Debian Codegraph @

recipes/tjournal.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 TJournal(BasicNewsRecipe):
8 title = 'TJournal'
9 __author__ = 'bug_me_not (with fixes by bugmen00t)'
10 description = 'TJournal: издание о медиа, технологиях и трендах'
11 publisher = 'tjournal.ru'
12 category = 'news'
13 language = 'ru'
14 no_stylesheets = False
15 remove_javascript = True
16 oldest_article = 30
17 max_articles_per_feed = 100
18 cover_url = 'https://tjournal.ru/static/build/tjournal.ru/images/search_logo.png'
19
20 remove_tags_before = dict(name='div', attrs={'class': 'content-title"'})
21
22 remove_tags_after = dict(name='div', attrs={'class': 'content-footer content-footer--full l-island-a'})
23
24 remove_tags = [
25 dict(name='div', attrs={'class': 'content-footer content-footer--full l-island-a'}),
26 dict(name='div', attrs={'air-module': 'module.distributionFloating'}),
27 dict(name='span', attrs={'class': 'content-editorial-tick'}),
28 dict(name='vue'),
29 dict(name='div', attrs={'class': 'comments'}),
30 dict(name='div', attrs={'class': 'propaganda'}),
31 dict(name='div', attrs={'class': 'propaganda propaganda--with-footer'}),
32 dict(name='div', attrs={'air-module': 'module.gallery'}),
33 dict(name='div', attrs={'class': 'content-container'}),
34 dict(name='div', attrs={'class': 'content-header__item content-header-number'}),
35 dict(name='span', attrs={'class': 'views__value'}),
36 dict(name='span', attrs={'class': 'views__label'}),
37 ]
38
39 feeds = [
40 ('\u041f\u043e\u043f\u0443\u043b\u044f\u0440\u043d\u043e\u0435', 'https://tjournal.ru/rss'),
41 ('\u041d\u043e\u0432\u043e\u0441\u0442\u0438', 'https://tjournal.ru/rss/news'),
42 ('\u0421\u0432\u0435\u0436\u0435\u0435', 'https://tjournal.ru/rss/new'),
43 ('\u0422\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438', 'https://tjournal.ru/rss/tech'),
44 ('\u0420\u0430\u0437\u0431\u043e\u0440\u044b', 'https://tjournal.ru/rss/analysis'),
45 ('\u0418\u043d\u0442\u0435\u0440\u043d\u0435\u0442', 'https://tjournal.ru/rss/internet'),
46 ]
47
48 def preprocess_html(self, soup):
49 for img in soup.findAll('img', attrs={'data-image-src': True}):
50 img['src'] = img['data-image-src']
51 return soup