| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class Sobaka(BasicNewsRecipe): |
| 8 |
title = '\u0421\u043e\u0431\u0430\u043a\u0430.ru' |
| 9 |
__author__ = 'bugmen00t' |
| 10 |
description = ( |
| 11 |
'\u0416\u0443\u0440\u043d\u0430\u043b \u043e \u043b\u044e\u0434\u044f\u0445 \u0432 \u041f\u0435\u0442\u0435\u0440\u0431\u0443\u0440\u0433\u0435' # noqa: E501 |
| 12 |
) |
| 13 |
publisher = '\u041e\u041e\u041e \u00ab\u0416\u0443\u0440\u043d\u0430\u043b\u044b \u0438 \u0441\u0430\u0439\u0442\u044b "\u0424\u0430\u0431\u0440\u0438\u043a\u0430 \u043a\u043e\u043d\u0442\u0435\u043d\u0442\u0430 "\u0422\u043e\u0447\u043a\u0430 \u0420\u0443"\u00bb' # noqa: E501 |
| 14 |
category = 'magazine' |
| 15 |
cover_url = 'https://static.sobaka.ru/images/post/00/04/31/21/_rotator.jpg' |
| 16 |
language = 'ru' |
| 17 |
no_stylesheets = False |
| 18 |
remove_javascript = False |
| 19 |
auto_cleanup = False |
| 20 |
oldest_article = 7 |
| 21 |
max_articles_per_feed = 50 |
| 22 |
|
| 23 |
remove_tags_before = dict(name='div', attrs={'class': 'b-post-view__head'}) |
| 24 |
|
| 25 |
remove_tags_after = dict(name='div', attrs={'class': 'b-post-view__foot'}) |
| 26 |
|
| 27 |
remove_tags = [ |
| 28 |
dict(name='div', attrs={'class': 'b-post-view__telegram-promo'}), |
| 29 |
dict(name='div', attrs={'class': 'b-post-view__tgb'}), |
| 30 |
dict(name='div', attrs={'id': 'comments'}), |
| 31 |
dict(name='div', attrs={'class': 'b-post-view__section'}), |
| 32 |
dict(name='div', attrs={'class': 'b-post-view__share'}), |
| 33 |
dict(name='div', attrs={'class': 'b-post-view__details-col b-post-view__details-col--w1'}), |
| 34 |
] |
| 35 |
|
| 36 |
feeds = [('\u041d\u043e\u0432\u043e\u0441\u0442\u0438', 'https://www.sobaka.ru/rss/news.xml')] |
| 37 |
|
| 38 |
def preprocess_html(self, soup): |
| 39 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 40 |
img['src'] = img['data-src'] |
| 41 |
return soup |