| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class Zerkalo(BasicNewsRecipe): |
| 8 |
title = '\u0417\u0435\u0440\u043a\u0430\u043b\u043e \u043d\u0435\u0434\u0435\u043b\u0438. \u0423\u043a\u0440\u0430\u0438\u043d\u0430' |
| 9 |
__author__ = 'bugmen00t' |
| 10 |
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: E501 |
| 11 |
publisher = '\u00ab\u0417\u0435\u0440\u043a\u0430\u043b\u043e \u043d\u0435\u0434\u0435\u043b\u0438. \u0423\u043a\u0440\u0430\u0438\u043d\u0430\u00bb' |
| 12 |
category = 'newspaper' |
| 13 |
cover_url = 'https://zn.ua/user/img/zn_no_photo_amp.png' |
| 14 |
language = 'ru_UK' |
| 15 |
no_stylesheets = False |
| 16 |
remove_javascript = False |
| 17 |
auto_cleanup = False |
| 18 |
remove_empty_feeds = True |
| 19 |
oldest_article = 7 |
| 20 |
max_articles_per_feed = 200 |
| 21 |
|
| 22 |
remove_tags_before = dict(name='h1') |
| 23 |
|
| 24 |
remove_tags_after = dict(name='div', attrs={'class': 'article_body'}) |
| 25 |
|
| 26 |
remove_tags = [ |
| 27 |
dict(name='span', attrs={'class': 'print print-art-js'}), |
| 28 |
dict(name='div', attrs={'class': 'questionnaire '}), |
| 29 |
dict(name='div', attrs={'class': 'nts-video-wrapper'}), |
| 30 |
dict(name='div', attrs={'class': 'telegram'}), |
| 31 |
dict(name='div', attrs={'class': 'mist_block'}), |
| 32 |
dict(name='div', attrs={'class': 'auth_articles_block'}), |
| 33 |
dict(name='div', attrs={'class': 'special_theme_news_block'}), |
| 34 |
dict(name='div', attrs={'class': 'article_attached acenter'}), |
| 35 |
dict(name='div', attrs={'class': 'article_left'}), |
| 36 |
dict(name='div', attrs={'class': 'top_social_holder'}), |
| 37 |
] |
| 38 |
|
| 39 |
feeds = [ |
| 40 |
('\u041d\u043e\u0432\u043e\u0441\u0442\u0438', 'https://zn.ua/rus/rss/full.rss'), |
| 41 |
# ('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://zn.ua/rus/rss/articles.rss') |
| 42 |
] |
| 43 |
|
| 44 |
def preprocess_html(self, soup): |
| 45 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 46 |
img['src'] = img['data-src'] |
| 47 |
return soup |