calibre/recipes/wired_daily.recipe
2020-05-24 11:36:40 +05:30

94 lines
3.3 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2014, Darko Miletic <darko.miletic at gmail.com>'
'''
www.wired.com
'''
from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class WiredDailyNews(BasicNewsRecipe):
title = 'Wired Daily Edition'
__author__ = 'Darko Miletic, PatStapleton(update 2020-05-24)'
description = (
'Wired is a full-color monthly American magazine, published in both print'
' and online editions, that reports on how emerging technologies affect culture,'
' the economy and politics.'
)
masthead_url = 'https://www.wired.com/images/logos/apple-touch-icon.png'
cover_url = 'https://www.wired.com/images/logos/wired.png'
publisher = 'Conde Nast'
category = 'news, IT, computers, technology'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'en'
ignore_duplicate_articles = {'url'}
remove_empty_feeds = True
publication_type = 'newsportal'
extra_css = """
.entry-header{
text-transform: uppercase;
vertical-align: baseline;
display: inline;
}
ul li{display: inline}
"""
remove_tags = [
classes('related-cne-video-component tags-component podcast_42 storyboard inset-left-component social-icons'),
dict(name=['meta', 'link', 'aside']),
dict(id=['sharing', 'social', 'article-tags', 'sidebar']),
]
keep_only_tags = [
dict(name='article', attrs={'class': 'article main-content'}),
]
remove_attributes = ['srcset']
handle_gzip = True
feeds = [
(u'Top Stories', u'https://www.wired.com/feed/rss'),
(u'Business', u'https://www.wired.com/feed/category/business/latest/rss'),
(u'Culture', u'https://www.wired.com/feed/category/culture/latest/rss'),
(u'Gear', u'https://www.wired.com/feed/category/gear/latest/rss'),
(u'Ideas', u'https://www.wired.com/feed/category/ideas/latest/rss'),
(u'Science', u'https://www.wired.com/feed/category/science/latest/rss'),
(u'Security', u'https://www.wired.com/feed/category/security/latest/rss'),
(
u'Transportation',
u'https://www.wired.com/feed/category/transportation/latest/rss'
),
(
u'Backchannel',
u'https://www.wired.com/feed/category/backchannel/latest/rss'
),
(u'WIRED Guides', u'https://www.wired.com/feed/tag/wired-guide/latest/rss'),
# (u'Photo', u'https://www.wired.com/feed/category/photo/latest/rss'),
]
def get_article_url(self, article):
return article.get('link', None)
# Wired changes the content it delivers based on cookies, so the
# following ensures that we send no cookies
def get_browser(self, *args, **kwargs):
return self
def clone_browser(self, *args, **kwargs):
return self.get_browser()
def open_novisit(self, *args, **kwargs):
br = browser()
return br.open_novisit(*args, **kwargs)
open = open_novisit