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 Engadget

Browse Source
This commit is contained in:
Kovid Goyal 2022-09-18 19:13:18 +05:30
parent 2e1fdf56b1
commit 3734d008f9
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 26 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
recipes/endgadget.recipe
View File

@ -6,14 +6,14 @@ __copyright__ = 'Copyright 2011 Starson17'
engadget.com engadget.com
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe, classes
class Engadget(BasicNewsRecipe): class Engadget(BasicNewsRecipe):
title = u'Engadget' title = u'Engadget'
__author__ = 'Starson17, modified by epubli' __author__ = 'Starson17, modified by epubli'
__version__ = 'v1.00' __version__ = 'v2.0'
__date__ = '08, Feb 2021' __date__ = '14, Sep 2022'
description = 'Tech news' description = 'Tech news'
language = 'en' language = 'en'
oldest_article = 7 oldest_article = 7
@ -24,36 +24,39 @@ class Engadget(BasicNewsRecipe):
remove_empty_feeds = True remove_empty_feeds = True
compress_news_images = True compress_news_images = True
scale_news_images_to_device = True scale_news_images_to_device = True
remove_attributes = ['class'] cover_url = 'https://upload.wikimedia.org/wikipedia/commons/b/bb/Engadget-logo.svg'
keep_only_tags = [ keep_only_tags = [
dict(name='figure'), dict(name='figure', attrs={'data-component': 'DefaultLede'}),
dict(name='div', attrs={'data-component': 'ArticleHeader'}), dict(name='div', attrs={'data-component': 'ArticleHeader'}),
dict( dict(
name='div', name='div',
attrs={'class': ['article-text', 'article-text c-gray-1 no-review']} attrs={'class': ['article-text', 'article-text c-gray-1 no-review']}
) ),
dict(name='figure')
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'data-component': 'ArticleAuthorInfo'}), dict(name='div', attrs={'data-component': 'ArticleAuthorInfo'}),
dict(name='span', attrs={'class': 'c-gray-7'}) classes('notification-upsell-push article-slideshow D(f) rapid-with-clickid athena-button')
] ]
feeds = [(u'Posts', u'https://www.engadget.com/rss.xml')] feeds = [(u'Posts', u'https://www.engadget.com/rss.xml')]
extra_css = ''' def parse_feeds(self):
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} # Call parent's method.
h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:small;} feeds = BasicNewsRecipe.parse_feeds(self)
p{font-family:Arial,Helvetica,sans-serif;font-size:small;} # Loop through all feeds.
body{font-family:Helvetica,Arial,sans-serif;font-size:small;} for feed in feeds:
''' # Loop through all articles in feed.
for article in feed.articles[:]:
def preprocess_raw_html(self, raw, url): # Remove articles with '...' in the title.
# remove sponsored articles and daily article with summaries of previous articles if 'best tech deals' in article.title:
unwanted_article_keywords = [ print('Removing:', article.title)
'made possible by our sponsor', 'The Morning After' feed.articles.remove(article)
] elif 'Podcast' in article.title:
for keyword in unwanted_article_keywords: print('Removing:', article.title)
if keyword in raw: feed.articles.remove(article)
self.abort_article('Skipping unwanted article') elif 'The Morning After' in article.title:
return raw print('Removing:', article.title)
feed.articles.remove(article)
return feeds