Debian Codegraph @

recipes/frontline.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 from collections import defaultdict
4
5 from calibre.web.feeds.news import BasicNewsRecipe, classes
6
7
8 class Frontline(BasicNewsRecipe):
9 title = 'Frontline'
10 __author__ = 'unkn0wn'
11 description = 'Frontline, the fortnightly English magazine from the stable of The Hindu, has been a distinguished presence in the media world since 1984.'
12 language = 'en_IN'
13 no_stylesheets = True
14 remove_javascript = True
15 use_embedded_content = False
16 encoding = 'utf-8'
17 ignore_duplicate_articles = {'url'}
18 masthead_url = 'https://frontline.thehindu.com/theme/images/fl-online/frontline-logo.png'
19 remove_attributes = ['height', 'width']
20 resolve_internal_links = True
21 extra_css = '''
22 .environment, .publish-time, .author { font-size:small; color:#404040; }
23 .caption { font-size:small; text-align:center; }
24 img { display:block; margin:0 auto; }
25 .question {font-weight:bold;}
26 '''
27
28 keep_only_tags = [dict(name='div', attrs={'class': 'container article-section'})]
29
30 remove_tags = [
31 classes('breadcrumb comments-shares share-page article-video referpara slide-mobile title-patch hide-mobile related-stories'),
32 ]
33
34 def preprocess_html(self, soup):
35 for img in soup.findAll('img', attrs={'data-original': True}):
36 if img['data-original'].endswith('1x1_spacer.png'):
37 source = img.findPrevious('source', srcset=True)
38 img.extract()
39 if source:
40 source['src'] = source['srcset'].replace('_320', '_1200')
41 source.name = 'img'
42 else:
43 img['src'] = img['data-original']
44 for cap in soup.findAll(**classes('caption')):
45 cap.name = 'figcaption'
46 return soup
47
48 def postprocess_html(self, soup, first_fetch):
49 for src in soup.findAll('source'):
50 src.extract()
51 return soup
52
53 recipe_specific_options = {'issue': {'short': 'Enter the Issue Number you want to download\n(Volume-Issue format)', 'long': 'For example, 41-12'}}
54
55 def parse_index(self):
56 issue_url = 'https://frontline.thehindu.com/current-issue/'
57 d = self.recipe_specific_options.get('issue')
58 if d and isinstance(d, str):
59 issue_url = 'https://frontline.thehindu.com/magazine/issue/vol' + d
60
61 soup = self.index_to_soup(issue_url)
62
63 if cover := soup.find('div', attrs={'class': 'magazine'}):
64 self.cover_url = cover.find(**classes('sptar-image')).img['data-original'].replace('SQUARE_80', 'FREE_615')
65 self.log('Cover ', self.cover_url)
66 if desc := cover.find(**classes('sub-text')):
67 self.description = self.tag_to_string(desc)
68
69 feeds_dict = defaultdict(list)
70
71 mag = soup.find(**classes('current-issue-in-this-issue'))
72 for div in mag.findAll('div', attrs={'class': 'content'}):
73 a = div.find(**classes('title')).find('a')
74 url = a['href']
75 title = self.tag_to_string(a)
76 section = 'Articles'
77 if cat := div.find(**classes('label')):
78 section = self.tag_to_string(cat)
79 desc = ''
80
81 if art := div.find(**classes('sub-text')):
82 desc = self.tag_to_string(art)
83 if auth := div.find(**classes('author')):
84 desc = self.tag_to_string(auth) + ' | ' + desc
85 if not url or not title:
86 continue
87 self.log(section, '\n\t', title, '\n\t', desc, '\n\t\t', url)
88 feeds_dict[section].append({'title': title, 'url': url, 'description': desc})
89 return list(feeds_dict.items())