Debian Codegraph @

recipes/dr_dk.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 # License: GPLv3 Copyright: 2023, Joel Davies <joeld.dev at gmail.com>
4
5 from calibre.web.feeds.news import BasicNewsRecipe
6
7
8 class DRNyheder(BasicNewsRecipe):
9 # Feeds are found here: https://www.dr.dk/nyheder/dr-nyheder-som-rss-feed
10 feeds = [
11 ('Seneste nyt', 'https://www.dr.dk/nyheder/service/feeds/senestenyt'),
12 ('Indland', 'https://www.dr.dk/nyheder/service/feeds/indland'),
13 ('Udland', 'https://www.dr.dk/nyheder/service/feeds/udland'),
14 ('Penge', 'https://www.dr.dk/nyheder/service/feeds/penge'),
15 ('Politik', 'https://www.dr.dk/nyheder/service/feeds/politik'),
16 # ('Sporten', 'https://www.dr.dk/nyheder/service/feeds/sporten'),
17 # ('Seneste sport', 'https://www.dr.dk/nyheder/service/feeds/senestesport'),
18 ('Viden', 'https://www.dr.dk/nyheder/service/feeds/viden'),
19 ('Kultur', 'https://www.dr.dk/nyheder/service/feeds/kultur'),
20 ('Musik', 'https://www.dr.dk/nyheder/service/feeds/musik'),
21 ('Mit Liv', 'https://www.dr.dk/nyheder/service/feeds/mitliv'),
22 ('Mad', 'https://www.dr.dk/nyheder/service/feeds/mad'),
23 ('Vejret', 'https://www.dr.dk/nyheder/service/feeds/vejret'),
24 ('Regionale', 'https://www.dr.dk/nyheder/service/feeds/regionale'),
25 ('DR Hovedstadsområdet', 'https://www.dr.dk/nyheder/service/feeds/regionale/kbh'),
26 ('DR Bornholm', 'https://www.dr.dk/nyheder/service/feeds/regionale/bornholm'),
27 ('DR Syd og Sønderjylland', 'https://www.dr.dk/nyheder/service/feeds/regionale/syd'),
28 ('DR Fyn', 'https://www.dr.dk/nyheder/service/feeds/regionale/fyn'),
29 ('DR Midt- og Vestjylland', 'https://www.dr.dk/nyheder/service/feeds/regionale/vest'),
30 ('DR Nordjylland', 'https://www.dr.dk/nyheder/service/feeds/regionale/nord'),
31 ('DR Trekantområdet', 'https://www.dr.dk/nyheder/service/feeds/regionale/trekanten'),
32 ('DR Sjælland', 'https://www.dr.dk/nyheder/service/feeds/regionale/sjaelland'),
33 ('DR Østjylland', 'https://www.dr.dk/nyheder/service/feeds/regionale/oestjylland'),
34 ]
35
36 title = 'DR Nyheder'
37 __author__ = 'Joel Davies'
38 publisher = 'DR Nyheder'
39 description = 'Her finder du nyheder fra DR.'
40 category = 'news, politics, money, culture, sport, science, Denmark'
41 publication_type = 'newspaper'
42 encoding = 'utf8'
43 language = 'da'
44 oldest_article = 4 # 2 might be best
45 max_articles_per_feed = 50 # 100 better, this is just for testing
46 no_stylesheets = True
47 use_embedded_content = False
48 auto_cleanup = False
49 remove_empty_feeds = True
50 ignore_duplicate_articles = {'title', 'url'}
51 simultaneous_downloads = 20
52 compress_news_images = True
53 masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/1/18/DR_logo.svg/1024px-DR_logo.svg.png'
54
55 extra_css = '''
56 .dre-byline__contributions {
57 margin-bottom: 10px;
58 }
59
60 .dre-byline__contributions div {
61 display: inline;
62 }
63
64 .dre-byline__contribution + .dre-byline__contribution:before {
65 display: inline;
66 content: ", ";
67 }
68
69 .dre-standard-article__figure {
70 margin-bottom: 30px;
71 text-align: center;
72 }
73
74 .dre-picture {
75 margin-bottom: 10px;
76 }
77
78 .dre-picture__image {
79 max-width: 100%;
80 height: auto;
81 }
82
83 .dre-standard-article__figure-caption {
84 font-size: .85em;
85 color: #575757;
86 }
87 '''
88
89 # Skip articles with /stories/ URL as these are Instagram story-style interactive pieces that play videos
90 # Also DRTV as these are just links to the live TV channel
91 def preprocess_raw_html(self, raw_html, url):
92 if '/stories/' in url or '/drtv/' in url:
93 self.abort_article('Skipping unsupported article type')
94 return raw_html
95
96 # Generate cover from the first image on the dr.dk homepage
97 def get_cover_url(self):
98 cover_url = None
99 soup = self.index_to_soup('https://www.dr.dk/')
100 main_content = soup.find('ul', attrs={'class': 'dre-grid-layout'})
101 cover_item = main_content.find('img')
102 if cover_item:
103 cover_url = cover_item['src']
104 return cover_url
105
106 keep_only_tags = [
107 dict(name='h1', attrs={'class': 'dre-article-title__heading'}), # Title
108 dict(name='div', attrs={'class': 'dre-article-byline'}), # Author
109 dict(name='figure', attrs={'class': 'dre-standard-article__figure'}), # Comment out to remove images
110 dict(name='p', attrs={'class': 'dre-article-body-paragraph'}), # All body text of the article
111 dict(name='article', attrs={'itemtype': 'http://schema.org/NewsArticle'}),
112 # dict(name="h1", attrs={'class': 'hydra-latest-news-page-short-news__title'}),
113 # dict(name="p", attrs={'class': 'hydra-latest-news-page-short-news__paragraph'}),
114 # dict(name="div", attrs={'class': 'dre-speech'}),
115 # dict(name="div", attrs={'itemprop': 'author'})
116 ]
117
118 remove_tags = [
119 dict(name='ol', attrs={'class': 'hydra-latest-news-page__list'}),
120 dict(
121 name='div',
122 attrs={
123 'class': [
124 'hydra-latest-news-page-short-news__share',
125 'hydra-latest-news-page-short-news__a11y-container',
126 'hydra-latest-news-page-short-news__meta',
127 'hydra-latest-news-page-short-news__image-slider',
128 'dre-byline__dates',
129 ]
130 },
131 ),
132 dict(name='source'),
133 # dict(name='menu', attrs={'class': 'share'}),
134 # dict(name='menu', attrs={'class': 'dr-site-share-horizontal'}),
135 ]
136
137 # Fixes images having the wrong aspect ratio
138 remove_attributes = ['width', 'height']