Debian Codegraph @

recipes/spiegel_int.recipe

raw
1 """
2 spiegel.de
3 """
4
5 from calibre.web.feeds.news import BasicNewsRecipe
6
7
8 class Spiegel_int(BasicNewsRecipe):
9 title = 'Spiegel Online International'
10 __author__ = 'unkn0wn'
11 description = "Daily news, analysis and opinion from Europe's leading newsmagazine and Germany's top news Web site"
12 oldest_article = 7
13 max_articles_per_feed = 100
14 language = 'en_DE'
15 no_stylesheets = True
16 use_embedded_content = False
17 encoding = 'utf-8'
18 publisher = 'SPIEGEL ONLINE GmbH'
19 category = 'news, politics, Germany'
20 publication_type = 'magazine'
21 remove_empty_feeds = True
22 remove_attributes = ['style', 'height', 'width']
23 ignore_duplicate_articles = {'url'}
24 masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/0/06/Logo-Der-Spiegel-de.png'
25
26 conversion_options = {'comments': description, 'tags': category, 'language': language, 'publisher': publisher}
27
28 def get_cover_url(self):
29 soup = self.index_to_soup('https://www.spiegel.de/spiegel/print/')
30 div = soup.find('div', attrs={'data-component': 'MagazineImage'})
31 citem = div.find('img', attrs={'data-src': True})['data-src'].replace('260', '800')
32 return citem
33
34 keep_only_tags = [dict(name='article')]
35
36 remove_tags = [
37 dict(name='section', attrs={'data-app-hidden': True}),
38 dict(name='div', attrs={'data-issue-context-hidden': True}),
39 dict(name='div', attrs={'data-area': 'related_articles'}),
40 dict(name='div', attrs={'data-component': 'HTMLEmbed'}),
41 dict(name=['footer', 'button', 'svg']),
42 ]
43
44 extra_css = '''
45 time{font-size:small;}
46 [data-area="quote"]{text-align:center; color:#404040;}
47 #fig-c{font-size:small; text-align:center;}
48 '''
49
50 feeds = [
51 ('World', 'https://www.spiegel.de/international/world/index.rss'),
52 ('Europe', 'https://www.spiegel.de/international/europe/index.rss'),
53 ('Germany', 'https://www.spiegel.de/international/germany/index.rss'),
54 ('Business', 'https://www.spiegel.de/international/business/index.rss'),
55 ('Zeitgeist', 'https://www.spiegel.de/international/zeitgeist/index.rss'),
56 ('Tomorrow', 'https://www.spiegel.de/international/tomorrow/index.rss'),
57 ('Others', 'http://www.spiegel.de/international/index.rss'),
58 ]
59
60 def preprocess_html(self, soup):
61 for img in soup.findAll('img', attrs={'data-src': True}):
62 img['src'] = img['data-src']
63 for fig in soup.findAll('figcaption'):
64 fig['id'] = 'fig-c'
65 return soup