Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update salon.com

Browse Source
This commit is contained in:
Kovid Goyal 2024-11-02 13:36:14 +05:30
parent d5ed484703
commit f8c76984d4
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 38 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/salon.recipe
View File

@ -5,6 +5,11 @@ from __future__ import absolute_import, division, print_function, unicode_litera
from calibre.web.feeds.news import BasicNewsRecipe 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): class Salon_com(BasicNewsRecipe):
title = 'Salon.com' title = 'Salon.com'
@ -14,19 +19,43 @@ class Salon_com(BasicNewsRecipe):
language = 'en' language = 'en'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
auto_cleanup = True no_stylesheets = True
#auto_cleanup = True
#auto_cleanup_keep = '//div[@id="image-id"]'
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds = True 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 = [ feeds = [
('News', 'http://www.salon.com/category/news/feed/rss/'), #('News', 'http://www.salon.com/category/news/feed/rss/'),
('Politics', 'http://www.salon.com/category/politics/feed/rss/'), #('Politics', 'http://www.salon.com/category/politics/feed/rss/'),
('Business', 'http://www.salon.com/category/business/feed/rss/'), #('Business', 'http://www.salon.com/category/business/feed/rss/'),
('Technology', 'http://www.salon.com/category/technology/feed/rss/'), #('Technology', 'http://www.salon.com/category/technology/feed/rss/'),
('Innovation', 'http://www.salon.com/category/innovation/feed/rss/'), #('Innovation', 'http://www.salon.com/category/innovation/feed/rss/'),
('Sustainability', 'http://www.salon.com/category/sustainability/feed/rss/'), #('Sustainability', 'http://www.salon.com/category/sustainability/feed/rss/'),
('Entertainment', 'http://www.salon.com/category/entertainment/feed/rss/'), #('Entertainment', 'http://www.salon.com/category/entertainment/feed/rss/'),
('Life', 'http://www.salon.com/category/life/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): def get_browser(self, *args, **kwargs):