calibre/recipes/salon.recipe
2025-01-24 11:14:21 +01:00

66 lines
2.7 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
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 Salon_com(BasicNewsRecipe):
title = 'Salon.com'
__author__ = 'ebrandon'
description = 'Salon.com - Breaking news, opinion, politics, entertainment, sports and culture.'
timefmt = ' [%b %d, %Y]'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
# auto_cleanup = True
# auto_cleanup_keep = '//div[@id="image-id"]'
ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds = True
keep_only_tags = [
dict(itemprop=['headline', 'description']),
classes('article-content title-container article_rail_wrapper cover-wrapper article_img_desc'),
]
remove_tags = [
classes('social_comments_app_wrapper related_article layout_template_wrapper writer-container right-rail topic_explore_box'),
dict(name=['object', 'link', 'embed', 'iframe', 'meta']),
dict(id=['social-left', 'article-footer-wrap']),
dict(name='nav', attrs={'class': 'subheading'}),
]
remove_attributes = ['lang', 'style']
feeds = [
# ('News', 'http://www.salon.com/category/news/feed/rss/'),
# ('Politics', 'http://www.salon.com/category/politics/feed/rss/'),
# ('Business', 'http://www.salon.com/category/business/feed/rss/'),
# ('Technology', 'http://www.salon.com/category/technology/feed/rss/'),
# ('Innovation', 'http://www.salon.com/category/innovation/feed/rss/'),
# ('Sustainability', 'http://www.salon.com/category/sustainability/feed/rss/'),
# ('Entertainment', 'http://www.salon.com/category/entertainment/feed/rss/'),
# ('Life', 'http://www.salon.com/category/life/feed/rss/'),
('News and Politics', 'https://www.salon.com/category/news-and-politics/feed'),
('Culture', 'http://www.salon.com/category/culture/feed/'),
('Science & Health', 'https://www.salon.com/category/science-and-health/feed/'),
('Food', 'https://www.salon.com/category/food/feed/'),
('Money', 'https://www.salon.com/category/money/feed/'),
('Life Stories', 'https://www.salon.com/category/life-stories/feed/'),
('Reviews', 'https://www.salon.com/category/reviews/feed/'),
('Top', 'http://www.salon.com/feed/'),
]
def get_browser(self, *args, **kwargs):
br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
br.set_handle_gzip(True)
return br