Debian Codegraph @

recipes/theprint.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 # License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
4
5 from __future__ import absolute_import, division, print_function, unicode_literals
6
7 from collections import defaultdict
8
9 from calibre.web.feeds.news import BasicNewsRecipe
10
11
12 def classes(classes):
13 q = frozenset(classes.split(' '))
14 return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
15
16
17 class ThePrint(BasicNewsRecipe):
18 title = 'The Print'
19 __author__ = 'Kovid Goyal'
20 description = 'News and current affairs in India'
21 language = 'en_IN'
22
23 no_stylesheets = True
24 ignore_duplicate_articles = {'url'}
25 remove_attributes = ['style']
26
27 keep_only_tags = [classes('td-post-title td-post-content')]
28
29 remove_tags = [
30 dict(name='button'),
31 classes('fontsize_Btn postBtm'),
32 ]
33
34 def parse_index(self):
35 soup = self.index_to_soup('https://theprint.in/')
36 current_section = 'Unknown'
37 ans = defaultdict(list)
38 secs = []
39 for x in soup.findAll(['h3', 'h4'], attrs={'class': True}):
40 cls = x['class']
41 if 'td-block-title' in cls:
42 current_section = self.tag_to_string(x)
43 secs.append(current_section)
44 self.log(current_section)
45 elif 'entry-title' in cls:
46 h3 = x
47 title = self.tag_to_string(h3)
48 url = h3.find('a')['href']
49 desc = ''
50 dnode = h3.parent.find(**classes('td-excerpt'))
51 if dnode:
52 desc = self.tag_to_string(dnode)
53 self.log('\t', title)
54 ans[current_section].append({'title': title, 'url': url, 'description': desc})
55 ret = []
56 for sec in secs:
57 if sec == 'On Camera':
58 continue
59 arts = ans[sec]
60 if arts:
61 ret.append((sec, arts))
62 return ret