calibre/recipes/lifehacker.recipe
2020-10-21 11:15:53 +05:30

53 lines
1.5 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2017, Kovid Goyal <kovid at kovidgoyal.net>
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 LifeHacker(BasicNewsRecipe):
title = u'LifeHacker'
__author__ = 'Kovid Goyal'
language = 'en'
description = u'Tips, tricks, and downloads for getting things done.'
publisher = u'lifehacker.com'
oldest_article = 4
max_articles_per_feed = 20
summary_length = 1000
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
remove_empty_feeds = True
remove_attributes = ['style']
keep_only_tags = [
dict(name='h1'),
classes('headline author post-content js_post-content'),
]
remove_tags = [
classes('magnifier commerce-inset gmg-avatar js_ad-dynamic instream-native-video inset--story js_commerce-inset-permalink'),
dict(id='lifehacker-avatar-svg'),
dict(name='aside'),
]
remove_tags_after = classes('post-content')
feeds = [(u'Articles', u'https://lifehacker.com/rss')]
def preprocess_html(self, soup):
def choose_from_srcset(raw):
parts = raw.split()
if len(parts) > 2:
return parts[2]
return parts[0]
for img in soup.findAll(attrs={'data-srcset':True}):
img['src'] = choose_from_srcset(img['data-srcset'])
return soup