Debian Codegraph @

recipes/denik.to.recipe

raw
1 import re
2
3 from calibre.web.feeds.recipes import BasicNewsRecipe
4
5
6 class todenikRecipe(BasicNewsRecipe):
7 __author__ = 'bubak'
8 title = 'Deník To'
9 description = 'denik.to'
10 oldest_article = 1
11 max_articles_per_feed = 20
12
13 feeds = [('Deník TO', 'https://denik.to/rss')]
14
15 language = 'cs'
16 cover_url = 'https://denik.to/wp-content/uploads/2023/06/logo.svg'
17 remove_javascript = True
18 no_stylesheets = True
19 use_embedded_content = False
20
21 ignore_duplicate_articles = {'title', 'url'}
22
23 remove_attributes = []
24 remove_tags_after = dict(name='div', attrs={'id': 'comments'})
25 remove_tags = [
26 dict(name='div', attrs={'class': ['picture', 'top-tags', 'caption']}),
27 dict(name='div', attrs={'class': re.compile(r'hustle|sidebar-widget|breadcrumbs|inline-post|byline', re.IGNORECASE)}),
28 dict(name='div', attrs={'id': 'comments'}),
29 dict(name='figure'),
30 dict(name='aside'),
31 dict(name='footer'),
32 ]
33
34 keep_only_tags = [dict(name='main')]
35 preprocess_regexps = [
36 (re.compile(r'<a\s[^>]*>(<[^>]*>)*([^<]*)(<[^>]*>)*</a>', re.DOTALL | re.IGNORECASE), lambda match: match.group(2)),
37 ]
38
39 def get_browser(self, *a, **kw):
40 from calibre import browser
41
42 kw['user_agent'] = 'Silver'
43 return browser(*a, **kw)