Debian Codegraph @

recipes/demorgen_be.recipe

raw
1 #!/usr/bin/env python
2
3 """
4 demorgen.be
5 """
6
7 from calibre.web.feeds.news import BasicNewsRecipe
8
9
10 class DeMorganBe(BasicNewsRecipe):
11 title = 'De Morgen'
12 __author__ = 'Darko Miletic'
13 description = 'News from Belgium in Dutch'
14 oldest_article = 1
15 language = 'nl_BE'
16 encoding = 'utf-8'
17 max_articles_per_feed = 100
18 no_stylesheets = True
19 remove_attributes = ['style', 'height', 'width']
20 use_embedded_content = False
21 remove_javascript = True
22 ignore_duplicate_articles = {'url'}
23 masthead_url = 'https://www.demorgen.be/_next/static/media/demorgen_logo.dce579e2.svg'
24 cover_url = 'https://usercontent.one/wp/www.insidejazz.be/wp-content/uploads/2018/11/pic0143.png'
25
26 extra_css = '''
27 time, [data-test-id:"article-label"], [data-test-id:"article-sublabel"], [[data-test-id:"article-author"]] { font-size:small; }
28 [data-test-id:"header-intro"] { font-style: italic; }
29 '''
30
31 keep_only_tags = [
32 dict(name='article', attrs={'id': 'article-content'}),
33 ]
34
35 remove_tags = [dict(name=['iframe', 'aside'])]
36
37 remove_tags_after = [
38 dict(name='div', attrs={'class': 'paywall'}),
39 ]
40
41 feeds = [
42 ('In het nieuws', 'https://www.demorgen.be/in-het-nieuws/rss.xml'),
43 ('Niet te missen', 'https://www.demorgen.be/niet-te-missen/rss.xml'),
44 ('Beter leven', 'http://www.demorgen.be/beter-leven/rss.xml'),
45 ('Crisis Midden-Oosten', 'http://www.demorgen.be/aanval-op-israel/rss.xml'),
46 ('Koken met de Morgen', 'http://www.demorgen.be/koken-met-de-morgen/rss.xml'),
47 ('Meningen', 'http://www.demorgen.be/meningen/rss.xml'),
48 ('Politiek', 'http://www.demorgen.be/politiek/rss.xml'),
49 ('TV & Cultuur', 'http://www.demorgen.be/tv-cultuur/rss.xml'),
50 ('Oorlog in Oekraine', 'http://www.demorgen.be/oorlog-in-oekraine/rss.xml'),
51 ('Tech & Wetenschap', 'http://www.demorgen.be/tech-wetenschap/rss.xml'),
52 ('Sport', 'http://www.demorgen.be/sport/rss.xml'),
53 ('Podcasts', 'http://www.demorgen.be/podcasts/rss.xml'),
54 ('Puzzels', 'http://www.demorgen.be/puzzels/rss.xml'),
55 ('Cartoons', 'http://www.demorgen.be/puzzels-cartoons/rss.xml'),
56 ('Achter de schermen', 'http://www.demorgen.be/achter-de-schermen/rss.xml'),
57 ('Best gelezen', 'http://www.demorgen.be/popular/rss.xml'),
58 ('Nieuws', 'http://www.demorgen.be/nieuws/rss.xml'),
59 ]
60
61 def preprocess_html(self, soup):
62 for img in soup.findAll('img', attrs={'srcset': True}):
63 img['src'] = img['srcset'].split()[0]
64 return soup