Debian Codegraph @

recipes/the_diplomat.recipe

raw
1 #!/usr/bin/env python
2
3 from calibre.web.feeds.news import BasicNewsRecipe, classes
4
5
6 class Diplomat(BasicNewsRecipe):
7 title = 'The Diplomat'
8 description = 'The Diplomat is the premier international current-affairs magazine for the Asia-Pacific region. READ THE DIPLOMAT, KNOW THE ASIA-PACIFIC'
9 language = 'en'
10 __author__ = 'unkn0wn'
11 oldest_article = 14 # days
12 max_articles_per_feed = 100
13 encoding = 'utf-8'
14 use_embedded_content = False
15 no_stylesheets = True
16 remove_attributes = ['style', 'height', 'width']
17 masthead_url = 'https://thediplomat.com/wp-content/themes/td_theme_v3/assets/logo/diplomat_logo_black.svg'
18 ignore_duplicate_articles = {'url'}
19 extra_css = '''
20 #td-meta { font-size: x-small }
21 #td-story-authors { font-size: small}
22 #td-story-image{font-size: small; font-style: italic;}
23 [id^="caption-attachment"] {font-size: small; font-style: italic;}
24 '''
25
26 def get_cover_url(self):
27 soup = self.index_to_soup('https://thediplomat.com')
28 tag = soup.find(attrs={'class': 'td-nav-mag'})
29 if tag:
30 url = tag.find('img')['src'].split('/')[-1]
31 self.cover_url = 'https://magazine.thediplomat.com/media/1080/' + url
32 # /ads/magazine/cover/td-mag-s-1/issue_89_cover.jpg
33 # https://magazine.thediplomat.com/media/1080/issue_89_cover.jpg
34 return super().get_cover_url()
35
36 keep_only_tags = [
37 dict(name='header', attrs={'id': 'td-story-head'}),
38 classes('td-media--story td-prose td-story-magazine__link td-authors'),
39 ]
40
41 remove_tags = [
42 dict(name='aside', attrs={'id': 'td-box-newsletter'}),
43 classes('td-share td-ad td-ad-inline-txt'),
44 ]
45
46 feeds = [
47 ('Features', 'https://thediplomat.com/category/features/feed'),
48 ('Interviews', 'https://thediplomat.com/category/interviews/feed'),
49 ('Magazine Preview', 'https://thediplomat.com/category/magazine/feed'),
50 # REGIONS
51 ('Central Asia', 'https://thediplomat.com/regions/central-asia/feed'),
52 ('East Asia', 'https://thediplomat.com/regions/east-asia/feed'),
53 ('Oceania', 'https://thediplomat.com/regions/oceania-region/feed'),
54 ('South Asia', 'https://thediplomat.com/regions/south-asia/feed'),
55 ('South East Asia', 'https://thediplomat.com/regions/southeast-asia/feed'),
56 # TOPICS
57 ('Diplomacy', 'https://thediplomat.com/topics/diplomacy/feed'),
58 ('Economy', 'https://thediplomat.com/topics/economy/feed'),
59 ('Environment', 'https://thediplomat.com/topics/environment/feed'),
60 ('Opinion', 'https://thediplomat.com/topics/opinion/feed'),
61 ('Politics', 'https://thediplomat.com/topics/politics/feed'),
62 ('Security', 'https://thediplomat.com/topics/security/feed'),
63 ('Society', 'https://thediplomat.com/topics/society/feed'),
64 ]
65
66 def preprocess_html(self, soup):
67 for img in soup.findAll('img', attrs={'src': True}):
68 img['src'] = img['src'].replace('td-story-s-1', 'td-story-s-2')
69 return soup