Debian Codegraph @

recipes/bar_and_bench.recipe

raw
1 #!/usr/bin/env python
2 from calibre.web.feeds.news import BasicNewsRecipe, prefixed_classes
3
4
5 class bar(BasicNewsRecipe):
6 title = 'Bar and Bench'
7 __author__ = 'unkn0wn'
8 description = (
9 'Bar & Bench is the premier online portal for Indian legal news. News, interviews,'
10 ' and columns related to the Supreme Court of India and the High Courts are published.'
11 )
12 language = 'en_IN'
13 masthead_url = 'https://gumlet.assettype.com/barandbench/2019-12/7a743b15-5d5d-44d7-96c2-13616780ed95/brand_2x.png'
14
15 no_stylesheets = True
16 remove_javascript = True
17 remove_attributes = ['height', 'width', 'style']
18
19 keep_only_tags = [prefixed_classes('text-story-m_header-details__ text-story-m_hero-image__ text-story-m_story-content-inner-wrapper__')]
20
21 remove_tags = [prefixed_classes('text-story-m_story-tags__ story-footer-module__metype__'), dict(name='svg')]
22
23 def preprocess_html(self, soup):
24 for img in soup.findAll('img', attrs={'data-src': True}):
25 img['src'] = img['data-src']
26 return soup
27
28 ignore_duplicate_articles = {'title'}
29 resolve_internal_links = True
30 remove_empty_feeds = True
31
32 def parse_index(self):
33 index = 'https://www.barandbench.com/'
34 sections = ['news', 'columns', 'interviews', 'law-firms', 'apprentice-lawyer', 'legal-jobs']
35 feeds = []
36 soup = self.index_to_soup(index)
37 for sec in sections:
38 section = sec.capitalize()
39 self.log(section)
40 articles = []
41 for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith(index + sec + '/')}):
42 url = a['href'].split('?')[0]
43 if url in {index + sec + '/', index + sec}:
44 continue
45 title = self.tag_to_string(a)
46 self.log('\t', title, '\n\t\t', url)
47 articles.append({'title': title, 'url': url})
48 if articles:
49 feeds.append((section, articles))
50 return feeds