calibre/recipes/zn_ru.recipe
2024-07-31 18:55:52 +05:30

51 lines
2.3 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class Zerkalo(BasicNewsRecipe):
title = '\u0417\u0435\u0440\u043A\u0430\u043B\u043E \u043D\u0435\u0434\u0435\u043B\u0438. \u0423\u043A\u0440\u0430\u0438\u043D\u0430'
__author__ = 'bugmen00t'
description = '\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E-\u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0439 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E-\u0430\u043D\u0430\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0439 \u0435\u0436\u0435\u043D\u0435\u0434\u0435\u043B\u044C\u043D\u0438\u043A.' # noqa
publisher = '\u00AB\u0417\u0435\u0440\u043A\u0430\u043B\u043E \u043D\u0435\u0434\u0435\u043B\u0438. \u0423\u043A\u0440\u0430\u0438\u043D\u0430\u00BB'
category = 'newspaper'
cover_url = u'https://zn.ua/user/img/zn_no_photo_amp.png'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 200
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'article_body'}),
remove_tags = [
dict(name='span', attrs={'class': 'print print-art-js'}),
dict(name='div', attrs={'class': 'questionnaire '}),
dict(name='div', attrs={'class': 'nts-video-wrapper'}),
dict(name='div', attrs={'class': 'telegram'}),
dict(name='div', attrs={'class': 'mist_block'}),
dict(name='div', attrs={'class': 'auth_articles_block'}),
dict(name='div', attrs={'class': 'special_theme_news_block'}),
dict(name='div', attrs={'class': 'article_attached acenter'}),
dict(name='div', attrs={'class': 'article_left'}),
dict(name='div', attrs={'class': 'top_social_holder'})
]
feeds = [
(
'\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
'https://zn.ua/rus/rss/full.rss'
),
# ('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://zn.ua/rus/rss/articles.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup