Debian Codegraph @

recipes/wired_daily.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 __license__ = 'GPL v3'
4 __copyright__ = '2014, Darko Miletic <darko.miletic at gmail.com>'
5 '''
6 www.wired.com
7 '''
8
9 from calibre import browser
10 from calibre.web.feeds.news import BasicNewsRecipe
11
12
13 def classes(classes):
14 q = frozenset(classes.split(' '))
15 return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
16
17
18 class WiredDailyNews(BasicNewsRecipe):
19 title = 'Wired Daily Edition'
20 __author__ = 'Darko Miletic, PatStapleton(update 2020-05-24)'
21 description = (
22 'Wired is a full-color monthly American magazine, published in both print'
23 ' and online editions, that reports on how emerging technologies affect culture,'
24 ' the economy and politics.'
25 )
26 publisher = 'Conde Nast'
27 category = 'news, IT, computers, technology'
28 oldest_article = 2
29 max_articles_per_feed = 200
30 no_stylesheets = True
31 encoding = 'utf-8'
32 use_embedded_content = False
33 language = 'en'
34 ignore_duplicate_articles = {'url'}
35 remove_empty_feeds = True
36 publication_type = 'newsportal'
37 extra_css = '''
38 .entry-header{
39 text-transform: uppercase;
40 vertical-align: baseline;
41 display: inline;
42 }
43 ul li{display: inline}
44 '''
45
46 recipe_specific_options = {
47 'days': {
48 'short': 'Oldest article to download from this news source. In days ',
49 'long': 'For example, 0.5, gives you articles from the past 12 hours',
50 'default': str(oldest_article),
51 }
52 }
53
54 def __init__(self, *args, **kwargs):
55 BasicNewsRecipe.__init__(self, *args, **kwargs)
56 d = self.recipe_specific_options.get('days')
57 if d and isinstance(d, str):
58 self.oldest_article = float(d)
59
60 keep_only_tags = [
61 classes('content-header lead-asset article__body'),
62 ]
63 remove_tags = [
64 classes(
65 'related-cne-video-component tags-component callout--related-list iframe-embed podcast_storyboard'
66 ' inset-left-component ad consumer-marketing-component social-icons'
67 ),
68 dict(name=['meta', 'link', 'aside']),
69 dict(id=['sharing', 'social', 'article-tags', 'sidebar']),
70 ]
71 remove_attributes = ['srcset']
72 handle_gzip = True
73
74 feeds = [
75 ('Top Stories', 'https://www.wired.com/feed/rss'),
76 ('Business', 'https://www.wired.com/feed/category/business/latest/rss'),
77 ('Culture', 'https://www.wired.com/feed/category/culture/latest/rss'),
78 ('Gear', 'https://www.wired.com/feed/category/gear/latest/rss'),
79 ('Ideas', 'https://www.wired.com/feed/category/ideas/latest/rss'),
80 ('Science', 'https://www.wired.com/feed/category/science/latest/rss'),
81 ('Security', 'https://www.wired.com/feed/category/security/latest/rss'),
82 ('Transportation', 'https://www.wired.com/feed/category/transportation/latest/rss'),
83 ('Backchannel', 'https://www.wired.com/feed/category/backchannel/latest/rss'),
84 ('WIRED Guides', 'https://www.wired.com/feed/tag/wired-guide/latest/rss'),
85 # (u'Photo', u'https://www.wired.com/feed/category/photo/latest/rss'),
86 ]
87
88 def get_article_url(self, article):
89 return article.get('link', None)
90
91 # Wired changes the content it delivers based on cookies, so the
92 # following ensures that we send no cookies
93 def get_browser(self, *args, **kwargs):
94 return self
95
96 def clone_browser(self, *args, **kwargs):
97 return self.get_browser()
98
99 def open_novisit(self, *args, **kwargs):
100 br = browser()
101 return br.open_novisit(*args, **kwargs)
102
103 open = open_novisit