| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from __future__ import absolute_import, division, print_function, unicode_literals |
| 4 |
|
| 5 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 6 |
|
| 7 |
|
| 8 |
def classes(classes): |
| 9 |
q = frozenset(classes.split(' ')) |
| 10 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 11 |
|
| 12 |
|
| 13 |
class Salon_com(BasicNewsRecipe): |
| 14 |
title = 'Salon.com' |
| 15 |
__author__ = 'ebrandon' |
| 16 |
description = 'Salon.com - Breaking news, opinion, politics, entertainment, sports and culture.' |
| 17 |
timefmt = ' [%b %d, %Y]' |
| 18 |
language = 'en' |
| 19 |
oldest_article = 7 |
| 20 |
max_articles_per_feed = 100 |
| 21 |
no_stylesheets = True |
| 22 |
# auto_cleanup = True |
| 23 |
# auto_cleanup_keep = '//div[@id="image-id"]' |
| 24 |
ignore_duplicate_articles = {'title', 'url'} |
| 25 |
remove_empty_feeds = True |
| 26 |
|
| 27 |
keep_only_tags = [ |
| 28 |
dict(itemprop=['headline', 'description']), |
| 29 |
classes('article-content title-container article_rail_wrapper cover-wrapper article_img_desc'), |
| 30 |
] |
| 31 |
|
| 32 |
remove_tags = [ |
| 33 |
classes('social_comments_app_wrapper related_article layout_template_wrapper writer-container right-rail topic_explore_box'), |
| 34 |
dict(name=['object', 'link', 'embed', 'iframe', 'meta']), |
| 35 |
dict(id=['social-left', 'article-footer-wrap']), |
| 36 |
dict(name='nav', attrs={'class': 'subheading'}), |
| 37 |
] |
| 38 |
remove_attributes = ['lang', 'style'] |
| 39 |
|
| 40 |
feeds = [ |
| 41 |
# ('News', 'http://www.salon.com/category/news/feed/rss/'), |
| 42 |
# ('Politics', 'http://www.salon.com/category/politics/feed/rss/'), |
| 43 |
# ('Business', 'http://www.salon.com/category/business/feed/rss/'), |
| 44 |
# ('Technology', 'http://www.salon.com/category/technology/feed/rss/'), |
| 45 |
# ('Innovation', 'http://www.salon.com/category/innovation/feed/rss/'), |
| 46 |
# ('Sustainability', 'http://www.salon.com/category/sustainability/feed/rss/'), |
| 47 |
# ('Entertainment', 'http://www.salon.com/category/entertainment/feed/rss/'), |
| 48 |
# ('Life', 'http://www.salon.com/category/life/feed/rss/'), |
| 49 |
('News and Politics', 'https://www.salon.com/category/news-and-politics/feed'), |
| 50 |
('Culture', 'http://www.salon.com/category/culture/feed/'), |
| 51 |
('Science & Health', 'https://www.salon.com/category/science-and-health/feed/'), |
| 52 |
('Food', 'https://www.salon.com/category/food/feed/'), |
| 53 |
('Money', 'https://www.salon.com/category/money/feed/'), |
| 54 |
('Life Stories', 'https://www.salon.com/category/life-stories/feed/'), |
| 55 |
('Reviews', 'https://www.salon.com/category/reviews/feed/'), |
| 56 |
('Top', 'http://www.salon.com/feed/'), |
| 57 |
] |
| 58 |
|
| 59 |
def get_browser(self, *args, **kwargs): |
| 60 |
br = BasicNewsRecipe.get_browser(self, *args, **kwargs) |
| 61 |
br.set_handle_gzip(True) |
| 62 |
return br |