Debian Codegraph @

recipes/scroll.recipe

raw
1 #!/usr/bin/env python
2 from calibre.web.feeds.news import BasicNewsRecipe, classes
3
4
5 class scroll(BasicNewsRecipe):
6 title = 'Scroll.in'
7 __author__ = 'unkn0wn'
8 description = (
9 'The leading destination for original reporting on news, politics, and culture in India. '
10 'Our award-winning team of journalists brings readers insightful analysis and opinion on the day’s '
11 'headlines alongside a fresh mix of features on music, books, and cinema.'
12 )
13 language = 'en_IN'
14 masthead_url = 'https://scroll.in/static/assets/scroll-logo.0f68c78dd023e2598248ea107feba562.003.svg'
15
16 no_stylesheets = True
17 remove_javascript = True
18
19 ignore_duplicate_articles = {'title', 'url'}
20 remove_attributes = ['style', 'height', 'width']
21
22 extra_css = '''
23 .orange-tag, .article-meta-container { font-size:small; }
24 .featured-image, .cms-block-image { text-align:center; font-size:small; }
25 '''
26
27 keep_only_tags = [dict(name='header'), classes('featured-image article-body')]
28
29 remove_tags = [classes('comments-entry-point-meta')]
30
31 def parse_index(self):
32 index = 'https://scroll.in/'
33 sections = ['article', 'magazine']
34 feeds = []
35 soup = self.index_to_soup(index)
36 for sec in sections:
37 section = sec.capitalize()
38 self.log(section)
39 articles = []
40 for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith(index + sec + '/')}):
41 url = a['href'].split('?')[0]
42 if url in {index + sec + '/', index + sec}:
43 continue
44 title = self.tag_to_string(a)
45 self.log('\t', title, '\n\t\t', url)
46 articles.append({'title': title, 'url': url})
47 if articles:
48 feeds.append((section, articles))
49 return feeds
50
51 def populate_article_metadata(self, article, soup, first):
52 if soup.find('h2'):
53 article.summary = article.text_summary = self.tag_to_string(soup.find('h2'))