Debian Codegraph @

recipes/deutsche_welle_ru.recipe

raw
1 from calibre.web.feeds.news import BasicNewsRecipe, classes
2
3
4 class DeutscheWelle(BasicNewsRecipe):
5 title = 'Deutsche Welle \u043d\u0430 \u0440\u0443\u0441\u0441\u043a\u043e\u043c'
6 description = '\u0420\u0443\u0441\u0441\u043a\u0430\u044f \u0440\u0435\u0434\u0430\u043a\u0446\u0438\u044f Deutsche Welle: \u043d\u043e\u0432\u043e\u0441\u0442\u0438, \u0430\u043d\u0430\u043b\u0438\u0442\u0438\u043a\u0430, \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0438 \u0438 \u0440\u0435\u043f\u043e\u0440\u0442\u0430\u0436\u0438 \u0438\u0437 \u0413\u0435\u0440\u043c\u0430\u043d\u0438\u0438 \u0438 \u0415\u0432\u0440\u043e\u043f\u044b, \u043d\u0435\u043c\u0435\u0446\u043a\u0438\u0439 \u0438 \u0435\u0432\u0440\u043e\u043f\u0435\u0439\u0441\u043a\u0438\u0439 \u0432\u0437\u0433\u043b\u044f\u0434 \u043d\u0430 \u0441\u043e\u0431\u044b\u0442\u0438\u044f \u0432 \u0420\u043e\u0441\u0441\u0438\u0438 \u0438 \u043c\u0438\u0440\u0435, \u043f\u0440\u0430\u043a\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0441\u043e\u0432\u0435\u0442\u044b \u0434\u043b\u044f \u0442\u0443\u0440\u0438\u0441\u0442\u043e\u0432 \u0438 \u0442\u0435\u0445, \u043a\u0442\u043e \u0436\u0435\u043b\u0430\u0435\u0442 \u0443\u0447\u0438\u0442\u044c\u0441\u044f \u0438\u043b\u0438 \u0440\u0430\u0431\u043e\u0442\u0430\u0442\u044c \u0432 \u0413\u0435\u0440\u043c\u0430\u043d\u0438\u0438 \u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u0441\u0442\u0440\u0430\u043d\u0430\u0445 \u0415\u0432\u0440\u043e\u0441\u043e\u044e\u0437\u0430.' # noqa: E501
7 __author__ = 'bugmen00t, unkn0wn'
8 publication_type = 'newspaper'
9 oldest_article = 2
10 max_articles_per_feed = 100
11 language = 'ru'
12 # cover_url = 'https://www.dw.com/cssi/dwlogo-print.gif'
13
14 remove_javascript = True
15 no_stylesheets = True
16 remove_empty_feeds = True
17 ignore_duplicate_articles = {'title', 'url'}
18 remove_attributes = ['height', 'width', 'style']
19
20 recipe_specific_options = {
21 'days': {
22 'short': 'Oldest article to download from this news source. In days ',
23 'long': 'For example, 0.5, gives you articles from the past 12 hours',
24 'default': str(oldest_article),
25 }
26 }
27
28 def __init__(self, *args, **kwargs):
29 BasicNewsRecipe.__init__(self, *args, **kwargs)
30 d = self.recipe_specific_options.get('days')
31 if d and isinstance(d, str):
32 self.oldest_article = float(d)
33
34 def preprocess_html(self, soup):
35 for img in soup.findAll('img', srcset=True):
36 img['src'] = img['srcset'].split()[6]
37 return soup
38
39 keep_only_tags = [dict(name='article')]
40
41 remove_tags = [dict(name=['footer', 'source']), dict(attrs={'data-tracking-name': 'sharing-icons-inline'}), classes('kicker advertisement vjs-wrapper')]
42
43 feeds = [
44 ('\u0412\u0435\u0441\u044c \u0441\u0430\u0439\u0442', 'https://rss.dw.com/xml/rss-ru-all'),
45 ('\u041d\u043e\u0432\u043e\u0441\u0442\u0438', 'http://rss.dw.de/xml/rss-ru-news'),
46 ('\u041f\u043e\u043b\u0438\u0442\u0438\u043a\u0430 \u0438 \u043e\u0431\u0449\u0435\u0441\u0442\u0432\u043e', 'http://rss.dw.de/xml/rss-ru-pol'),
47 ('\u042d\u043a\u043e\u043d\u043e\u043c\u0438\u043a\u0430', 'http://rss.dw.de/xml/rss-ru-eco'),
48 ('\u0410\u0432\u0442\u043e\u043c\u043e\u0431\u0438\u043b\u044c', 'http://rss.dw.de/xml/rss-ru-auto'),
49 (
50 '\u041a\u0443\u043b\u044c\u0442\u0443\u0440\u0430 \u0438 \u0441\u0442\u0438\u043b\u044c \u0436\u0438\u0437\u043d\u0438',
51 'http://rss.dw.de/xml/rss-ru-cul',
52 ),
53 ('\u0420\u043e\u0441\u0441\u0438\u044f', 'http://rss.dw.de/xml/rss-ru-rus'),
54 ('\u0413\u0435\u0440\u043c\u0430\u043d\u0438\u044f', 'http://rss.dw.de/xml/rss-ru-ger'),
55 ('\u0415\u0432\u0440\u043e\u043f\u0430', 'http://rss.dw.de/xml/rss-ru-eu'),
56 ('\u0411\u0435\u043b\u0430\u0440\u0443\u0441\u044c', 'http://rss.dw.de/xml/rss-ru-bel'),
57 ('\u0423\u0447\u0435\u0431\u0430 \u0438 \u043a\u0430\u0440\u044c\u0435\u0440\u0430', 'http://rss.dw.de/xml/rss-ru-campus-karriere'),
58 ('\u0423\u0447\u0435\u0431\u0430 ', 'http://rss.dw.de/xml/rss-ru-campus'),
59 ('\u041a\u0430\u0440\u044c\u0435\u0440\u0430 ', 'http://rss.dw.de/xml/rss-ru-karriere'),
60 ('\u0422\u0443\u0440\u0438\u0441\u0442\u0443 \u043d\u0430 \u0437\u0430\u043c\u0435\u0442\u043a\u0443', 'http://rss.dw.de/xml/rss-ru-discover-ger'),
61 ]