Debian Codegraph @

recipes/popscience.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 # License: GPLv3 Copyright: 2020, Kovid Goyal <kovid at kovidgoyal.net>
4
5 from __future__ import absolute_import, division, print_function, unicode_literals
6
7 from calibre.web.feeds.news import BasicNewsRecipe
8
9
10 def classes(classes):
11 q = frozenset(classes.split(' '))
12 return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
13
14
15 class AdvancedUserRecipe1282101454(BasicNewsRecipe):
16 title = 'Popular Science'
17 language = 'en'
18 __author__ = 'Kovid Goyal'
19 description = 'Popular Science'
20 publisher = 'Popular Science'
21 max_articles_per_feed = 100
22 ignore_duplicate_articles = {'url'}
23 no_stylesheets = True
24 keep_only_tags = [
25 classes('Article-header Article-excerpt Article-author Article-thumbnail Article-bodyText article-title article-dek article-paragraph articlebody'),
26 ]
27 remove_tags = [dict(name='section', attrs={'class': ['recurrent-share']})]
28
29 def parse_section_index(self, slug):
30 url = 'https://www.popsci.com/{}/'.format(slug)
31 self.log('Section:', url)
32 soup = self.index_to_soup(url)
33 main = soup.find(**classes('category-content-wrapper lg:pb-12'))
34 if main is None:
35 return
36 for div in main.findAll(**classes('card-post')):
37 a = div.find('a', href=True, **classes('card-post-image-link'))
38 url = a['href']
39 tdiv = div.find(**classes('card-post-title')).find(**classes('mobile'))
40 title = self.tag_to_string(tdiv)
41 desc = ''
42 dek = div.find(**classes('card-post-excerpt'))
43 if dek is not None:
44 desc = self.tag_to_string(dek)
45 self.log(' ', title, url)
46 yield {'title': title, 'url': url, 'description': desc}
47
48 def parse_index(self):
49 sections = []
50 for slug, title in {
51 'science': 'Science',
52 'technology': 'Technology',
53 'diy': 'DIY',
54 'reviews': 'Reviews',
55 }.items():
56 self.log('slug:', slug)
57 articles = list(self.parse_section_index(slug))
58 if articles:
59 sections.append((title, articles))
60 return sections
61
62 def preprocess_html(self, soup):
63 for img in soup.findAll('img', attrs={'data-medsrc': True}):
64 img['src'] = img['data-medsrc']
65 return soup