#!/usr/bin/env python
# vim:fileencoding=utf-8

from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe

class Sova(BasicNewsRecipe):
    title          		  = 'SOVA'
    __author__            = 'bugmen00t'
    description           = ' \u0420\u0443\u0441\u0441\u043A\u043E\u044F\u0437\u044B\u0447\u043D\u043E\u0435 \u043D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u043E\u0435 \u043E\u043D\u043B\u0430\u0439\u043D-\u0438\u0437\u0434\u0430\u043D\u0438\u0435, \u043E\u0441\u043D\u043E\u0432\u0430\u043D\u043D\u043E\u0435 \u0432 \u0422\u0431\u0438\u043B\u0438\u0441\u0438 \u0432 2016 \u0433\u043E\u0434\u0443 \u0433\u0440\u0443\u043F\u043F\u043E\u0439 \u043F\u0440\u043E\u0444\u0435\u0441\u0441\u0438\u043E\u043D\u0430\u043B\u044C\u043D\u044B\u0445 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432, \u043F\u0440\u0435\u0434\u043E\u0441\u0442\u0430\u0432\u043B\u044F\u044E\u0449\u0435\u0435 \u043A\u0430\u0447\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u0443\u044E \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u044E \u043E \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0435, \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0435 \u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u043D\u0435\u043E\u0442\u044A\u0435\u043C\u043B\u0435\u043C\u044B\u0445 \u0430\u0441\u043F\u0435\u043A\u0442\u0430\u0445 \u0436\u0438\u0437\u043D\u0438 \u0441\u043E\u0432\u0440\u0435\u043C\u0435\u043D\u043D\u043E\u0433\u043E \u0447\u0435\u043B\u043E\u0432\u0435\u043A\u0430 \u0432 \u0413\u0440\u0443\u0437\u0438\u0438 \u0438 \u0440\u0435\u0433\u0438\u043E\u043D\u0435 \u0432 \u0446\u0435\u043B\u043E\u043C.'
    publisher             = '\u041D\u0435\u043F\u0440\u0430\u0432\u0438\u0442\u0435\u043B\u044C\u0441\u0442\u0432\u0435\u043D\u043D\u0430\u044F \u043E\u0440\u0433\u0430\u043D\u0438\u0437\u0430\u0446\u0438\u044F Sova News'
    category              = 'blog'
    cover_url = u'https://i0.wp.com/sova.news/wp-content/uploads/2021/08/sova@512.png'
    language              = 'ru'
    no_stylesheets        = False
    remove_javascript = False
    auto_cleanup   = False
    oldest_article = 60
    max_articles_per_feed = 30

    remove_tags_before = dict(name='div', attrs={'class':'site-wrapper header-7'})
    
    remove_tags_after = dict(name='div', attrs={'class':'single-body entry-content typography-copy'})

    remove_tags =   [
        dict(name='nav', attrs={'aria-label': 'breadcrumbs'}),
        dict(name='header', attrs={'class': 'site-header site-header--skin-5'}),
        dict(name='footer'),
        dict(name='ins'),
        dict(name='div', attrs={'class': 'entry-interaction__left'}),
        dict(name='div', attrs={'class': 'entry-interaction__right'}),
        dict(name='div', attrs={'id': 'mnmd-sticky-header'}),
        dict(name='div', attrs={'id': 'mnmd-offcanvas-primary'}),
        dict(name='div', attrs={'id': 'mnmd-offcanvas-mobile'}),
        dict(name='div', attrs={'class': 'entry-interaction__right'}),
        dict(name='blockquote', attrs={'class': 'wp-embedded-content'})
        ] 

    feeds = [
        ('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://sova.news/news/feed/'),
        ('\u041F\u043E\u043B\u0438\u0442\u0438\u043A\u0430', 'https://sova.news/analytics/politics/feed/'),
        ('\u042D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'https://sova.news/analytics/economy/feed/'),
        ('\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u043E', 'https://sova.news/analytics/society/feed/'),
        ('\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://sova.news/interview/feed/'),
        ('Unfake', 'https://sova.news/unfake/feed/'),
        ('\u0414\u0440\u0443\u0433\u0430\u044F \u0421\u043E\u0432\u0430', 'https://sova.news/sova-other/feed/'),
        ('\u0418\u0441\u043A\u0443\u0441\u0441\u0442\u0432\u043E', 'https://sova.news/sova-other/art/feed/'),
        ('\u0422\u0443\u0440\u0438\u0437\u043C', 'https://sova.news/sova-other/tourism/feed/'),
        ('#weekendnavigator', 'https://sova.news/weekendnavigator/feed/'),
        ('\u0421\u043E\u0441\u0435\u0434\u0438', 'https://sova.news/sova-other/neighbours/feed/'),
        ('\u041D\u0435\u0434\u0435\u043B\u044F \u0432 \u0433\u043E\u0440\u043E\u0434\u0435', 'https://sova.news/week-in-the-city/feed/'),
        ('\u0424\u043E\u0442\u043E\u043F\u0440\u043E\u0433\u0443\u043B\u043A\u0438', 'https://sova.news/photowalks/feed/'),
        ('\u0424\u043E\u0442\u043E', 'https://sova.news/photo/feed/')
    ]
    
    def preprocess_html(self, soup):
        for img in soup.findAll('img', attrs={'data-src': True}):
            img['src'] = img['data-src']
        return soup