Debian Codegraph @

recipes/newtab.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3
4 from calibre.web.feeds.news import BasicNewsRecipe
5
6
7 class NewTab(BasicNewsRecipe):
8 title = '\u041d\u043e\u0432\u0430\u044f \u0432\u043a\u043b\u0430\u0434\u043a\u0430'
9 __author__ = 'bugmen00t'
10 description = '\u041f\u043b\u043e\u0449\u0430\u0434\u043a\u0430 \u0434\u043b\u044f \u043f\u0443\u0431\u043b\u0438\u043a\u0430\u0446\u0438\u0438 \u0440\u0435\u043f\u043e\u0440\u0442\u0430\u0436\u0435\u0439 \u0438 \u0437\u0430\u043c\u0435\u0442\u043e\u043a \u043e \u0442\u043e\u043c, \u043a\u0430\u043a \u043c\u0435\u043d\u044f\u044e\u0442\u0441\u044f \u0440\u0435\u0433\u0438\u043e\u043d\u044b \u0420\u043e\u0441\u0441\u0438\u0438 \u043f\u043e\u0441\u043b\u0435 24 \u0444\u0435\u0432\u0440\u0430\u043b\u044f 2022 \u0433\u043e\u0434\u0430.' # noqa: E501
11 publisher = '\u041c\u0438\u0445\u0430\u0438\u043b \u0414\u0430\u043d\u0438\u043b\u043e\u0432\u0438\u0447'
12 category = 'blog'
13 cover_url = 'https://static.tildacdn.com/tild3765-3961-4337-b366-323437626331/thenewtab-sn.jpg'
14 language = 'ru'
15 no_stylesheets = True
16 remove_javascript = False
17 auto_cleanup = False
18 oldest_article = 30
19 max_articles_per_feed = 10
20
21 remove_tags_before = dict(name='h1')
22
23 remove_tags = [
24 dict(name='div', attrs={'class': 't-popup'}),
25 dict(name='div', attrs={'class': 't185'}),
26 dict(name='div', attrs={'class': 't403'}),
27 dict(name='div', attrs={'class': 't404'}),
28 dict(name='div', attrs={'class': 't134'}),
29 dict(name='div', attrs={'class': 'sp-form-fields-wrapper'}),
30 ]
31
32 feeds = [('\u041d\u043e\u0432\u0430\u044f \u0432\u043a\u043b\u0430\u0434\u043a\u0430', 'https://thenewtab.io/feed/')]
33
34 def preprocess_html(self, soup):
35 for img in soup.findAll('img', attrs={'data-original': True}):
36 img['src'] = img['data-original']
37 return soup