calibre/recipes/endgadget.recipe
2022-09-18 19:13:18 +05:30

63 lines
2.1 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = 'Copyright 2011 Starson17'
'''
engadget.com
'''
from calibre.web.feeds.news import BasicNewsRecipe, classes
class Engadget(BasicNewsRecipe):
title = u'Engadget'
__author__ = 'Starson17, modified by epubli'
__version__ = 'v2.0'
__date__ = '14, Sep 2022'
description = 'Tech news'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
remove_empty_feeds = True
compress_news_images = True
scale_news_images_to_device = True
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/b/bb/Engadget-logo.svg'
keep_only_tags = [
dict(name='figure', attrs={'data-component': 'DefaultLede'}),
dict(name='div', attrs={'data-component': 'ArticleHeader'}),
dict(
name='div',
attrs={'class': ['article-text', 'article-text c-gray-1 no-review']}
),
dict(name='figure')
]
remove_tags = [
dict(name='div', attrs={'data-component': 'ArticleAuthorInfo'}),
classes('notification-upsell-push article-slideshow D(f) rapid-with-clickid athena-button')
]
feeds = [(u'Posts', u'https://www.engadget.com/rss.xml')]
def parse_feeds(self):
# Call parent's method.
feeds = BasicNewsRecipe.parse_feeds(self)
# Loop through all feeds.
for feed in feeds:
# Loop through all articles in feed.
for article in feed.articles[:]:
# Remove articles with '...' in the title.
if 'best tech deals' in article.title:
print('Removing:', article.title)
feed.articles.remove(article)
elif 'Podcast' in article.title:
print('Removing:', article.title)
feed.articles.remove(article)
elif 'The Morning After' in article.title:
print('Removing:', article.title)
feed.articles.remove(article)
return feeds