u043C\u0435\u043D\u0442\u0430\u0440\u0438\u0438 \u0438 \u0440\u0435\u043F\u043E\u0440\u0442\u0430\u0436\u0438 \u0438\u0437 \u0413\u0435\u0440\u043C\u0430\u043D\u0438\u0438 \u0438 \u0415\u0432\u0440\u043E\u043F\u044B, \u043D\u0435\u043C\u0435\u0446\u043A\u0438\u0439 \u0438 \u0435\u0432\u0440\u043E\u043F\u0435\u0439\u0441\u043A\u0438\u0439 \u0432\u0437\u0433\u043B\u044F\u0434 \u043D\u0430 \u0441\u043E\u0431\u044B\u0442\u0438\u044F \u0432 \u0420\u043E\u0441\u0441\u0438\u0438 \u0438 \u043C\u0438\u0440\u0435,  \u043F\u0440\u0430\u043A\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0435 \u0441\u043E\u0432\u0435\u0442\u044B \u0434\u043B\u044F \u0442\u0443\u0440\u0438\u0441\u0442\u043E\u0432 \u0438 \u0442\u0435\u0445, \u043A\u0442\u043E \u0436\u0435\u043B\u0430\u0435\u0442 \u0443\u0447\u0438\u0442\u044C\u0441\u044F \u0438\u043B\u0438 \u0440\u0430\u0431\u043E\u0442\u0430\u0442\u044C \u0432 \u0413\u0435\u0440\u043C\u0430\u043D\u0438\u0438 \u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u0441\u0442\u0440\u0430\u043D\u0430\u0445 \u0415\u0432\u0440\u043E\u0441\u043E\u044E\u0437\u0430.'  # noqa: E501
    __author__ = 'bugmen00t, unkn0wn'
    publication_type = 'newspaper'
    oldest_article = 2
    max_articles_per_feed = 100
    language = 'ru'
    # cover_url = 'https://www.dw.com/cssi/dwlogo-print.gif'

    remove_javascript = True
    no_stylesheets = True
    remove_empty_feeds = True
    ignore_duplicate_articles = {'title', 'url'}
    remove_attributes = ['height', 'width', 'style']

    recipe_specific_options = {
        'days': {
            'short': 'Oldest article to download from this news source. In days ',
            'long': 'For example, 0.5, gives you articles from the past 12 hours',
            'default': str(oldest_article)
        }
    }

    def __init__(self, *args, **kwargs):
        BasicNewsRecipe.__init__(self, *args, **kwargs)
        d = self.recipe_specific_options.get('days')
        if d and isinstance(d, str):
            self.oldest_article = float(d)

    def preprocess_html(self, soup):
        for img in soup.findAll('img', srcset=True):
            img['src'] = img['srcset'].split()[6]
        return soup

    keep_only_tags = [
        dict(name='article')
    ]

    remove_tags = [
        dict(name=['footer', 'source']),
        dict(attrs={'data-tracking-name':'sharing-icons-inline'}),
        classes('kicker advertisement vjs-wrapper')
    ]

    feeds = [
        (
            u'\u0412\u0435\u0441\u044C \u0441\u0430\u0439\u0442',
            'https://rss.dw.com/xml/rss-ru-all'
        ),
        (
            u'\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
            'http://rss.dw.de/xml/rss-ru-news'
        ),
        (
            u'\u041F\u043E\u043B\u0438\u0442\u0438\u043A\u0430 \u0438 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u043E',
            'http://rss.dw.de/xml/rss-ru-pol'
        ),
        (
            u'\u042D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430',
            'http://rss.dw.de/xml/rss-ru-eco'
        ),
        (
            u'\u0410\u0432\u0442\u043E\u043C\u043E\u0431\u0438\u043B\u044C',
            'http://rss.dw.de/xml/rss-ru-auto'
        ),
        (
            u'\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430 \u0438 \u0441\u0442\u0438\u043B\u044C \u0436\u0438\u0437\u043D\u0438',
            'http://rss.dw.de/xml/rss-ru-cul'
        ),
        (u'\u0420\u043E\u0441\u0441\u0438\u044F', 'http://rss.dw.de/xml/rss-ru-rus'),
        (
            u'\u0413\u0435\u0440\u043C\u0430\u043D\u0438\u044F',
            'http://rss.dw.de/xml/rss-ru-ger'
        ),
        (u'\u0415\u0432\u0440\u043E\u043F\u0430', 'http://rss.dw.de/xml/rss-ru-eu'),
        (
            u'\u0411\u0435\u043B\u0430\u0440\u0443\u0441\u044C',
            'http://rss.dw.de/xml/rss-ru-bel'
        ),
        (
            u'\u0423\u0447\u0435\u0431\u0430 \u0438 \u043A\u0430\u0440\u044C\u0435\u0440\u0430',
            'http://rss.dw.de/xml/rss-ru-campus-karriere'
        ),
        (u'\u0423\u0447\u0435\u0431\u0430 ', 'http://rss.dw.de/xml/rss-ru-campus'),
        (
            u'\u041A\u0430\u0440\u044C\u0435\u0440\u0430 ',
            'http://rss.dw.de/xml/rss-ru-karriere'
        ),
        (
            u'\u0422\u0443\u0440\u0438\u0441\u0442\u0443 \u043D\u0430 \u0437\u0430\u043C\u0435\u0442\u043A\u0443',
            'http://rss.dw.de/xml/rss-ru-discover-ger'
        )
    ]